Motor abnormality judgment system

Abstract

A motor abnormality determination device is provided that can determine the level of mechanical and electrical changes inside the motor when an abnormality occurs. The motor abnormality determination device (1) includes a recorder (11) that collects time-series operation data including data on a current flowing through a motor (20), a feature amount calculation unit (12) that performs frequency analysis on the operation data collected by the recorder and calculates an amplitude value for each frequency as a feature amount of the operation data, and an abnormality identification unit (13) that identifies the presence or absence of an abnormality, the type of the abnormality, and the abnormality level from the feature amount calculated by the feature amount calculation unit. The abnormality level is the level of mechanical and electrical changes inside the motor corresponding to the type of abnormality.

Description

Technical Field

[0001] This application relates to a motor The difference constant determination system.

Background Art

[0002] In the maintenance management of plant equipment equipped with a motor, the development of a technology for detecting motor abnormalities is desired from the perspective of cost reduction. As a motor abnormality detection system, an abnormality detection system that identifies the type of abnormality and the location where the abnormality occurs based on data such as the vibration, temperature, and pressure of the motor during rotational operation has been disclosed (see, for example, Patent Document 1). Further, as another abnormality detection system, an abnormality detection system that measures the power consumption of a motor during rotational operation and detects the presence or absence of an abnormality based on the time from the start of operation until the power consumption reaches the peak power has been disclosed (see, for example, Patent Document 2). Furthermore, as another abnormality detection system, an abnormality detection system that detects the presence or absence of an abnormality based on the vibration sound of a motor during rotational operation has been disclosed (see, for example, Patent Document 3).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional motor abnormality detection systems, it is possible to detect the presence or absence of a motor abnormality and the location where the abnormality occurs. However, conventional motor abnormality detection systems have a problem in that they cannot determine the levels of mechanical and electrical change amounts inside the motor when an abnormality occurs.

[0005] This invention was made to solve the above-mentioned problems, and provides a motor abnormality detection system that can determine the levels of mechanical and electrical changes inside the motor when an abnormality occurs. system The purpose is to provide. [Means for solving the problem]

[0006] Motor abnormality detection according to this invention system The system comprises a recorder that collects time-series operating data including current data flowing through the motor; a feature calculation unit that performs frequency analysis on the time-series operating data collected by the recorder and calculates amplitude values ​​for each frequency as feature quantities of the operating data; and an abnormality identification unit that identifies the presence or absence of an abnormality, the type of abnormality, and the level of the abnormality from the feature quantities calculated by the feature calculation unit. A motor abnormality detection system having a motor abnormality detection device, The abnormality level is the level of mechanical and electrical changes inside the motor corresponding to the type of abnormality. The system includes an abnormality content input unit into which abnormality details, including the type of abnormality of the motor that has occurred, the amount of mechanical change inside the motor, and the amount of electrical change, are input; a motor abnormality detection device connected to the motor; a database unit that stores the abnormality details in association with the feature quantities calculated by the feature quantity calculation unit of the motor abnormality detection device; and an abnormality detection criterion setting unit that sets an abnormality level criterion, which is the level of the amount of mechanical change inside the motor that corresponds to the type of abnormality, based on the relationship between the abnormality details and feature quantities stored in the database unit. The abnormality content input unit receives information obtained from disassembling and inspecting the motor that has occurred, and the abnormality detection criterion setting unit updates the abnormality level criterion based on the information obtained from disassembling and inspecting the motor after it has been recovered from abnormality detection. . [Effects of the Invention]

[0007] Motor abnormality detection according to this invention system In this system, the abnormality identification unit can determine the abnormality level, which is the level of mechanical and electrical changes inside the motor corresponding to the type of abnormality. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing the configuration of the motor abnormality detection system according to Embodiment 1. [Figure 2] This is a flowchart showing the abnormality investigation process in the motor abnormality detection system according to Embodiment 1. [Figure 3] This flowchart shows the operation of the abnormality detection device according to Embodiment 1. [Figure 4] This diagram illustrates the operation of the abnormality detection device according to Embodiment 1. [Figure 5]This is a diagram showing the configuration of the motor abnormality detection system according to Embodiment 2. [Figure 6] This is a diagram showing the configuration of the motor abnormality detection system according to Embodiment 3. [Figure 7] This is a diagram showing the configuration of the machine learning unit in the motor abnormality detection system according to Embodiment 3. [Figure 8] This is a diagram showing the configuration of the abnormality identification unit in the motor abnormality detection system according to Embodiment 3. [Figure 9] This figure shows an example of the hardware configuration of the anomaly determination criterion setting unit, machine learning unit, feature calculation unit, and anomaly identification unit according to Embodiments 1 to 3. [Modes for carrying out the invention]

[0009] Hereinafter, a motor abnormality detection device and a motor abnormality detection system according to embodiments for carrying out the present invention will be described in detail with reference to the drawings. In each figure, the same reference numerals indicate the same or corresponding parts.

[0010] Embodiment 1. Figure 1 is a diagram showing the configuration of a motor abnormality detection system according to Embodiment 1. The motor abnormality detection system 10 of this embodiment is a system for detecting abnormalities in the motor 20. The abnormality detection system 10 of this embodiment consists of an abnormality detection device 1, an abnormality content input unit 2, a database unit 3, and an abnormality detection criterion setting unit 4. The motor 20 is a rotating machine that performs rotational motion, or a linear motor that performs linear motion. Hereafter, the rotational speed when the motor is a rotating machine and the moving speed when the motor is a linear motor will be collectively referred to as the motor's operating speed.

[0011] The abnormality determination device 1 includes a recorder 11, a feature quantity calculation unit 12, and an abnormality discrimination unit 13. The recorder 11 is connected to the motor 20 and collects time-series operation data including the current data flowing through the motor 20. The feature quantity calculation unit 12 performs frequency analysis on the time-series operation data collected by the recorder 11 and calculates the amplitude value for each frequency as a feature quantity of the operation data. The abnormality discrimination unit 13 discriminates the presence or absence of an abnormality, the type of abnormality, and the abnormality level from the feature quantity calculated by the feature quantity calculation unit 12. Further, the abnormality discrimination unit 13 outputs the discriminated presence or absence of an abnormality, the type of abnormality, and the abnormality level to an external abnormality content display unit 30. The current data collected by the recorder 11 may be the phase current of the motor 2 or the current converted to the dq axis. Further, the recorder 11 may be included in an inverter that drives the motor 20.

[0012] The operation data collected by the recorder 11 includes, in addition to the current data, vibration data collected by a vibration sensor, sound pressure data collected by a microphone, and the like. Since vibration data, sound pressure data, etc. can be collected by vibration sensors, microphones, etc. attached to the outside of the motor 20, it is easy to collect the data.

[0013] When the operation speed of the motor 20 is constant during constant-speed operation, the feature quantity calculation unit 12 may perform frequency analysis on the time-series operation data using Fourier transform. When the operation speed of the motor 20 fluctuates during acceleration and deceleration operation, the feature quantity calculation unit 12 may perform frequency analysis on the time-series operation data using short-time Fourier transform or wavelet transform. By performing frequency analysis using short-time Fourier transform or wavelet transform for each short time during acceleration and deceleration operation, the feature quantity calculation unit 12 can calculate the feature quantity without depending on the operation state of the motor 20.

[0014] The abnormal content input unit 2 receives the type of abnormality at the time of occurrence determined by the subsequent abnormal content investigation, the mechanical change amount inside the motor 20 caused by the abnormality, and the electrical change amount of the motor 20 changed by the abnormality. The types of abnormalities include, for example, an increase in the resistance of the winding, a break in the winding, damage to the bearing, damage to the magnet, etc. The mechanical change amount inside the motor 20 caused by the abnormality is, for example, the amount of change in shape from normal times such as scratches, cracks, and wear inside the motor 20. The electrical change amount of the motor 20 changed by the abnormality is, for example, the amount of change from the reference value of the impedance between the terminals of the motor 20.

[0015] The database unit 3 stores information associating the type of abnormality, the mechanical change amount, and the electrical change amount input from the abnormal content input unit 2 with the feature amount of the operation data calculated by the feature amount calculation unit 12 at the time of occurrence of the abnormality.

[0016] The abnormal determination criterion setting unit 4 sets an abnormal determination threshold for determining an abnormal level indicating the degree of abnormality for each type of abnormality from the information associating the type of abnormality, the mechanical change amount, and the electrical change amount stored in the database unit 3 with the feature amount of the operation data, and sets a determination criterion for the abnormal level based on the abnormal determination threshold. Here, the abnormal level is the level of the mechanical change amount and the electrical change amount inside the motor. Note that the level may be described numerically, or may be expressed as large, medium, small, etc. Or, the level may be converted into the remaining life of the motor or parts and expressed as time. In this way, the numerical value displayed may be increased as the abnormal level increases. Also, the numerical value displayed may be decreased as the abnormal level increases.

[0017] Next, the abnormal content investigation will be described. Figure 2 is a flowchart showing the abnormality investigation in the motor abnormality detection system according to this embodiment. This abnormality investigation is conducted by the user or the motor manufacturer on a motor in which an abnormality has occurred. This investigation is performed on multiple motors, each with a different type of abnormality and varying degree of abnormality. Here, motors with different degrees of abnormality mean motors with different amounts of mechanical and electrical changes inside the motor.

[0018] In step S01, the impedance of the motor is measured. In step S02, it is determined whether the measured impedance differs from the reference value. The reference value of the impedance is the impedance value when the motor is functioning normally. In step S02, if the measured impedance differs from the reference value (YES), the process proceeds to step S03. In step S03, the type of abnormality and the amount of electrical change are input to the abnormality content input unit 2, and then the process proceeds to step S04. Here, the amount of electrical change is the difference between the measured impedance and the reference value. In step S02, if the measured impedance is the same as the reference value (NO), the process proceeds to step S04.

[0019] In step S04, the user or the motor manufacturer's investigator disassembles the motor. Then, in step S05, it is determined whether or not mechanical changes have occurred in the motor. If mechanical changes have occurred in the motor in step S05 (YES), the process proceeds to step S06. In step S06, the user or the motor manufacturer's investigator measures the amount of mechanical changes, such as scratches or cracks, that have occurred in the bearings and magnets inside the motor. Here, the amount of mechanical change refers to the size of scratches, cracks, etc., that have occurred in the bearings and magnets. In step S07, the type of abnormality and the amount of mechanical change are input to the abnormality content input unit 2. In this way, the abnormality content input unit 2 receives input of the type of abnormality at the time of occurrence, the amount of mechanical change inside the motor 20 caused by the abnormality, and the amount of electrical change in the motor 20 caused by the abnormality. The abnormality content input unit 2 outputs the input type of abnormality, the amount of mechanical change, and the amount of electrical change to the database unit 3.

[0020] Furthermore, if the type of malfunction and the amount of mechanical change inside the motor can be identified without disassembling the motor, then disassembly of the motor is not necessary.

[0021] Next, the database unit 3 and the abnormality determination criterion setting unit 4 in the motor abnormality determination system 10 according to this embodiment will be described.

[0022] Multiple motors whose abnormalities have been investigated based on the flowchart shown in Figure 2 are connected to the motor abnormality detection system shown in Figure 1. Recorder 11 collects time-series operating data of motors whose abnormality types have been identified in advance. Feature calculation unit 12 performs frequency analysis on the time-series operating data collected by recorder 11 and calculates the amplitude value for each frequency as a feature of the operating data. Feature calculation unit 12 outputs the feature of the operating data to database unit 3.

[0023] The database unit 3 stores a table that associates the type of abnormality, the amount of mechanical change, and the amount of electrical change input from the abnormality content input unit 2 with the characteristics of the operating data input from the characteristic calculation unit 12. In other words, the database unit 3 stores a table that associates the amount of mechanical change and the amount of electrical change in motors with different types of abnormalities and degrees of abnormality with the characteristics of the operating data.

[0024] Furthermore, it is preferable that this table include the correlation between the mechanical and electrical changes in a normal motor and the characteristics of the operating data. Including data for a normal motor makes it possible to determine if it is functioning normally in the abnormality detection process.

[0025] The abnormality judgment criterion setting unit 4 sets the criteria for abnormality judgment from a table stored in the database unit 3 that associates the types of abnormalities, the mechanical and electrical changes in motors with different degrees of abnormality, and the features of the operating data. Specifically, the abnormality judgment criterion setting unit 4 calculates a relational expression from the data of the mechanical and electrical changes in motors with different degrees of abnormality for each type of abnormality, and the features of the operating data of those motors, for example, by polynomial approximation using the least squares method, and determines multiple thresholds for the features based on a predetermined number of divisions. Then, it sets the criteria for determining the abnormality level based on the features divided by the multiple thresholds. The degree of the polynomial may be an integer such as 1 or 2. When the degree is 1, it becomes a linear approximation and cannot express nonlinear relationships, but problems such as data variability and over-approximation of noise are less likely to occur. In this way, the abnormality judgment criterion setting unit 4 determines multiple thresholds for the features and sets the criteria for determining the abnormality level based on those thresholds. The anomaly determination criterion setting unit 4 then outputs to the anomaly identification unit 13 a plurality of thresholds for the determined feature quantities and the criteria for determining the anomaly level set based on those thresholds.

[0026] Next, the operation of the abnormality detection device 1 in this embodiment will be described. Figure 3 is a flowchart illustrating the operation of the abnormality detection device in this embodiment. The motor 20, which is the object of investigation, is connected to the abnormality detection device 1. In step S11, the recorder 11 collects time-series operating data. The operating data is time-series data of, for example, operating speed, including current data. The operating data is stored in the recorder 11 continuously or intermittently. Next, in step S12, the feature calculation unit 12 calculates features from the time-series operating data stored in the recorder 11.

[0027] In step S13, the anomaly identification unit 13 determines the type of anomaly occurring in the motor 20 based on the feature quantities. Then, in step S14, the anomaly identification unit 13 determines the level of the anomaly occurring in the motor 20 based on the feature quantities. Finally, in step S15, the anomaly identification unit 13 outputs the presence or absence of an anomaly, the type of anomaly, and the level of the anomaly to the anomaly content display unit 30. The anomaly content display unit 30 displays the input information.

[0028] Figure 4 is a diagram illustrating an example of the operation of the abnormality detection device in this embodiment. In Figure 4, the horizontal axis represents frequency and the vertical axis represents amplitude. As shown in Figure 4, the feature calculation unit 12 performs frequency analysis on the time-series driving data collected by the recorder 11 and calculates the amplitude value for each frequency as a feature of the driving data. The abnormality identification unit 13 stores in advance multiple thresholds for the feature determined by the abnormality judgment criterion setting unit 4 for each type of abnormality, and the judgment criteria for the abnormality level set based on those thresholds. For example, the abnormality identification unit 13 stores that when abnormality type A occurs, the amplitude of frequency F1 increases, and when abnormality type B occurs, the amplitude of frequency F2 increases. Furthermore, the abnormality identification unit 13 stores the amplitude thresholds A1, A2, ... A5 of frequency F1 that serve as the judgment criteria for the abnormality level when abnormality type A occurs.

[0029] As an example, let's consider the case where damage occurs to the motor bearing. Assume that when damage occurs to the motor bearing, the amplitude of frequency F1 increases. In this case, the abnormality identification unit 13 can determine that there is no abnormality if the amplitude is A1 or less, that there is damage of 0.2 mm or less to the bearing if the amplitude exceeds A1 but is A2 or less, and that there is damage of 0.5 mm or less to the bearing if the amplitude exceeds A2 but is A3 or less.

[0030] In a motor abnormality detection device configured in this way, the abnormality level can be indicated by the amount of mechanical change and electrical change inside the motor corresponding to the type of abnormality. Therefore, the motor abnormality detection device of this embodiment can determine the level of the amount of mechanical change and electrical change inside the motor when an abnormality occurs.

[0031] Furthermore, if the motor that has been detected as abnormal can be recovered, it is preferable to recover the motor and disassemble it for inspection. By disassembling and inspecting the recovered motor, the correlation between the actual amount of mechanical change that occurred in the motor and the features calculated by the feature calculation unit 12 can be confirmed. Then, by inputting the amount of mechanical change obtained from the disassembly inspection into the abnormality content input unit 2, the multiple thresholds for the features determined by the abnormality judgment criterion setting unit 4 and the abnormality level judgment criteria based on those thresholds can be updated.

[0032] In the motor abnormality detection system of this embodiment, the database unit 3 may be a remotely located server. If the database unit 3 is a server connected to other devices via a network, a database unit shared by multiple abnormality detection systems can be constructed.

[0033] Embodiment 2. Figure 5 is a diagram showing the configuration of a motor abnormality detection system according to Embodiment 2. The motor abnormality detection system 10 of this embodiment is a system that detects abnormalities in multiple motors 20. The abnormality detection system 10 of this embodiment consists of multiple abnormality detection devices 1, an abnormality content input unit 2, a database unit 3, and an abnormality detection criterion setting unit 4.

[0034] Multiple anomaly detection devices 1 are connected to multiple motors 20. Each anomaly detection device 1 includes a recorder 11, a feature calculation unit 12, and an anomaly identification unit 13. The recorder 11 is connected to one motor 20 and collects time-series operating data, including current data flowing through the motor 20. The feature calculation unit 12 performs frequency analysis on the time-series operating data collected by the recorder 11 and calculates the amplitude value for each frequency as a feature of the operating data. The anomaly identification unit 13 identifies the presence or absence of an anomaly, the type of anomaly, and the level of the anomaly based on the feature calculated by the feature calculation unit 12. The anomaly identification unit 13 also outputs the identified presence or absence of an anomaly, the type of anomaly, and the level of the anomaly to an external anomaly content display unit 30.

[0035] The abnormality input unit 2 receives input regarding the type of abnormality that occurred in each of the multiple motors 20, the amount of mechanical change inside the motor 20 caused by the abnormality, and the amount of electrical change in the motor 20 that resulted from the abnormality.

[0036] The database unit 3 is connected to the feature calculation units 12 of multiple anomaly detection devices. The database unit 3 stores information relating the type of anomaly, the amount of mechanical change, and the amount of electrical change input for each motor 20 from the anomaly content input unit 2, with the feature quantities of the operating data calculated by the feature calculation unit 12 when an anomaly occurs.

[0037] The abnormality judgment criterion setting unit 4 sets abnormality judgment thresholds for determining the degree of abnormality for each type of abnormality, and abnormality level judgment criteria based on abnormality judgment thresholds, using information stored in the database unit 3 that associates the type of abnormality, mechanical change amount, electrical change amount of each motor 20 with the characteristic quantities of the operating data.

[0038] In a motor abnormality detection system configured in this way, the abnormality detection criterion setting unit 4 sets abnormality detection thresholds for determining the degree of abnormality for each type of abnormality, and abnormality level determination criteria based on abnormality detection thresholds, using information that associates the type of abnormality, mechanical change amount, electrical change amount, and characteristic quantities of the operating data for each motor. Therefore, data from when abnormalities occur in multiple motors can be utilized.

[0039] Furthermore, the frequency of disassembling and examining the recovered motors to confirm the correlation between the actual mechanical changes that occurred in the motor and the features calculated by the feature calculation unit 12 can be increased. As a result, the frequency of updating the multiple thresholds for the features determined by the anomaly judgment criterion setting unit 4 and the anomaly level judgment criteria based on those thresholds can be increased.

[0040] Embodiment 3. Figure 6 is a diagram showing the configuration of the motor abnormality detection system according to Embodiment 3. In this embodiment, the abnormality detection system 10 is configured such that the abnormality detection criterion setting unit of the abnormality detection system shown in Figure 1 of Embodiment 1 is replaced by a machine learning unit 5.

[0041] In the abnormality detection system 10 of this embodiment, the abnormality investigation is the same as the flowchart shown in Figure 2 of Embodiment 1. Furthermore, the process is the same as in Embodiment 1 up to the point where the database unit 3 stores a table that associates the type of abnormality, the amount of mechanical change, and the amount of electrical change input from the abnormality input unit 2 with the characteristics of the operating data input from the characteristic calculation unit 12.

[0042] Figure 7 is a diagram of the configuration of the machine learning unit in the motor anomaly detection system according to this embodiment. As shown in Figure 7, the machine learning unit 5 comprises a data acquisition unit 51 and a model generation unit 52. The data acquisition unit 51 acquires a table stored in the database unit 3 as training data. The training data is a table that associates the mechanical and electrical changes in motors with different types of anomalies and degrees of anomalies with the features of the operating data. The model generation unit 52 learns the correlation between the features and the type and level of anomalies occurring in the motor based on the training data acquired by the data acquisition unit 51. That is, the model generation unit 52 generates a learning model that infers the presence or absence of an anomaly, the type of anomaly and the level of anomaly at the time of an anomaly from the features of the motor in operation calculated by the feature calculation unit 12. The machine learning unit 5 outputs this trained model to the anomaly identification unit 13. Learning in the machine learning unit 5 is performed each time an anomaly content is input to the anomaly content input unit 2. This updates the trained model.

[0043] Figure 8 is a diagram showing the configuration of the abnormality identification unit in the motor abnormality detection system according to this embodiment. As shown in Figure 8, the abnormality identification unit 13 comprises a feature acquisition unit 131 and an inference unit 132. The feature acquisition unit 131 acquires the features of the motor in operation from the feature calculation unit 12. The inference unit 132 receives a trained model as input from the machine learning unit 5. Using this trained model, the inference unit 132 infers the presence or absence of an abnormality, the type of abnormality and the abnormality level when an abnormality occurs, from the features of the motor in operation acquired by the feature acquisition unit 131. The inference unit 132 outputs the inferred presence or absence of an abnormality, the type of abnormality and the abnormality level when an abnormality occurs.

[0044] In the motor anomaly detection system configured in this way, it is not necessary to set multiple thresholds for the feature quantities based on a predetermined number of divisions, as in the motor anomaly detection system of Embodiment 1. The machine learning performed in the machine learning unit 5 may be, for example, polynomial approximation or a neural network. The machine learning method performed in the machine learning unit 5 may be any other machine learning method that can take feature quantities calculated from motor operation data as input and generate a trained model capable of determining the presence or absence of an anomaly, the type of anomaly, and the level of the anomaly.

[0045] In Embodiments 1 to 3, the anomaly determination criterion setting unit 4, machine learning unit 5, feature calculation unit 12, and anomaly identification unit 13 are composed of a processor 40 and a storage device 50, as shown in Figure 9 as an example of the hardware. The storage device, although not shown, includes a volatile storage device such as random access memory and a non-volatile auxiliary storage device such as flash memory. Alternatively, a hard disk may be provided as an auxiliary storage device instead of flash memory. The processor 40 executes the program input from the storage device 50. In this case, the program is input to the processor 40 from the auxiliary storage device via the volatile storage device. The processor 40 may also output data such as calculation results to the volatile storage device of the storage device 50, or it may save the data to the auxiliary storage device via the volatile storage device.

[0046] Although this application describes various exemplary embodiments, the various features, aspects, and functions described in one or more embodiments are not limited to the application of a particular embodiment, but can be applied individually or in various combinations to the embodiments. Accordingly, countless variations not illustrated are conceivable within the scope of the art disclosed herein. These include, for example, modifying, adding or omitting at least one component, or even extracting at least one component and combining it with components of other embodiments. [Explanation of symbols]

[0047] 1 Anomaly detection device, 2 Anomaly content input unit, 3 Database unit, 4 Anomaly detection criterion setting unit, 5 Machine learning unit, 10 Anomaly detection system, 11 Recorder, 12 Feature calculation unit, 13 Anomaly identification unit, 20 Motor, 30 Anomaly content display unit, 40 Processor, 50 Storage device, 51 Data acquisition unit, 52 Model generation unit, 131 Feature acquisition unit, 132 Inference unit.

Claims

1. A recorder that collects time-series operation data including data on the current flowing through a motor; a feature amount calculation unit that performs frequency analysis on the time series driving data collected by the recorder and calculates an amplitude value for each frequency as a feature amount of the driving data; a motor abnormality determination system including an abnormality determination device for a motor, the abnormality determination device including an abnormality identification unit that identifies the presence or absence of an abnormality, a type of abnormality, and an abnormality level from the feature amount calculated by the feature amount calculation unit, the abnormality level is a level of a mechanical change amount and an electrical change amount inside the motor corresponding to the type of the abnormality, an abnormality content input unit for inputting the type of abnormality in the motor in which the abnormality has occurred and the abnormality content including the amount of mechanical change and the amount of electrical change inside the motor; A motor abnormality determination device connected to the motor; a database unit that stores the abnormality details and the feature amount calculated by the feature amount calculation unit of the motor abnormality determination device in association with each other; an abnormality determination criterion setting unit that sets a criterion for an abnormality level, which is a level of a mechanical change amount and an electrical change amount inside the motor corresponding to a type of the abnormality, based on a relationship between the abnormality content stored in the database unit and the feature amount; the type of abnormality, the amount of mechanical change inside the motor, and the amount of electrical change inside the motor input to the abnormality content input unit are information obtained by disassembling and inspecting the motor in which an abnormality has occurred, The motor abnormality determination system according to claim 1, wherein the abnormality determination criterion setting unit updates the abnormality level criterion based on information obtained by disassembly and inspection of the motor recovered after abnormality determination.

2. A recorder that collects time-series operation data including data on the current flowing through a motor; a feature amount calculation unit that performs frequency analysis on the time series driving data collected by the recorder and calculates an amplitude value for each frequency as a feature amount of the driving data; a motor abnormality determination system including a motor abnormality determination device including an abnormality identification unit that identifies the presence or absence of an abnormality, a type of abnormality, and an abnormality level from the feature amount calculated by the feature amount calculation unit, the abnormality level is a level of a mechanical change amount and an electrical change amount inside the motor corresponding to the type of the abnormality, an abnormality content input unit for inputting the type of abnormality of each of the plurality of motors in which an abnormality has occurred and the abnormality content including the amount of mechanical change and the amount of electrical change inside the motor; a plurality of motor abnormality determination devices connected to the plurality of motors, respectively; a database unit that stores the abnormality details and the feature amounts calculated by the feature amount calculation units of the abnormality determination devices for the plurality of motors in association with each other; an abnormality determination criterion setting unit that sets a criterion for an abnormality level, which is a level of a mechanical change amount and an electrical change amount inside the motor corresponding to a type of the abnormality, based on a relationship between the abnormality content stored in the database unit and the feature amount; the type of abnormality, the amount of mechanical change inside the motor, and the amount of electrical change inside the motor input to the abnormality content input unit are information obtained by disassembling and inspecting the motor in which an abnormality has occurred, The motor abnormality determination system according to claim 1, wherein the abnormality determination criterion setting unit updates the abnormality level criterion based on information obtained by disassembly and inspection of the motor recovered after abnormality determination.

3. The motor abnormality determination system according to claim 1 or 2, characterized in that the abnormality determination criterion setting unit sets a criterion for an abnormality level, which is the level of mechanical and electrical change amounts inside the motor corresponding to the type of abnormality, based on a learned model generated by machine learning using the association between the abnormality content and the feature amount stored in the database unit as learning data.

Images