CN106409120B - Machine learning method, machine learning device, and failure prediction device and system - Google Patents
Machine learning method, machine learning device, and failure prediction device and system Download PDFInfo
- Publication number
- CN106409120B CN106409120B CN201610616706.XA CN201610616706A CN106409120B CN 106409120 B CN106409120 B CN 106409120B CN 201610616706 A CN201610616706 A CN 201610616706A CN 106409120 B CN106409120 B CN 106409120B
- Authority
- CN
- China
- Prior art keywords
- failure
- learning
- industrial machine
- data
- machine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B25/00—Models for purposes not provided for in G09B23/00, e.g. full-sized devices for demonstration purposes
- G09B25/02—Models for purposes not provided for in G09B23/00, e.g. full-sized devices for demonstration purposes of industrial processes; of machinery
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1674—Programme controls characterised by safety, monitoring, diagnostic
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
- G05B19/4063—Monitoring general control system
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
- G05B19/4065—Monitoring tool breakage, life or condition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31359—Object oriented model for fault, quality control
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/33—Director till display
- G05B2219/33321—Observation learning
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/34—Director, elements to supervisory
- G05B2219/34477—Fault prediction, analyzing signal trends
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/37—Measurements
- G05B2219/37214—Detect failed machine component, machine performance degradation
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/50—Machine tool, machine tool null till machine tool work handling
- G05B2219/50185—Monitoring, detect failures, control of efficiency of machine, tool life
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S901/00—Robots
- Y10S901/46—Sensing device
- Y10S901/47—Optical
Abstract
The invention provides a machine learning method, a machine learning device, a failure prediction device and a system. The failure prediction system (1) is provided with a machine learning device (5) for learning conditions associated with a failure of the industrial machine (2). A machine learning device (5) is provided with: a state observation unit (52) that observes a state variable that is composed of output data of the sensor (11), internal data of the control software, or calculation data obtained based on the data, during operation or while the industrial machine (2) is stationary; a determination data acquisition unit (51) that acquires determination data that determines whether or not the industrial machine (2) has a failure or the degree of failure; and a learning unit (53) that learns conditions associated with a failure of the industrial machine (2) in accordance with a training data set generated based on a combination of the state variables and the determination data.
Description
Technical Field
The present invention relates to a machine learning method and a machine learning device for learning a failure condition, and a failure prediction device and a failure prediction system provided with the machine learning device.
Background
In industrial machines, it is sometimes required to detect an abnormality of a structural member in advance in order to improve yield or prevent occurrence of a serious accident. For example, a method is known in which an output value of a sensor is compared with a predetermined threshold value, and an abnormality is detected based on the result. Here, the "industrial machine" means not only an industrial robot or a machine controlled by a Computer Numerical Control (CNC) device, but also a machine including a service robot or various machine devices.
Japanese patent application laid-open No. 63-123105 discloses a failure prediction diagnosis method for predicting a failure of a robot by comparing a standard operation pattern of the robot in a normal state with an operation pattern of the robot in operation.
Japanese patent application laid-open No. 10-039908 discloses a failure prediction method for evaluating the presence or absence of deterioration of a robot structural part and the level of deterioration by comparing the difference between a load-side power based on the actual operating state of a drive shaft and a drive-side power based on an operation command for the drive shaft with a determination value.
However, as industrial machinery is complicated or upgraded, the cause of the malfunction is also complicated. Therefore, the existing failure prediction methods performed according to certain standards cannot be applied to actual conditions or lack correctness. Therefore, a failure prediction device capable of accurately predicting a failure according to the situation is required.
Disclosure of Invention
According to a first aspect of the present invention, there is provided a machine learning device that learns a condition associated with a failure of an industrial machine, the machine learning device including: a state observation unit that observes a state variable including at least one of output data of a sensor that detects a state of the industrial machine or a surrounding environment, internal data of control software that controls the industrial machine, and calculation data obtained based on the output data or the internal data while the industrial machine is operating or stationary; a determination data acquisition unit that acquires determination data for determining whether or not the industrial machine has a failure or a failure degree; and a learning unit that learns conditions associated with a failure of the industrial machine, in accordance with a training data set generated based on a combination of the state variables and the determination data.
According to a second aspect of the present invention, in the machine learning device according to the first aspect, the learning unit is configured to learn the condition in accordance with the training data set generated for a plurality of industrial machines.
According to a third aspect of the present invention, in the machine learning device according to the first or second aspect, the learning unit is configured to learn a normal state only for a certain fixed period, and then detect occurrence of a failure based on the determination data acquisition unit.
A fourth aspect of the present invention is the machine learning device according to any one of the first to third aspects, wherein the learning unit is configured to, when the determination data acquisition unit acquires determination data indicating a failure of the industrial machine, weight the determination data included in the training data group in accordance with a time length from when the failure occurred to when the determination data was acquired, and update the condition.
According to a fifth aspect of the present invention, there is provided a failure prediction device including the machine learning device according to any one of the first to fourth aspects, the failure prediction device predicting a failure of the industrial machine, and a failure information output unit outputting failure information indicating whether or not the industrial machine has a failure or a failure degree in response to a current input of the state variable based on a result of learning by the learning unit in accordance with the training data set.
According to a sixth aspect of the present invention, in the failure prediction device according to the fifth aspect, the learning unit is configured to relearn the condition in accordance with an additional training data set generated based on a combination of the current state variable and the determination data.
According to a seventh aspect of the present invention, in the failure prediction device according to the fifth or sixth aspect, the machine learning device is connected to the industrial machine via a network, and the state observation unit is configured to acquire the current state variable via the network.
According to an eighth aspect of the present invention, in the failure prediction device according to the seventh aspect, the machine learning device is present on a cloud server.
According to a ninth aspect of the present invention, in the failure prediction device according to any one of the fifth to eighth aspects, the machine learning device is incorporated in a control device that controls the industrial machine.
According to a tenth aspect of the present invention, in the failure prediction device according to any one of the fifth to ninth aspects, the learning result of the machine learning device is shared by a plurality of industrial machines.
According to an eleventh aspect of the present invention, there is provided a failure prediction system including: the failure predicting device according to any one of the fifth to tenth inventions; a sensor that outputs the output data; and a failure information notification unit configured to notify an operator of the failure information.
According to a twelfth aspect of the present invention, in the failure prediction system according to the eleventh aspect, the failure information notification unit notifies the operator of the failure information at a timing at which the failure occurs, at least one of before the timing determined by the first predetermined period from the timing at which the failure occurs and after the period determined by the second predetermined period from the timing at which the failure occurs.
According to a thirteenth aspect of the present invention, there is provided a machine learning method for learning a condition related to a failure of an industrial machine, wherein a state variable including at least one of output data of a sensor for detecting a state of the industrial machine or an ambient environment, internal data of control software for controlling the industrial machine, and calculation data obtained based on the output data or the internal data is observed while the industrial machine is operating or stationary, determination data for determining whether or not the industrial machine has a failure or a degree of failure is obtained, and the condition related to the failure of the industrial machine is learned in accordance with a training data set generated based on a combination of the state variable and the determination data.
Drawings
The present invention will be more clearly understood by reference to the following drawings.
Fig. 1 is a block diagram showing an example of a failure prediction system according to an embodiment.
Fig. 2 is a flowchart showing an example of a flow of a learning process of the machine learning device.
Fig. 3 shows an example of the structure of a neural network.
Fig. 4 is an example of a learning period for explaining the teachers-less learning method.
Fig. 5 is a diagram for explaining an example of the recurrent neural network.
Fig. 6 is a block diagram showing an example of a failure prediction system according to another embodiment.
Fig. 7 is a diagram for explaining an example of an index value indicating the degree of a failure in the failure prediction system according to the embodiment (1).
Fig. 8 is a diagram for explaining an example of the index value indicating the degree of failure of the failure prediction system according to the embodiment (2).
Fig. 9 is a flowchart showing an example of a failure prediction flow using the learning result.
Detailed Description
Embodiments of a machine learning method and a machine learning device, and a failure prediction device and a failure prediction system provided with the machine learning device according to the present invention will be described below with reference to the drawings. It is to be understood, however, that the invention is not limited to the embodiments illustrated in the drawings or described below. In order to facilitate understanding of the present invention, the scale of the components of the illustrated embodiment is appropriately changed. The same reference numerals are used for the same or corresponding components.
Fig. 1 is a block diagram showing an example of a failure prediction system according to an embodiment. The failure prediction system 1 can learn a condition associated with a failure of an industrial machine (hereinafter referred to as a "failure condition") using a machine learning device 5 having a machine learning function. Further, the failure prediction system 1 can generate failure information corresponding to the state of the industrial machine and its surrounding environment based on the result of learning by the machine learning device 5.
In the present specification, "industrial machine" means various machines including an industrial robot, a service robot, and a machine controlled by a Computer Numerical Control (CNC) device. In the present specification, the term "failure of an industrial machine" includes a failure of a structural component of the industrial machine. That is, the "failure of the industrial machine" is not limited to a state in which the intended industrial machine function cannot be executed, and includes, for example, a state in which the normal operation cannot be reproduced temporarily or permanently.
The "failure information" generated by the failure prediction system 1 includes a signal indicating whether or not the industrial machine has failed or information indicating "the degree of failure". The "failure information" may include information indicating that the industrial machine is in a normal state. "degree of failure" means the severity of the failure. The "degree of failure" may be limited to either the maximum value or the minimum value. The "degree of failure" may be a continuous quantity or a discrete quantity. The operator can determine from the "degree of failure" whether the target component should be directly replaced or repaired or whether the target component should be replaced or repaired at the time of the next maintenance operation.
In the following description, a failure prediction system 1 used for predicting a failure of the robot 2 will be described. However, those skilled in the art will recognize that the present invention is equally applicable to any other industrial machine.
The robot 2 shown in fig. 1 is a six-axis vertical multi-joint robot in which each joint is driven by a motor. The robot 2 is connected to the robot controller 3 via a known communication means. The robot controller 3 generates a command for the robot 2 in accordance with the control program.
The robot control device 3 is a digital computer having a CPU, ROM, RAM, nonvolatile memory, and an interface connected to an external device. As shown in fig. 1, the robot controller 3 includes a failure determination unit 31.
The failure determination unit 31 determines a failure of the robot 2 by a known failure diagnosis method. The failure determination unit 31 determines the presence or absence of a failure or the degree of a failure of the robot 2, independently of failure information generated by the failure prediction system 1. For example, the failure determination unit 31 determines that a failure has occurred when the disturbance torque detected by the torque sensor or the amplitude of the vibration of the output data of the sensor exceeds a predetermined threshold value. Alternatively, the failure determination unit 31 may determine that the robot 2 has failed based on internal data of control software stored in the robot control device 3. In this manner, the failure determination unit 31 determines a failure due to various causes. The determination result of the failure determination unit 31 is input to a determination data acquisition unit 51 of the machine learning device 5, which will be described later.
In another embodiment, the machine learning device 5 may be configured to input failure information to the determination data acquisition unit 51 in response to an input operation by an operator who has found or known a failure of the robot 2.
The failure prediction system 1 further includes a sensor 11 that detects a state of the robot 2 or the surrounding environment. The sensor 11 may include at least one of a force sensor, a torque sensor, a vibration sensor, a sound collection sensor, a photographing sensor, a distance sensor, a temperature sensor, a humidity sensor, a flow sensor, a light amount sensor, a pH sensor, a pressure sensor, a viscosity sensor, and an odor sensor. Data output from the sensor 11 (hereinafter simply referred to as "output data") is input to the state observation unit 52 of the machine learning device 5.
The machine learning device 5 learns the failure condition of the robot 2. In one embodiment, the machine learning device 5 may be a digital computer different from the robot control device 3 connected to the robot 2 via a network.
In another embodiment, the machine learning device 5 may be incorporated in the robot controller 3. At this time, the machine learning device 5 executes machine learning by the processor of the robot control device 3. In other embodiments, the machine learning device 5 may be present on a cloud server.
As shown in fig. 1, the machine learning device 5 includes a determination data acquisition unit 51, a state observation unit 52, and a learning unit 53.
The determination data acquiring unit 51 acquires the determination data from the failure determining unit 31. The determination data used when the machine learning device 5 learns the failure condition is input from the determination data acquisition unit 51 to the learning unit 53. The determination data is data for determining whether or not there is a failure or the degree of failure. The determination data may not include data indicating that there is a failure, that is, that the robot 2 is in an abnormal state.
The state observation unit 52 observes a state variable that is an input value for machine learning while the robot 2 is in motion or is stationary. In the embodiment in which the machine learning device 5 is connected to the robot 2 and the sensor 11 via a network, the state observation unit 52 acquires the state variables via the network.
The state variable may comprise output data of the sensor 11. The state variables may also contain internal data of the control software controlling the robot 2. The internal data may include at least any one of torque, position, velocity, acceleration, jerk, current, voltage, and an estimated disturbance value. The estimated disturbance value is, for example, a disturbance value estimated by an observer based on a torque command and a speed feedback.
The state variables may also contain calculated data based on output data or internal data. The calculation data may be obtained using at least one of frequency resolution, time-frequency resolution, and autocorrelation resolution. Of course, the calculation data may be obtained by a simpler calculation such as a coefficient multiplication operation or a differential integration operation.
The learning unit 53 learns the failure condition in accordance with a training data set generated based on a combination of the state variables output from the state observation unit 52 and the determination data output from the determination data acquisition unit 51. The training data set is data in which state variables and decision data are associated with each other.
Fig. 2 illustrates an example of the learning process in the mechanical learning apparatus 5. When the learning is started, in step S201, the state observation unit 52 acquires a state variable including output data, internal data, calculation data, and the like. In step S202, the determination data obtaining unit 51 obtains determination data based on the determination result of the failure determination unit 31.
In step S203, the learning unit 53 learns the failure condition according to a training data set generated based on a combination of the state variables acquired in step S201 and the determination data acquired in step S202. The processing of steps S201 to S203 is repeatedly executed until the machine learning device 5 sufficiently learns the failure condition.
In one embodiment, the learning unit 53 of the machine learning device 5 may learn the failure condition in accordance with a neural network model. Fig. 3 shows an example of a neural network model. The neural network consists of l neurons x1、x2、x3、…、xlInput layer of (2), comprising m neurons y1、y2、y3、…、ymContains n neurons z1、z2、z3、…、znThe output layer of (2). In fig. 3, only one intermediate layer is shown, but two or more intermediate layers may be provided. The machine learning device 5 (neural network) may use a General-Purpose computer or a processor, but can perform Processing at a higher speed when a GPGPU (General-Purpose-Graphics Processing unit) or a large-scale PC cluster is used.
The neural network learns fault conditions associated with a fault of the robot 2. The neural network learns the relationship between the state variables and the occurrence of the failure, that is, the failure condition, by so-called teacher learning, in accordance with a training data set generated based on a combination of the state variables observed by the state observation unit 52 and the determination data acquired by the determination data acquisition unit 51. The teacher learning means that a large number of data sets of a certain input and result (label) are provided to the learning device, so that the characteristics of the data sets can be learned, and a model based on the input estimation result, that is, the relationship thereof, can be obtained in a generalized manner.
Alternatively, the neural network may accumulate only a state without a failure, that is, a state variable when the robot 2 is operating normally, and learn the failure condition by so-called teachers-free learning. For example, the method of teachers-less learning is effective when the failure frequency of the robot 2 is extremely low. Teacher-free learning refers to the following method: a device for learning how input data is distributed by supplying only a large amount of input data to a learning device, and performing processes such as compression, classification, and shaping on the input data without supplying corresponding teacher output data. The features that are present in these data sets can be clustered in a similar manner to each other. Using the result, a certain criterion is set to perform optimal output allocation, thereby enabling output prediction. As a problem setting intermediate between teacher-less learning and teacher-less learning, there is learning called half teacher learning, and there is only a combination of input and output data of a part of the learning, and in addition, the case of only input data corresponds to the half teacher learning.
Fig. 4 is a diagram for explaining an example of a learning period of the teachers-less learning method. Here, the horizontal axis represents time (passage of time), and the vertical axis represents the degree of failure. As shown in fig. 4, the above-described teachers-less learning method is configured such that a state variable is updated only at a fixed period starting from the point when the robot 2 is shipped or maintained, for example, several weeks, and is defined as a normal state. Then, after that, the state variables are not updated, and only the abnormality determination is performed by outputting "the degree of failure" based on the distance from the normal model based on the output result output from the neural network, thereby enabling the abnormality detection.
In the present embodiment, for example, because time-series data having a correlation in time is modeled, it is also effective to use a neural network called a cyclic type. The Recurrent Neural Network (RNN) forms a learning model not only using the state at the current time, but also using the internal state at the time up to this point. The cyclic neural network can be handled in the same manner as a general neural network by expanding the network on the time axis and considering it. Here, the recurrent neural network also has a variety of types, and a simple recursive network (Elman network) is illustrated as an example.
Fig. 5 is a diagram illustrating an example of a recurrent neural network. Fig. 5(a) shows a Time axis development of the Elman network, and fig. 5(b) shows a Back Propagation Through Time (BPTT) of the error Back Propagation algorithm. Here, if the structure of the Elman network shown in fig. 5(a) is used, a back propagation algorithm can be applied.
However, in the Elman network, unlike a general neural network, as shown in fig. 5(b), an error propagates in a time-tracing manner, and such a back propagation algorithm is called back propagation along time (BPTT). By applying such a neural network structure, it is possible to estimate an output model in consideration of the transition of the input up to now, and for example, it is possible to use whether or not the estimated output value is a certain abnormal value as having a relationship with the occurrence of a failure.
When failure prediction described later is performed, the output layer outputs information indicating the presence or absence of a failure corresponding to the failure information or "degree of failure" in response to a state variable input to the input layer of the neural network. Further, the preferable value of the "degree of failure" may be a value in which any one of the maximum value and the minimum value is limited, or may be a continuous amount or a discrete amount.
With the machine learning device and the machine learning method according to the above-described embodiment, it is possible to learn a more accurate failure condition corresponding to an actual usage situation than a failure condition based on the determination data output from the determination data acquisition unit 51. Thus, even when the cause of the failure is complicated and it is difficult to set a failure condition in advance, it is possible to predict the failure with high accuracy.
In one embodiment, when the determination data acquiring unit 51 acquires the determination data indicating the failure of the robot 2, the learning unit 53 may update the failure condition by weighting the determination data according to the length of time from when the failure occurs to when each determination data is acquired. Here, it is estimated that the shorter the time until the failure actually occurs after the determination data is acquired, the closer the state directly related to the occurrence of the failure is. Therefore, if the determination data is weighted according to the elapsed time from the acquisition of the training data set, the failure condition can be effectively learned.
In one embodiment, the learning unit 53 may learn the failure condition in accordance with a training data set generated for a plurality of robots 2. The learning unit 53 may acquire training data sets from a plurality of robots 2 used at the same site, or may learn a failure condition using training data sets collected from a plurality of robots 2 independently operating at different sites. The robot 2 that collects the training data set may be added to the object on the way or deleted from the object on the other hand.
Next, the following three examples are given as a method of sharing (sharing) the training data sets of the plurality of robots 2, but it is needless to say that other methods may be applied. First, as a first example, a method of sharing a neural network model is used, and for example, for each weight coefficient of the network, a difference between the robots 2 is transmitted and reflected using a communication unit. As a second example, the weights of the learning device 5 and the like can be shared by sharing the data sets of the input and output of the neural network. As a third example, a database is prepared, and a more appropriate model of the neural network is loaded by accessing the database, thereby sharing (setting the same model) the state.
Fig. 6 is a block diagram showing an example of a failure prediction system according to another embodiment. The failure prediction system 1 includes a failure prediction device 4, and the failure prediction device 4 generates failure information of the robot 2 using a result of learning by a machine learning device 5.
The failure prediction device 4 includes a state observation unit 41 and a failure information output unit 42. The state observation unit 41 has the same function as the state observation unit 52 described with reference to fig. 1, and acquires state variables reflecting the states of the robot 2 and the surrounding environment. The failure information output unit 42 outputs failure information of the robot 2 in response to input of the state variables via the state observation unit 41 based on the result of learning by the learning unit 53 of the machine learning device 5 in accordance with the training data set.
As shown in fig. 6, the robot controller 3 may include a notification unit (failure information notification unit) 32. The notification unit 32 notifies the operator of the failure information output by the failure information output unit 42. The method of notifying the failure information is not particularly limited as long as the operator can know it. For example, the presence or absence of a failure or the degree of a failure may be displayed on a display device not shown, or a warning sound may be generated according to the content of failure information.
Fig. 7 and 8 are diagrams for explaining examples (first to fourth examples) of index values indicating the degree of failure in the failure prediction system according to the embodiment. In fig. 7(a), 7(b), 7(c), and 8, the horizontal axis represents time, and the vertical axis represents the degree of failure. First, as shown in fig. 7(a), for example, in the first example, the following structure may be employed: the index value indicating "the degree of failure" is determined so as to increase as the failure approaches, and the failure information output unit 42 outputs the index value obtained by learning as the failure information. As shown in fig. 7(b), for example, in the second example, the following structure may be employed: a threshold value is set for the index value, and if the index value is equal to or greater than the threshold value, the index value is abnormal, and if the index value is less than the threshold value, the index value is normal, and the failure information output unit 42 outputs information indicating the presence or absence of a failure as failure information. As shown in fig. 7(c), for example, in the third example, the following structure may be employed: the index value is provided with a plurality of thresholds (threshold 1 to threshold 3), and the failure information output unit 42 outputs, as failure information, the levels (failure level 1 to failure level 4) classified by the respective thresholds.
As shown in fig. 8, for example, in the fourth example, the relationship between the index value and the time until the failure is caused is obtained based on a plurality of pieces of data (teacher data) causing the failure, and the first threshold value for satisfying the case where the time before the time determined by the first predetermined period is traced from the time when the failure occurs is obtained from the relationship. Further, a second threshold value is determined for satisfying a situation that a trace back is made from the time when the failure occurred after the time determined by the second predetermined period. Then, when at least one of the case where the index value is less than the first threshold value and the case where the index value is equal to or greater than the second threshold value is satisfied, the failure information output unit 42 may output the index value itself as failure information or output a level obtained by dividing the index value by the threshold value as failure information. In this case, the threshold value may be set, for example, so that all past teacher data satisfy the condition, or may be set by setting a margin as necessary, or may be set so that a decision error within a certain probability is allowed in terms of probability theory.
Next, an example of failure prediction performed using the result of learning by the machine learning device will be described with reference to fig. 9. In step S501, the state observation unit 41 acquires, for example, a current state variable including output data from the sensor 11. In step S502, the failure information output unit 42 outputs failure information corresponding to the state variable acquired in step S501 based on the learning result of the machine learning device 5. When the failure prediction system 1 includes the notification unit 32, the step of notifying the operator of the failure information may be executed after step S502.
The failure prediction by the failure prediction device 4 described with reference to fig. 9 can be performed when the robot 2 executes a predetermined specific operation. Alternatively, the processes of steps S501 to S502 may be continuously executed while the robot 2 is moving or stationary. Alternatively, the failure prediction may be performed periodically at a predetermined timing.
In one embodiment, the mechanical learning may be performed by the mechanical learning device 5 in parallel with the failure prediction performed by the failure prediction device 4. At this time, the failure predicting device 4 generates failure information and the learning unit 53 of the machine learning device 5 learns the failure condition again based on the determination data acquired through the operation of the failure determining unit 31 or the operator and the state variable at that time point.
The embodiment of mechanical learning using a neural network is described, but mechanical learning may be performed according to other well-known methods, such as genetic programming, functional logic programming, support vector machines, and the like. Note that, as described above, the "industrial machine" in the present specification means various machines including an industrial robot, a service robot, and a machine controlled by a Computer Numerical Control (CNC) device.
The machine learning device and the machine learning method of the present invention learn conditions associated with a failure of an industrial machine in accordance with a training data set generated based on a combination of state variables and determination data. Since the fault condition is learned while the industrial machine is actually operated, an accurate fault condition corresponding to an actual usage state can be learned. Further, according to the failure prediction device and the failure prediction system of the present invention, since the failure condition learning device capable of mechanically learning a failure condition is provided, it is possible to perform accurate failure prediction according to an actual usage situation.
While various embodiments of the present invention have been described above, those skilled in the art will recognize that the intended operational effects of the present invention can be achieved by other embodiments. In particular, the components of the above embodiments may be deleted or replaced, or a known means may be further added, without departing from the scope of the present invention. In addition, it is obvious to those skilled in the art that the present invention can be implemented by arbitrarily combining the features of the embodiments disclosed in the present specification or implicitly.
Claims (11)
1. A machine learning device that learns conditions associated with a failure of an industrial machine, comprising:
a state observation unit that observes a state variable including at least one of output data of a sensor that detects a state of the industrial machine or a surrounding environment, internal data of control software that controls the industrial machine, and calculation data obtained based on the output data or the internal data while the industrial machine is operating or stationary;
a determination data acquisition unit that acquires determination data for determining whether or not the industrial machine has a failure or a failure degree; and
a learning unit that learns conditions associated with a failure of the industrial machine, through a neural network, in accordance with a training data set generated based on a combination of the state variables and the determination data,
the learning unit, after learning a normal state using a certain fixed period, outputs failure information indicating the presence or absence of a failure or the degree of a failure of the industrial machine based on an output from the neural network when the current state variable is input and a normal model,
the learning unit is configured to, when the determination data acquisition unit acquires determination data indicating a failure of the industrial machine, weight the determination data included in the training data group in accordance with a time length from when the failure occurs to when the determination data is acquired, and update the condition.
2. The machine learning apparatus of claim 1,
the learning unit is configured to learn the condition in accordance with the training data set generated for a plurality of industrial machines.
3. A failure prediction device provided with the machine learning device according to claim 1 or 2, which predicts the failure of the industrial machine, the failure prediction device being characterized in that,
the industrial machine control device further includes a failure information output unit that outputs failure information indicating whether or not the industrial machine has failed or a degree of failure in response to the current input of the state variable, based on a result of learning by the learning unit according to the training data set.
4. The failure prediction device of claim 3,
the learning unit is configured to relearn the condition in accordance with an additional training data set generated based on a combination of the current state variable and the determination data.
5. The failure prediction device according to claim 3 or 4,
the machine learning device is connected to the industrial machine via a network, and the state observation unit acquires the current state variable via the network.
6. The failure prediction device of claim 5,
the mechanical learning device resides on a cloud server.
7. The failure prediction device according to claim 3 or 4,
the machine learning device is built in a control device that controls the industrial machine.
8. The failure prediction device according to claim 3 or 4,
the learning result of the machine learning device is shared by a plurality of the industrial machines.
9. A failure prediction system is characterized by comprising:
the failure prediction apparatus of any one of claim 3 to claim 8;
a sensor that outputs the output data; and
and a failure information notification unit configured to notify an operator of the failure information.
10. The fault prediction system of claim 9,
a timing at which the failure information is notified to an operator by the failure information notification unit satisfies at least one of:
tracing back from a time when the failure occurs before a time determined by the first predetermined period; and
the period determined by the second predetermined period is traced back from the time when the failure occurs.
11. A machine learning method of learning a condition associated with a malfunction of an industrial machine,
observing a state variable including at least one of output data of a sensor that detects a state of the industrial machine or a surrounding environment, internal data of control software that controls the industrial machine, and calculation data obtained based on the output data or the internal data during the action or standstill of the industrial machine,
acquiring determination data for determining whether or not the industrial machine has a failure or a failure degree,
learning, by a neural network, a condition associated with a failure of the industrial machine in accordance with a training data set generated based on a combination of the state variables and the determination data,
learning the condition associated with the failure of the industrial machine means that, after a normal state is learned using a certain fixed period, failure information indicating the presence or absence of a failure or the degree of a failure of the industrial machine is output based on the output from the neural network and a normal model in the case where the current state variable has been input,
when determination data indicating a failure of the industrial machine is acquired, the condition is updated by weighting the determination data included in the training data group according to a time length from when the failure occurs to when the determination data is acquired.
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015152572 | 2015-07-31 | ||
JP2015-152572 | 2015-07-31 | ||
JP2015234022A JP6148316B2 (en) | 2015-07-31 | 2015-11-30 | Machine learning method and machine learning device for learning failure conditions, and failure prediction device and failure prediction system provided with the machine learning device |
JP2015-234022 | 2015-11-30 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106409120A CN106409120A (en) | 2017-02-15 |
CN106409120B true CN106409120B (en) | 2021-03-23 |
Family
ID=57988307
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610616706.XA Active CN106409120B (en) | 2015-07-31 | 2016-07-29 | Machine learning method, machine learning device, and failure prediction device and system |
Country Status (2)
Country | Link |
---|---|
JP (4) | JP6148316B2 (en) |
CN (1) | CN106409120B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11971709B2 (en) | 2018-10-01 | 2024-04-30 | Omron Corporation | Learning device, control device, learning method, and recording medium |
Families Citing this family (97)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6346251B2 (en) * | 2016-11-25 | 2018-06-20 | ファナック株式会社 | Oil leak detection device |
JP7142257B2 (en) * | 2017-03-03 | 2022-09-27 | パナソニックIpマネジメント株式会社 | Deterioration diagnosis system additional learning method |
JP6499689B2 (en) | 2017-03-08 | 2019-04-10 | ファナック株式会社 | Finishing amount prediction device and machine learning device |
JP6693451B2 (en) * | 2017-03-14 | 2020-05-13 | オムロン株式会社 | Judgment device, judgment program, and learning method |
JP2018156151A (en) * | 2017-03-15 | 2018-10-04 | ファナック株式会社 | Abnormality detecting apparatus and machine learning device |
EP3605405A4 (en) * | 2017-03-21 | 2020-12-02 | Preferred Networks, Inc. | Server device, trained model providing program, trained model providing method, and trained model providing system |
JP6527187B2 (en) * | 2017-03-22 | 2019-06-05 | ファナック株式会社 | Learning model construction device, anomaly detection device, anomaly detection system and server |
JP6557272B2 (en) * | 2017-03-29 | 2019-08-07 | ファナック株式会社 | State determination device |
JP6313516B1 (en) * | 2017-03-30 | 2018-04-18 | 三菱総研Dcs株式会社 | Information processing apparatus, information processing method, and computer program |
JP6514260B2 (en) * | 2017-04-13 | 2019-05-15 | ファナック株式会社 | Control device and machine learning device |
JP6530779B2 (en) * | 2017-04-20 | 2019-06-12 | ファナック株式会社 | Machining defect factor estimation device |
DE112017007606T5 (en) | 2017-06-30 | 2020-02-27 | Mitsubishi Electric Corporation | INSTABILITY DETECTING DEVICE, INSTABILITY DETECTION SYSTEM AND INSTABILITY DETECTION METHOD |
JP6572265B2 (en) * | 2017-06-30 | 2019-09-04 | ファナック株式会社 | Control device and machine learning device |
KR102616698B1 (en) * | 2017-07-07 | 2023-12-21 | 오티스 엘리베이터 컴파니 | An elevator health monitoring system |
JP7082461B2 (en) * | 2017-07-26 | 2022-06-08 | 株式会社Ye Digital | Failure prediction method, failure prediction device and failure prediction program |
JP6380628B1 (en) * | 2017-07-31 | 2018-08-29 | 株式会社安川電機 | Power conversion apparatus, server, and data generation method |
JP6680730B2 (en) * | 2017-08-08 | 2020-04-15 | ファナック株式会社 | Control device and learning device |
JP6989841B2 (en) * | 2017-08-25 | 2022-01-12 | 国立大学法人 鹿児島大学 | Learning data generation method with teacher information, machine learning method, learning data generation system and program with teacher information |
JP6577542B2 (en) | 2017-09-05 | 2019-09-18 | ファナック株式会社 | Control device |
JP6926904B2 (en) * | 2017-09-28 | 2021-08-25 | 株式会社デンソーウェーブ | Robot abnormality judgment device |
EP3674822B1 (en) * | 2017-09-30 | 2022-10-26 | Siemens Aktiengesellschaft | Method and apparatus for generating fault diagnosis information base of numerical control machine tool |
JP6629815B2 (en) * | 2017-10-23 | 2020-01-15 | ファナック株式会社 | Life estimation device and machine learning device |
KR101989579B1 (en) * | 2017-10-31 | 2019-06-14 | 한국전자통신연구원 | Apparatus and method for monitoring the system |
JP6622778B2 (en) * | 2017-11-01 | 2019-12-18 | ファナック株式会社 | Rotary table device |
JP6798968B2 (en) * | 2017-11-22 | 2020-12-09 | ファナック株式会社 | Noise cause estimation device |
JP6721563B2 (en) | 2017-11-28 | 2020-07-15 | ファナック株式会社 | Numerical control device |
JP6972971B2 (en) * | 2017-11-28 | 2021-11-24 | 株式会社安川電機 | Control system, machine learning device, maintenance support device, and maintenance support method |
EP3726437A4 (en) | 2017-12-11 | 2020-12-16 | NEC Corporation | Failure analysis device, failure analysis method, and failure analysis program |
JP7173273B2 (en) * | 2017-12-11 | 2022-11-16 | 日本電気株式会社 | Failure analysis device, failure analysis method and failure analysis program |
JP7007715B2 (en) * | 2017-12-28 | 2022-01-25 | ローレル精機株式会社 | Status determination device, money processor status determination system, status determination method and program |
CN107919054B (en) * | 2018-01-04 | 2019-06-25 | 南京旭上数控技术有限公司 | A kind of industrial robot instructional device |
CN110065091A (en) * | 2018-01-24 | 2019-07-30 | 固德科技股份有限公司 | A kind of mechanical arm dynamic monitoring system and its implementation method |
JP6892400B2 (en) | 2018-01-30 | 2021-06-23 | ファナック株式会社 | Machine learning device that learns the failure occurrence mechanism of laser devices |
JP6662926B2 (en) * | 2018-01-31 | 2020-03-11 | ファナック株式会社 | Notification method of robot and maintenance time for robot |
WO2019150726A1 (en) * | 2018-02-01 | 2019-08-08 | 本田技研工業株式会社 | Robot system and method for controlling robot |
JP2019141869A (en) * | 2018-02-19 | 2019-08-29 | ファナック株式会社 | Controller and machine learning device |
JP6711854B2 (en) * | 2018-02-22 | 2020-06-17 | ファナック株式会社 | Failure prediction device and machine learning device |
WO2019171123A1 (en) * | 2018-03-05 | 2019-09-12 | Omron Corporation | Method, apparatus, system and program for controlling a robot, and storage medium |
DE102018203234A1 (en) * | 2018-03-05 | 2019-09-05 | Kuka Deutschland Gmbh | Predictive assessment of robots |
JP6882719B2 (en) * | 2018-03-07 | 2021-06-02 | オムロン株式会社 | Robot control device, abnormality diagnosis method, and abnormality diagnosis program |
JP6965798B2 (en) * | 2018-03-12 | 2021-11-10 | オムロン株式会社 | Control system and control method |
DE102019001760A1 (en) * | 2018-03-19 | 2019-09-19 | Fanuc Corporation | INFORMATION PROCESSING DEVICE, MECHANICAL LEARNING DEVICE AND SYSTEM |
CN108459933B (en) * | 2018-03-21 | 2021-10-22 | 哈工大大数据(哈尔滨)智能科技有限公司 | Big data computer system fault detection method based on deep recursion network |
JP2019191799A (en) | 2018-04-23 | 2019-10-31 | 株式会社日立製作所 | Failure sign diagnosis system and failure sign diagnosis method |
CN108621159B (en) * | 2018-04-28 | 2020-05-19 | 首都师范大学 | Robot dynamics modeling method based on deep learning |
JP6909410B2 (en) * | 2018-05-08 | 2021-07-28 | オムロン株式会社 | Robot control device, maintenance management method, and maintenance management program |
JP6810097B2 (en) * | 2018-05-21 | 2021-01-06 | ファナック株式会社 | Anomaly detector |
CN110539331A (en) * | 2018-05-28 | 2019-12-06 | 睿胜自动化工程有限公司 | Method and device for detecting abnormality of mechanical arm and pump in advance |
DE112018007729B4 (en) * | 2018-06-14 | 2022-09-08 | Yamaha Hatsudoki Kabushiki Kaisha | Machine learning device and robotic system equipped with same |
KR102239040B1 (en) * | 2018-06-29 | 2021-04-13 | 성균관대학교산학협력단 | Prognostics and health management systems for component of vehicle and methods thereof |
KR102576327B1 (en) * | 2018-06-29 | 2023-09-08 | 로베르트 보쉬 게엠베하 | Methods for monitoring and identifying sensor faults in electric drive systems |
JP7060546B2 (en) * | 2018-07-10 | 2022-04-26 | ファナック株式会社 | Tooth contact position adjustment amount estimation device, machine learning device, robot system and tooth contact position adjustment amount estimation system |
WO2020026344A1 (en) * | 2018-07-31 | 2020-02-06 | 日産自動車株式会社 | Abnormality determination device and abnormality determination method |
JP7079420B2 (en) * | 2018-08-06 | 2022-06-02 | 日産自動車株式会社 | Abnormality diagnosis device and abnormality diagnosis method |
JP6856591B2 (en) | 2018-09-11 | 2021-04-07 | ファナック株式会社 | Control device, CNC device and control method of control device |
CN109270921A (en) * | 2018-09-25 | 2019-01-25 | 深圳市元征科技股份有限公司 | A kind of method for diagnosing faults and device |
JP2020052821A (en) * | 2018-09-27 | 2020-04-02 | 株式会社ジェイテクト | Deterioration determination device and deterioration determination system |
JP7110884B2 (en) * | 2018-10-01 | 2022-08-02 | オムロン株式会社 | LEARNING DEVICE, CONTROL DEVICE, LEARNING METHOD, AND LEARNING PROGRAM |
JP6885911B2 (en) | 2018-10-16 | 2021-06-16 | アイダエンジニアリング株式会社 | Press machine and abnormality monitoring method for press machine |
JP6787971B2 (en) | 2018-10-25 | 2020-11-18 | ファナック株式会社 | State judgment device and state judgment method |
US11119716B2 (en) * | 2018-10-31 | 2021-09-14 | Fanuc Corporation | Display system, machine learning device, and display device |
JP6867358B2 (en) * | 2018-11-13 | 2021-04-28 | ファナック株式会社 | State judgment device and state judgment method |
JP7107830B2 (en) * | 2018-12-21 | 2022-07-27 | ファナック株式会社 | Learning data confirmation support device, machine learning device, failure prediction device |
CN109514560A (en) * | 2018-12-25 | 2019-03-26 | 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) | Industrial robot failure monitoring system, method and device |
JP7162550B2 (en) * | 2019-02-15 | 2022-10-28 | オムロン株式会社 | Model generation device, prediction device, model generation method, and model generation program |
JP7219117B2 (en) * | 2019-02-28 | 2023-02-07 | コマツ産機株式会社 | Industrial machine predictive maintenance device, method, and system |
JP7357450B2 (en) * | 2019-02-28 | 2023-10-06 | コマツ産機株式会社 | System and method for collecting learning data |
JP6915638B2 (en) * | 2019-03-08 | 2021-08-04 | セイコーエプソン株式会社 | Failure time estimation device, machine learning device, failure time estimation method |
WO2020183539A1 (en) * | 2019-03-08 | 2020-09-17 | 三菱電機株式会社 | Breakdown diagnosis system, prediction rule generation method, and prediction rule generation program |
JP6993374B2 (en) * | 2019-03-25 | 2022-01-13 | ファナック株式会社 | Robot control system |
JP6811878B1 (en) * | 2019-03-28 | 2021-01-13 | 三菱電機株式会社 | Numerical control device and numerical control method |
US10996664B2 (en) * | 2019-03-29 | 2021-05-04 | Mitsubishi Electric Research Laboratories, Inc. | Predictive classification of future operations |
JP7000376B2 (en) * | 2019-04-23 | 2022-01-19 | ファナック株式会社 | Machine learning equipment, prediction equipment, and control equipment |
TR201906067A2 (en) * | 2019-04-24 | 2020-11-23 | Borusan Makina Ve Guec Sistemleri Sanayi Ve Ticaret Anonim Sirketi | A SYSTEM AND METHOD FOR FAULT PREDICTION IN BUSINESS MACHINES |
CN111942973B (en) * | 2019-05-16 | 2023-04-11 | 株式会社日立制作所 | Elevator control device, robot fault precursor diagnosis system and method thereof |
JP7260402B2 (en) * | 2019-05-31 | 2023-04-18 | ファナック株式会社 | MACHINE LEARNING DEVICE, ROBOT SYSTEM, AND MACHINE LEARNING METHOD FOR LEARNING CABLE STATE |
JP7347969B2 (en) | 2019-06-18 | 2023-09-20 | ファナック株式会社 | Diagnostic equipment and method |
JP7401207B2 (en) | 2019-06-21 | 2023-12-19 | ファナック株式会社 | Machine learning device, robot system, and machine learning method for learning tool status |
US20210331655A1 (en) * | 2019-07-08 | 2021-10-28 | Lg Electronics Inc. | Method and device for monitoring vehicle's brake system in autonomous driving system |
JP7436169B2 (en) * | 2019-09-18 | 2024-02-21 | ファナック株式会社 | Diagnostic equipment and method |
JP7396850B2 (en) | 2019-10-18 | 2023-12-12 | ファナック株式会社 | robot |
CN111086025A (en) * | 2019-12-25 | 2020-05-01 | 南京熊猫电子股份有限公司 | Multi-fault-cause diagnosis system and method applied to industrial robot |
JP7282700B2 (en) * | 2020-01-22 | 2023-05-29 | 双葉電子工業株式会社 | ROBOT, MOTOR DRIVE UNIT, ROBOT CONTROL METHOD |
JP7298494B2 (en) | 2020-01-31 | 2023-06-27 | 横河電機株式会社 | Learning device, learning method, learning program, determination device, determination method, and determination program |
US20210247753A1 (en) | 2020-02-07 | 2021-08-12 | Kabushiki Kaisha Yaskawa Denki | State estimation device, system, and manufacturing method |
US11531339B2 (en) * | 2020-02-14 | 2022-12-20 | Micron Technology, Inc. | Monitoring of drive by wire sensors in vehicles |
JP2021160031A (en) * | 2020-03-31 | 2021-10-11 | セイコーエプソン株式会社 | Failure prediction method and device |
KR102181432B1 (en) * | 2020-04-22 | 2020-11-24 | 김한수 | Intelligent robot control system |
KR102129480B1 (en) * | 2020-04-23 | 2020-07-02 | 호서대학교 산학협력단 | The predictive maintenance apparatus of automatic guided vehicle and predictive maintenance method of thereof |
KR102316773B1 (en) * | 2020-07-31 | 2021-10-26 | 삼성중공업(주) | System and method for predicting health of vessel |
KR102538542B1 (en) * | 2021-04-12 | 2023-05-30 | 서울대학교산학협력단 | Method and apparatus for diagnosis of motor using current signals |
US20220342391A1 (en) | 2021-04-27 | 2022-10-27 | Aida Engineering, Ltd. | Press machine and method of displaying operating state of press machine |
CN114142605B (en) | 2021-11-09 | 2022-07-15 | 广东工业大学 | Pilot protection method, device and storage medium |
CN114055516B (en) * | 2021-11-10 | 2023-08-11 | 合肥欣奕华智能机器股份有限公司 | Fault diagnosis and maintenance method, system, equipment and storage medium |
CN114565058A (en) * | 2022-03-16 | 2022-05-31 | 广东电网有限责任公司 | Training method, device, equipment and medium for island detection model |
CN114770509A (en) * | 2022-05-05 | 2022-07-22 | 新代科技(苏州)有限公司 | Fault diagnosis method applied to welding robot system |
WO2024053101A1 (en) * | 2022-09-09 | 2024-03-14 | 富士通株式会社 | Learning program, generation program, learning method, and information processing device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101008992A (en) * | 2006-12-30 | 2007-08-01 | 北京市劳动保护科学研究所 | Method for detecting leakage of pipeline based on artificial neural network |
CN101126929A (en) * | 2007-09-05 | 2008-02-20 | 东北大学 | Continuous miner remote real-time failure forecast and diagnosis method and device |
CN102063109A (en) * | 2010-11-29 | 2011-05-18 | 株洲南车时代电气股份有限公司 | Neural network-based subway train fault diagnosis device and method |
CN102609764A (en) * | 2012-02-01 | 2012-07-25 | 上海电力学院 | CPN neural network-based fault diagnosis method for stream-turbine generator set |
CN102844721A (en) * | 2010-02-26 | 2012-12-26 | 株式会社日立制作所 | Failure source diagnosis system and method |
CN103064340A (en) * | 2011-10-21 | 2013-04-24 | 沈阳高精数控技术有限公司 | Failure prediction method facing to numerically-controlled machine tool |
Family Cites Families (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08202444A (en) * | 1995-01-25 | 1996-08-09 | Hitachi Ltd | Method and device for diagnosing abnormality of machine facility |
JPH08263131A (en) * | 1995-03-27 | 1996-10-11 | Hitachi Ltd | Device and method for diagnosing plant deterioration |
JPH1049223A (en) * | 1996-07-31 | 1998-02-20 | Nissan Motor Co Ltd | Method and device for fault diagnosis using neural network |
JPH10154900A (en) * | 1996-11-25 | 1998-06-09 | Hitachi Ltd | Method and system for analyzing failure of printed board for mounting electronic device |
JP3604860B2 (en) * | 1997-03-24 | 2004-12-22 | 三洋電機株式会社 | Equipment operation status management device |
JPH11212637A (en) * | 1998-01-22 | 1999-08-06 | Hitachi Ltd | Method and device for preventive maintenance |
JP2000064964A (en) * | 1998-08-21 | 2000-03-03 | Ebara Corp | Failure prediction system of vacuum pump |
JP4592235B2 (en) * | 2001-08-31 | 2010-12-01 | 株式会社東芝 | Fault diagnosis method for production equipment and fault diagnosis system for production equipment |
JP2003208220A (en) | 2002-01-11 | 2003-07-25 | Hitachi Industries Co Ltd | Method and device for diagnosing deterioration of facility |
TWI240216B (en) * | 2002-06-27 | 2005-09-21 | Ind Tech Res Inst | Pattern recognition method by reducing classification error |
EP1793296A1 (en) * | 2005-12-05 | 2007-06-06 | Insyst Ltd. | An apparatus and method for the analysis of a process having parameter-based faults |
CN101127100A (en) * | 2006-08-18 | 2008-02-20 | 张湛 | Construction method for intelligent system for processing uncertain cause and effect relationship information |
US8036999B2 (en) * | 2007-02-14 | 2011-10-11 | Isagacity | Method for analyzing and classifying process data that operates a knowledge base in an open-book mode before defining any clusters |
US8275735B2 (en) | 2007-03-29 | 2012-09-25 | Nec Corporation | Diagnostic system |
CN101697079B (en) * | 2009-09-27 | 2011-07-20 | 华中科技大学 | Blind system fault detection and isolation method for real-time signal processing of spacecraft |
JP2012168799A (en) | 2011-02-15 | 2012-09-06 | Hitachi Ltd | Plant monitoring device and plant monitoring method |
CN102629243B (en) * | 2012-03-02 | 2015-01-07 | 燕山大学 | End effect suppression method based on neural network ensemble and B-spline empirical mode decomposition (BS-EMD) |
JP5996384B2 (en) * | 2012-11-09 | 2016-09-21 | 株式会社東芝 | Process monitoring diagnostic device, process monitoring diagnostic program |
CN103018660B (en) * | 2012-12-25 | 2015-04-22 | 重庆邮电大学 | Multi-fault intelligent diagnosing method for artificial circuit utilizing quantum Hopfield neural network |
US9332028B2 (en) * | 2013-01-25 | 2016-05-03 | REMTCS Inc. | System, method, and apparatus for providing network security |
JP5530019B1 (en) * | 2013-11-01 | 2014-06-25 | 株式会社日立パワーソリューションズ | Abnormal sign detection system and abnormality sign detection method |
JP5684941B1 (en) * | 2014-07-31 | 2015-03-18 | 株式会社日立パワーソリューションズ | Abnormal sign diagnostic apparatus and abnormal sign diagnostic method |
CN104571079A (en) * | 2014-11-25 | 2015-04-29 | 东华大学 | Wireless long-distance fault diagnosis system based on multiple-sensor information fusion |
CN104699994A (en) * | 2015-04-02 | 2015-06-10 | 刘岩 | FBF (fuzzy basis function) neural network based motor air gap eccentricity fault diagnosis method |
-
2015
- 2015-11-30 JP JP2015234022A patent/JP6148316B2/en active Active
-
2016
- 2016-07-29 CN CN201610616706.XA patent/CN106409120B/en active Active
-
2017
- 2017-02-07 JP JP2017020403A patent/JP6773582B2/en active Active
-
2020
- 2020-10-01 JP JP2020167222A patent/JP7104121B2/en active Active
-
2022
- 2022-07-07 JP JP2022109778A patent/JP2022125288A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101008992A (en) * | 2006-12-30 | 2007-08-01 | 北京市劳动保护科学研究所 | Method for detecting leakage of pipeline based on artificial neural network |
CN101126929A (en) * | 2007-09-05 | 2008-02-20 | 东北大学 | Continuous miner remote real-time failure forecast and diagnosis method and device |
CN102844721A (en) * | 2010-02-26 | 2012-12-26 | 株式会社日立制作所 | Failure source diagnosis system and method |
CN102063109A (en) * | 2010-11-29 | 2011-05-18 | 株洲南车时代电气股份有限公司 | Neural network-based subway train fault diagnosis device and method |
CN103064340A (en) * | 2011-10-21 | 2013-04-24 | 沈阳高精数控技术有限公司 | Failure prediction method facing to numerically-controlled machine tool |
CN102609764A (en) * | 2012-02-01 | 2012-07-25 | 上海电力学院 | CPN neural network-based fault diagnosis method for stream-turbine generator set |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11971709B2 (en) | 2018-10-01 | 2024-04-30 | Omron Corporation | Learning device, control device, learning method, and recording medium |
Also Published As
Publication number | Publication date |
---|---|
JP2022125288A (en) | 2022-08-26 |
JP6148316B2 (en) | 2017-06-14 |
JP2021002398A (en) | 2021-01-07 |
JP2017120649A (en) | 2017-07-06 |
JP7104121B2 (en) | 2022-07-20 |
JP6773582B2 (en) | 2020-10-21 |
CN106409120A (en) | 2017-02-15 |
JP2017033526A (en) | 2017-02-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106409120B (en) | Machine learning method, machine learning device, and failure prediction device and system | |
US11275345B2 (en) | Machine learning Method and machine learning device for learning fault conditions, and fault prediction device and fault prediction system including the machine learning device | |
CN107272586B (en) | Machine learning device, machine learning method, failure prediction device, and failure prediction system | |
JP6810097B2 (en) | Anomaly detector | |
JP7320368B2 (en) | FAILURE PREDICTION DEVICE, FAILURE PREDICTION METHOD AND COMPUTER PROGRAM | |
CN109693354B (en) | State determination device | |
CN109219738A (en) | Apparatus for diagnosis of abnormality and abnormality diagnostic method | |
EP2923311A1 (en) | Method and apparatus for deriving diagnostic data about a technical system | |
JP6711323B2 (en) | Abnormal state diagnosis method and abnormal state diagnosis device | |
US10809695B2 (en) | Information processing apparatus, machine learning device and system | |
CN114175044A (en) | Production planning for predictive maintenance and optimization of devices in the food industry by digital twinning | |
JP2013196698A (en) | System monitoring | |
Medjaher et al. | Failure prognostic by using dynamic Bayesian networks | |
CN115329796A (en) | Abnormality detection device, computer-readable storage medium, and abnormality detection method | |
CN113748597A (en) | Motor control device | |
WO2020071066A1 (en) | Abnormality determination device, signal feature value predictor, abnormality determination method, learning model generation method, and learning model | |
US20210178615A1 (en) | Abnormality diagnosis device and abnormality diagnosis method | |
US10955836B2 (en) | Diagnosis system and electronic control device | |
CN109814499A (en) | Noise producing cause estimating device | |
JP2020038594A (en) | Abnormality detecting apparatus, abnormality detecting method, and program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210415 Address after: Yamanashi Prefecture Patentee after: FANUC Corp. Address before: Yamanashi Prefecture Patentee before: FANUC Corp. Patentee before: PREFERRED NETWORKS, Inc. |
|
TR01 | Transfer of patent right |