JP2023021514A - Device diagnostic system and device diagnostic method - Google Patents

Abstract

To provide a device diagnostic technique capable of evaluating abnormality from actual measurement data of a device even if the device has never had an abnormality in the past.SOLUTION: A device diagnostic system 1 includes: an analysis unit 10 that performs calculations by reflecting parameters in equations formulated based on a physical model; a learning unit 11 that learns each parameter corresponding to the calculation result of the analysis unit 10 as teacher data; a physical quantity measuring unit 12 that acquires physical quantities actually measured in each equipment 21 as measured data; a parameter identification unit 14 for identifying measured parameters, which are parameters when the calculation result of the analysis unit 10 reproduces the measured data, based on the teacher data learned by the learning unit 11; and a state determination unit 15 that determines whether there is an abnormality in the device based on each measured parameter identified by the parameter identification unit 14.SELECTED DRAWING: Figure 1

Description

Embodiments of the present invention relate to device diagnostic techniques.

Conventionally, there is a technique for determining the presence or absence of an abnormality or evaluating the remaining life of an electric motor based on measurement data detected by a sensor, using past abnormality or life-related data. For example, there is known a technique for predicting the remaining life by associating measured data with the actual life through machine learning.

Japanese Patent No. 6140229 Japanese Patent No. 6625280

Abnormality data acquired when an abnormality occurs is necessary when using data related to past abnormalities or lifespans to determine signs of abnormalities, determine the presence or absence of abnormalities, or evaluate remaining lifespan. However, it is difficult to obtain abnormal data for equipment with few abnormal occurrences, and it is difficult to associate the measured data with the cause of the abnormality and the actual service life. For example, for important equipment such as large-scale plants that may be shut down for a long period of time, or equipment that is important for safety such as nuclear power plants, periodic overhauls are performed before an abnormality occurs, and repair or replacement is carried out. will be Therefore, there are very few cases of occurrence of anomalies, and the amount of acquired anomaly data is also small. Moreover, various abnormal modes may occur in one device, and it is necessary to acquire abnormal data corresponding to all such abnormal modes.

In particular, the number of sensors and the positions where the sensors are installed are limited, and measurement data required for evaluation of load and the like cannot be obtained directly, and diagnosis may not be possible in some cases. Also, in many cases, a technique is used to monitor vibrations of electric motors and determine the presence or absence of signs of abnormality from changes in levels and changes in frequency characteristics. However, since the change in vibration depends on the frequency characteristics of the device or the installation state of the sensor, it may be difficult to determine whether there is an abnormality or to estimate the cause. In addition, diagnosis of only a specific portion of the electric motor may cause failure to be overlooked in a portion other than this portion.

The embodiments of the present invention have been made in consideration of such circumstances, and provide a device diagnosis technology that can evaluate abnormalities from actual measurement data of the device even if the device has never experienced an abnormality in the past. intended to

A device diagnostic system according to an embodiment of the present invention reproduces the operation of a device composed of a plurality of devices including at least a rotating electric machine, and builds a physical model that reproduces the state of the device that occurs in relation to the operation. a model construction unit that performs calculations by reflecting parameters in equations formulated based on the physical model; and learning that uses each of the parameters corresponding to the calculation results of the analysis unit as teacher data. a physical quantity measuring unit that acquires physical quantities actually measured by each of the devices as measured data; and a measured parameter that is the parameter when the calculation results of the analysis unit reproduce the measured data. A parameter identification unit that identifies based on the teacher data learned by the unit, and a state determination unit that determines the presence or absence of an abnormality in the device based on each of the measured parameters identified by the parameter identification unit.

The embodiment of the present invention provides a device diagnosis technique that can evaluate an abnormality from actual measurement data of the device, even if the device has never experienced an abnormality in the past.

FIG. 2 is a block diagram showing the system configuration of a device diagnosis system; FIG. FIG. 2 is a configuration diagram showing a device diagnosis system connected to the device; Explanatory drawing which shows the aspect which converts the physical quantity acquired from the sensor into the data for analysis. Explanatory drawing which shows the 1st example of coupling installation failure. FIG. 5 is an explanatory diagram showing a second example of a coupling installation failure; Explanatory drawing which shows the aspect of learning based on a parameter and a calculation result. A graph showing the relationship between fatigue and time. Graph showing the relationship between stress amplitude and number of repetitions to failure. The graph which shows the operation|use aspect of remaining-life evaluation. 4 is a flow chart showing a method for diagnosing a device;

Hereinafter, embodiments of a device diagnostic system and a device diagnostic method will be described in detail with reference to the drawings.

Reference numeral 1 in FIG. 1 denotes an apparatus diagnosis system of this embodiment. This device diagnosis system 1 optimizes the inspection plan for a predetermined device 20 (FIG. 2), and when an abnormality occurs, presents the cause and the location of the abnormality, thereby supporting maintenance activities for the device 20. is. In particular, it is used to evaluate the presence or absence of signs of abnormality, the degree of abnormality, the type of abnormality, and the remaining life of each device 21 from actual measurement data for the device 20 that has never experienced an abnormality in the past.

The device diagnosis system 1 of the present embodiment has hardware resources such as a CPU, ROM, RAM, and HDD, and the CPU executes various programs to realize information processing by software using the hardware resources. It consists of computers. Furthermore, the apparatus diagnostic method of this embodiment is implemented by causing a computer to execute various programs.

First, the system configuration of the device diagnosis system 1 will be described with reference to the block diagram shown in FIG.

The device diagnosis system 1 includes a plurality of sensors 2 and an analysis computer 3. FIG. The analysis computer 3 includes an input section 4 , an output section 5 , a communication section 6 , a storage section 7 and a main control section 8 .

Predetermined information is input to the input unit 4 according to the operation of the user who uses the system. The input unit 4 includes an input device such as a mouse or keyboard. That is, predetermined information is input to the input unit 4 according to the operation of these input devices.

The output unit 5 outputs predetermined information. The device diagnosis system 1 of the present embodiment includes a device that displays images, such as a display that outputs analysis results. That is, the output unit 5 controls the image displayed on the display. The display may be separate from the computer main body, or may be integrated with the computer main body.

Note that the device diagnostic system 1 of the present embodiment may control an image displayed on a display of another computer connected via a network. In that case, the output unit 5 provided in another computer may control the output of the analysis result of this embodiment.

In addition, in this embodiment, the display is exemplified as a device for displaying images, but other modes may be used. For example, information may be displayed using a head-mounted display or a projector. Furthermore, a printer that prints information on a paper medium may be used as an alternative to the display. In other words, the target controlled by the output unit 5 may include a head-mounted display, a projector, or a printer.

The communication unit 6 communicates with other computers via communication lines such as the Internet. In this embodiment, the device diagnosis system 1 and another computer are connected to each other via the Internet, but other modes are also possible. For example, they may be connected to each other via a LAN (Local Area Network), a WAN (Wide Area Network), or a mobile communication network.

The storage unit 7 stores various types of information necessary for diagnosing the device. Note that this storage unit 7 has a predetermined database. These are collections of information stored in memory, HDD or cloud and organized so that they can be retrieved or stored.

The main control unit 8 includes a model construction unit 9, an analysis unit 10, a learning unit 11, a physical quantity measurement unit 12, a measured data processing unit 13, a parameter identification unit 14, a state determination unit 15, an abnormality identification unit 16, and a remaining life evaluation unit 17. and an inspection estimation unit 18 . These are implemented by executing programs stored in the memory or HDD by the CPU.

Note that each configuration of the analysis computer 3 does not necessarily have to be provided in one computer. For example, one system may be implemented using a plurality of computers connected to each other via a network. For example, the learning unit 11 may be provided in a computer different from the computer 3 for analysis.

As shown in FIG. 2, the device 20 to be diagnosed in this embodiment is provided in a nuclear power plant or the like. The device 20 is composed of a plurality of devices 21 . For example, the device 20 includes a control panel 21A, an electric motor 21B, a rotor 21C, a load-side device group 21D, and the like.

Here, the control panel 21A corresponds to a component (control section) related to control of behavior of the electric motor 21B. For example, it controls the rotational speed or torque of the electric motor 21B.

Further, the rotating body 21C is a component that transmits the energy output from the electric motor 21B to the device group 21D on the load side.

The load-side device group 21D corresponds to components that consume the energy transmitted from the rotating body 21C. Note that the load-side device group 21D includes, for example, pumps, fans, gears, and the like.

Here, an electric motor 21B is exemplified as the rotary electric machine of the present embodiment. That is, the device 20 is composed of a plurality of devices 21 including at least rotating electric machines. In addition, a generator may be sufficient as a rotary electric machine. This embodiment can be applied whether the rotating electric machine is the electric motor 21B or the generator.

For example, assume that there is a parameter of a predetermined frequency related to a rotating electric machine. This frequency may be either the frequency of power output from the rotating electrical machine or the frequency of power supplied to the rotating electrical machine. When the rotary electric machine is the electric motor 21B, the frequency is the alternating current supplied to the electric motor 21B from the outside. Further, when the rotating electric machine is a generator, the frequency is the alternating current output from the generator to the outside.

Each sensor 2 of the device diagnostic system 1 is installed in the device 20 . The sensor 2 detects at least one of vibration, current, voltage, magnetic flux, temperature, pressure, and rotational torque as a physical quantity. In this way, the physical quantity can be acquired by the sensor 2 regardless of the type of device 21 .

For example, the sensor 2 is provided in the control panel 21A, the electric motor 21B, the rotor 21C, and the device group 21D on the load side. Predetermined information acquired by these sensors 2 is input to the analysis computer 3 . It should be noted that the sensor 2 may not only be installed in the device 20 in advance, but may be added at each inspection. Also, the installation location of the already installed sensor 2 may be changed.

These sensors 2 detect physical quantities that change according to the state of the device 20 . Specific examples of physical quantities include the current and voltage in the control panel 21A and the electric motor 21B, the temperature of the electric motor 21B, the vibration of the electric motor 21B and the rotor 21C, the magnetic flux, load, and torque of the electric motor 21B.

In this embodiment, the model builder 9 (FIG. 1) builds a physical model that reproduces the behavior of the device 20 and the state of the equipment 21 that occurs in relation to the behavior. It should be noted that the physical model is a virtual model with which physical quantities of the device 20 can be simulated. By using the physical model, it is possible not only to simulate the device 21 operating normally, but also to simulate the device 21 operating abnormally.

A physical model reproduces the behavior of the device 20 by a combination of parameters. For example, the physical model includes at least one of a dynamic model, a control model, an electrical model, a magnetic model, a thermal model, a fluid model, a physical property model, and a structural model.

Here, the dynamic model represents the behavior of the dynamic system regarding at least one of rotational motion and translational motion of each device 21 such as the electric motor 21B, the rotor 21C, and the device group 21D on the load side. The control model is for controlling the behavior of the entire device 20 by a control panel 21A as a control unit that constitutes at least one device 21 . The electrical model represents the behavior of the electrical system of device 20 . The magnetic model represents the behavior of the magnetic system of device 20 . The thermal model represents the thermal behavior of device 20 . The fluid model represents the behavior of at least one of flow rate and pressure of fluid flowing through piping connected to a pump that constitutes at least one device 21 . The physical property model represents material properties of each device 21 . The structural model has information on at least one of the dimensions and shape of each device 21 . In this way, the behavior of the device 20 can be precisely reproduced according to various models.

In other words, the physical model models and formulates the structure or function of the device 20 . Equations corresponding to these are then formulated.

In addition, the physical model includes an abnormality model that indicates an abnormality of each device 21 that constitutes the device 20 . For example, as shown in FIGS. 4 and 5, consider a coupling as the rotor 21C. The effect of eccentricity _ec or deflection _dc from the center of rotation caused by mis-installation of the coupling is formulated as a model. In addition, parameters are defined that represent the extent of the anomaly, such as the magnitude of the eccentricity _ec or the deflection angle _dc .

In addition, as an abnormality model of the rotating body 21C, misalignment of the bearing, breakage of the rotor bar or the short-circuit ring of the electric motor 21B, protrusion of the rotor bar, protrusion of the coil in the stator or in the slot, bending or cracking of the rotating body 21C, Missing parts, short circuit or burnout of stator windings, unbalanced power supply voltage, irregular waves in inverters, flaws in rolling bearings (inner ring, outer ring, rolling element), etc. Parameters for each anomaly are defined.

The analysis unit 10 (FIG. 1) performs calculations by reflecting parameters in an equation (group of equations) formulated based on a physical model. This calculation includes structural analysis using a finite element method (FEM) or the like.

Here, the physical quantity measuring unit 12 (FIG. 1) acquires the physical quantity actually measured by each device 21 as measured data. This physical quantity measuring unit 12 acquires the physical quantities detected by the sensor 2 (FIG. 1) as time-series data. For example, as shown in FIG. 3, time-series data including physical quantities representing current, magnetic flux, acceleration, angular velocity, displacement, pressure, etc. are obtained from each device 21 as measured data.

In this embodiment, the physical quantity measuring unit 12 uses the sensor 2 while the device 20 is running to obtain the physical quantity in real time. For example, the physical quantity may be acquired and recorded by attaching the sensor 2 to the device 21 for periodic inspection, and the physical quantity measurement unit 12 may acquire the record at a later date.

In other words, the physical quantity measuring unit 12 converts at least one of the physical quantity detected by each sensor 2 and the physical quantity included in the test data or inspection data obtained when the device 21 was tested or inspected in the past into actual measurement data. to get as In this way, it is possible to determine whether or not there is an abnormality in the device 20 by acquiring at least one of the current physical quantity and the past physical quantity.

The test data or inspection data also includes information indicating whether or not the device 21 has failed. That is, the physical quantity of this embodiment includes information indicating whether or not the device 21 has failed in the past. In addition, the physical quantity includes information indicating the date, location, and state of past failures.

In addition, it is preferable that the data acquired by the physical quantity measuring unit 12 are obtained from a plurality of types of physical quantities. For example, since the vibration is affected by the support structure characteristics of the device 21 or the installation state of the sensor, it is difficult to determine whether or not the change in physical quantity is due to an abnormality based only on the vibration data. In such a case, comprehensive determination can be made from physical quantities such as electric current in addition to vibration.

The measured data processing unit 13 ( FIG. 1 ) also converts the measured data acquired by the physical quantity measuring unit 12 into data for analysis in a format corresponding to the calculation of the analyzing unit 10 . Here, the calculations executed by the analysis unit 10 include calculations for outputting data in the same format as the analysis data output from the measured data processing unit 13 .

For example, as shown in FIG. 3, when the measured data processing unit 13 outputs vibration spectrum data, the corresponding calculation result of the analysis unit 10 is similarly subjected to Fourier transform for outputting vibration spectrum data. (Fast Fourier Transform: FFT). Here, time-series data as actual measurement data is converted into analysis data. In this way, the measured data can be converted into the optimum format for calculation, and the analysis section 10 can perform the calculation at high speed.

The measured data processing unit 13 converts, for example, measured data such as vibration, current, voltage, and magnetic flux acquired by the physical quantity measuring unit 12 into spectrum data by Fourier transform. Also, filter processing is performed as necessary. Also, time-series data such as temperature and pressure are converted into maximum, minimum, average, and effective values as necessary. By these processes, it is possible to extract the feature amount of the actually measured data and remove unnecessary noise and the like. In addition, processing for errors and variations caused by measurement is performed. For example, since there are measurement errors or statistical errors of measuring instruments, these are processed.

The parameter identification unit 14 ( FIG. 1 ) identifies the measured parameters, which are the parameters when the calculation result of the analysis unit 10 reproduces the measured data, based on the teacher data learned by the learning unit 11 . In this embodiment, analysis data converted from actual measurement data is used. That is, the parameters are identified based on the teacher data learned by the learning unit 11 so that the calculation result of the analysis unit 10 reproduces the analysis data. In other words, analysis using the physical model is performed by the analysis unit 10 so that the analysis data derived as a result of the reproduction match the measured data.

For example, if the physical model reproduces the operation of the device 20 in an abnormal state, the parameters at the time of the abnormality can be obtained. In this way, the parameters at the time of abnormality can be used to determine whether or not the actual device 20 is abnormal.

Also, the analysis unit 10 performs calculations reflecting the parameters identified by the parameter identification unit 14 . For example, it acquires the calculation results related to the time change of the load acting on each device 21 constituting the apparatus 20 or the position of the rotating body 21C. It also evaluates numerical errors that occur in calculations.

Further, the parameter identification unit 14 infers the optimum combination of parameters for the physical model of the device 20 to reproduce the analysis data output from the measured data processing unit 13, and outputs these as measured parameters. At this time, estimation is performed in consideration of errors and variations.

In the apparatus diagnostic system 1 of the present embodiment, the parameter identification unit 14 uses, for example, a trained model generated by a neural network to obtain measured parameters that reproduce the analysis data output from the measured data processing unit 13. .

For example, in the case of the motor 21B, the parameters of this embodiment include those related to the size and shape of the motor 21B, the number of coil turns or the number of slots. Parameters also include component properties such as electrical resistance. The parameters also include the operating conditions of the device 20, the ambient environment, and the like. These parameters may be obtained based on the specifications of each device 21 that constitutes the apparatus 20, may be obtained by actual testing, or may be obtained by simulation.

The learning unit 11 (FIG. 1) learns each parameter corresponding to the calculation result of the analysis unit 10 as teacher data. The learning unit 11 learns each parameter and the calculation result corresponding to these parameters when the calculation corresponding to the combination of a plurality of parameters is performed in advance by the analysis unit 10 as teacher data. In this way, the accuracy of learning can be improved.

As shown in FIG. 6, the learning unit 11 generates a learning model by machine learning using the results preliminarily calculated under various parameter conditions in the analysis unit 10 as training data. For example, there is a learning model generated by machine learning using a neural network. Here, the learning unit 11 creates a learning model using the parameters used in the calculation of the analysis unit 10 and the calculation results as teacher data.

The device diagnosis system 1 of this embodiment includes a computer having an algorithm for machine learning. In other words, computers with artificial intelligence (AI) that perform machine learning are included. For example, the system may be composed of a single computer equipped with a neural network, or may be composed of a plurality of computers equipped with a neural network.

Note that the device diagnostic system 1 may include a deep learning unit that extracts a specific pattern from a plurality of patterns based on deep learning.

An analysis technique based on artificial intelligence learning can be used for analysis using a computer in this embodiment. For example, a learning model generated by machine learning using a neural network, a learning model generated by other machine learning, a deep learning algorithm, a mathematical algorithm such as regression analysis can be used. Further, forms of machine learning include forms such as clustering and deep learning.

Here, a neural network is a mathematical model that expresses the characteristics of brain functions by computer simulation. For example, we present a model in which artificial neurons (nodes), which form a network through synaptic connections, change the strength of synaptic connections through learning and acquire problem-solving ability. Furthermore, the neural network acquires problem-solving ability through deep learning.

For example, a neural network is provided with an intermediate layer having 6 layers. Each layer of this intermediate layer consists of 300 units. In addition, by pre-learning a multi-layered neural network using learning data, it is possible to automatically extract feature amounts in patterns of changes in the state of a circuit or system. The multi-layered neural network can set an arbitrary number of intermediate layers, an arbitrary number of units, an arbitrary learning rate, an arbitrary number of times of learning, and an arbitrary activation function on the user interface.

It should be noted that deep reinforcement learning, in which a reward function is set for various information items to be learned and the information item with the highest value is extracted based on the reward function, may be used for the neural network.

For example, CNN (Convolution Neural Network), which has a proven track record in image recognition, is used. In this CNN, the intermediate layer is composed of a convolutional layer and a pooling layer. The convolutional layer obtains the feature map by filtering nearby nodes in the previous layer. The pooling layer further reduces the feature map output from the convolution layer to obtain a new feature map. At this time, by obtaining the maximum value of the pixels included in the region of interest in the feature map, it is possible to absorb some deviation in the position of the feature amount.

A convolutional layer extracts local features of an image, and a pooling layer performs processing to combine the local features. These processes reduce the image while maintaining the features of the input image. In other words, CNN can significantly compress (abstract) the amount of information in an image. Then, using the abstracted image stored in the neural network, it is possible to recognize the input image and classify the image.

Deep learning includes various techniques such as autoencoder, RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), and GAN (Generative Adversarial Network). These methods may be applied to the deep learning of this embodiment.

The life expectancy evaluation unit 17 (FIG. 1) calculates the life expectancy of each device 21 based on the calculation result of the analysis unit 10 when the parameter identified by the parameter identification unit 14 is reflected in the measured data. In this way, the remaining life of each device 21 can be calculated based on the measured data.

In addition, the remaining life evaluation unit 17 determines at least one of load, stress, voltage, current, and temperature related to each device 21 obtained by the analysis unit 10 when the measured parameters identified by the parameter identification unit 14 are reflected. Evaluate the remaining life from the results obtained. In this way, it is possible to evaluate the remaining life considering the load or stress applied to the device 21 .

For example, the time change of the load and stress of each device 21 constituting the device 20 is obtained by calculation, and the remaining life is determined from the life evaluation formula and material properties. In addition, in this embodiment, it is also possible to determine the remaining life from not only the load and stress, but also the deterioration of the insulating material due to the time change of the voltage or current, and the deterioration of the material due to the thermal cycle (time change of the temperature). It's becoming

As a life evaluation formula, for example, there is a basic rated life L10 when a radial load P acts on a rolling bearing that supports the rotating body 21C. This radial load P is calculated by the following equation in the analysis unit 10 based on a physical model.

L10 = (C/P) ^p

Here, C is the basic dynamic load rating and represents the dynamic load capacity of the rolling bearing. For example, it refers to a constant load that gives a basic rating life L10 of 1 million revolutions. Also, p is an index that changes for each type of rolling bearing. For example, p=3 for ball bearings. For roller bearings, p=10/3.

Further, for the fluctuating stress obtained by the analysis unit 10, the remaining life may be evaluated using, for example, Miner's rule (modified Miner's rule) for determining the remaining life from material properties. At this time, the stress frequency distribution of the actual working stress can be obtained using the rainflow method or the like.

A remaining life evaluation method based on the Miner's rule will be described with reference to the graphs of FIGS. 7 and 8. FIG. The solid-line graph G1 in FIG. 8 is a fatigue limit curve (material properties). A broken-line graph G2 in FIG. 8 is obtained when the fatigue limit curve is extended by the modified Miner's rule.

Here, in the SN curve of the target material, let Ni be the number of repetitions at which rupture occurs due to repeated stress σi of a constant stress amplitude. For example, assume that k repeated stresses σi (i=1 to k) with different amplitudes are applied to a given object ni times (i=1 to k). At this time, the fatigue damage D accumulated in this object is given by the following equation. Here, the life is defined as the time when D reaches 1.

The operation method of remaining life evaluation will be described with reference to the graph of FIG. In this graph, the vertical axis is the fatigue damage D, and the horizontal axis is the number of cycles.

The range indicated by the dashed line graph G3 in FIG. 9 indicates the results of evaluating the remaining life at the start of operation of the device 20 . As shown in the dashed line graph, the load evaluation by simulation takes into consideration the variations in parameters and calculation errors, so the calculated service life has a statistical distribution. Therefore, the life of the equipment 21 is determined from the failure probability. A reference failure probability is set for each device 21 .

The range indicated by the solid line graph G4 in FIG. 9 indicates the remaining life evaluation result after the device 20 has been operated for a predetermined period. If the state of the equipment 21 changes during operation, the remaining life evaluation result will change accordingly. Such evaluation is preferably performed in real time during the operating period, but may be performed periodically according to the operation method.

The state determination unit 15 ( FIG. 1 ) of the present embodiment determines whether there is an abnormality in the device 20 based on each measured parameter identified by the parameter identification unit 14 . Here, the state determination unit 15 determines whether or not there is an abnormality in the device 20 by comparing the remaining life calculated by the remaining life evaluation unit 17 and the pre-planned operating time. In this way, it is possible to evaluate whether or not an abnormality occurs in the device 20 during the pre-planned operating period. For example, the presence or absence of abnormality is evaluated by comparing the remaining life of each device 21 with the planned operating time.

Further, the state determination unit 15 determines whether or not there is an abnormality in the device 20 by comparing the measured parameter identified by the parameter identification unit 14 with an arbitrarily set parameter allowable range. In this way, it is possible to easily perform the process of determining whether or not there is an abnormality in the device 20 based on the arbitrarily set parameter allowable range.

Further, the state determination unit 15 determines whether or not there is an abnormality in the device 20 by comparing the actual measurement data acquired by the physical quantity measurement unit 12 with an arbitrarily set data allowable range. In this way, it is possible to easily determine whether or not there is an abnormality in the device 20 based on the arbitrarily set allowable range for data.

For example, the state determination unit 15 determines whether or not there is an abnormality by comparing the actual measurement data acquired by the physical quantity measurement unit 12 with the allowable range for data. Also, the presence or absence of abnormality is determined by comparing the analysis data output from the data processing unit with the allowable range.

The permissible range for parameters and the permissible range for data used for determination by the state determination unit 15 are set in advance. These allowable ranges may be arbitrarily set by the user in advance. Also, all of these tolerances may be the same for the device 20 or may be different for each individual device 20 .

Also, these allowable ranges may be set based on actual measurement data, may be set based on specifications relating to the behavior of the device 20, may be set based on actual test results, It may be set based on a simulation result, or may be set based on a combination of these results.

The abnormality identification unit 16 (FIG. 1) identifies the degree and cause of the abnormality when the state determination unit 15 determines that the device 20 is abnormal. In this way, the degree and cause of the abnormality can be specified based on the measured data. In addition, the degree of abnormality can be evaluated from the combination of measured parameters and the magnitude of the values.

The inspection estimation unit 18 (FIG. 1) estimates the progress of the abnormality from the combination and magnitude of the actually measured parameters when the state determination unit 15 determines that the device 20 is normal, and estimates the remaining life evaluation unit 17. The next inspection location and inspection time are estimated from the remaining life of the device 21 calculated in . In this way, it is possible to automatically present the inspection location and the inspection time to the user.

The main control unit 8 controls the output unit 5 to output the evaluation result of the device diagnostic system 1 . For example, the results derived by the abnormality identification unit 16 and the inspection estimation unit 18 are output.

Next, the device diagnosis method (processing) executed by the device diagnosis system 1 of this embodiment will be described with reference to the flowchart of FIG. In addition, the aforementioned drawings will be referred to as appropriate. The following steps are at least part of the processing included in the device diagnostic method, and other steps may be included in the device diagnostic method.

First, in step S1, the model construction unit 9 creates a physical model that reproduces the operation of the device 20 composed of a plurality of devices 21 including at least a rotating electric machine, and that reproduces the state of the device 21 that occurs in relation to the operation. To construct.

In the next step S2, the analysis unit 10 performs calculations by reflecting the parameters in the equations formulated based on the physical model.

In the next step S3, the learning unit 11 learns the calculation result of the analysis unit 10 and each parameter corresponding thereto as teacher data.

In the next step S4, the physical quantity measuring unit 12 acquires the physical quantity actually measured by each device 21 as measured data.

In the next step S<b>5 , the measured data processing unit 13 converts the measured data acquired by the physical quantity measuring unit 12 into analysis data in a format corresponding to the calculation of the analyzing unit 10 .

In the next step S6, the parameter identification unit 14 identifies the measured parameters, which are the parameters when the calculation result of the analysis unit 10 reproduces the data for analysis (actually measured data), based on the teacher data learned by the learning unit 11. do.

In the next step S<b>7 , the state determination unit 15 determines whether or not there is an abnormality in the device 20 at the present time based on each measured parameter identified by the parameter identification unit 14 . Here, if there is no abnormality (NO in step S7), the process proceeds to step S8. On the other hand, if there is an abnormality (YES in step S7), the process proceeds to step S10.

In step S8, which proceeds in the case of NO in step S7, the remaining life evaluation unit 17 performs calculation based on the calculation result of the analysis unit 10 when the analysis data (actual measurement data) by the parameter identification unit 14 reflects the parameters identified. , the remaining life of each device 21 is calculated.

In the next step S9, the inspection estimating unit 18 estimates the progress of the abnormality from the combination and size of the measured parameters, and the next inspection location and inspection time from the remaining life of the equipment 21 calculated by the remaining life evaluating unit 17. to estimate The main control unit 8 controls the output unit 5 to output the evaluation result of the device diagnostic system 1 . Then, the device diagnosis method is terminated.

In step S10, to which the determination is YES in step S7, the abnormality identification unit 16 identifies the degree and cause of the abnormality when the state determination unit 15 determines that the device 20 is abnormal. The main control unit 8 controls the output unit 5 to output the evaluation result of the device diagnostic system 1 . Then, the device diagnosis method is terminated.

In addition, in the flowchart of the above-described embodiment, the form in which each step is executed in series is exemplified. Also good. Also, some steps may be executed in parallel with other steps.

The system of the above-described embodiment includes a control device in which a processor such as a dedicated chip, FPGA (Field Programmable Gate Array), GPU (Graphics Processing Unit), or CPU (Central Processing Unit) is highly integrated, and a ROM (Read Only Memory) or RAM (Random Access Memory), external storage devices such as HDD (Hard Disk Drive) or SSD (Solid State Drive), display devices such as displays, and input devices such as mice or keyboards and a communication interface. This system can be realized with a hardware configuration using a normal computer.

It should be noted that the program executed by the system of the above-described embodiment is pre-installed in a ROM or the like and provided. Alternatively, this program can be stored as an installable or executable file on a non-transitory computer-readable storage medium such as CD-ROM, CD-R, memory card, DVD, flexible disk (FD), etc. may be stored and provided.

Also, the program executed by this system may be stored on a computer connected to a network such as the Internet, downloaded via the network, and provided. In addition, this system can also be configured by combining separate modules that independently perform each function of the constituent elements and are interconnected by a network or a dedicated line.

According to the embodiments described above, the model construction unit reproduces the operation of a device composed of a plurality of devices including at least a rotating electric machine, and constructs a physical model that reproduces the state of the device that occurs in relation to the operation. By providing it, even if the device has never experienced an abnormality in the past, it is possible to evaluate the abnormality from the actual measurement data of the device.

While several embodiments of the invention have been described, these embodiments have been presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, changes, and combinations can be made without departing from the scope of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, as well as the invention described in the claims and equivalents thereof.

DESCRIPTION OF SYMBOLS 1... Device diagnosis system 2... Sensor 3... Computer for analysis 4... Input part 5... Output part 6... Communication part 7... Storage part 8... Main control part 9... Model building part 10... Analysis unit 11 Learning unit 12 Physical quantity measurement unit 13 Measured data processing unit 14 Parameter identification unit 15 State determination unit 16 Abnormality identification unit 17 Remaining life evaluation unit 18 Inspection estimation Part 20... Apparatus 21... Equipment 21A... Control panel 21B... Electric motor 21C... Rotating body 21D... Load side equipment group.

Claims (14)

a model building unit that builds a physical model that reproduces the operation of a device composed of a plurality of devices including at least a rotating electric machine and that reproduces the state of the device that occurs in relation to the operation;
an analysis unit that performs calculations by reflecting parameters in equations formulated based on the physical model;
a learning unit that learns each of the parameters corresponding to the calculation result of the analysis unit as teacher data;
a physical quantity measuring unit that acquires physical quantities actually measured by each of the devices as measured data;
a parameter identification unit that identifies the measured parameters, which are the parameters when the calculation result of the analysis unit reproduces the measured data, based on the teacher data learned by the learning unit;
a state determination unit that determines whether or not there is an abnormality in the device based on each of the measured parameters identified by the parameter identification unit;
comprising
Device diagnostic system. A remaining life evaluation unit that calculates the remaining life of each device based on the calculation result of the analysis unit when the parameter identified by the measured data by the parameter identification unit is reflected,
The device diagnosis system according to claim 1. The state determination unit determines whether there is an abnormality in the device by comparing the remaining life calculated by the remaining life evaluation unit with a pre-planned operating time.
The device diagnosis system according to claim 2. The remaining life evaluation unit calculates at least one of load, stress, voltage, current, and temperature associated with each of the devices obtained by the analysis unit when the measured parameters identified by the parameter identification unit are reflected. Evaluating the remaining life from the obtained results,
4. The device diagnosis system according to claim 2 or 3. When the state determining unit determines that the device is normal, the progress of the abnormality is estimated from the combination and magnitude of the actually measured parameters, and the remaining life of the device calculated by the remaining life evaluating unit An inspection estimation unit that estimates the next inspection location and inspection time from
The device diagnostic system according to any one of claims 2 to 4. An abnormality identification unit that identifies the degree and cause of abnormality when the device is determined to be abnormal by the state determination unit,
The device diagnosis system according to any one of claims 1 to 5. A measured data processing unit that converts the measured data acquired by the physical quantity measurement unit into analysis data in a format corresponding to the calculation of the analysis unit,
The device diagnostic system according to any one of claims 1 to 6. The learning unit learns, as the teacher data, each of the parameters and the calculation results corresponding to the parameters when calculations corresponding to a plurality of combinations of the parameters are performed in advance by the analysis unit,
The device diagnosis system according to any one of claims 1 to 7. The physical model is
a dynamic model representing the behavior of a dynamic system with respect to at least one of rotational motion and translational motion of each of said devices;
a control model for a control unit that constitutes at least one of the devices to control the behavior of the entire device;
an electrical model representing the behavior of the electrical system of the device;
a magnetic model representing the behavior of the magnetic system of the device;
a thermal model representing the thermal behavior of the device;
a fluid model representing the behavior of at least one of the flow rate and pressure of a fluid flowing through a pipe connected to a pump that constitutes at least one of the devices;
a physical property model representing material properties of each of the devices;
a structural model having information of at least one of dimensions and shape of each of said devices;
including at least one of
reproducing the behavior of the device by a combination of the parameters;
The device diagnostic system according to any one of claims 1 to 8. The state determination unit determines whether or not there is an abnormality in the device by comparing the measured parameter identified by the parameter identification unit with an arbitrarily set permissible range for parameters.
The device diagnostic system according to any one of claims 1 to 9. The state determination unit determines whether there is an abnormality in the device by comparing the measured data acquired by the physical quantity measurement unit with an arbitrarily set data allowable range.
The device diagnostic system according to any one of claims 1 to 10. A sensor provided on each of said devices,
The physical quantity measuring unit
the physical quantity detected by each of the sensors;
The physical quantity included in the test data or inspection data obtained when the device was tested or inspected in the past,
Obtaining at least one of as the measured data,
The device diagnostic system according to any one of claims 1 to 11. The sensor detects at least one of vibration, current, voltage, magnetic flux, temperature, pressure, and rotational torque as the physical quantity.
13. The device diagnostic system of claim 12. a step in which the model construction unit constructs a physical model that reproduces the operation of a device composed of a plurality of devices including at least a rotating electric machine and that reproduces the state of the device that occurs in relation to the operation;
an analysis unit performing calculations by reflecting parameters in equations formulated based on the physical model;
a step in which the learning unit learns each of the parameters corresponding to the calculation result of the analysis unit as teacher data;
a step in which a physical quantity measuring unit acquires physical quantities actually measured by each of the devices as measured data;
a step in which a parameter identification unit identifies, based on the teacher data learned by the learning unit, the measured parameters that are the parameters when the calculation result of the analysis unit reproduces the measured data;
a step in which a state determination unit determines whether or not there is an abnormality in the device based on each of the measured parameters identified by the parameter identification unit;
including,
Device diagnostic method.

Images