CN113361022A

CN113361022A - State estimation device, control valve, storage medium, and state estimation method

Info

Publication number: CN113361022A
Application number: CN202110250809.XA
Authority: CN
Inventors: 冈本武司; 久保山丰; 川瀬贵章
Original assignee: Nabtesco Corp
Current assignee: Nabtesco Corp
Priority date: 2020-03-06
Filing date: 2021-03-08
Publication date: 2021-09-07
Also published as: JP2021139459A; KR102557766B1; KR20210113067A

Abstract

The invention provides a state estimation device, a control valve, a storage medium, and a state estimation method. Techniques are provided for accurately estimating the state of a control valve. A state estimation device (400) is provided with: an acquisition unit that acquires a target position or an actual position of a first movable unit in a control valve that controls a flow rate of a working fluid according to a position of the first movable unit, and an actual position of a second movable unit that changes position according to the flow rate of the working fluid; and an estimating unit that estimates an amount of leakage of the working fluid based on the information acquired by the acquiring unit.

Description

State estimation device, control valve, storage medium, and state estimation method

Technical Field

The present invention relates to a state estimation device, a control valve, a state estimation program, and a state estimation method for estimating a state of a control valve.

Background

In order to control an engine mounted on a mobile body such as a ship, a control valve such as a hydraulic servo valve is used. By finely controlling the supply of fuel to the engine, the exhaust gas discharged from the engine, and the like using an electrically controllable control valve, the thermal efficiency of the engine can be improved, and the amount of fuel consumption can be suppressed.

Documents of the prior art

Patent document

Patent document 1: japanese patent No. 5465365

Disclosure of Invention

Problems to be solved by the invention

Since a ship is sailing on the ocean, it is not always possible to immediately cope with a failure or a defect in a control valve mounted thereon. Conventionally, when a ship is moored at an estuary or the like, a control valve in which a failure, a defect, or the like has occurred is detached, taken to a factory or the like, and inspected, and necessary repair, replacement, or the like is performed. However, in order to prevent a situation in which a ship falls into a non-sailing state and causes a great damage, it is important to accurately grasp the state of the control valve and take appropriate measures in advance before the ship becomes inoperable due to a failure or a malfunction.

The present invention has been made in view of such a problem, and an object thereof is to provide a technique for estimating the state of a control valve more accurately.

Means for solving the problems

In order to solve the above problem, a state estimation device according to an aspect of the present invention includes: an acquisition unit that acquires a target position or an actual position of a first movable unit in a control valve that controls a flow rate of a working fluid according to a position of the first movable unit, and an actual position of a second movable unit that changes position according to the flow rate of the working fluid; and an estimating unit that estimates an amount of leakage of the working fluid based on the information acquired by the acquiring unit.

Another aspect of the invention is a control valve. The control valve includes: a first movable portion whose position changes in accordance with a control signal for specifying a position, the first movable portion controlling a flow rate of the working fluid in accordance with the position; an acquisition unit that acquires a target position or an actual position of the first movable unit and an actual position of the second movable unit that changes position according to a flow rate of the working fluid; and an estimating section that estimates an amount of leakage of the working fluid based on the target position or the actual position of the first movable part and the actual position of the second movable part acquired by the acquiring section, using an estimation model for estimating the amount of leakage of the working fluid based on the target position or the actual position of the first movable part and the actual position of the second movable part.

Another aspect of the present invention is a state estimation procedure. The program causes a computer to function as an acquisition unit that acquires a target position or an actual position of a first movable part in a control valve that controls a flow rate of a working fluid according to a position of the first movable part, and an actual position of a second movable part that changes position according to the flow rate of the working fluid, and as an estimation unit that estimates an amount of leakage of the working fluid based on information acquired by the acquisition unit.

Another embodiment of the present invention is a state estimation method. The method causes a computer to perform the steps of: an acquisition step of acquiring a target position or an actual position of a first movable portion in a control valve that controls a flow rate of a working fluid according to a position of the first movable portion, and an actual position of a second movable portion that changes position according to the flow rate of the working fluid; and an estimating step of estimating an amount of leakage of the working fluid based on the information acquired in the acquiring step.

In addition, any combination of the above-described constituent elements, and a mode in which the constituent elements or the expressions of the present invention are replaced with each other among a method, an apparatus, a program, a transient or non-transient storage medium in which the program is recorded, a system, and the like are also effective as the modes of the present invention.

ADVANTAGEOUS EFFECTS OF INVENTION

According to the present invention, the state of the control valve can be estimated more accurately.

Drawings

Fig. 1 is a diagram showing a configuration of a management system according to an embodiment of the present invention.

Fig. 2 is a schematic diagram showing a configuration around a hydraulic servo valve mounted on a ship.

Fig. 3 is a diagram schematically showing the structure of the hydraulic servo valve.

Fig. 4 is a schematic diagram schematically showing the position of the valve body of the pilot valve in the first direction and the open-closed state of the ports.

Fig. 5 is a diagram showing the structure of the servo valve control device.

Fig. 6 is a diagram showing the configuration of the learning device and the state estimation device.

Fig. 7 is a flowchart showing the procedure of the state estimation method of the present embodiment.

Fig. 8 is a diagram showing the configurations of the learning device and the state estimation device according to embodiment 1-1.

Fig. 9 is a diagram showing the configurations of the learning device and the state estimation device according to embodiments 1 to 2.

Fig. 10 is a diagram showing the configurations of the learning device and the state estimation device according to embodiments 1 to 3.

Fig. 11 is a diagram showing the configurations of the learning device and the state estimation device according to embodiments 1 to 4.

Fig. 12 is a diagram showing the configurations of the learning device and the state estimation device according to embodiments 1 to 5.

Fig. 13 is a diagram showing the configuration of a learning device and a state estimation device according to embodiment 2.

Fig. 14 is a diagram schematically showing the operation of the valve spool of the pilot valve and the valve spool of the main valve.

Fig. 15 is a diagram showing the configurations of a learning device and a state estimation device according to embodiment 3.

Fig. 16 is a diagram showing the configuration of a learning device and a state estimation device according to embodiment 4.

Fig. 17 is a diagram schematically showing the operation of the valve body of the pilot valve and the valve body of the main valve.

Fig. 18 is a diagram showing the configuration of a learning device and a state estimation device according to embodiment 5.

Fig. 19 is a diagram showing a state of a position sensor of a spool of a main valve.

Fig. 20 is a diagram showing the configurations of a learning device and a state estimation device according to embodiment 6.

Fig. 21 is a diagram showing the configuration of a learning device and a state estimation device according to embodiment 7.

Description of the reference numerals

1: a management system; 2: a vessel; 10: a pilot valve; 12: a valve core; 16: a port; 18: a valve element driving part; 19: a position sensor; 20: a main valve; 28: a valve core; 29: a position sensor; 48: working oil; 80: an engine; 81: a cylinder; 82: a sensor; 90: a log data storage device; 91: an engine control device; 92: a junction box; 100: a hydraulic servo valve; 110: a servo valve control device; 120: a power supply circuit; 130: a servo valve control circuit; 140: a servo valve drive circuit; 150: a voltage detection unit; 160: a data collection circuit; 300: a learning device; 301: a learning data acquisition unit; 302: an estimation model generation unit; 303: an estimation model providing unit; 313: an internal oil leakage amount estimation model generation unit; 314: an internal oil leakage amount estimation model providing unit; 315: a feature value calculation unit; 319: an offset time calculation unit; 320: a data selection unit; 400: a state estimation device; 401: a detection information acquisition unit; 402: a state estimation unit; 403: an estimation result output unit; 412: an internal oil leakage amount estimation unit; 413: an internal oil leakage amount estimation value output unit; 414: a feature value calculation unit; 417: a data selection unit.

Detailed Description

The present invention will be described below based on preferred embodiments with reference to the drawings. In the embodiment and the modifications, the same or equivalent constituent elements and members are denoted by the same reference numerals, and overlapping descriptions are appropriately omitted. In addition, the sizes of the components in the respective drawings are shown enlarged or reduced as appropriate for easy understanding. In the drawings, parts of members that are not essential to the explanation of the embodiments are omitted.

The terms including the ordinal numbers of the first, second, etc. are used to describe various components, but the terms are used only to distinguish one component from another component, and the components are not limited by the terms.

Fig. 1 shows a configuration of a management system according to an embodiment of the present invention. The management system 1 manages the control valve based on information associated with the action of the control valve. The management system 1 can be used to manage an arbitrary control valve, but in the present embodiment, an example of managing a hydraulic servo valve for controlling an engine mounted on the ship 2 will be mainly described. The management system 1 includes a learning device 300 and a state estimation device 400. The learning device 300 learns an estimation model for estimating the state of the hydraulic servo valve based on information associated with the hydraulic servo valve. The state estimation device 400 estimates the state of the hydraulic servo valve using the estimation model learned by the learning device 300.

The learning device 300 learns the estimation model using learning data for learning the estimation model. The learning data may be log data recorded when the hydraulic servo valve or another hydraulic servo valve of the same type as the hydraulic servo valve is actually used in the ship 2, may be test data recorded when the hydraulic servo valve or another hydraulic servo valve of the same type as the hydraulic servo valve is used in a test environment or the like other than the ship 2, may be simulation data generated by a simulator for simulating the operation of the hydraulic servo valve, or may be a combination of 2 or more of them. Hereinafter, unless otherwise specified, the log data or the test data may be log data or test data recorded when the hydraulic servo valve itself to be the target of the estimated state is used or tested, or may be log data or test data recorded when another hydraulic servo valve of the same type as the hydraulic servo valve is used or tested, or may be a combination thereof.

When the log data is used as the learning data, the estimation model can be learned based on the log data collected when the hydraulic servo valve is actually used in the same environment as the hydraulic servo valve to be an object of the estimation state, and therefore, the accuracy of the estimation model can be improved. In this case, a log data storage device for storing log data may be mounted on the ship 2, and the log data may be read from the log data storage device and supplied to the learning device 300 when the ship 2 lands. Further, a communication device for ship-to-ship land communication may be mounted on the ship 2, and the log data may be transmitted from the ship 2 to the learning device 300 via the communication network 3.

When the test data or the simulation data is used as the learning data, data when the hydraulic servo valve is used in various states or environments can be generated in a large amount, and therefore, the accuracy and the versatility of the estimation model can be improved. For example, even if it is difficult to obtain log data when a failure having a very low frequency of occurrence actually occurs, an estimation model capable of accurately estimating such a failure can be generated by learning an estimation model using test data when the failure occurs tentatively or simulation data when the failure is simulated.

The learning device 300 may further learn and update the learned estimation model used in the state estimation device 400.

The state estimation device 400 acquires information related to the hydraulic servo valve mounted on the ship 2, and estimates the state of the hydraulic servo valve using an estimation model. The state estimation device 400 may read log data from a log data storage device mounted on the ship 2, and estimate the state of the hydraulic servo valve during the past travel of the ship 2 based on the read log data. The state estimation device 400 may receive information related to the hydraulic servo valves from a communication device for ship-to-ship land communication mounted on the ship 2 via the communication network 3, and estimate the state of the hydraulic servo valves of the ship 2 during the course of the voyage based on the received information. The state estimation device 400 may be mounted on the ship 2, and may acquire information related to the hydraulic servo valve in real time to estimate the state of the hydraulic servo valve. In this case, the estimation result of the state estimation device 400 may be transmitted to the owner of the ship 2, the management agent, the maintenance agent, and the like through ship-land communication.

According to the technique of the present embodiment, since the state of the hydraulic servo valve in the past or the present can be accurately estimated, even if a failure, a defect, or the like occurs in the hydraulic servo valve, it is possible to quickly and appropriately take measures. In addition, even when the hydraulic servo valve is not broken down or defective, the possibility of the hydraulic servo valve being broken down or defective in future navigation, the life of the hydraulic servo valve, and the like can be accurately predicted from the current or past state of the hydraulic servo valve. As described above, the technique of the present embodiment is very important to improve the safety and efficiency of a moving body such as the ship 2.

Fig. 2 schematically shows the configuration of the periphery of the hydraulic servo valve 100 mounted on the ship 2. An engine 80 mounted on the ship 2 includes a sensor 82 and a plurality of cylinders 81. The sensor 82 detects the number of revolutions, load, pressure, exhaust temperature, and the like of the engine 80. The hydraulic servo valve 100 is provided corresponding to each of the plurality of cylinders 81, and controls fuel injection, exhaust, and the like in each cylinder 81. In the present embodiment, the hydraulic servo valve 100 includes: a pilot valve that controls a flow rate of hydraulic oil supplied to an actuator by electrically controlling a position of a valve element; and a main valve, which is an example of an actuator controlled by the pilot valve. The hydraulic servo valve 100 controls the flow rate of the hydraulic oil supplied to another actuator provided to drive an injection valve, an exhaust valve, and the like, in accordance with the position of the spool of the main valve. In another example, the hydraulic servo valve 100 may directly drive an injection valve, an exhaust valve, or the like by the movement of a spool of a main valve.

In response to an instruction input from a control panel, not shown, for controlling the voyage of the ship 2, the engine control device 91 determines the number of revolutions of the engine 80 and inputs the instruction to the servo valve control device 110. The servo valve control device 110 calculates target positions of the valve elements of the main valves of the plurality of hydraulic servo valves 100 in response to an instruction from the engine control device 91, and controls the positions of the valve elements of the pilot valves so that the positions of the valve elements of the main valves become the calculated target positions. The servo valve control device 110 acquires information indicating the actual position of the spool of the main valve from each of the plurality of hydraulic servo valves 100 via the junction box 92, calculates the target position of the spool of the pilot valve based on the target position and the actual position of the spool of the main valve, and outputs the target position to the hydraulic servo valve 100, thereby performing feedback control on the position of the spool of the main valve. The servo valve control device 110 can feedback-control the position of the spool of the main valve by any method such as P control, PI control, and PID control.

The servo valve control device 110 records input data from the engine control device 91, output data to the hydraulic servo valve 100, various kinds of detection data indicating the states of the hydraulic servo valve 100 and the engine 80 acquired via the junction box 92, and the like in the log data storage device 90.

In the figure, the example in which the log data storage device 90 is connected to the servo valve control device 110 is shown, but the log data storage device 90 may be connected to the junction box 92, may be connected between the junction box 92 and the hydraulic servo valve 100, or may be mounted in the hydraulic servo valve 100. When the log data storage device 90 is connected to the servo valve control device 110, the log data storage device 90 can be provided at a position relatively distant from the engine 80, and therefore, the influence of vibration, heat, or the like generated in the engine 80 can be suppressed. In addition, it is possible to reduce the change of wiring and the like required when installing the log data storage device 90 to the existing ship 2. When the log data storage device 90 is connected to the terminal block 92, even if the configuration is such that data indicating the actual position of the valve body of the pilot valve of the hydraulic servo valve 100 is not transmitted to the servo valve control device 110, the data indicating the actual position of the valve body of the pilot valve can be acquired and recorded, and therefore the state of the hydraulic servo valve 100 can be estimated more accurately. In the case where the log data storage device 90 is connected between the hydraulic servo valve 100 and the junction box 92, in addition to data indicating the actual position of the spool of the pilot valve of the hydraulic servo valve 100, it is possible to obtain the value of the voltage or current supplied to the hydraulic servo valve 100, and therefore it is possible to estimate the state of the hydraulic servo valve 100 more accurately. The same applies to the case where the log data storage device 90 is mounted in the hydraulic servo valve 100.

When the state estimation device 400 is mounted on the ship 2, the state estimation device 400 may acquire data from the log data storage device 90, or the state estimation device 400 may be provided instead of the log data storage device 90. In this case, as described above, the state estimation device 400 may be connected to the servo valve control device 110, may be connected to the junction box 92, may be connected between the junction box 92 and the hydraulic servo valve 100, or may be mounted in the hydraulic servo valve 100.

Fig. 3 schematically shows the structure of the hydraulic servo valve 100. The hydraulic servo valve 100 includes a pilot valve 10 and a main valve 20. The pilot valve 10 controls the position of the valve element 28 of the main valve 20 by changing the delivery state of the hydraulic oil 48 to the main valve 20, which is a controlled device, based on a command from the servo valve control device 110.

The pilot valve 10 is coupled to the main valve 20 by a plurality of bolts B1. The pilot valve 10 is provided with a plurality of through holes 10h through which bolts B1 pass. A plurality of female screws 20h for screwing with the bolts B1 are provided in the main valve 20. The through holes 10h are disposed at positions corresponding to the positions of the female screws 20 h. The pilot valve 10 and the main valve 20 are coupled by screwing the bolt B1 to the female screw 20h through the through hole 10 h. By removing the bolt B1, the pilot valve 10 is thereby separated from the main valve 20.

The hydraulic system of the main valve 20 of fig. 3 comprises: a drain tank (drain tank)44 for storing working oil 48; and a hydraulic pump 42 that pumps the hydraulic oil 48 from the drain tank 44. The hydraulic oil 48 sent out by the hydraulic pump 42 is supplied to the interior of the main valve 20 and the pilot valve 10 through the pump-side piping portion 22p in the main valve 20. The hydraulic oil 48 discharged from the interior of the main valve 20 and the pilot valve 10 returns to the drain tank 44 through the tank-side piping portion 22t in the main valve 20. The pump-side piping portion 22p and the cabinet-side piping portion 22t are collectively referred to as a main valve piping portion.

The pilot valve 10 mainly includes a main body portion 10b, a spool 12, a port 16, and a spool drive portion 18. The valve body 12 functions as a first movable portion, and includes a shaft 12s and a plurality of valve elements 14 that move integrally with the shaft 12 s. The spool 12 is driven by the spool drive section 18 to advance and retract in the first direction. For convenience, the direction in which the valve body 12 extends from the valve body driving portion 18 in the first direction (downward in fig. 3) is referred to as "extending direction" or "extending side", and the direction opposite to the extending direction is referred to as "extending opposite direction" or "extending opposite side".

On the projecting side of the valve body 12, a biasing member 12h is provided for biasing the valve body 12 in the direction opposite to the projecting direction. The urging member 12h may be, for example, a coil spring that expands and contracts in the first direction. The valve body driving unit 18 includes an electromagnetic actuator (not shown) such as a coil that moves the shaft 12s forward and backward in the first direction. The valve element driving unit 18 controls the position of the valve element 14 by moving the shaft 12s forward and backward in accordance with a command from the servo valve control device 110 and balancing the biasing force of the biasing member 12 h.

The valve body 14 includes a first valve body 14a, a second valve body 14b, and a third valve body 14c arranged separately in the first direction. The second valve element 14b is disposed on the opposite side of the first valve element 14a from the extension, and the third valve element 14c is disposed on the extension side of the first valve element 14 a. The first valve body 14a changes the communication state of the a port 16a described later according to its position in the first direction. The body portion 10b has a cylindrical space 10s extending in the first direction to accommodate the valve element 12. The cylindrical space 10s functions as a cylinder surrounding the valve element 14 with a narrow gap therebetween.

The body 10b is provided with a port 16. The ports 16 of the present embodiment include a P port 16P, an a port 16a, and a T port 16T. The P port 16P is connected to the pump-side pipe section 22P, and is supplied with the hydraulic oil 48 pressurized by the hydraulic pump 42. The a port 16a is connected to the hydraulic oil receiver 22a of the main valve 20. The spool 28 of the main valve 20 moves due to the pressure of the hydraulic oil 48 supplied to the hydraulic oil reservoir 22 a. The T-port 16T is connected to the tank-side pipe portion 22T, and discharges the hydraulic oil 48 flowing through the main body portion 10b to the drain tank 44 through the tank-side pipe portion 22T.

The main valve 20 includes a valve body 28 functioning as a second movable portion. In the present figure, the main valve 20 is not described in detail, but the main valve 20 may have the same structure as the pilot valve 10.

A position sensor 19 for detecting the position of the valve body 12 is provided at the tip end portion of the valve body 12 of the pilot valve 10. A position sensor 29 for detecting the position of the valve body 28 is provided at the tip end portion of the valve body 28 of the main valve 20. The data indicating the actual position of the valve body 12 of the pilot valve 10 detected by the position sensor 19 and the data indicating the actual position of the valve body 28 of the main valve 20 detected by the position sensor 29 are transmitted to the junction box 92 via wires.

Fig. 4 is a schematic diagram schematically showing the position of the valve body 14 of the pilot valve 10 in the first direction and the open-closed state of the ports. In this figure, the description of elements that are not important for the description is omitted. Fig. 4 (a) shows a state in which the valve body 14 is located in the first region that communicates the a port 16a with the P port 16P. In this state, the a port 16a supplies the hydraulic oil 48 from the P port 16P to the hydraulic oil reservoir 22a (hereinafter referred to as "supply mode"). In the supply mode, the hydraulic oil 48 from the P port 16P is supplied to the hydraulic oil reservoir 22a of the main valve 20. By this operation, for example, the valve body 28 of the main valve 20 is moved in a direction to increase the amount of fuel supplied to the engine 80.

Fig. 4 (b) shows a state in which the valve body 14 is located in a neutral region (hereinafter, the position in the neutral region is also referred to as a "neutral position") in which the a port 16a is blocked from communicating with the P port 16P and the T port 16T. In this state, the a port 16a is blocked, and neither supply nor recovery is performed to the hydraulic oil reservoir 22a (hereinafter referred to as "neutral mode"). In the neutral mode, the hydraulic pressure of the hydraulic oil receiver 22a of the main valve 20 is maintained in a state immediately before the valve body 14 is located in the neutral region. By this operation, for example, the valve body 28 of the main valve 20 is stopped at the previous position, and the fuel supply amount to the engine 80 is maintained in the previous state.

Fig. 4 (c) shows a state in which the valve body 14 is located in the second region that communicates the a port 16a with the T port 16T. In this state, the a port 16a recovers the hydraulic oil 48 from the hydraulic oil accommodating portion 22a and returns the hydraulic oil 48 to the pump-side pipe portion 22p (hereinafter referred to as "recovery mode"). In the recovery mode, the hydraulic oil 48 in the hydraulic oil accommodating portion 22a of the main valve 20 is recovered to the drain tank 44 through the a port 16a, the T port 16T, and the tank-side piping portion 22T. By this operation, for example, the valve body 28 of the main valve 20 is moved in a direction to reduce the amount of fuel supplied to the engine 80.

Fig. 5 shows the structure of the servo valve control device 110. The servo valve control device 110 includes a power supply circuit 120, a servo valve control circuit 130, a servo valve drive circuit 140, a voltage detection section 150, and a data collection circuit 160.

The power supply circuit 120 supplies power supplied from an external power supply to the servo valve control circuit 130 and the servo valve drive circuit 140. The voltage detection unit 150 detects a voltage input to the power supply circuit 120 or a voltage output from the power supply circuit 120. Instead of the voltage detection unit 150, a current detection unit that detects a current input to the power supply circuit 120 or a current output from the power supply circuit 120 may be provided, or a current detection unit that detects a current input to the power supply circuit 120 or a current output from the power supply circuit 120 may be provided in addition to the voltage detection unit 150.

The servo valve control circuit 130 calculates a target position of the spool 28 of the main valve 20 based on a command from the engine control device 91. The servo valve control circuit 130 calculates a target position of the spool 12 of the pilot valve 10 for moving the spool 28 of the main valve 20 to the calculated target position. The servo valve control circuit 130 inputs the calculated target position of the valve body 12 of the pilot valve 10 to the servo valve driving circuit 140.

The servo valve drive circuit 140 supplies electric power to the coil of the valve element drive unit 18 of the pilot valve 10 to move the valve element 12 in accordance with the target position of the valve element 12 of the pilot valve 10 input from the servo valve control circuit 130. A servo valve drive circuit 140 may also be provided within the hydraulic servo valve 100.

When the valve element 12 of the pilot valve 10 moves and the open/close state of the port 16 is changed, the valve element 28 of the main valve 20 is moved to the target position by the supply or recovery of the hydraulic oil 48. When the actual position of the spool 28 of the main valve 20 coincides with the target position, the servo valve control circuit 130 returns the spool 12 of the pilot valve 10 to the neutral position. Thereby, the spool 28 of the main valve 20 is stationary at the target position. This series of control is repeated during the operation of the engine 80.

The data collection circuit 160 records data such as the voltage value detected by the voltage detection unit 150 or the target position of the valve body 12 of the pilot valve 10 input from the servo valve control circuit 130 to the servo valve drive circuit 140 in the log data storage device 90. The data collection circuit 160 acquires data indicating the state of the engine 80 detected by the sensor 82, the actual position of the valve element 12 of the pilot valve 10 detected by the position sensor 19, the actual position of the valve element 28 of the main valve 20 detected by the position sensor 29, and the like via the junction box 92, and records the data in the log data storage device 90.

Fig. 6 shows the structures of the learning device 300 and the state estimation device 400. The learning device 300 includes a learning data acquisition unit 301, an estimation model generation unit 302, and an estimation model providing unit 303. The state estimation device 400 includes a probe information acquisition unit 401, a state estimation unit 402, and an estimation result output unit 403.

The learning data acquisition unit 301 acquires learning data used for learning an estimation model for estimating the state of the hydraulic servo valve 100. The learning data includes a set of data that can be acquired in association with the operation of the hydraulic servo valve 100 and data indicating the state of the hydraulic servo valve 100. The learning data acquisition unit 301 may acquire log data stored in the log data storage device 90, may acquire test data recorded when the hydraulic servo valve 100 is used in a test environment or the like other than the ship 2, or may acquire simulation data generated by a simulator for simulating the operation of the hydraulic servo valve 100.

The learning data acquisition unit 301 may acquire data recorded or generated under a specific situation as learning data. The learning data acquisition unit 301 may select, as the learning data, data recorded or generated in a specific situation from the acquired data. For example, the learning data acquisition section 301 may acquire or select log data when a specific state to be estimated by the estimation model is generated, experimental data when a specific state is generated in an experimental environment, or simulation data when a specific state is simulated by a simulator. The learning data acquisition unit 301 may acquire, as learning data, data recorded or generated when the hydraulic servo valve 100 is operated under a specific environment. For example, the learning data acquisition unit 301 may classify the data according to the type of the ship 2, the route, the voyage time, the type of the engine 80, the number of cylinders, the accumulated operating time, and the like, and learn a different estimation model for each of these environments.

The learning data acquisition unit 301 may preprocess the acquired data and generate learning data. For example, the learning data acquisition section 301 may calculate, as learning data, feature quantities having a correlation with the state to be estimated by the estimation model from the acquired data. Further, the offset time from when the target position is input until the actual position of the spool 12 or the spool 28 reaches the target position may be adjusted so as to correlate the target position or the actual position of the spool 12 of the pilot valve 10, the target position or the actual position of the spool 28 of the main valve 20, and other data.

The estimation model generation unit 302 generates an estimation reference used in the state estimation device 400 to estimate the state of the hydraulic servo valve 100, using the learning data acquired by the learning data acquisition unit 301. The estimation reference may be a table, a program, or the like obtained by associating data that can be acquired in association with the operation of the hydraulic servo valve 100 with data indicating the state of the hydraulic servo valve 100. The estimation reference may be an estimation model obtained by modeling a correspondence relationship between data that can be acquired in association with the operation of the hydraulic servo valve 100 and data indicating the state of the hydraulic servo valve 100. The estimation model may be an equation for calculating data representing the state of the hydraulic servo valve 100 using data that can be acquired in association with the action of the hydraulic servo valve 100 as input variables. In this case, the estimation model generation unit 302 may generate the estimation model by a statistical method such as multivariate analysis, multiple regression analysis, and principal component analysis. The estimation model may be a neural network or the like that inputs data representing the state of the hydraulic servo valve 100 to an input layer and outputs data representing the state of the hydraulic servo valve 100 from an output layer. In this case, the estimation model generation unit 302 learns the estimation model by adjusting the intermediate layer of the neural network so that a value approximate to the data representing the state of the hydraulic servo valve 100 corresponding to the data is output from the output layer when the data acquired in association with the operation of the hydraulic servo valve 100 included in the learning data is input to the input layer. The estimation model can be a rule-based estimation algorithm, and can also be artificial intelligence in any form and the like.

The estimation model providing unit 303 provides the estimation model generated by the estimation model generating unit 302 to the state estimating apparatus 400. The estimation model providing section 303 may be provided to the state estimation device 400 when the state estimation device 400 is manufactured. In addition, when the learning device 300 also learns the estimation model to update the estimation model after the state estimation device 400 is manufactured, the updated estimation model may be supplied to the state estimation device 400 at a predetermined timing.

The detection information acquisition unit 401 acquires information detected in association with the operation of the hydraulic servo valve 100. The probe information acquisition unit 401 may acquire data stored in the log data storage device 90, may acquire data directly from the data collection circuit 160, or may acquire data from the ship 2 by ship-to-land communication. The probe information acquisition unit 401 may perform the same preprocessing as the learning data used in generating the estimation model on the acquired data.

The state estimating unit 402 estimates the state of the hydraulic servo valve 100 using the estimation model generated by the learning device 300. The state estimating unit 402 acquires, as an estimation result, the state of the hydraulic servo valve 100, which is input to and output from the estimation model by the data acquired by the probe information acquiring unit 401.

The estimation result output section 403 outputs the estimation result of the state estimation section 402. When the state estimating unit 402 estimates that the hydraulic servo valve 100 is in an abnormal state, the estimation result output unit 403 may notify this fact. Whether or not the state is abnormal may be determined by whether or not the state estimation data indicating the state of the hydraulic servo valve 100 output from the state estimation unit 402 is equal to or greater than or less than a predetermined threshold value, or is within a predetermined range, or may be determined by whether or not the amount of change of the state estimation data from the initial value is equal to or greater than a predetermined threshold value. The estimation result output unit 403 may determine whether or not the hydraulic servo valve 100 is in an abnormal state by comparing the state estimation results of the plurality of hydraulic servo valves 100 provided corresponding to the plurality of cylinders 81 of the same engine 80. For example, when the value of the state estimation result of a specific hydraulic servo valve 100 greatly deviates from the average value of the state estimation results of the plurality of hydraulic servo valves 100, it can be determined that the hydraulic servo valve 100 is in an abnormal state. A deviation value of the state estimation result of each of the plurality of hydraulic servo valves 100 may be calculated, and a hydraulic servo valve 100 having a deviation value of a predetermined threshold value, for example, 80 or more or less than a predetermined threshold value, for example, 30 may be determined to be in an abnormal state.

Fig. 7 is a flowchart showing the procedure of the state estimation method of the present embodiment. First, a procedure of a stage of generating an estimation model is explained. When the ship 2 on which the hydraulic servo valve 100 is mounted is sailing, data relating to the operation of the hydraulic servo valve 100 is recorded in the log data storage device 90 (step S10). The learning data acquisition unit 301 of the learning device 300 acquires the log data recorded in the log data storage device 90 as learning data (step S12). The learning data acquisition section 301 also acquires experimental data or simulation data as learning data. The estimation model generation unit 302 generates an estimation model based on the acquired learning data (step S14). The estimation model providing unit 303 provides the generated estimation model to the state estimation device 400 (step S16).

Next, a procedure of a stage of estimating the state of the hydraulic servo valve 100 using the estimation model is described. When the ship 2 on which the hydraulic servo valve 100 is mounted is sailing, data relating to the operation of the hydraulic servo valve 100 is recorded in the log data storage device 90 (step S20). The probe information acquisition section 401 of the state estimation device 400 acquires the probe information recorded in the log data storage device 90 (step S22). The state estimating unit 402 estimates the state of the hydraulic servo valve 100 using the estimation model based on the acquired detection information (step S24). The estimation result output unit 403 outputs the estimation result (step S26).

A specific example of the management system of the present embodiment will be described.

Example 1: estimation of internal oil leakage amount

When the pilot valve 10 is used for a long time, the valve body 14 wears and the pitch of the valve decreases, and the a port 16a, the P port 16P, and the T port 16T slightly communicate with each other even in the neutral mode. When the hydraulic oil 48 leaks from the P port 16P to the a port 16a in the neutral mode, the hydraulic pressure of the hydraulic oil reservoir 22a gradually increases, the fuel supply amount to the engine 80 increases, and the fuel consumption rate of the engine 80 deteriorates. When the hydraulic oil 48 leaks from the a port 16a to the T port 16T in the neutral mode, the hydraulic pressure of the hydraulic oil reservoir 22a gradually decreases, the fuel supply amount to the engine 80 decreases, and the output of the engine 80 decreases. When the leakage amount of the working oil 48 exceeds the allowable amount, the hydraulic servo valve 100 no longer functions normally, resulting in a malfunction. If the amount of leakage can be estimated with high accuracy, the hydraulic servo valve 100 is replaced or repaired before the amount of leakage exceeds the allowable amount, and unexpected malfunction can be avoided.

As described above, when the hydraulic servo valve 100 normally operates, the spool 28 of the main valve 20 is stationary when the spool 12 of the pilot valve 10 is in the neutral position, but if the leakage amount of the hydraulic oil 48 increases, the spool 28 of the main valve 20 moves even when the spool 12 of the pilot valve 10 is in the neutral position. Experiments by the present inventors have found that there is a strong correlation between the movement speed of the valve member 28 of the main valve 20 and the amount of leakage of the hydraulic oil 48 when the valve member 12 of the pilot valve 10 is at the neutral position. Therefore, the internal oil leakage amount in the pilot valve 10 can be estimated from the moving speed of the valve member 28 of the main valve 20 when the valve member 12 of the pilot valve 10 is at the neutral position.

[ example 1-1]

Fig. 8 shows the configurations of the learning device and the state estimation device according to embodiment 1-1. In the learning device 300 of the present embodiment, the learning data acquisition unit 301 acquires the pilot valve actual valve element position 310, the main valve actual valve element position 311, and the internal oil leakage amount actual measurement value 312 as learning data.

The pilot valve actual spool position 310 and the main valve actual spool position 311 are time-series data when the hydraulic servo valve 100 is used for a predetermined period before or after the time point when the internal oil leakage amount is actually measured. The time-series data may be time-series data of 1 to several cycles of the rotational operation of engine 80. Since the position of the valve element 12 of the pilot valve 10 is at least several times set to the neutral position in 1 cycle of the rotational operation of the engine 80, the time-series data of the pilot valve actual valve element position 310 and the main valve actual valve element position 311 in 1 cycle includes information indicating the movement speed of the valve element 28 of the main valve 20 when the valve element 12 of the pilot valve 10 is set to the neutral position.

The internal oil leakage amount actual measurement value 312 is a value of the internal oil leakage amount in the hydraulic servo valve 100. When log data or test data is used as the learning data, the internal oil leakage amount actual measurement value 312 is a value of an internal oil leakage amount actually measured by a flowmeter or the like. Since it is considered that the internal oil leakage amount does not change rapidly during the use of the hydraulic servo valve 100, it is considered that the hydraulic servo valve 100 is used in a state in which the actually measured amount of hydraulic oil 48 leaks inside for a predetermined period before or after the time point at which the internal oil leakage amount is actually measured, and the actual pilot valve spool position 310 and the actual main valve spool position 311 recorded during the predetermined period are associated with the actual internal oil leakage amount measurement value 312 to be used as learning data. The predetermined period may be a period in which the amount of internal oil leakage remains the same during the use of the hydraulic servo valve 100, and may be defined by the time of use of the hydraulic servo valve 100, the operation time of the engine 80, the number of revolutions of the engine 80, and the like. When the simulation data is used as the learning data, the internal oil leakage amount actual measurement value 312 is a value of the internal oil leakage amount input to the simulator as the simulation condition.

The internal oil leakage amount estimation model generation unit 313 generates an internal oil leakage amount estimation model used in the state estimation device 400 to estimate the internal oil leakage amount of the hydraulic servo valve 100, using the learning data acquired by the learning data acquisition unit 301. The internal oil leakage amount estimation model may be a neural network or the like that inputs time-series data of the pilot valve actual spool position 310 and the main valve actual spool position 311 for a predetermined period to the input layer and outputs the internal oil leakage amount of the hydraulic servo valve 100 from the output layer. In this case, the internal oil leakage amount estimation model generation unit 313 performs learning of the internal oil leakage amount estimation model by adjusting the intermediate layer of the neural network so that a value approximate to the internal oil leakage amount actual measurement value 312 is output from the output layer when the time-series data of the pilot valve actual valve element position 310 and the main valve actual valve element position 311 for a predetermined period is input to the input layer.

The internal oil leakage amount estimation model providing unit 314 provides the internal oil leakage amount estimation model generated by the internal oil leakage amount estimation model generation unit 313 to the state estimation device 400.

The detection information acquisition unit 401 acquires a pilot valve actual spool position 410 and a main valve actual spool position 411 as detection information. The probe information is time-series data of the same predetermined period as the learning data used for generating the internal leakage amount estimation model.

The internal oil leakage estimating unit 412 estimates the internal oil leakage of the hydraulic servo valve 100 using the internal oil leakage estimation model generated by the learning device 300. The internal oil leakage amount estimating unit 412 inputs the time-series data of the pilot valve actual valve element position 410 and the main valve actual valve element position 411 acquired by the probe information acquiring unit 401 to the internal oil leakage amount estimating model, and acquires the internal oil leakage amount output from the internal oil leakage amount estimating model as an estimation result.

The internal oil leakage amount estimated value output unit 413 outputs the estimated value of the internal oil leakage amount estimated by the internal oil leakage amount estimation unit 412. The internal oil leakage amount estimation value output unit 413 may notify that the hydraulic servo valve 100 is in an abnormal state when it is estimated that the state is abnormal. Whether or not the internal oil leakage amount estimation unit 412 is in the abnormal state may be determined by whether or not the value of the internal oil leakage amount output is equal to or greater than a predetermined threshold value, or may be determined by whether or not the amount of change in the internal oil leakage amount from the initial value is equal to or greater than a predetermined threshold value. The internal oil leakage amount estimated value output unit 413 may determine whether or not the hydraulic servo valve 100 is in an abnormal state by comparing the internal oil leakage amount values of the plurality of hydraulic servo valves 100 provided corresponding to the plurality of cylinders 81 of the same engine 80. For example, when the value of the internal oil leakage amount of a specific hydraulic servo valve 100 greatly deviates from the average value of the internal oil leakage amounts of the plurality of hydraulic servo valves 100, it can be determined that the hydraulic servo valve 100 is in an abnormal state. A deviation value of the internal oil leakage amount of each of the plurality of hydraulic servo valves 100 may be calculated, and a hydraulic servo valve 100 having a deviation value of a predetermined threshold value, for example, 80 or more or less than a predetermined threshold value, for example, 30 may be determined to be in an abnormal state.

[ examples 1-2]

Fig. 9 shows the configurations of the learning device and the state estimation device according to embodiments 1 to 2. The learning device 300 according to embodiment 1-2 includes a feature amount calculation unit 315 in addition to the configuration of the learning device 300 according to embodiment 1-1 shown in fig. 8. The state estimation device 400 according to embodiment 1-2 includes a feature amount calculation unit 414 in addition to the configuration of the state estimation device 400 according to embodiment 1-1 shown in fig. 8. Points different from example 1-1 will be mainly explained. Otherwise, the same points as in example 1-1 were used.

The feature amount calculation unit 315 of the learning device 300 calculates a feature amount having a correlation with the internal leakage amount from the pilot valve actual valve element position 310 or the main valve actual valve element position 311 acquired by the learning data acquisition unit 301. As described above, as a result of experiments by the present inventors, since the internal leakage amount has a correlation with the movement speed of the valve member 28 of the main valve 20 when the valve member 12 of the pilot valve 10 is at the neutral position, the characteristic amount calculation unit 315 calculates the movement speed of the valve member 28 of the main valve 20 from the main valve actual valve member position 311 while the pilot valve actual valve member position 310 is at the neutral position. When there is a time lag from when the spool 12 of the pilot valve 10 moves to the neutral position until the supply of the hydraulic oil to the main valve 20 is stopped and the position of the spool 28 of the main valve 20 is stationary, the characteristic amount calculation unit 315 may calculate the movement speed of the spool 28 of the main valve 20 after the time lag is adjusted. The amount of adjustment of the time lag may be determined in advance by experiments or the like, depending on the type and temperature of the hydraulic servo valve 100, the pressure of the hydraulic oil 48, the environment in which the hydraulic servo valve 100 is used, such as the number of revolutions, load, and exhaust temperature of the engine 80.

The internal oil leakage amount estimation model generation unit 313 generates an internal oil leakage amount estimation model using the learning data acquired by the learning data acquisition unit 301 and the feature amount calculated by the feature amount calculation unit 315. The internal oil leakage amount estimation model generation unit 313 may generate an internal oil leakage amount estimation model using the internal oil leakage amount actual measurement value 312 and the feature amount calculated by the feature amount calculation unit 315. For example, the internal oil leakage amount estimation model may be a numerical expression that calculates the internal oil leakage amount using the characteristic amount as an input variable. In this case, the internal oil leakage amount estimation model generation unit 313 may generate the numerical expression by a statistical method such as regression analysis. The internal oil leakage amount estimation model generation unit 313 may generate an internal oil leakage amount estimation model using the pilot valve actual spool position 310, the main valve actual spool position 311, and the characteristic amount. For example, the internal oil leakage amount estimation model may be a neural network or the like that inputs time-series data of the pilot valve actual valve element position 310 and the main valve actual valve element position 311 over a predetermined period and a characteristic amount within the predetermined period to the input layer and outputs the internal oil leakage amount from the output layer. In this case, the internal oil leakage amount estimation model generation unit 313 learns the internal oil leakage amount estimation model by adjusting the intermediate layer of the neural network so that a value approximate to the internal oil leakage amount actual measurement value 312 is output from the output layer when the time-series data of the pilot valve actual valve element position 310 and the main valve actual valve element position 311 for a predetermined period and the feature amount within the predetermined period are input to the input layer.

The characteristic amount calculation unit 414 of the state estimation device 400 calculates the characteristic amount from the pilot valve actual valve element position 410 or the main valve actual valve element position 411 acquired by the probe information acquisition unit 401 by the same method as the method of calculating the characteristic amount by the characteristic amount calculation unit 315 when generating the internal leakage amount estimation model used by the internal leakage amount estimation unit 412. When the pilot valve actual spool position 410 and the main valve actual spool position 411 of the hydraulic servo valve 100 used in an environment different from the learning data used in generating the internal leakage amount estimation model are acquired by the detection information acquisition unit 401, the characteristic amount calculation unit 414 may calculate the characteristic amount after adjusting the difference in environment. For example, the adjustment amount of the time lag may be changed according to the environment. This can improve the robustness of the estimation of the internal oil leakage amount.

[ examples 1 to 3]

Fig. 10 shows the configurations of the learning device and the state estimation device according to embodiments 1 to 3. In the learning device 300 of embodiment 1-2 shown in fig. 9, the learning data acquisition unit 301 acquires the pilot valve actual valve element position 310, but in the learning device 300 of embodiment 1-3, the learning data acquisition unit 301 acquires the pilot valve target valve element position 316 instead of the pilot valve actual valve element position 310. In the state estimation device 400 according to embodiment 1-2 shown in fig. 9, the detection information acquisition unit 401 acquires the pilot valve actual spool position 410, but in the state estimation device 400 according to embodiment 1-3, the detection information acquisition unit 401 acquires the pilot valve target spool position 415 instead of the pilot valve actual spool position 410. Points different from those in example 1-2 will be mainly explained. Otherwise, the same points as in example 1-1 or 1-2 were used.

As described above, depending on the connection position of the log data storage device 90, the actual valve body position of the pilot valve may not be recorded when the hydraulic servo valve 100 is used. In this case, as the learning data and the detection information, the pilot valve target spool position is used instead of the pilot valve actual spool position. Thereby, the internal oil leakage amount estimation model can be generated using data that can be acquired without depending on the connection position of the log data storage device 90, and the internal oil leakage amount can be estimated using the internal oil leakage amount estimation model. In the example of fig. 10, the feature amount calculation unit 315 and the feature amount calculation unit 414 are provided as in the example 1-2, but a feature amount calculation unit may be provided separately as in the example 1-1.

[ examples 1 to 4]

Fig. 11 shows the configurations of the learning device and the state estimation device according to embodiments 1 to 4. The learning device 300 according to embodiments 1 to 4 includes an offset time calculating unit 319 in addition to the configuration of the learning device 300 according to embodiments 1 to 3 shown in fig. 10. In the learning device 300 according to embodiments 1 to 4, the learning data acquisition unit 301 also acquires the coil drive voltage 317 and the pilot valve physical parameter 318. In addition, in the state estimating device 400 of the embodiment 1 to 4, the detection information acquiring section 401 also acquires the coil driving voltage 416. Points different from examples 1 to 3 will be mainly explained. The other points are the same as in examples 1-1 to 1-3.

When a command signal for a target position of the valve body 12 is input from the servo valve control device 110 to the pilot valve 10, a current is supplied to the coil of the valve body driving unit 18, and there is a time lag until the valve body 12 actually reaches the target position. Therefore, when the pilot valve target spool position 316 is used as the learning data instead of the pilot valve actual spool position 310, the accuracy of the internal oil leakage amount estimation model can be improved because the internal oil leakage amount estimation model can be generated based on the position of the spool 28 of the main valve 20 when the actual position of the spool 12 of the pilot valve 10 actually follows the neutral position by adjusting the offset time required until the actual position of the spool 12 of the pilot valve 10 follows the pilot valve target spool position 316.

The offset time calculation section 319 calculates the offset time based on the coil drive voltage 317 and the pilot valve physical parameter 318. The pilot valve physical parameter 318 includes physical quantities such as a resistance value of an element constituting a drive circuit of the valve element drive unit 18, an inductance of a coil, a mass of the valve element 12, and a friction coefficient between the main body 10b and the valve element 12. The offset time calculation section 319 calculates the offset time from the equation of motion including these physical parameters and the coil drive voltage 317. In the case where the offset time may differ depending on the position, the moving direction, the moving speed, and the like of the spool 12 of the pilot valve 10, the offset time may also be calculated using these data.

When the learning device 300 generates an internal oil leakage amount estimation model for estimating the internal oil leakage amount of the specific type of hydraulic servo valve 100, the pilot valve physical parameter 318 may be treated as a constant. This also enables the use of the log data in which the pilot valve physical parameter 318 is not recorded as the learning data. As the pilot valve physical parameter 318, a constant predetermined according to the type of the hydraulic servo valve 100 may be used. As the pilot valve physical parameter 318, a physical parameter measured at the time of shipment of the hydraulic servo valve 100 may be used. This can suppress the influence of variations in the physical parameter of the pilot valve due to individual differences of the hydraulic servo valve 100, and can calculate the offset time more accurately. As the pilot valve physical parameter 318, a physical parameter measured at the time of maintenance such as inspection of the hydraulic servo valve 100 can be used. This can suppress the influence of the secular change of the pilot valve 10, and can calculate the offset time more accurately.

The internal oil leakage amount estimation model generation unit 313 may generate an internal oil leakage amount estimation model that outputs an internal oil leakage amount by inputting the pilot valve actual spool position 410 and the main valve actual spool position 411 in the same manner as in embodiment 1-1 or 1-2, may generate an internal oil leakage amount estimation model that outputs an internal oil leakage amount by inputting the pilot valve target spool position 415 and the main valve actual spool position 411 in the same manner as in embodiment 1-3, may generate an internal oil leakage amount estimation model that outputs an internal oil leakage amount by inputting the pilot valve target spool position 415, the main valve actual spool position 411, and the coil drive voltage 416, and may generate an internal oil leakage amount estimation model that outputs an internal oil leakage amount by inputting the pilot valve physical parameters or the offset time in addition to these. In the example of the present figure, the internal oil leakage amount estimation model outputs the internal oil leakage amount by inputting the pilot valve target spool position 415, the main valve actual spool position 411, and the coil drive voltage 416. Since the coil drive voltage 416 supplied from the power supply circuit 120 of the servo valve control device 110 to the coil can vary according to the number of revolutions of the engine 80 or the like, by generating an internal leakage amount estimation model in which the pilot valve target spool position 415 and the main valve actual spool position 411 are input and the coil drive voltage 416 is input and the internal leakage amount is output, the influence of variation in the offset time can be suppressed and the estimation accuracy can be improved.

The probe information acquisition unit 401 of the state estimation device 400 acquires probe information that needs to be input to the internal oil leakage amount estimation model used by the internal oil leakage amount estimation unit 412. In the example of the present figure, the detection information acquisition unit 401 acquires a pilot valve target spool position 415, a main valve actual spool position 411, and a coil drive voltage 416. In the case where the pilot valve physical parameter needs to be input to the internal oil leakage amount estimation model, the detection information acquisition section 401 may further acquire the pilot valve physical parameter. Alternatively, the internal oil leakage amount estimating unit 412 may hold in advance a physical parameter corresponding to the type of the hydraulic servo valve 100 to be subjected to the estimation of the internal oil leakage amount. In addition, in the case where the offset time needs to be input to the internal oil leakage amount estimation model, the detection information acquisition unit 401 may further acquire the offset time. Alternatively, the state estimation device 400 may further include an offset time calculation unit that calculates an offset time based on the coil drive voltage 416, a pilot valve physical parameter, and the like.

[ examples 1 to 5]

Fig. 12 shows the configurations of the learning device and the state estimation device according to embodiments 1 to 5. The learning device 300 according to embodiments 1 to 5 includes a data selection unit 320 in addition to the configuration of the learning device 300 according to embodiment 1 to 1 shown in fig. 8. In addition, the learning device 300 according to embodiment 1-5 includes a data selection unit 417 in addition to the configuration of the state estimation device 400 according to embodiment 1-1 shown in fig. 8. Points different from example 1-1 will be mainly explained. The other points are the same as in examples 1-1 to 1-4.

In the present embodiment, in order to improve the estimation accuracy by the internal oil leakage amount estimation model, the internal oil leakage amount estimation model is generated using log data when the hydraulic servo valve 100 is used in the same environment as the environment in which the hydraulic servo valve 100 that is the target of the state estimation device 400 for estimating the internal oil leakage amount is used. This can suppress the influence of the environment and improve the robustness of the estimation of the internal oil leakage amount.

The data selection unit 320 selects the learning data recorded when the hydraulic servo valve 100 is used in a specific environment from the learning data acquired by the learning data acquisition unit 301. The data selection unit 320 may select the learning data recorded when the hydraulic servo valve 100 is used in a specific environment, by referring to data indicating the usage environment of the hydraulic servo valve 100 included in log data, test data, simulation data, and the like, for example, the exhaust temperature, pressure, and the like of the cylinder 81 of the engine 80. The data selecting unit 320 may classify the learning data for each environment. In this case, the internal oil leakage amount estimation model may be generated for each environment. The learning data such as log data, test data, and simulation data may be recorded or generated in a specific environment, or may be classified for each usage environment at the time of recording or generation. In this case, the learning data acquisition unit 301 may acquire the recorded, generated, or classified learning data in a specific environment, and thus the data selection unit 320 may not be provided.

The data selection unit 417 selects the probe information recorded when the hydraulic servo valve 100 is used in a specific environment from the probe information acquired by the probe information acquisition unit 401. The data selection unit 417 may select probe information recorded in the same environment as the environment in which the learning data used when the internal oil leakage amount estimation model used by the internal oil leakage amount estimation unit 412 is generated is recorded. When the state estimation device 400 holds a plurality of internal oil leakage amount estimation models generated for each usage environment, the internal oil leakage amount estimation unit 412 may select an internal oil leakage amount estimation model to be used by referring to data indicating the usage environment of the hydraulic servo valve 100 included in the probe information. In this case, the data selection unit 417 may not be provided.

The internal oil leakage amount estimation model may be generated using learning data recorded when the hydraulic servo valve 100 is operated in a test mode in which the valve body 12 of the pilot valve 10 is operated in a specific pattern. In this case, the state estimation device 400 estimates the amount of internal oil leakage using the detection information recorded when the hydraulic servo valve 100 is operated in the test mode. This can improve the robustness of the estimation of the internal oil leakage amount.

In order to further suppress the influence of the use environment, log data, test data, simulation data, and the like recorded when the engine 80 is stopped may be used as the learning data. When a stop command is issued from the engine control device 91 to the servo valve control device 110 while the engine 80 is stopped, but the hydraulic oil 48 is being pressurized by the hydraulic pump 42, the servo valve control device 110 repeatedly moves the valve body 12 of the pilot valve 10 in a pattern of small amplitude to the extent that fuel is not supplied to the engine 80 in order to prevent sticking of the valve body 12 of the pilot valve 10 and the valve body 28 of the main valve 20. Even when the internal oil leakage amount estimation model is generated using the learning data recorded during the sticking prevention operation and the state estimation device 400 estimates the internal oil leakage amount of the hydraulic servo valve 100, the influence of disturbance such as vibration caused by the operation of the engine 80 can be suppressed by using the log data recorded during the sticking prevention operation, thereby improving the estimation accuracy. The pattern of the blocking prevention action may be a sine wave pattern, a sawtooth wave pattern, a dither pattern, or the like. In the case where the adhesion preventing operation is performed according to a plurality of different patterns, the learning data and the detection information recorded when the adhesion preventing operation is performed according to a specific pattern may be used.

Example 1 modification

In addition to the data used as the learning data and the detection information in examples 1-1 to 1-5, any of other data such as the number of engine revolutions, the engine load, the hydraulic oil pressure, and the hydraulic oil temperature, or any combination of these data may be used as the learning data and the detection information. Of these data, data that can affect data such as the pilot valve actual spool position, the pilot valve target spool position, and the main valve actual spool position as an environmental factor may be selected and used. By generating an internal oil leakage amount estimation model reflecting the influence of these data, the robustness of estimation of the internal oil leakage amount can be further improved.

The features described in embodiments 1-1 to 1-5 above can be applied in any combination.

Example 2: failure determination of Power supply

In embodiment 2, a technique for determining a failure of a power supply that supplies power to the power supply circuit 120 and the power supply circuit 120 will be described. When the power supply or the power supply circuit 120 fails, the hydraulic servo valve 100 no longer operates normally, and thus an abnormality such as a decrease in the output of the engine 80 occurs. If the failure of the power supply or the power supply circuit 120 can be predicted with high accuracy, the power supply or the power supply circuit 120 can be replaced or repaired before the failure of the power supply or the power supply circuit 120 occurs, so that unexpected abnormality can be avoided.

Since the hydraulic servo valve 100 for controlling fuel supply and exhaust to and from the engine 80 repeats a fixed operation while the engine 80 is driven, a fixed pattern can be seen between the operation waveform of the spool 12 of the pilot valve 10 or the spool 28 of the main valve 20 and the power supply voltage waveform. Therefore, by modeling the difference between the pattern of the operating waveform and the power supply voltage waveform at the time of normal operation and the pattern of the operating waveform and the power supply voltage waveform at the time of a premonitory failure, it is possible to determine a failure of the power supply or the power supply circuit 120.

Fig. 13 shows the configuration of a learning device and a state estimation device according to embodiment 2. In the learning device 300 of the present embodiment, the learning data acquisition unit 301 acquires the power supply voltage 321, the pilot valve actual valve body position 310, and the power failure precursor index value 322 as learning data.

The pilot valve actual valve body position 310 is time-series data when the hydraulic servo valve 100 is used for a predetermined period before or after the time point when the power failure precursor index value 322 is actually measured. The power supply voltage 321 is time-series data of the power supply voltage detected by the voltage detection unit 150 when the pilot valve actual spool position 310 is recorded. The power supply voltage 321 may be an input voltage to be input to the power supply circuit 120, may be an output voltage to be output from the power supply circuit 120, or may be both of them. These time-series data may be time-series data of 1 to several cycles of the rotational operation of engine 80.

The power failure precursor index value 322 is calculated based on the accumulated operating time of the power supply circuit 120, the deterioration state of elements such as capacitors constituting the power supply circuit 120, the actual measurement value of the emission noise emitted from the power supply circuit 120, and the like. The calculation method of the power failure precursor index value 322 may be determined by experiments, field tests, and the like.

When the log data or the experimental data is used as the learning data, the power failure precursor index value 322 is calculated based on the actual measurement values of the variables described above. Since the power failure precursor index value 322 is considered not to change abruptly during the use of the hydraulic servo valve 100, it is considered that the power failure precursor index value 322 does not change for a predetermined period before or after the time point at which the variable for calculating the power failure precursor index value 322 is actually measured, and the power supply voltage 321 and the pilot valve actual valve body position 310 recorded during the predetermined period are associated with the power failure precursor index value 322 and are set as learning data. The predetermined period may be a period in which the power failure precursor index value 322 remains the same during the use of the hydraulic servo valve 100, and may be defined by the use time of the hydraulic servo valve 100, the operation time of the engine 80, the number of revolutions of the engine 80, and the like. In the case of using simulation data as learning data, the power failure precursor index value 322 is calculated based on the values of variables input to the simulator as simulation conditions.

The power failure determination model generation unit 323 generates a power failure determination model used in the state estimation device 400 to determine a failure of the power supply or the power supply circuit 120, using the learning data acquired by the learning data acquisition unit 301. The power failure determination model may be a neural network or the like that inputs the power supply voltage 321 and time-series data of the pilot valve actual valve element position 310 over a predetermined period to the input layer and outputs a power failure precursor index value from the output layer. In this case, the power failure determination model generation unit 323 performs power failure determination model learning by adjusting the intermediate layer of the neural network so that a value close to the power failure precursor index value 322 is output from the output layer when the power supply voltage 321 and the time-series data of the pilot valve actual valve element position 310 over a predetermined period are input to the input layer.

The power failure determination model providing unit 324 provides the power failure determination model generated by the power failure determination model generating unit 323 to the state estimating apparatus 400.

The detection information acquisition section 401 acquires the power supply voltage 420 and the pilot valve actual spool position 410 as detection information. The probe information is time-series data of the same predetermined period as the learning data used for generating the power failure determination model.

The power failure determination unit 421 determines a failure of the power supply of the hydraulic servo valve 100 or the power supply circuit 120 using the power failure determination model generated by the learning device 300. The power failure determination unit 421 inputs the power supply voltage 420 acquired by the probe information acquisition unit 401 and the time-series data of the pilot valve actual valve body position 410 to the power failure determination model, and acquires the power failure precursor index value output from the power failure determination model as a determination result. The power failure determination unit 421 may determine whether or not the power supply or the power supply circuit 120 has failed based on the output power failure precursor index value. For example, the power failure determination unit 421 may determine that the power supply or the power supply circuit 120 has failed when the output power failure precursor index value is equal to or greater than a predetermined threshold value, and the power failure determination unit 421 may determine that the power supply or the power supply circuit 120 has failed when the amount of change in the power failure precursor index value from the initial value is equal to or greater than the predetermined threshold value. The power failure determination unit 421 may estimate the period until the power supply or the power supply circuit 120 fails, that is, the lifetime, based on the output power failure precursor index value. For example, the power failure determination unit 421 may estimate the lifetime by using an expression or the like having the output power failure precursor index value as a variable. The power failure determination model may be configured to output the presence or absence of failure of the power supply or the power supply circuit 120, the lifetime of the power supply or the power supply circuit 120, or the presence or absence of failure of the power supply or the power supply circuit 120, or the lifetime of the power supply or the power supply circuit 120, in addition to the power failure precursor index value.

When the power supply circuit 120 is provided in each of the plurality of hydraulic servo valves 100 provided corresponding to the plurality of cylinders 81 of the same engine 80, the power supply failure determination unit 421 may determine whether or not the power supply circuit 120 has failed by comparing the power supply failure precursor index values of the respective hydraulic servo valves 100. For example, when the power supply failure precursor index value of a specific hydraulic servo valve 100 greatly deviates from the average value of the power supply failure precursor index values of the plurality of hydraulic servo valves 100, it can be determined that the power supply circuit 120 of the hydraulic servo valve 100 has failed. A deviation value of the power failure precursor index value of each of the plurality of hydraulic servo valves 100 is calculated, and it is determined that a failure has occurred in the power supply circuit 120 of the hydraulic servo valve 100 having a deviation value of a predetermined threshold value, for example, 80 or more or less than a predetermined threshold value, for example, 30.

The power failure determination result output unit 422 outputs the result determined by the power failure determination unit 421. When the power failure determination unit 421 determines that the power supply of the hydraulic servo valve 100 or the power supply circuit 120 has failed, the power failure determination result output unit 422 may notify this fact. The power failure determination result output unit 422 may output the life of the power supply or the power supply circuit 120 determined by the power failure determination unit 421.

It is found through experiments by the present inventors that the amount of decrease in the power supply voltage corresponding to the peak value of the load current has a correlation with a failure of the power supply or the power supply circuit 120. Therefore, when an ammeter for detecting the value of the current supplied to the hydraulic servo valve 100 is provided, the current value measured by the ammeter may be used instead of the pilot valve actual valve element position 310 or may be used in addition to the pilot valve actual valve element position 310 as the learning data and the detection information. This can improve the accuracy of failure determination.

The amount of decrease in the power supply voltage corresponding to the peak value of the load current can be calculated from the power supply voltage and the actual valve element position of the pilot valve. In this case, the learning device 300 may further include a feature amount calculation unit 315, and the state estimation device 400 may further include a feature amount calculation unit 414, as in embodiment 1-2.

The feature value calculation unit 315 of the learning device 300 calculates the amount of decrease in the power supply voltage corresponding to the peak value of the load current as a feature value having a correlation with a failure of the power supply or the power supply circuit 120, based on the power supply voltage 321 acquired by the learning data acquisition unit 301 and the pilot valve actual valve body position 310. The characteristic amount calculation section 315 may calculate the value of the current supplied to the hydraulic servo valve 100 based on the acceleration or the speed of the valve body 12 of the pilot valve 10 calculated from the variation of the pilot valve actual valve body position 310. The feature amount calculation unit 315 may calculate the amount of decrease in the power supply voltage based on the value of the power supply voltage 321 when the calculated current value becomes the peak value. In the case where there is a time lag from when the power supply circuit 120 supplies electric power to the coil of the valve body driving portion 18 of the pilot valve 10 until the valve body 12 of the pilot valve 10 moves, the characteristic amount calculation portion 315 may calculate the acceleration or speed of the valve body 12 of the pilot valve 10 after adjusting the time lag. The amount of adjustment of the time lag may be determined in advance by experiments or the like, depending on the type and temperature of the hydraulic servo valve 100, the pressure of the hydraulic oil 48, the environment in which the hydraulic servo valve 100 is used, such as the number of revolutions, load, and exhaust temperature of the engine 80.

The power failure determination model generation unit 323 generates a power failure determination estimation model using the learning data acquired by the learning data acquisition unit 301 and the feature amount calculated by the feature amount calculation unit 315. The power failure determination model generation unit 323 can generate a power failure determination model using the power failure precursor index value 322 and the feature amount calculated by the feature amount calculation unit 315. For example, the power failure determination model may be a numerical expression in which a power failure precursor index value is calculated using the feature amount as an input variable. In this case, the power failure determination model generation unit 323 may generate the numerical expression by a statistical method such as regression analysis. The power failure determination model generation unit 323 can generate a power failure determination model using the power supply voltage 321, the pilot valve actual valve body position 310, and the feature amount. For example, the power failure determination model may be a neural network or the like that inputs the power supply voltage 321 and time-series data of the pilot valve actual valve element position 310 over a predetermined period and the feature value of the predetermined period to the input layer and outputs a power failure precursor index value from the output layer. In this case, the power failure determination model generation unit 323 adjusts the intermediate layer of the neural network so that a value close to the power failure precursor index value 322 is output from the output layer when the power supply voltage 321, the time-series data of the pilot valve actual valve element position 310 over the predetermined period, and the feature amount over the predetermined period are input to the input layer, thereby learning the power failure determination model.

The feature amount calculation unit 414 of the state estimation device 400 calculates the feature amount from the power supply voltage 420 and the pilot valve actual valve body position 410 acquired by the probe information acquisition unit 401 by the same method as the method of calculating the feature amount by the feature amount calculation unit 315 when generating the power failure determination model used by the power failure determination unit 421. When the power supply voltage 420 and the pilot valve actual valve element position 410 of the hydraulic servo valve 100 used in an environment different from the learning data used when the power failure determination model is generated are acquired by the probe information acquisition portion 401, the characteristic amount calculation portion 414 may calculate the characteristic amount after adjusting the difference in environment. For example, the adjustment amount of the time lag may be changed according to the environment. This can improve the robustness of power failure determination. Further, since the amount of drop in the power supply voltage corresponding to the peak value of the load current can be calculated as the characteristic amount without installing the ammeter, the efficiency of the circuit can be improved and the cost can be reduced.

As the characteristic amount, a physical amount or the like indicating a characteristic of the operation of the valve body 12 of the pilot valve 10 may be calculated. For example, the acceleration, the speed, the overshoot amount, the delay amount, and the like of the spool 12 of the pilot valve 10 may be calculated as the characteristic amount.

As the learning data and the detection information, a pilot valve target spool position or a main valve actual spool position may be used instead of or in addition to the pilot valve actual spool position. In this case, as in embodiments 1 to 4, the learning device 300 may include an offset time calculation unit 319 for adjusting the offset time required until the actual valve element position of the pilot valve 10 follows the target valve element position of the pilot valve. The offset time calculation unit 319 may calculate an offset time between a variation in the current supplied to the hydraulic servo valve 100 and a variation in the power supply voltage in order to calculate a drop amount of the power supply voltage when the value of the current supplied to the hydraulic servo valve 100 becomes a peak value. The method of calculating the offset time may be the same as in embodiment 1-2.

As the learning data and the detection information, data recorded when the hydraulic servo valve 100 is used in a specific environment may be used. In this case, the learning device 300 may further include a data selection unit 320 and the state estimation device 400 may further include a data selection unit 417, as in embodiments 1 to 5. The data selection unit 320 and the data selection unit 417 can select data recorded when the hydraulic servo valve 100 is operated in a test mode in which the valve body 12 of the pilot valve 10 is operated in a specific pattern. This can improve the robustness of failure determination. The data selection unit 320 and the data selection unit 417 may select data recorded when the engine 80 is stopped and the valve element sticking prevention operation is being performed. This can suppress the influence of the disturbance and improve the failure determination accuracy.

Example 3: detection of foreign matter jamming

In embodiment 3, a technique for detecting that foreign matter is caught between the body portion 10b of the pilot valve 10 and the valve body 12 will be described. When a foreign object is caught between the main body portion 10b and the valve body 12, the valve body 12 of the pilot valve 10 does not normally operate any more, and therefore, an alarm is issued when the actual valve body position of the main valve 20 deviates from the target valve body position. The cause of the alarm cannot be identified in the past, but if the jammed foreign matter can be detected with high accuracy, the cause of the alarm can be identified when the alarm is issued, and appropriate treatment can be quickly taken.

Fig. 14 schematically illustrates the operation of the spool 12 of the pilot valve 10 and the spool 28 of the main valve 20. Fig. 14 (a) shows an operation example in the case where the hydraulic servo valve 100 is normally controlled. When the target spool position of the main valve 20 is input at time t1, a positive value is input as the target spool position of the pilot valve 10 at time t2 in order to move the spool 28 of the main valve 20 in the positive direction. When the valve body 12 of the pilot valve 10 follows the target valve body position, the hydraulic oil is supplied to the main valve 20, and the valve body 28 of the main valve 20 starts moving in the forward direction at time t 3. At time t4, the target spool position of the main valve 20 is fixed to a fixed value, and when the actual spool position of the main valve 20 follows the target spool position, the neutral position is input as the target spool position of the pilot valve 10, and at time t5, the spool 28 of the main valve 20 is stationary at the target spool position.

Fig. 14 (b) shows an operation example in the case where a foreign object is caught in the pilot valve 10. The operation until time t4 is the same as that in fig. 14 (a), but at time t4, foreign matter is caught in the pilot valve 10. The neutral position is input as the target valve body position of the pilot valve 10, but the valve body 12 cannot move due to the foreign matter being caught, and therefore the hydraulic oil is continuously supplied to the main valve 20, and the valve body 28 of the main valve 20 continues to move in the positive direction. Since the feedback signal of the actual valve spool position of the main valve is constantly shifted from the target position, a negative value is continuously input as the target valve spool position of the pilot valve 10 in order to return the valve spool 28 of the main valve 20 to the target position. When the spool 28 of the main valve 20 reaches the extreme position in the positive direction, it no longer moves any further but is stationary in the extreme position.

As described above, the operation patterns of the spool 12 of the pilot valve 10 and the spool 28 of the main valve 20 are greatly different from each other in the normal state and when foreign matter is caught. Therefore, the foreign object can be detected by modeling the difference between the normal operation pattern and the operation pattern when the foreign object is caught. The operation pattern may be different depending on the type, size, amount, etc. of the foreign matter, and thus, not only the presence or absence of the foreign matter jamming but also the type, size, amount, etc. of the jammed foreign matter can be detected. Even when foreign matter is naturally removed after the foreign matter is temporarily caught, the history of the caught foreign matter can be detected from the log data, and therefore, the history can be used as evidence of the cause of the malfunction. In the vessel 2 or the like, the hydraulic oil circulates not only in the hydraulic servo valve 100 for controlling the engine 80 but also in the hydraulic servo valve for controlling other devices or the like, and therefore even if foreign matter temporarily caught in the hydraulic servo valve 100 is naturally removed, the foreign matter may be caught in other hydraulic servo valves or the like. According to the technique of the present embodiment, it is possible to detect the occurrence of the intrusion of the foreign matter in the hydraulic servo valve 100 and perform appropriate maintenance such as replacement of the hydraulic oil, and therefore, the intrusion of the foreign matter in another device can be suppressed.

Fig. 15 shows the configurations of the learning device and the state estimation device according to embodiment 3. In the learning device 300 of the present embodiment, the learning data acquisition unit 301 acquires the main-valve actual spool position 311, the main-valve target spool position 330, the pilot-valve target spool position 316, and the foreign-matter data 331 as learning data.

The main-valve actual spool position 311, the main-valve target spool position 330, and the pilot-valve target spool position 316 are time-series data when the hydraulic servo valve 100 is used for a predetermined period before or after the time point when the foreign matter data 331 is actually measured. These time-series data may be time-series data of 1 to several cycles of the rotational operation of engine 80.

The foreign object data 331 is data indicating the presence, kind, size, amount, and the like of a foreign object that has caught the pilot valve 10. In the case of using the log data as the learning data, the foreign object data 331 is an actual measurement value of the foreign object stuck in the pilot valve 10. In the case of using the test data as the learning data, the foreign matter data 331 is an actual measurement value of the foreign matter stuck into the pilot valve 10. In the case of using simulation data as learning data, the foreign substance data 331 is data of a foreign substance input to the simulator as a simulation condition.

The foreign object detection model generation unit 333 generates a foreign object detection model used in the state estimation device 400 to detect the intrusion of a foreign object, using the learning data acquired by the learning data acquisition unit 301. The foreign object detection model may be a neural network or the like that inputs time-series data of the main valve actual spool position 311, the main valve target spool position 330, and the pilot valve target spool position 316 over a predetermined period to the input layer and outputs foreign object data from the output layer. In this case, the foreign object detection model generation unit 333 performs foreign object detection model learning by adjusting the intermediate layer of the neural network so that a value similar to the foreign object data 331 is output from the output layer when the time-series data of the main valve actual spool position 311, the main valve target spool position 330, and the pilot valve target spool position 316 over a predetermined period is input to the input layer.

The foreign object detection model providing unit 334 provides the foreign object detection model generated by the foreign object detection model generating unit 333 to the state estimating apparatus 400.

The detection information acquisition unit 401 acquires, as detection information, a main-valve actual spool position 411, a main-valve target spool position 430, and a pilot-valve target spool position 415. The detection information is time-series data of the same predetermined period as the learning data used for generating the foreign object detection model.

The foreign object detection part 431 detects the jamming of the foreign object in the pilot valve 10 using the foreign object detection model generated by the learning device 300. The foreign object detection unit 431 inputs the time-series data of the main valve actual spool position 411, the main valve target spool position 430, and the pilot valve target spool position 415 acquired by the detection information acquisition unit 401 to the foreign object detection model, and acquires the foreign object data output from the foreign object detection model as a determination result. The foreign object detection part 431 may estimate a period until the foreign object is stuck into the pilot valve 10 based on the outputted foreign object data. In this case, the period until the foreign matter is caught is estimated by comparing the foreign matter data of the plurality of hydraulic servo valves 100 provided corresponding to the plurality of cylinders 81 of the same engine 80.

The foreign object detection result output section 432 outputs the result determined by the foreign object detection section 431. When the foreign object detection unit 431 detects that a foreign object is caught in the pilot valve 10, the foreign object detection result output unit 432 can notify this fact. The foreign object detection result output unit 432 may output a period until the foreign object is caught, which is estimated by the foreign object detection unit 431.

The presence or absence of the foreign object jamming or the feature quantity correlated with the type, size, or quantity of the jammed foreign object may be calculated from the main valve actual spool position, the main valve target spool position, the pilot valve target spool position, or the like. In this case, the learning device 300 may further include a feature amount calculation unit 315, and the state estimation device 400 may further include a feature amount calculation unit 414, as in embodiment 1-2. When there is a time lag from when the power supply circuit 120 supplies electric power to the coil of the valve body driving portion 18 of the pilot valve 10 until the valve body 12 of the pilot valve 10 moves and the main valve actual valve body position follows the main valve target valve body position, the characteristic amount calculating portion 315 may calculate the characteristic amount after adjusting the time lag. The amount of adjustment of the time lag may be determined in advance by experiments or the like, depending on the type and temperature of the hydraulic servo valve 100, the pressure of the hydraulic oil 48, the environment in which the hydraulic servo valve 100 is used, such as the number of revolutions, load, and exhaust temperature of the engine 80.

As the learning data and the detection information, the pilot valve actual spool position may be used instead of the pilot valve target spool position, or may be used in addition to the pilot valve target spool position. As the learning data and the detection information, any combination of 2 or more positions among the pilot valve target spool position, the pilot valve actual spool position, the main valve target spool position, and the main valve actual spool position may be used.

As the learning data and the detection information, data recorded when the hydraulic servo valve 100 is used in a specific environment may be used. In this case, the learning device 300 may further include a data selection unit 320 and the state estimation device 400 may further include a data selection unit 417, as in embodiments 1 to 5. The data selection unit 320 and the data selection unit 417 can select data recorded when the hydraulic servo valve 100 is operated in a test mode in which the valve body 12 of the pilot valve 10 is operated in a specific pattern. This can improve the robustness of detection of foreign matter jamming. The data selection unit 320 and the data selection unit 417 may select data recorded when the engine 80 is stopped and the valve element sticking prevention operation is being performed. This can suppress the influence of the disturbance and improve the detection accuracy of the foreign matter jam.

Example 4: evaluation of cleanliness of working oil

In example 4, a technique for estimating the cleanliness of the working oil will be described. If foreign matter is mixed into the hydraulic oil during the operation of the hydraulic servo valve 100 and the cleanliness is reduced, the operation of the valve element 12 of the pilot valve 10 is hindered by the influence of the mixed foreign matter or the pressure of the hydraulic oil supplied to the main valve 20 is reduced, which may cause an operation failure of the control target such as the engine 80. In addition, the possibility of foreign matter getting caught in the valve body 12 of the pilot valve 10 increases. By accurately estimating the cleanliness of the hydraulic oil and quickly taking appropriate measures when the cleanliness of the hydraulic oil decreases, it is possible to prevent foreign matter from getting stuck while maintaining the operation of the hydraulic servo valve 100 and the controlled object in a satisfactory manner.

When the cleanliness of the hydraulic oil is reduced by the contamination of a small amount of foreign matter, the friction force generated between the valve body 10b and the valve body 12 increases when the valve body 12 of the pilot valve 10 slides, and the behavior of the valve body 12 changes. Therefore, the cleanliness of the hydraulic oil can be estimated by modeling the difference in the pattern of the waveform of the current supplied to the coil of the valve element driving unit 18 of the pilot valve 10 and the operation waveform of the target valve element position and the actual valve element position of the pilot valve 10, which is caused by the cleanliness of the hydraulic oil.

Fig. 16 shows the configurations of the learning device and the state estimation device according to embodiment 4. In the learning device 300 of the present embodiment, the learning data acquisition unit 301 acquires the coil applied current 341, the pilot valve target valve body position 316, the pilot valve actual valve body position 310, and the actual hydraulic oil cleanliness value 342 as learning data.

The coil applied current 341, the pilot valve target valve body position 316, and the pilot valve actual valve body position 310 are time-series data when the hydraulic servo valve 100 is used for a predetermined period before or after the time point when the actual measurement value 342 of the hydraulic oil cleanliness is actually measured. These time-series data may be time-series data of 1 to several cycles of the rotational operation of engine 80.

The measured value 342 of the cleanliness of the hydraulic oil is data indicating the type, number, size, and the like of foreign matter mixed in the hydraulic oil. When the log data or the test data is used as the learning data, the measured value 342 of the cleanliness of the hydraulic oil used in the hydraulic servo valve 100 is measured by a general in-liquid particle measuring device or the like. The cleanliness of the working oil can be measured by, for example, a gravimetric method, a microscopic method, a light scattering method, a photoresist method, a resistance method, an acoustic method, a dynamic light scattering method, or the like. Since it is considered that the cleanliness of the hydraulic oil does not change rapidly during use of the hydraulic servo valve 100, it is considered that the hydraulic oil of the actually measured cleanliness has been used for a predetermined period before or after the time point at which the cleanliness of the hydraulic oil is actually measured, and the coil applied current 341, the pilot valve target spool position 316, and the pilot valve actual spool position 310 recorded during the predetermined period are associated with the actual measured value 342 of the cleanliness of the hydraulic oil as learning data. The predetermined period may be a period in which the cleanliness of the hydraulic oil is maintained to the same extent during the use of the hydraulic servo valve 100, and may be defined by the use time of the hydraulic servo valve 100, the operation time of the engine 80, the number of revolutions of the engine 80, and the like. When the simulation data is used as the learning data, the measured hydraulic oil cleanliness value 342 is a value of the cleanliness of the hydraulic oil input to the simulator as the simulation condition.

The hydraulic oil cleanliness estimation model generation unit 343 generates a hydraulic oil cleanliness estimation model used in the state estimation device 400 to estimate the cleanliness of the hydraulic oil used, using the learning data acquired by the learning data acquisition unit 301. The working oil cleanliness estimation model may be a neural network or the like that inputs time-series data of the coil applied current 341, the pilot valve target spool position 316, and the pilot valve actual spool position 310 over a predetermined period to the input layer and outputs working oil cleanliness from the output layer. In this case, the hydraulic oil cleanliness estimation model generation unit 343 adjusts the intermediate layer of the neural network so as to output a value close to the hydraulic oil cleanliness actual measurement value 342 from the output layer when the time-series data of the coil applied current 341, the pilot valve target valve body position 316, and the pilot valve actual valve body position 310 over a predetermined period is input to the input layer, thereby learning the hydraulic oil cleanliness estimation model.

The hydraulic oil cleanliness estimation model providing unit 344 provides the hydraulic oil cleanliness estimation model generated by the hydraulic oil cleanliness estimation model generating unit 343 to the state estimating device 400.

The detection information acquisition unit 401 acquires the coil applied current 441, the pilot valve target spool position 415, and the pilot valve actual spool position 410 as detection information. The probe information is time-series data of the same predetermined period as learning data used for generating the working oil cleanliness estimation model.

The hydraulic oil cleanliness estimating section 442 estimates the cleanliness of the hydraulic oil using the hydraulic oil cleanliness estimation model generated by the learning device 300. The hydraulic oil cleanliness estimating section 442 acquires, as an estimation result, the hydraulic oil cleanliness that is input to the hydraulic oil cleanliness estimation model and output from the hydraulic oil cleanliness estimation model, the time-series data of the coil applied current 441, the pilot valve target spool position 415, and the pilot valve actual spool position 410 acquired by the probe information acquiring section 401.

The hydraulic oil cleanliness estimation result output unit 443 outputs the result estimated by the hydraulic oil cleanliness estimation unit 442. The working oil cleanliness estimation result output unit 443 may determine whether or not maintenance such as cleaning or replacement of the working oil is necessary based on the output working oil cleanliness, and may notify that maintenance is necessary when it is determined that the maintenance of the working oil is necessary. For example, the hydraulic oil cleanliness estimation result output unit 443 may determine that maintenance is necessary for the hydraulic oil when the cleanliness of the output hydraulic oil is smaller than a predetermined threshold value, or may determine that maintenance is necessary for the hydraulic oil when the amount of change in the cleanliness of the hydraulic oil from the initial value is equal to or greater than a predetermined threshold value. The working oil cleanliness estimation result output unit 443 may estimate a period until the working oil needs to be maintained and output the period. For example, the hydraulic oil cleanliness estimation result output unit 443 may estimate the period until the hydraulic oil needs to be maintained, using an expression or the like that takes the output hydraulic oil cleanliness as a variable. The hydraulic oil cleanliness estimation model may be configured to output a period until maintenance of the hydraulic oil is required or not, in place of the hydraulic oil cleanliness, or a period until maintenance of the hydraulic oil is required or not, in addition to the hydraulic oil cleanliness.

In the case where a plurality of hydraulic servo valves 100 are provided corresponding to a plurality of cylinders 81 of the same engine 80, the hydraulic oil cleanliness estimating section 442 may determine whether or not maintenance of the hydraulic oil is necessary based on the hydraulic oil cleanliness estimated in each hydraulic servo valve 100. When a common hydraulic oil is circulated and used in a plurality of hydraulic servo valves 100, if the cleanliness of the hydraulic oil estimated in any one of the hydraulic servo valves 100 is smaller than a predetermined threshold value, even if the cleanliness of the hydraulic oil estimated in the other hydraulic servo valves 100 is equal to or greater than the threshold value, the circulation of the hydraulic oil having low cleanliness may affect the operation of the other hydraulic servo valves 100. Therefore, when the cleanliness of the hydraulic oil estimated in at least 1 hydraulic servo valve 100 is smaller than the predetermined threshold value, the hydraulic oil cleanliness estimation result output portion 443 may determine that maintenance of the hydraulic oil is necessary. The working oil cleanliness estimation result output portion 443 may also determine whether or not maintenance of the working oil is necessary based on the order of the working oil circulation. For example, the threshold value for determining whether maintenance of the hydraulic oil is necessary for the upstream hydraulic servo valve 100 may be higher than the threshold value for determining whether maintenance of the hydraulic oil is necessary for the downstream hydraulic servo valve 100. The hydraulic oil cleanliness estimation result output portion 443 may calculate a statistical value such as an average value of the cleanliness of the hydraulic oil estimated in the plurality of hydraulic servo valves 100, and determine whether or not maintenance of the hydraulic oil is necessary based on the calculated statistical value.

The characteristic quantity having a correlation with the cleanliness of the working oil can be calculated from the coil applied current, the target valve element position of the pilot valve, the actual valve element position of the pilot valve, and the like. In this case, the learning device 300 may further include a feature amount calculation unit 315, and the state estimation device 400 may further include a feature amount calculation unit 414, as in embodiment 1-2. When the cleanliness of the hydraulic oil decreases and the friction between the valve body 10b and the valve member 12 of the pilot valve 10 increases, the speed or acceleration of the valve member 12 is considered to decrease, and therefore the characteristic amount calculation portion can calculate the speed or acceleration of the valve member 12 of the pilot valve 10 by calculating the rate of change or the rate of change of the actual valve member position of the pilot valve.

The hydraulic oil cleanliness estimation model generation unit 343 generates a hydraulic oil cleanliness estimation model using the learning data acquired by the learning data acquisition unit 301 and the feature amount calculated by the feature amount calculation unit 315. The hydraulic oil cleanliness estimation model generation unit 343 generates a hydraulic oil cleanliness estimation model using the hydraulic oil cleanliness measured value 342 and the feature amount calculated by the feature amount calculation unit 315. For example, the working oil cleanliness estimation model may be a numerical expression that calculates the working oil cleanliness using the feature quantity as an input variable. In this case, the hydraulic oil cleanliness estimation model generation unit 343 may generate the numerical expression by a statistical method such as regression analysis. The working oil cleanliness estimation model may be a numerical expression for calculating the working oil cleanliness using, as input variables, the velocity or acceleration of the valve body 12 when the coil applied current or the pilot valve target valve body position satisfies a predetermined condition. For example, the speed or acceleration of the valve body 12 when the coil applies the peak value of the current may be used as the input variable, or the speed or acceleration of the valve body 12 when the valve body 12 moves from the neutral position may be used as the input variable. The hydraulic oil cleanliness estimation model generation unit 343 can generate a hydraulic oil cleanliness estimation model using the coil applied current 341, the pilot valve target valve body position 316, the pilot valve actual valve body position 310, and the feature amount. For example, the hydraulic oil cleanliness estimation model may be a neural network or the like that inputs the coil applied current 341, the time-series data of the pilot valve target spool position 316 and the pilot valve actual spool position 310 over a predetermined period, and the characteristic amount over the predetermined period to the input layer and outputs the hydraulic oil cleanliness from the output layer. In this case, the hydraulic oil cleanliness estimation model generation unit 343 learns the hydraulic oil cleanliness estimation model by adjusting the intermediate layer of the neural network so that a value close to the hydraulic oil cleanliness actual measurement value 342 is output from the output layer when the coil applied current 341, the time-series data of the pilot valve target valve body position 316 and the pilot valve actual valve body position 310 over a predetermined period, and the characteristic amount over the predetermined period are input to the input layer.

The feature amount calculation unit 414 of the state estimation device 400 calculates the feature amount from the coil applied current 441, the pilot valve target spool position 415, or the pilot valve actual spool position 410 acquired by the probe information acquisition unit 401 by the same method as the method for calculating the feature amount by the feature amount calculation unit 315 when generating the hydraulic oil cleanliness estimation model used by the hydraulic oil cleanliness estimation unit 442. When the coil applied current 441, the pilot valve target spool position 415, and the pilot valve actual spool position 410 of the hydraulic servo valve 100 used in an environment different from the learning data used in generating the hydraulic oil cleanliness estimation model are acquired by the probe information acquisition unit 401, the feature amount calculation unit 414 may calculate the feature amount after adjusting the difference in environment. This can improve the robustness of the estimation of the cleanliness of the working oil.

As the characteristic amount, other physical amounts indicating characteristics of the operation of the valve body 12 of the pilot valve 10 and the like may be calculated. For example, an overshoot amount, a delay amount, and the like of the spool 12 of the pilot valve 10 may be calculated as the feature amount.

As the learning data and the detection information, data recorded when the hydraulic servo valve 100 is used in a specific environment may be used. In this case, the learning device 300 may further include a data selection unit 320 and the state estimation device 400 may further include a data selection unit 417, as in embodiments 1 to 5. The data selection unit 320 and the data selection unit 417 can select data recorded when the hydraulic servo valve 100 is operated in a test mode in which the valve body 12 of the pilot valve 10 is operated in a specific pattern. This can improve the robustness of the estimation of the cleanliness of the working oil. The data selection unit 320 and the data selection unit 417 may select data recorded when the engine 80 is stopped and the valve element sticking prevention operation is being performed. Thus, the influence of disturbance can be suppressed, and the estimation accuracy of the cleanliness of the working oil can be improved.

In addition to the data used as the learning data and the detection information, any one of other data such as the number of engine revolutions, the engine load, the pressure of the hydraulic oil pressurized by the hydraulic pump 42, the pressure or flow rate of the hydraulic oil before and after the filter for removing foreign substances mixed in the hydraulic oil, the temperature of the hydraulic oil, the power supply voltage, and the power supply current, or any combination thereof may be used as the learning data and the detection information. Of these data, data that can affect data such as the current applied to the coil, the target valve element position of the pilot valve, and the actual valve element position of the pilot valve as an environmental factor may be selected and used. Not only the cleanliness of the hydraulic oil but also the friction force when the valve spool 12 of the pilot valve 10 slides can be changed by the abrasion of the inner wall of the valve spool 12 or the main body portion 10b of the pilot valve 10, and therefore, factors that can affect the abrasion of the inner wall of the valve spool 12 or the main body portion 10b of the pilot valve 10, such as the cumulative use time of the pilot valve 10, the cumulative moving distance of the valve spool 12, and the like, can be used as the learning data and the detection information. By generating the working oil cleanliness estimation model reflecting the influence of these data, the robustness of the estimation of the working oil cleanliness can be further improved.

Example 5: position sensor wire break detection

In example 5, a technique for detecting a disconnection of the position sensor 29 for detecting the actual position of the valve body 28 of the main valve 20 will be described. When the position sensor 29 is disconnected, the position sensor 29 cannot receive a signal indicating the correct actual position of the valve body 28 any more, and therefore the actual valve body position of the main valve 20 is shifted from the target valve body position. As described in example 3, conventionally, an alarm is issued when the actual valve body position of the main valve 20 is deviated from the target valve body position, but the cause of the alarm cannot be specified. If the position sensor 29 can detect the occurrence of a disconnection with high accuracy, the cause of an alarm can be identified when the alarm is issued, and appropriate treatment can be promptly taken.

Fig. 17 schematically shows the operation of the spool 12 of the pilot valve 10 and the spool 28 of the main valve 20. Fig. 17 (a) shows an operation example in the case where the hydraulic servo valve 100 is normally controlled. The operation example shown in fig. 17 (a) is the same as the operation example shown in fig. 14 (a).

Fig. 17 (b) shows an operation example in the case where the position sensor 29 of the spool 28 of the main valve 20 is disconnected. The operation up to time t3 is the same as that in fig. 17 (a), but at time t6, the position sensor 29 of the valve body 28 of the main valve 20 is disconnected. The feedback signal of the actual valve element position of the main valve 20 rapidly changes to an abnormal value (for example, zero) immediately after the disconnection, and is fixed after the abnormal value. In the example of the present figure, since the actual spool position of the main valve 20 is fixed in a state of being shifted in the positive direction from the target spool position, the negative maximum value is continuously input as the target spool position of the pilot valve 10 in order to return the spool 28 of the main valve 20 to the target spool position. Therefore, as shown by the broken line, the spool 28 of the main valve 20 continues to move in the negative direction, and when reaching the limit position in the negative direction, it stops moving at the limit position instead of continuing to move.

As described above, the operation patterns of the valve body 12 of the pilot valve 10 and the valve body 28 of the main valve 20 are greatly different from each other when the position sensor 29 is disconnected in a normal state. Therefore, the disconnection of the position sensor 29 can be detected by modeling the difference between the normal operation pattern and the operation pattern when the disconnection of the position sensor 29 occurs. Even when time elapses after an alarm for notifying that the actual valve body position of the main valve 20 is deviated from the target valve body position is issued, the history of occurrence of disconnection of the position sensor 29 can be detected from the log data, and therefore, it can be used as evidence of the occurrence of a malfunction. According to the technique of the present embodiment, when an alarm for notifying that the actual valve body position of the main valve 20 is deviated from the target valve body position is issued, whether the cause of the foreign matter engagement described in embodiment 3 or the cause of the disconnection of the position sensor 29 described in the present embodiment can be accurately determined, and appropriate maintenance can be performed. In addition, the occurrence of the hunting due to the contact failure of the position sensor 29 or the like can be accurately detected by modeling the operation pattern of the actual valve body position of the main valve 20 and the target valve body position of the pilot valve 10. Accordingly, since an abnormality can be detected before the position sensor 29 is disconnected and appropriate maintenance can be performed, occurrence of malfunction due to disconnection of the position sensor 29 can be prevented.

Fig. 18 shows the configurations of the learning device and the state estimation device according to embodiment 5. In the learning device 300 of the present embodiment, the learning data acquisition unit 301 acquires the main valve actual valve element position 311, the pilot valve target valve element position 316, and the position sensor disconnection data 351 as learning data.

The main-valve actual valve element position 311 and the pilot-valve target valve element position 316 are time-series data when the hydraulic servo valve 100 is used within a predetermined period before or after the time point at which the position sensor disconnection data 351 is actually measured. These time-series data may be time-series data of 1 to several cycles of the rotational operation of engine 80.

The position sensor disconnection data 351 is data indicating the presence, timing, mode, cause, and the like of disconnection of the position sensor 29 of the valve body 28 of the main valve 20. When log data is used as the learning data, the position sensor disconnection data 351 is an actual measurement value when the position sensor 29 is actually disconnected. When the test data is used as the learning data, the position sensor disconnection data 351 is an actual measurement value when the position sensor 29 is disconnected. In the case of using simulation data as learning data, the position sensor disconnection data 351 is data input to the simulator as simulation conditions.

The position sensor disconnection detection model generation unit 353 generates a position sensor disconnection detection model used in the state estimation device 400 to detect disconnection of the position sensor 29, using the learning data acquired by the learning data acquisition unit 301. The position sensor disconnection detection model may be a neural network or the like that inputs time-series data of the main valve actual spool position 311 and the pilot valve target spool position 316 over a predetermined period to the input layer and outputs position sensor disconnection data from the output layer. In this case, the position sensor disconnection detection model generation unit 353 adjusts the intermediate layer of the neural network so as to output a value similar to the position sensor disconnection data 351 from the output layer when the time-series data of the main valve actual valve body position 311 and the pilot valve target valve body position 316 over the predetermined period is input to the input layer, thereby learning the position sensor disconnection detection model.

The position sensor disconnection detection model providing unit 354 provides the position sensor disconnection detection model generated by the position sensor disconnection detection model generating unit 353 to the state estimating device 400.

The detection information acquisition unit 401 acquires, as detection information, a main-valve actual spool position 411 and a pilot-valve target spool position 415. The detection information is time-series data of the same predetermined period as learning data used for generating the position sensor disconnection detection model.

The position sensor disconnection detecting unit 451 detects disconnection of the position sensor 29 of the valve body 28 of the main valve 20 using the position sensor disconnection detection model generated by the learning device 300. The position sensor disconnection detecting unit 451 inputs the time-series data of the main valve actual spool position 411 and the pilot valve target spool position 415 acquired by the detection information acquiring unit 401 to the position sensor disconnection detection model, and acquires the position sensor disconnection data output from the position sensor disconnection detection model as a determination result. The position sensor disconnection detecting unit 451 may estimate a period until the position sensor 29 is disconnected based on the output position sensor disconnection data. In this case, the period until the position sensor 29 is disconnected may be estimated by comparing the position sensor disconnection data of the plurality of hydraulic servo valves 100 provided corresponding to the plurality of cylinders 81 of the same engine 80.

The position sensor disconnection detection result output portion 452 outputs the result determined by the position sensor disconnection detection portion 451. When the position sensor disconnection detecting unit 451 detects the disconnection of the position sensor 29, the position sensor disconnection detection result output unit 452 may notify this fact. The position sensor disconnection detection result output unit 452 may output the period until the position sensor 29 is disconnected, which is estimated by the position sensor disconnection detection unit 451.

The characteristic amount having a correlation with the disconnection of the position sensor 29 can be calculated from the main valve actual spool position, the pilot valve target spool position, or the like. In this case, the learning device 300 may further include a feature amount calculation unit 315, and the state estimation device 400 may further include a feature amount calculation unit 414, as in embodiment 1-2. Since the main valve actual spool position rapidly changes to an abnormal value when the position sensor 29 of the spool 28 of the main valve 20 is disconnected, the characteristic amount calculation unit can calculate the speed or acceleration of the spool 28 of the main valve 20 by calculating the rate of change or the rate of change of the main valve actual spool position.

The position sensor disconnection detection model generation unit 353 generates a position sensor disconnection detection model using the learning data acquired by the learning data acquisition unit 301 and the feature amount calculated by the feature amount calculation unit 315. The position sensor disconnection detection model generation unit 353 can generate a position sensor disconnection detection model using the position sensor disconnection data 351 and the feature amount calculated by the feature amount calculation unit 315. The position sensor disconnection detection model generation unit 353 can generate a position sensor disconnection detection model using the main valve actual valve body position 311, the pilot valve target valve body position 316, and the feature amount. For example, the position sensor disconnection detection model may be a neural network or the like that inputs time-series data of the main valve actual spool position 311 and the pilot valve target spool position 316 over a predetermined period and a feature amount of the predetermined period to the input layer and outputs position sensor disconnection data from the output layer. In this case, the position sensor disconnection detection model generation unit 353 adjusts the intermediate layer of the neural network so as to output a value approximate to the position sensor disconnection data 351 from the output layer when the time-series data of the main valve actual valve body position 311 and the pilot valve target valve body position 316 over the predetermined period and the feature amount over the predetermined period are input to the input layer, thereby learning the position sensor disconnection detection model.

The feature amount calculation unit 414 of the state estimation device 400 calculates the feature amount from the main valve actual valve element position 411 or the pilot valve target valve element position 415 acquired by the detection information acquisition unit 401 by the same method as the method for calculating the feature amount by the feature amount calculation unit 315 when generating the position sensor disconnection detection model used by the position sensor disconnection detection unit 451. When the detection information acquiring unit 401 acquires the main valve actual spool position 411 and the pilot valve target spool position 415 of the hydraulic servo valve 100 used in an environment different from the learning data used when the position sensor disconnection detection model is generated, the characteristic amount calculating unit 414 may calculate the characteristic amount after adjusting the difference in the environment. This can improve the robustness of the position sensor disconnection detection.

As the characteristic amount, other physical amounts indicating the characteristic of the operation of the spool 28 of the main valve 20, and the like may be calculated. For example, the overshoot amount, the delay amount, and the like of the spool 28 of the main valve 20 may be calculated as the characteristic amount.

As the learning data and the detection information, the pilot valve actual spool position may be used instead of the pilot valve target spool position, or may be used in addition to the pilot valve target spool position. In this case, as in embodiments 1 to 4, the learning device 300 may include an offset time calculation unit 319 for adjusting the offset time required until the actual valve element position of the pilot valve 10 follows the target valve element position of the pilot valve. The method of calculating the offset time may be the same as in embodiment 1-2. As the learning data and the detection information, any combination of 2 or more positions among the pilot valve target spool position, the pilot valve actual spool position, the main valve target spool position, and the main valve actual spool position may be used.

As the learning data and the detection information, data recorded when the hydraulic servo valve 100 is used in a specific environment may be used. In this case, the learning device 300 may further include a data selection unit 320 and the state estimation device 400 may further include a data selection unit 417, as in embodiments 1 to 5. The data selection unit 320 and the data selection unit 417 can select data recorded when the hydraulic servo valve 100 is operated in a test mode in which the valve body 12 of the pilot valve 10 is operated in a specific pattern. This can improve the robustness of the disconnection detection of the position sensor 29. The data selection unit 320 and the data selection unit 417 may select data recorded when the engine 80 is stopped and the valve element sticking prevention operation is being performed. This can suppress the influence of the disturbance and improve the accuracy of detecting the disconnection of the position sensor 29.

Example 6: position sensor looseness detection

In example 6, a technique for detecting the following situation is explained: the position of the position sensor 29 is displaced due to loosening of a screw or the like for fixing the position sensor 29 for detecting the actual position of the spool 28 of the main valve 20. When the position of the position sensor 29 is displaced, a displacement occurs between the feedback signal of the main valve actual spool position and the actual position of the spool 28 of the main valve 20, and therefore the spool 28 of the main valve 20 cannot be normally controlled any more, and an operation failure of the control target such as the engine 80 may occur. If the positional deviation of the position sensor 29 can be detected with high accuracy, appropriate measures such as fastening a screw or replacing the position sensor 29 can be taken quickly.

Fig. 19 shows a state of the position sensor 29 of the spool 28 of the main valve 20. Fig. 19 (a) shows a state in which the position sensor 29 is normally attached. The position sensor 29 is screwed into a female screw 30 cut at the upper end of the spool 28. When the screw is loosened, as shown in fig. 19 (b), a gap is generated between the position sensor 29 and the valve body 28, and therefore the position of the valve body 28 is displaced downward by an amount corresponding to the gap d. However, since the position of the valve body 28 is detected by the position sensor 29, the same position is detected in both the case (a) of fig. 19 and the case (b) of fig. 19, and the actual position of the valve body 28 that is shifted downward cannot be detected. In the state of fig. 19 (b), although it appears that the main valve actual spool position accurately follows the main valve target spool position, the actual position of the spool 28 is shifted further downward than the main valve target spool position, and therefore, a problem arises in the operation of the control target. In the present embodiment, since the amount of control oil supplied to the fuel injection actuator for supplying fuel to the cylinder 81 of the engine 80 is reduced, the amount of fuel supplied to the cylinder 81 is reduced, and therefore the pressure in the cylinder 81 or the temperature of exhaust gas discharged from the cylinder 81 is reduced, thereby issuing an alarm.

As described above, when the position sensor 29 is displaced due to backlash, the main valve actual spool position follows the main valve target spool position, but the pressure and the exhaust temperature of the cylinder 81 decrease. Therefore, when an abnormality occurs in the pressure, the exhaust temperature, or the like of the cylinder 81 and an alarm is issued, it is possible to determine whether the cause is the abnormality of the position sensor 29 by checking whether or not the main valve actual spool position follows the main valve target spool position. Even when time has elapsed since the alarm for notifying an abnormality of engine 80 is issued, the looseness of position sensor 29 can be detected from the log data, and this can be used as evidence of the occurrence of a malfunction. This makes it possible to accurately detect the looseness of the position sensor 29 and perform appropriate maintenance, and therefore, it is possible to reduce the cost and man-hours of maintenance required to improve the operational failure of the engine 80.

Fig. 20 shows the configurations of the learning device and the state estimation device according to embodiment 6. In the learning device 300 of the present embodiment, the learning data acquisition unit 301 acquires the main-valve actual spool position 311, the main-valve target spool position 330, the cylinder exhaust temperature 361, and the position sensor looseness data 362 as learning data.

The main-valve actual spool position 311, the main-valve target spool position 330, and the cylinder exhaust temperature 361 are time-series data when the hydraulic servo valve 100 is used for a predetermined period before or after the time point when the position sensor looseness data 362 is actually measured. These time-series data may be time-series data of 1 to several cycles of the rotational operation of engine 80.

The position sensor looseness data 362 is data indicating the presence, degree, mode, cause, and the like of the positional deviation of the position sensor 29 of the valve body 28 of the main valve 20. When the log data is used as the learning data, the position sensor looseness data 362 is an actual measurement value when the position sensor 29 is actually displaced. When the test data is used as the learning data, the position sensor backlash data 362 is an actual measurement value when the position sensor 29 is offset. In the case of using simulation data as learning data, the position sensor looseness data 362 is data input to the simulator as simulation conditions.

The position sensor looseness detection model generation unit 363 generates a position sensor looseness detection model used in the state estimation device 400 to detect looseness of the position sensor 29, using the learning data acquired by the learning data acquisition unit 301. The position sensor looseness detection model may be a neural network or the like that inputs time-series data of the main valve actual spool position 311, the main valve target spool position 330, and the cylinder exhaust temperature 361 for a predetermined period to the input layer and outputs position sensor looseness data from the output layer. In this case, the position sensor looseness detection model generation unit 363 adjusts the intermediate layer of the neural network so as to output a value approximate to the position sensor looseness data 362 from the output layer when the time-series data of the main valve actual spool position 311, the main valve target spool position 330, and the cylinder exhaust temperature 361 during a predetermined period is input to the input layer, thereby learning the position sensor looseness detection model.

The position sensor looseness detection model providing unit 364 provides the position sensor looseness detection model generated by the position sensor looseness detection model generating unit 363 to the state estimating device 400.

The detection information acquisition unit 401 acquires, as detection information, a main-valve actual spool position 411, a main-valve target spool position 430, and a cylinder exhaust temperature 461. The detection information is time-series data of the same predetermined period as learning data used for generating the position sensor play detection model.

The position sensor looseness detecting unit 462 detects looseness of the position sensor 29 of the valve body 28 of the main valve 20 using a position sensor looseness detection model generated by the learning device 300. The position sensor looseness detecting unit 462 inputs the time-series data of the main valve actual spool position 411, the main valve target spool position 430, and the cylinder exhaust temperature 461 acquired by the detection information acquiring unit 401 to the position sensor looseness detection model, and acquires the position sensor looseness data output from the position sensor looseness detection model as a determination result. The position sensor looseness detecting unit 462 may estimate a period until the position sensor 29 deviates by a predetermined value or more based on the output position sensor looseness data. In this case, the period until the position sensor 29 deviates by a predetermined value or more may be estimated by comparing the position sensor looseness data of the plurality of hydraulic servo valves 100 provided corresponding to the plurality of cylinders 81 of the same engine 80.

In the case where a plurality of hydraulic servo valves 100 are provided corresponding to a plurality of cylinders 81 of the same engine 80, the position sensor looseness detecting section 462 may detect looseness of the position sensor 29 based on position sensor looseness data estimated in each of the hydraulic servo valves 100. For example, the position sensor looseness detecting portion 462 may detect looseness of the position sensor 29 by comparing exhaust gas temperatures of the respective cylinders 81. The position sensor looseness detecting unit 462 may determine that the position sensor 29 of the hydraulic servo valve 100 provided in a certain cylinder 81 is loosened when the exhaust gas temperature of the cylinder 81 is lower than the average value of the exhaust gas temperatures of the other cylinders 81 by a predetermined value or more.

The position sensor looseness detection result output part 463 outputs the result determined by the position sensor looseness detection part 462. The position sensor looseness detection result output portion 463 may notify that the position sensor 29 is loosened when the position sensor looseness detecting portion 462 detects the looseness. The position sensor looseness detection result output unit 463 may output the period until the position sensor 29 deviates by a predetermined value or more, which is estimated by the position sensor looseness detecting unit 462.

The characteristic amount having a correlation with the looseness of the position sensor 29 can be calculated from the main valve actual spool position, the main valve target spool position, the cylinder exhaust temperature, or the like. In this case, the learning device 300 may further include a feature amount calculation unit 315, and the state estimation device 400 may further include a feature amount calculation unit 414, as in embodiment 1-2. The greater the degree of looseness of the position sensor 29 of the spool 28 of the main valve 20, the greater the deviation between the actual spool position of the main valve and the actual position of the spool 28, and therefore, it is considered that the amount of decrease in the exhaust temperature or pressure of the cylinder from the normal value is greater. Therefore, the characteristic amount calculation portion may calculate, as the characteristic amount, a decrease amount, a change rate of the change rate, and the like of the exhaust gas temperature or pressure of the cylinder from a normal value.

The position sensor looseness detection model generation unit 363 generates a position sensor looseness detection model using the learning data acquired by the learning data acquisition unit 301 and the feature amount calculated by the feature amount calculation unit 315. For example, the position sensor looseness detection model may be a numerical expression that calculates position sensor looseness data using the feature quantity as an input variable. In this case, the position sensor looseness detection model generation unit 363 may generate the numerical expression by a statistical method such as regression analysis. The position sensor looseness detection model generation unit 363 may generate a position sensor looseness detection model using the position sensor looseness data 362 and the feature amount calculated by the feature amount calculation unit 315. The position sensor looseness detection model generation unit 363 may generate a position sensor looseness detection model using the main valve actual spool position 311, the main valve target spool position 330, and the feature amount. For example, the position sensor looseness detection model may be a neural network or the like that inputs time-series data of the main valve actual spool position 311 and the main valve target spool position 330 over a predetermined period and characteristic quantities of the predetermined period to the input layer and outputs position sensor looseness data from the output layer. In this case, the position sensor looseness detection model generation unit 363 adjusts the intermediate layer of the neural network so that a value approximate to the position sensor looseness data 362 is output from the output layer when the time-series data of the main valve actual spool position 311 and the main valve target spool position 330 for a predetermined period and the feature amount for the predetermined period are input to the input layer, thereby learning the position sensor looseness detection model.

The characteristic amount calculation unit 414 of the state estimation device 400 calculates the characteristic amount from the main valve actual valve element position 411, the main valve target valve element position 430, or the cylinder exhaust temperature 461 acquired by the detection information acquisition unit 401 by the same method as the method of calculating the characteristic amount by the characteristic amount calculation unit 315 when generating the position sensor looseness detection model used by the position sensor looseness detection unit 462. When the main valve actual spool position 411, the main valve target spool position 430, or the cylinder exhaust temperature 461 of the hydraulic servo valve 100 used in an environment different from the learning data used in generating the position sensor looseness detection model is acquired by the detection information acquisition unit 401, the characteristic amount calculation unit 414 may calculate the characteristic amount after adjusting the difference in environment. This can improve the robustness of the position sensor backlash detection.

As the learning data and the detection information, the pressure of the cylinder 81 or the maximum value of the pressure may be used instead of the cylinder exhaust temperature, or the maximum value of the pressure of the cylinder 81 or the maximum value of the pressure may be used in addition to the cylinder exhaust temperature. As the learning data and the detection information, various data indicating the state, the operation, and the like of the control target controlled by the hydraulic servo valve 100 can be used.

As the learning data and the detection information, data recorded when the hydraulic servo valve 100 is used in a specific environment may be used. In this case, the learning device 300 may further include a data selection unit 320 and the state estimation device 400 may further include a data selection unit 417, as in embodiments 1 to 5. The data selection unit 320 and the data selection unit 417 can select data recorded when the hydraulic servo valve 100 is operated in a test mode in which the valve body 12 of the pilot valve 10 is operated in a specific pattern. This can improve the robustness of the position sensor backlash detection. The data selection unit 320 and the data selection unit 417 may select data recorded when the engine 80 is stopped and the valve element sticking prevention operation is being performed. Thus, the influence of the disturbance can be suppressed, and the detection accuracy of the position sensor backlash can be improved.

Example 7: neutral position offset detection of pilot valves

In embodiment 7, a technique for detecting that the neutral position of the valve body 12 of the pilot valve 10 is shifted will be described. When the pilot valve 10 is normally operated when the neutral position is designated as the pilot valve target valve body position, the valve body 12 is moved to the neutral position, the supply and recovery of the hydraulic oil to the main valve 20 are stopped, and the valve body 28 of the main valve 20 is stationary at the main valve target valve body position. However, if the neutral position of the valve body 12 is shifted for some reason, the supply and recovery of the hydraulic oil to and from the main valve 20 cannot be normally controlled, and there may be a case where the operation of the control target such as the engine 80 is defective. If the neutral position deviation of the valve body 12 of the pilot valve 10 can be detected with high accuracy, appropriate measures such as maintenance of the control system of the pilot valve 10 and replacement of the pilot valve 10 can be taken quickly.

The causes of the neutral position shift of the valve body 12 of the pilot valve 10 are mainly 2 types. One of the cases is an electrical cause that the valve body 12 cannot be accurately moved to the neutral position due to an abnormality of the position sensor 19 for detecting the position of the valve body 12 of the pilot valve 10, an abnormality of an electrical system for driving the valve body 12, or the like. In another case, the valve body 12 or the main body portion 10b is unevenly worn, and therefore, even when the valve body 12 is in the neutral position, there is no mechanical reason why the valve body 14 blocks the a port 16a so as not to communicate with both the P port 16P and the T port 16T. In either case, when the neutral position is designated as the pilot valve target spool position, the spool 28 of the main valve 20 moves and does not stop, and therefore the feedback signal of the main valve actual spool position is offset from the main valve target spool position, and the pilot valve 10 is controlled to correct the offset. As described above, the operation patterns of the valve body 12 of the pilot valve 10 and the valve body 28 of the main valve 20 are greatly different from the neutral position of the valve body 12 of the pilot valve 10 in a normal state. Therefore, the neutral position shift of the valve body 12 can be detected by modeling the difference between the normal operation pattern and the operation pattern when the neutral position of the valve body 12 is shifted. The operation pattern may be different depending on the degree or cause of the neutral position deviation from the valve body 12, and therefore, not only the presence or absence of the neutral position deviation of the valve body 12 but also the cause of the neutral position deviation, the magnitude of the deviation, and the like can be detected.

When the valve body 12 is unevenly worn, the valve body 14 cannot block the a port 16a even when the valve body 12 is at the correct neutral position, and therefore the hydraulic oil leaks from the a port 16 a. By actually measuring this internal leakage amount, it is possible to determine whether the neutral position shift of the spool 12 is caused by uneven wear or by an electrical cause. The internal oil leakage amount may be measured by providing a flow meter to the pilot valve 10, may be measured by an external flow meter when the pilot valve 10 is maintained, or may be estimated by the technique of embodiment 1.

When the neutral position of the valve body 12 of the pilot valve 10 is shifted, an abnormality occurs in the pressure, the exhaust gas temperature, and the like of the cylinder 81 in the engine 80 as a control target, and a warning is issued. When the alarm is issued, by checking the operation patterns of the valve body 12 of the pilot valve 10 and the valve body 28 of the main valve 20, it can be determined whether the cause is the abnormality of the position sensor 29 described in embodiment 6 or the cause is the neutral position shift of the valve body 12 of the pilot valve 10. Further, when the cause is a neutral position shift of the valve body 12 of the pilot valve 10, it is possible to determine whether the neutral position shift is caused by an electrical cause or a mechanical cause by checking the internal oil leakage amount. This makes it possible to accurately determine the cause of the malfunction of engine 80 and perform appropriate maintenance according to the cause, and therefore, it is possible to reduce the cost and man-hours of maintenance required to improve the malfunction of engine 80. Further, in the case where the PID control is executed in the feedback control of the hydraulic servo valve 100, the amount of displacement is corrected to a certain extent by the integral component (I component), but according to the technique of the present embodiment, even in the case where the neutral position displacement is corrected by the PID control, the neutral position displacement of the valve spool 12 of the pilot valve 10 can be accurately detected. In addition, in the case where the P control or the PD control is executed, since the offset amount is not corrected, the technique of the present embodiment is particularly effective.

Fig. 21 shows the configurations of a learning device and a state estimation device according to embodiment 7. In the learning device 300 of the present embodiment, the learning data acquisition unit 301 acquires, as learning data, a main valve actual spool position 311, a main valve target spool position 330, a pilot valve actual spool position 310, a cylinder exhaust temperature 361, and neutral position offset data 371.

The main valve actual spool position 311, the main valve target spool position 330, the pilot valve actual spool position 310, and the cylinder exhaust temperature 361 are time-series data when the hydraulic servo valve 100 is used for a predetermined period before or after the time point when the neutral position offset data 371 is actually measured. These time-series data may be time-series data of 1 to several cycles of the rotational operation of engine 80.

The neutral position offset data 371 is data indicating the presence, degree, cause, and the like of the neutral position offset of the valve body 12 of the pilot valve 10. When the log data is used as the learning data, the neutral position offset data 371 is an actual measurement value when the neutral position offset of the spool 12 is actually generated. When the test data is used as the learning data, the neutral position offset data 371 is an actual measurement value when the neutral position of the valve body 12 is offset. In the case of using the simulation data as the learning data, the neutral position offset data 371 is data input to the simulator as simulation conditions.

The neutral position deviation detection model generation unit 373 generates a neutral position deviation detection model used in the state estimation device 400 to detect the neutral position deviation of the valve body 12 of the pilot valve 10, using the learning data acquired by the learning data acquisition unit 301. The neutral position offset detection model may be a neural network or the like that inputs time-series data of the main valve actual spool position 311, the main valve target spool position 330, the pilot valve actual spool position 310, and the cylinder exhaust temperature 361 for a predetermined period to the input layer and outputs neutral position offset data from the output layer. In this case, the neutral position offset detection model generation unit 373 learns the neutral position offset detection model by adjusting the intermediate layer of the neural network so that a value similar to the neutral position offset data 371 is output from the output layer when time-series data of the main valve actual spool position 311, the main valve target spool position 330, the pilot valve actual spool position 310, and the cylinder exhaust temperature 361 during a predetermined period is input to the input layer.

The neutral position shift detection model providing unit 374 provides the neutral position shift detection model generated by the neutral position shift detection model generating unit 373 to the state estimating device 400.

The detection information acquisition unit 401 acquires, as detection information, a main valve actual spool position 411, a main valve target spool position 430, a pilot valve actual spool position 410, and a cylinder exhaust temperature 461. The detection information is time-series data of the same predetermined period as the learning data used for generating the neutral position shift detection model.

The neutral position deviation detecting unit 472 detects a neutral position deviation of the valve body 12 of the pilot valve 10 using a neutral position deviation detection model generated by the learning device 300. The neutral position offset detection unit 472 inputs the time-series data of the main valve actual valve element position 411, the main valve target valve element position 430, the pilot valve actual valve element position 410, and the cylinder exhaust temperature 461 acquired by the detection information acquisition unit 401 to the neutral position offset detection model, and acquires the neutral position offset data output from the neutral position offset detection model as a determination result. The neutral position deviation detection unit 472 may estimate a period until the neutral position of the valve body 12 of the pilot valve 10 deviates from the actual neutral position by a predetermined value or more based on the output neutral position deviation data. In this case, the period until the neutral position of the valve body 12 of the pilot valve 10 deviates from the actual neutral position by a predetermined value or more can be estimated by comparing the neutral position deviation data of the plurality of hydraulic servo valves 100 provided corresponding to the plurality of cylinders 81 of the same engine 80.

In the case where a plurality of hydraulic servo valves 100 are provided corresponding to a plurality of cylinders 81 of the same engine 80, the neutral position offset detection unit 472 may detect the neutral position offset of the valve body 12 of the pilot valve 10 based on the neutral position offset data estimated in each of the hydraulic servo valves 100. For example, the neutral position deviation detecting unit 472 may detect the neutral position deviation of the valve body 12 of the pilot valve 10 by comparing the exhaust gas temperatures of the respective cylinders 81. The neutral position deviation detection unit 472 may determine that the neutral position of the valve member 12 of the pilot valve 10 of the hydraulic servo valve 100 provided in a certain cylinder 81 is deviated when the exhaust temperature of the cylinder 81 is lower than the average value of the exhaust temperatures of the other cylinders 81 by a predetermined value or more.

The neutral position displacement detection result output part 473 outputs the result determined by the neutral position displacement detection part 472. When the neutral position deviation detecting unit 472 detects that the neutral position of the valve body 12 of the pilot valve 10 has deviated, the neutral position deviation detection result output unit 473 may notify this. The neutral position deviation detection result output unit 473 may output the period until the neutral position of the valve body 12 of the pilot valve 10 deviates by a predetermined value or more, which is estimated by the neutral position deviation detection unit 472.

The characteristic amount having a correlation with the neutral position shift of the spool 12 of the pilot valve 10 can be calculated from the main valve actual spool position, the main valve target spool position, the pilot valve actual spool position, the cylinder exhaust temperature, or the like. In this case, the learning device 300 may further include a feature amount calculation unit 315, and the state estimation device 400 may further include a feature amount calculation unit 414, as in embodiment 1-2. The larger the degree of the neutral position deviation of the spool 12 of the pilot valve 10 is, the larger the degree of the main valve actual spool position deviation from the main valve target spool position is, and therefore, the larger the amount of fluctuation of the exhaust gas temperature or pressure of the cylinder from the normal value is considered to be. Therefore, the characteristic amount calculation section may calculate, as the characteristic amount, a variation rate of the variation rate, or the like of the exhaust gas temperature or pressure of the cylinder from a normal value.

The neutral position shift detection model generation unit 373 generates a neutral position shift detection model using the learning data acquired by the learning data acquisition unit 301 and the feature amount calculated by the feature amount calculation unit 315. For example, the neutral position shift detection model may be a numerical expression in which neutral position shift data is calculated using the feature amount as an input variable. In this case, the neutral position shift detection model generation unit 373 can generate the numerical expression by a statistical method such as regression analysis. The neutral position deviation detection model generation unit 373 can generate a neutral position deviation detection model using the neutral position deviation data 371 and the feature amount calculated by the feature amount calculation unit 315. The neutral position offset detection model generation unit 373 can generate the neutral position offset detection model using the main valve actual spool position 311, the main valve target spool position 330, the pilot valve actual spool position 310, and the feature amount. For example, the neutral position offset detection model may be a neural network or the like that inputs time-series data of the main valve actual spool position 311, the main valve target spool position 330, and the pilot valve actual spool position 310 over a predetermined period, and a feature amount of the predetermined period to the input layer and outputs neutral position offset data from the output layer. In this case, the neutral position offset detection model generation unit 373 learns the neutral position offset detection model by adjusting the intermediate layer of the neural network so that a value approximate to the neutral position offset data 371 is output from the output layer when the time-series data of the main valve actual spool position 311, the main valve target spool position 330, and the pilot valve actual spool position 310 over a predetermined period and the feature amount over the predetermined period are input to the input layer.

The feature amount calculation unit 414 of the state estimation device 400 calculates the feature amount from the main valve actual valve element position 411, the main valve target valve element position 430, the pilot valve actual valve element position 410, or the cylinder exhaust temperature 461 acquired by the detection information acquisition unit 401 by the same method as the method of calculating the feature amount by the feature amount calculation unit 315 when generating the neutral position offset detection model used by the neutral position offset detection unit 472. When the main valve actual spool position 411, the main valve target spool position 430, the pilot valve actual spool position 410, or the cylinder exhaust temperature 461 of the hydraulic servo valve 100 used in an environment different from the learning data used in generating the neutral position offset detection model is acquired by the detection information acquisition unit 401, the characteristic amount calculation unit 414 may calculate the characteristic amount after adjusting the difference in environment. This can improve the robustness of neutral position shift detection.

As the characteristic amount, other physical amounts indicating characteristics of the operation of the spool 12 of the pilot valve 10 or the spool 28 of the main valve 20, and the like may be calculated. For example, the acceleration, the speed, the overshoot, the delay amount, and the like of the spool 12 of the pilot valve 10 or the spool 28 of the main valve 20 may be calculated as the characteristic amounts.

As the learning data and the detection information, a pilot valve target spool position may be used instead of or in addition to the pilot valve actual spool position. In this case, as in embodiments 1 to 4, the learning device 300 may include an offset time calculation unit 319 for adjusting the offset time required until the actual valve element position of the pilot valve 10 follows the target valve element position of the pilot valve. The method of calculating the offset time may be the same as in embodiment 1-2. As the learning data and the detection information, any combination of 2 or more positions among the pilot valve target spool position, the pilot valve actual spool position, the main valve target spool position, and the main valve actual spool position may be used.

As the learning data and the detection information, data recorded when the hydraulic servo valve 100 is used in a specific environment may be used. In this case, the learning device 300 may further include a data selection unit 320 and the state estimation device 400 may further include a data selection unit 417, as in embodiments 1 to 5. The data selection unit 320 and the data selection unit 417 can select data recorded when the hydraulic servo valve 100 is operated in a test mode in which the valve body 12 of the pilot valve 10 is operated in a specific pattern. This can improve the robustness of detecting the neutral position shift. The data selection unit 320 and the data selection unit 417 may select data recorded when the engine 80 is stopped and the valve element sticking prevention operation is being performed. This can suppress the influence of the disturbance and improve the detection accuracy of the neutral position shift.

The features described in embodiments 1 to 7 above can be applied in any combination.

The embodiments of the present invention have been described in detail. The above embodiments are merely specific examples for carrying out the present invention. The contents of the embodiments are not intended to limit the scope of the present invention, and many design changes such as changes, additions, deletions, and the like of the constituent elements can be made without departing from the scope of the inventive concept defined in the claims. In the above-described embodiments, the description has been given with the expression "in the embodiments" or "in the embodiments" regarding the contents in which such a design change is possible, but the contents not having such an expression are not allowed to be subjected to the design change.

[ modified examples ]

Next, a modified example will be explained. In the drawings and the description of the modified examples, the same or equivalent constituent elements and members as those of the embodiment are denoted by the same reference numerals. The description overlapping with the embodiment is appropriately omitted, and the description of the structure different from the embodiment is repeated.

In the description of the embodiment, the pilot valve 10 of the hydraulic servo valve 100 is a 3-port valve, but the present invention is not limited to this. The hydraulic servo valve 100 may also be other types of valves.

In the description of the embodiment, the pilot valve 10 of the hydraulic servo valve 100 controls the main valve 20, but the present invention is not limited to this. The control target of the pilot valve 10 may be any other actuator.

In the description of the embodiment, the example in which the hydraulic servo valve 100 is used to control the engine 80 of the ship 2 is shown, but the present invention is not limited to this. The hydraulic servo valve 100 can be used to control an arbitrary control target.

The above-described modification example achieves the same operation and effect as the embodiment.

Any combination of the above-described embodiment and the modification is also useful as an embodiment of the present invention. The new embodiment resulting from the combination has the effects of both the combined embodiment and the modified example.

[ modes for carrying out the invention ]

One embodiment of the present invention is a state estimation device. The state estimation device includes: an acquisition unit that acquires a target position or an actual position of a first movable unit in a control valve that controls a flow rate of a working fluid according to a position of the first movable unit, and an actual position of a second movable unit that changes position according to the flow rate of the working fluid; and an estimating unit that estimates an amount of leakage of the working fluid based on the information acquired by the acquiring unit. According to this aspect, since the accuracy of estimating the amount of leakage of the working fluid in the control valve can be improved, the state of the control valve can be grasped more accurately, and appropriate measures can be taken according to the state of the control valve.

The estimating section may estimate the leakage amount of the working fluid using an estimation reference for estimating the leakage amount of the working fluid based on the target position or the actual position of the first movable part and the actual position of the second movable part. According to this aspect, the accuracy of estimating the amount of leakage of the working fluid can be improved.

The estimation reference may be generated based on a measured value of the leakage amount of the working fluid, and a relationship between a target position or an actual position of the first movable part and an actual position of the second movable part when the control valve or a control valve of the same type as the control valve is used for a predetermined period before or after a time point at which the leakage amount is measured. According to this aspect, the accuracy of estimating the amount of leakage of the working fluid can be improved.

The estimation reference may be generated based on a relationship between a measured value of the leakage amount of the working fluid, a target position of the first movable unit when the control valve or a control valve of the same type as the control valve is used for a predetermined period before or after a time point at which the leakage amount is measured, and an actual position of the second movable unit after an offset time required from setting the target position for the first movable unit until the actual position of the first movable unit reaches the target position has elapsed. According to this aspect, the accuracy of estimating the amount of leakage of the working fluid can be improved.

The offset time may be calculated from a physical parameter of the first movable portion and a drive voltage or a drive current supplied to the first movable portion. According to this aspect, the accuracy of estimating the amount of leakage of the working fluid can be improved. In addition, the robustness of the estimation can be improved.

The acquisition unit may further acquire a drive voltage or a drive current supplied to the first movable part, and the estimation unit may estimate the leakage amount of the working fluid based on the target position of the first movable part, the actual position of the second movable part, and the drive voltage or the drive current supplied to the first movable part, which are acquired by the acquisition unit. According to this aspect, the accuracy of estimating the amount of leakage of the working fluid can be improved. In addition, the robustness of the estimation can be improved.

The estimation reference may be generated based on a relationship between a characteristic amount calculated from the target position or the actual position of the first movable part and the actual position of the second movable part and a measured value of the leakage amount of the working fluid, the estimation unit may calculate the characteristic amount from the target position or the actual position of the first movable part and the actual position of the second movable part acquired by the acquisition unit, and the leakage amount of the working fluid may be estimated based on the calculated characteristic amount. According to this aspect, the accuracy of estimating the amount of leakage of the working fluid can be improved.

The characteristic amount may be a moving speed of the second movable portion when the actual position of the first movable portion is at a neutral position for minimizing the flow rate of the working fluid. According to this aspect, the leakage amount of the working fluid can be estimated using the characteristic amount having a high correlation with the leakage amount of the working fluid, and therefore the accuracy of estimating the leakage amount of the working fluid can be improved.

The acquisition unit may acquire the target position or the actual position of the first movable part and the actual position of the second movable part in a use environment similar to a use environment of a control valve or a control valve of the same type as the control valve when the target position or the actual position of the first movable part and the actual position of the second movable part used for generating the estimation reference are recorded. According to this aspect, the robustness of the estimation of the leakage amount of the working fluid can be improved.

The usage environment may be a situation in which a control target of the control valve or a control valve of the same type as the control valve is stopped and the sticking prevention operation of the first movable part and the second movable part is being performed. According to this aspect, the robustness of the estimation of the leakage amount of the working fluid can be improved.

The state estimating device may further include a notifying unit configured to notify, when the amount of leakage of the working fluid estimated by the estimating unit is equal to or greater than a predetermined value, that effect. According to this aspect, it is possible to accurately grasp an abnormality of the control valve and appropriately cope with the state of the control valve.

The notification unit may notify that the leakage amount of the working fluid estimated by the estimation unit has increased from an initial value by a predetermined value or more. According to this aspect, it is possible to accurately grasp an abnormality of the control valve and appropriately cope with the state of the control valve.

The notification unit may estimate a time until the leakage amount of the working fluid exceeds a threshold value and notify the estimated time. According to this aspect, it is possible to accurately predict the abnormality of the control valve and appropriately cope with the state of the control valve.

The control valve may be a control valve for adjusting the amount of fuel supplied to the engine. According to this aspect, it is possible to accurately detect an abnormality of the control valve for controlling the engine, and to appropriately cope with the state of the control valve.

In order to adjust the amount of fuel supplied to each cylinder of an engine having a plurality of cylinders, a control valve may be provided for each cylinder, and the estimation unit may determine an abnormality of the control valve by comparing information on each of a plurality of control valves provided for the plurality of cylinders. According to this aspect, it is possible to accurately detect an abnormality of the control valve for controlling the engine, and to appropriately cope with the state of the control valve.

Another aspect of the invention is a control valve. The control valve includes: a first movable portion whose position changes in accordance with a control signal for specifying a position, the first movable portion controlling a flow rate of the working fluid in accordance with the position; an acquisition unit that acquires a target position or an actual position of the first movable unit and an actual position of the second movable unit that changes position according to a flow rate of the working fluid; and an estimating section that estimates an amount of leakage of the working fluid based on the target position or the actual position of the first movable part and the actual position of the second movable part acquired by the acquiring section, using an estimation reference for estimating the amount of leakage of the working fluid based on the target position or the actual position of the first movable part and the actual position of the second movable part. According to this aspect, since the accuracy of estimating the amount of leakage of the working fluid in the control valve can be improved, the state of the control valve can be grasped more accurately, and appropriate measures can be taken according to the state of the control valve.

Another aspect of the present invention is a state estimation procedure. The state estimation program causes a computer to function as an acquisition unit that acquires a target position or an actual position of a first movable unit in a control valve that controls a flow rate of a working fluid according to a position of the first movable unit, and an actual position of a second movable unit that changes position according to the flow rate of the working fluid, and an estimation unit that estimates a leakage amount of the working fluid based on information acquired by the acquisition unit. According to this aspect, since the accuracy of estimating the amount of leakage of the working fluid in the control valve can be improved, the state of the control valve can be grasped more accurately, and appropriate measures can be taken according to the state of the control valve.

Another embodiment of the present invention is a state estimation method. The state estimation method causes a computer to execute the steps of: an acquisition step of acquiring a target position or an actual position of a first movable portion in a control valve that controls a flow rate of a working fluid according to a position of the first movable portion, and an actual position of a second movable portion that changes position according to the flow rate of the working fluid; and an estimating step of estimating an amount of leakage of the working fluid based on the information acquired in the acquiring step. According to this aspect, since the accuracy of estimating the amount of leakage of the working fluid in the control valve can be improved, the state of the control valve can be grasped more accurately, and appropriate measures can be taken according to the state of the control valve.

Claims

1. A state estimation device is provided with:

an acquisition unit that acquires a target position or an actual position of a first movable unit in a control valve that controls a flow rate of a working fluid according to a position of the first movable unit, and an actual position of a second movable unit that changes position according to the flow rate of the working fluid; and

an estimating section that estimates an amount of leakage of the working fluid based on the information acquired by the acquiring section.

2. The state estimation device according to claim 1,

the estimating section estimates the leakage amount of the working fluid using an estimation reference for estimating the leakage amount of the working fluid based on a target position or an actual position of the first movable part and an actual position of the second movable part.

3. The state estimation device according to claim 2,

the estimation reference is generated based on a relationship between a measured value of the leakage amount of the working fluid, a target position or an actual position of the first movable part when the control valve or a control valve of the same type as the control valve is used for a predetermined period before or after a point of time when the leakage amount is measured, and an actual position of the second movable part.

4. The state estimation device according to claim 3,

the estimation reference is generated based on a relationship between a measured value of the leakage amount of the working fluid, a target position of the first movable part when the control valve or a control valve of the same type as the control valve is used for a predetermined period before or after a point of time when the leakage amount is measured, and an actual position of the second movable part after an offset time required from setting the target position for the first movable part until the actual position of the first movable part reaches the target position has elapsed.

5. The state estimation device according to claim 4,

the offset time is calculated from a physical parameter of the first movable unit and a drive voltage or a drive current supplied to the first movable unit.

6. The state estimation device according to claim 5,

the acquisition section further acquires a drive voltage or a drive current supplied to the first movable section,

the estimation portion estimates an amount of leakage of the working fluid based on the target position of the first movable portion, the actual position of the second movable portion, and the driving voltage or the driving current supplied to the first movable portion, which are acquired by the acquisition portion.

7. The state estimation device according to any one of claims 2 to 6,

the estimation reference is generated based on a relationship between a characteristic amount calculated from a target position or an actual position of the first movable part and an actual position of the second movable part and a measurement value of a leakage amount of the working fluid,

the estimation unit calculates the characteristic amount from the target position or the actual position of the first movable part and the actual position of the second movable part acquired by the acquisition unit, and estimates the amount of leakage of the working fluid based on the calculated characteristic amount.

8. The state estimation device according to claim 7,

the characteristic amount is a moving speed of the second movable portion when an actual position of the first movable portion is at a neutral position for minimizing a flow rate of the working fluid.

9. The state estimation device according to any one of claims 2 to 6,

the acquisition unit acquires the target position or the actual position of the first movable unit and the actual position of the second movable unit in a use environment that is the same as a use environment of a control valve or a control valve of the same type as the control valve when the target position or the actual position of the first movable unit and the actual position of the second movable unit used for generating the estimation reference are recorded.

10. The state estimation device according to claim 9,

the usage environment is a situation in which a control target of the control valve or a control target of a control valve of the same type as the control valve is stopped and an adhesion preventing operation of the first movable part and the second movable part is being performed.

11. The state estimation device according to any one of claims 1 to 6,

the leakage amount estimation device further includes a notification unit configured to notify that the leakage amount of the working fluid estimated by the estimation unit is equal to or greater than a predetermined value.

12. The state estimation device according to claim 11,

the notification unit notifies that the leakage amount of the working fluid estimated by the estimation unit has increased from an initial value by a predetermined value or more.

13. The state estimation device according to claim 11,

the notification unit estimates a time until the amount of leakage of the working fluid exceeds a threshold value and notifies the estimated time.

14. The state estimation device according to any one of claims 1 to 6,

the control valve is a control valve for adjusting the amount of fuel supplied to the engine.

15. The state estimation device according to claim 14,

the control valve is provided for each cylinder in order to adjust the amount of fuel supplied to each cylinder of an engine having a plurality of cylinders,

the estimation portion determines abnormality of the control valve by comparing information on each of a plurality of control valves provided to the plurality of cylinders.

16. A control valve is provided with:

a first movable portion whose position changes in accordance with a control signal for specifying a position, the first movable portion controlling a flow rate of the working fluid in accordance with the position;

an acquisition unit that acquires a target position or an actual position of the first movable unit and an actual position of the second movable unit that changes position according to a flow rate of the working fluid; and

an estimating section that estimates an amount of leakage of the working fluid based on the target position or the actual position of the first movable part and the actual position of the second movable part acquired by the acquiring section, using an estimation model for estimating the amount of leakage of the working fluid based on the target position or the actual position of the first movable part and the actual position of the second movable part.

17. A computer-readable storage medium storing a state estimation program for causing a computer to function as an acquisition unit and an estimation unit,

the acquisition unit acquires a target position or an actual position of a first movable unit in a control valve that controls a flow rate of a working fluid according to a position of the first movable unit, and an actual position of a second movable unit that changes position according to the flow rate of the working fluid,

the estimating section estimates the amount of leakage of the working fluid based on the information acquired by the acquiring section.

18. A state estimation method for causing a computer to execute the steps of:

an acquisition step of acquiring a target position or an actual position of a first movable portion in a control valve that controls a flow rate of a working fluid according to a position of the first movable portion, and an actual position of a second movable portion that changes position according to the flow rate of the working fluid; and

an estimating step of estimating an amount of leakage of the working fluid based on the information acquired in the acquiring step.