阅读说明：本技术 故障确定设备、电动机驱动系统和故障确定方法 (Fault determination device, motor drive system, and fault determination method ) 是由 中村诚 于 2020-02-11 设计创作，主要内容包括：本公开的实施例涉及故障确定设备、电动机驱动系统和故障确定方法。故障诊断可以使用电动机的检测值及其学习模型而方便地执行。设备50具有采样单元51,用于在电动机再生的时候对电流进行采样；以及确定单元52,用于使用学习模型和从通过采样单元51的采样结果所获得的数据来确定电动机的故障,其中所述学习模型在电动机的健全性状态是预定状态时,使用从在电动机再生的时候的电流的采样结果所获得的数据而预先学习。(Embodiments of the present disclosure relate to a fault determination apparatus, a motor drive system, and a fault determination method. The failure diagnosis can be conveniently performed using the detected value of the motor and its learning model. The device 50 has a sampling unit 51 for sampling the current while the motor is regenerating; and a determination unit 52 for determining a failure of the motor using a learning model learned in advance using data obtained from a sampling result of the current at the time of regeneration of the motor when the health state of the motor is a predetermined state and data obtained from the sampling result by the sampling unit 51.)

1. A fault determination device comprising:

the sampling unit is used for sampling the current when the motor is regenerated; and

a determination unit for determining a fault of the motor using a learning model that has been previously learned using data obtained from a sampling result of a current at the time of regeneration of the motor when a health state of the motor is a predetermined state and data obtained from a sampling result by the sampling unit.

2. The fault determination device of claim 1,

wherein the learning model is a model that is learned in advance using data obtained from a result of sampling a current at the time of regeneration of the motor when a soundness state of the motor and a component connected to the motor is a predetermined state, and

wherein the determination unit determines a failure of the motor and the component.

3. The fault determination device of claim 1, further comprising:

a sampling interval determination unit for determining a sampling interval based on the frequency of the current, an

Wherein the sampling unit performs a sampling operation at the sampling interval determined by the sampling interval determination unit.

4. The fault determination device of claim 3,

wherein the sampling interval determination unit estimates the frequency of the current after a predetermined time has elapsed from the start of motor regeneration, and determines the sampling interval based on the estimated frequency.

5. The fault determination device of claim 1, further comprising

A control unit for controlling to change a rotation speed of the motor to a predetermined rotation speed when the motor is switched from a power running state to a regeneration state.

6. The fault determination device of claim 3,

wherein the control unit further controls the electric power consumed during regeneration of the motor to a predetermined value.

7. The fault determination device of claim 1, further comprising:

a frequency analysis unit for performing frequency analysis on the sampling result,

wherein the frequency analysis unit analyzes frequency components of a predetermined frequency band contributing to determination of a fault; and

wherein the determination unit uses an analysis result by the frequency analysis unit as data obtained from the sampling result by the sampling unit.

8. The fault determination device of claim 1, further comprising:

a regenerative state detection unit for detecting a regenerative state of the motor by acquiring a voltage value and a current value of the motor.

9. An electric motor drive system comprising:

an inverter for supplying an alternating current to the motor;

a smoothing capacitor coupled to the inverter; and

the fault-determining device is arranged to determine,

wherein the fault determination device comprises:

a sampling unit for sampling a current when the motor is regenerated; and

a determination unit for determining a fault of the motor using a learning model that is previously learned using data obtained from a sampling result of a current at a time of regeneration of the motor when a health state of the motor is a predetermined state and data obtained from a sampling result of the current by the sampling unit.

10. The motor drive system according to claim 9,

wherein the determination unit further determines degradation of the electrolytic capacitor based on a voltage of the electrolytic capacitor at the time of regeneration of the motor.

11. The motor drive system according to claim 9,

wherein the determination unit further determines a malfunction of the motor based on whether or not the voltages of the three-phase alternating currents are balanced at the time of regeneration of the motor.

12. The motor drive system according to claim 9, further comprising,

a plurality of motors, wherein the inverter is provided for each of the plurality of motors.

13. The motor drive system according to claim 9,

wherein a current at the time of regeneration of the motor is detected using a shunt resistor provided for controlling the inverter.

14. A fault determination method, comprising:

sampling the current while the motor is regenerating; and

determining a failure of the motor by using data obtained from a sampling result and by using a learning model that has been learned in advance using data obtained from the sampling result of the current at the time of regeneration of the motor when a soundness state of the motor is a predetermined state.

Technical Field

Embodiments of the present disclosure generally relate to a fault determination apparatus, a motor drive system, and a fault determination method.

Background

In recent years, various techniques using machine learning have been proposed. The disclosed techniques are listed below.

[ patent document 1] Japanese unexamined patent application publication No.: 2017-127099.

[ non-patent document 1] Vittaya Tipsuwanpon et al, "Fault Detection In compressing Using FFT Algorithm", Proceedings of the World consistency on Engineering and company Science 2013 volume I, WCECS 2013, 10 months, 23-25 days, USA old Jinshan.

For example, patent document 1 discloses a machine learning device capable of adjusting values of a resistor regeneration start voltage and a resistor regeneration stop voltage, which are optimal for respective motors.

For example, non-patent document 1 is known for detection of a motor failure. This document provides a theoretical expression of the frequency components that occur when a motor failure occurs.

Disclosure of Invention

The inventors have found that when failure determination of the motor or a component related to the motor is performed using machine learning, if learning data of the motor in a force action state is used, the following problem occurs. In an environment where the motor is powered, there are many parameters (e.g., current supplied to the motor) that affect the sensed value of the motor, such that various frequency components for the sensed value occur. This makes the design of machine learning models difficult. In addition, even if a machine learning model can be designed, a large amount of learning data for machine learning of the model needs to be collected.

On the other hand, none of the above-mentioned methods uses machine learning to verify the determination of the fault. Therefore, there is a need for a technique that can easily perform failure diagnosis using a detected value of a motor and a learning model thereof. In the following disclosure, "fault" includes the preliminary stage of a fault.

Other objects and novel features will become apparent from the description of the specification and drawings.

According to one embodiment, a fault determination apparatus includes a sampling unit for sampling a current while a motor is regenerating; and a determination unit for determining a failure of the motor using data obtained from the sampling result and the learning model.

According to the above-described embodiment, the failure diagnosis can be easily performed using the detected value of the motor and the learning model thereof.

Drawings

Fig. 1 is a schematic diagram showing one example of the configuration of a motor drive system according to an embodiment.

Fig. 2 is a block diagram showing an exemplary configuration of a failure determination device according to an outline of an embodiment.

Fig. 3 is a block diagram showing one example of the configuration of the MCU.

Fig. 4 is a diagram for explaining frequency control and current control by the control unit.

Fig. 5 is a graph showing an example of the relationship between the motor rotation speed and time during regeneration.

Fig. 6 is one example of a flowchart showing an operation flow for the fault diagnosis.

Fig. 7A is a schematic perspective view of a mechanism having two gears that are rotated by rotation of a motor.

Fig. 7B is a side view of the gear shown in fig. 7A.

Fig. 8 is one example of a flowchart showing a diagnostic operational flow including a plurality of diagnostic methods.

Fig. 9 is a diagram showing one example of the analysis result by the FFT when the motor is driving.

Fig. 10 is one example of a flowchart showing an operation flow for the fault diagnosis.

Fig. 11 is a schematic diagram showing one example of the configuration of the motor drive system.

Fig. 12 is a schematic diagram showing an exemplary configuration of a motor drive system provided as a control system device other than the control inverter, in which the diagnostic device executes a process for diagnosing a fault.

Detailed Description

The following description and the drawings are appropriately omitted and simplified for the purpose of facilitating the description. Further, elements described as functional blocks in the drawings for performing various processes may be configured as a CPU (central processing unit), a memory, and other circuits in terms of hardware, and implemented by a program loaded into the memory in terms of software. Accordingly, those skilled in the art understand that these functional blocks can be implemented in various forms by hardware alone, software alone, or a combination thereof, and the present invention is not limited to any one of them. In the drawings, the same elements are denoted by the same reference numerals, and repeated description thereof is omitted as necessary.

Also, the above-described program may be stored using various types of non-transitory computer-readable media and provided to a computer. Non-transitory computer readable media include various types of tangible storage media. Examples of the non-transitory computer-readable medium include a magnetic recording medium (e.g., a floppy disk, a magnetic tape, a hard disk drive), a magneto-optical recording medium (e.g., a magneto-optical disk), a CD-ROM (read only memory, CD-R, CD-R/W), a solid-state memory (e.g., a mask ROM, a PROM (programmable ROM), an EPROM (erasable PROM, flash ROM, RAM (random access memory)). the program may also be supplied to the computer by various types of transitory computer-readable media, examples of which include electric signals, optical signals, and electromagnetic waves.

Fig. 1 is a schematic diagram showing one example of the configuration of a motor drive system according to an embodiment. The motor drive system 1 includes a three-phase power supply 20, a motor drive apparatus 10, and a motor 30. The three-phase power supply 20 supplies the motor drive apparatus 10 with three-phase alternating current transmitted from a power station or the like. The motor 30 is a three-phase motor, and is controlled by the motor drive apparatus 10. The motor drive apparatus 10 is an apparatus for controlling the motor 30. The motor drive apparatus 10 includes a power supply switch 101, an alternating current filter 102, a rectifier 103, a resistor 104, a resistor switch 105, an electrolytic capacitor 106, an inverter 107, and an MCU (micro control unit) 110.

The power supply switch 101 is a switch for turning on and off three-phase currents from the three-phase power supply 20, and is operated by a switch switching signal from the MCU 110. The ac filter 102 is provided to prevent noise from the inverter 107 from propagating outside the motor drive device 10, and the ac filter 102 includes an ac reactor. An ac filter 102 is provided between the power supply switch 101 and the rectifier 103. Rectifier 103 is a converter for converting alternating current from three-phase power supply 20 to direct current. The resistor 104 is a circuit element that consumes power supplied from the motor 30 when the motor 30 is in a regenerative state. The resistor switch 105 is a switch for turning on/off the connection of the resistor 104 to the direct current circuit, and operates in response to a switch switching signal from the MCU 110. The MCU110 controls the on-time and off-time of the resistive switch 105, thereby controlling the power consumed by the resistor 104 when the motor 30 is regenerating.

The electrolytic capacitor 106 has a plurality of smoothing capacitors, which are connected to an inverter 107. More specifically, the electrolytic capacitor 106 is disposed between the rectifier 103 and the inverter 107. When the motor 30 is supplied with power, the inverter 107 supplies three-phase AC current (alternating current) to the motor 30 according to a PWM (pulse width modulation) signal from the MCU 110. During the regeneration of the motor 30, the inverter 107 converts the three-phase alternating current from the motor 30 into direct current. The MCU110 includes a processor such as a CPU, a memory, a peripheral circuit, and the like, and controls the entire motor drive apparatus 10.

Here, in the motor drive system 1 described above, when the determination of the malfunction of the motor 30 or the component related to the motor 30 is performed by using machine learning, it is considered that the learning data in which the motor is in the force action operating state is used. In this case, the variation of the various values affects the detected values of the motor, such as the current value and the voltage value. The various values mentioned herein include, for example, the voltage values of the three-phase power supply 20, the voltage differences between the phases of the three-phase power supply 20, the internal impedance of the ac filter 102, and the inductance value of the ac filter 102. Therefore, even if it becomes difficult to design a machine learning model using the detected values or even if design of the machine learning model is possible, a considerable amount of learning data must be collected in consideration of the above-described variations.

On the other hand, when the motor 30 is regenerated, the power supply from the three-phase power supply 20 may be cut off, and the ac filter 102 operation is not necessary. That is, regarding the detection value at the time of regeneration of the motor 30, the above-described variation is not necessarily taken into consideration. Therefore, the model can be constructed with less learning data than machine learning using the detection values at the time of power running of the motor 30.

Therefore, the failure determination device according to the outline of the present embodiment has the following devices. Fig. 2 is a block diagram showing an exemplary configuration of a failure determination device according to an outline of an embodiment. As shown in fig. 2, the fault determination device 50 includes a sampling unit 51 and a determination unit 52. The fault determination device 50 is implemented as, for example, the MCU110 described above, but may be implemented as another device.

The sampling unit 51 samples the current at the time of regeneration of the motor 30. The determination unit 52 determines the malfunction of the motor 30 using data obtained from the sampling result by the sampling unit 51 and a learning model. The learning model is a model that is learned in advance by using data obtained from a sampling result of a current at the time of regeneration of the motor 30 in a case where the soundness state of the motor 30 is a predetermined state. It should be noted that the health state is a predetermined state, for example, a state in which the motor 30 is normal, but a state in which the motor 30 has failed may be used.

According to the failure determination device 50, since the current at the time of regeneration of the motor 30 is sampled as the detected value for the determination using the learning model, the above-described variations do not necessarily have to be considered. Therefore, the fault determining apparatus 50 can diagnose a fault using a model that can be easily constructed, as compared to a model constructed by machine learning using detected values while the motor 30 is power running. In other words, according to the failure determination device 50, it is possible to easily diagnose a failure using the detected value of the motor 30 and its learning model.

Details of the embodiment will be described below.

< example 1>

Fig. 3 is a block diagram showing one example of the configuration of the MCU. As shown in fig. 3, the MCU110 includes a control unit 111, a detected value acquisition unit 112, a sampling unit 113, a sampling interval determination unit 114, a frequency analysis unit 115, and a determination unit 116.

The control unit 111 controls the operation of the motor drive apparatus 10. The control unit 111 is realized by, for example, the MCU110 processor reading software (computer program) from a memory and executing the software, but the control unit 111 may also be realized as a hardware circuit. The control unit 111 controls the operation of the power supply switch 101 and the resistor switch 105, for example, by a switch switching signal. Further, the control unit 111 performs control to switch the motor 30 between the power running state and the regeneration state. Further, the control unit 111 outputs a PWM signal to the inverter 107, thereby controlling the rotation of the motor 30.

In particular, in the present embodiment, the control unit 111 executes the following two types of control so as to make the condition at the time of diagnosing the failure constant.

The first control is control for changing the rotation speed of the electric motor 30 to a predetermined rotation speed when the electric motor 30 is switched from the power running state to the regenerative state. In this control, the control unit 111 performs frequency control by PWM so as to set the rotation speed of the motor 30 at the start of the regenerative operation, that is, the rotation speed of the motor 30 at the end of the power running operation, to a predetermined rotation speed. Hereinafter, such control is sometimes referred to as frequency control.

The second control is control in which the electric power consumed when the motor 30 is regenerated becomes a predetermined value. In this control, the control unit 111 controls the opening and closing of the resistor switch 105 so that the electric power consumed by the resistor 104 when the motor 30 is in the regenerative operation becomes a predetermined value. That is, the control unit 111 controls the current flowing through the resistor 104 at the time of regeneration. Hereinafter, this control is sometimes referred to as current control.

Fig. 4 is a diagram for explaining frequency control and current control by the control unit. In the graph shown in fig. 4, the horizontal axis represents time, and the vertical axis represents the rotation speed of the motor 30. As shown in fig. 4, when the motor 30 is in the power running state, the frequency control is performed, and the rotation speed of the motor 30 is set to a predetermined value. Then, when the rotational speed of the motor 30 reaches a predetermined value, the control unit 111 switches the operation state of the motor 30 to the regenerative operation. That is, the control unit 111 sets the rotation speed at the start of the regeneration operation to a predetermined value by frequency control. During the regeneration operation, the control unit 111 performs current control and controls the consumed power to a predetermined value. Then, the failure diagnosis is performed during the regeneration operation. Therefore, the above-described control by the control unit 111 enables the conditions for the rotation speed and the power consumption to be made constant when the failure diagnosis is performed. In other words, the diagnostic conditions are always the same. Therefore, it is possible to perform failure determination with high accuracy using a learning model that uses learning of data only at the time of regeneration. In the present embodiment, the control unit 111 performs both the frequency control and the current control, but may perform only one of them. Preferably, the control unit 111 performs these controls, but these controls do not necessarily have to be performed.

The detected value acquisition unit 112 is an interface circuit for acquiring a detected value (measured value) of the electrical value of the motor 30 during the regeneration operation. Specifically, the detected value acquisition unit 112 acquires analog data of the current value output from the motor 30 during the regeneration operation. The detected value acquisition unit 112 may acquire analog data of the voltage value of the current output from the motor 30 during the regenerative operation, or may acquire analog data of the voltage value of the electrolytic capacitor 106. Generally, in order to perform PWM control, the inverter 107 is provided with an element for detecting a current, such as a shunt resistor. Such an element may also be used in obtaining a current value determined for a fault. That is, the current at the time of regeneration of the motor 30 may be detected using a shunt resistor provided for controlling the inverter 107. In this way, the fault diagnosis can be realized without adding a new element for detecting the current.

The sampling unit 113 is an analog-to-digital converter that samples analog data of the detection value acquired by the detection value acquisition unit 112 at sampling intervals determined by the sampling interval determination unit 114, and outputs digital data. The sampling interval determination unit 114 determines the sampling interval based on the frequency of the current acquired by the detection value acquisition unit 112, that is, the frequency of the current of the motor 30 at the time of regeneration. The sampling interval determination unit 114 is realized by, for example, an MCU110 processor that reads and executes software (computer program) from a memory, but may be realized as a hardware circuit.

The frequency analysis unit 115 performs frequency analysis on the sampling result by the sampling unit 113. That is, the frequency analysis unit 115 performs frequency analysis on the digital data output from the sampling unit 113. In the present embodiment, the frequency analysis unit 115 performs FFT analysis. The frequency analysis unit 115 is realized by, for example, an MCU110 processor that reads and executes software (computer program) from a memory, but may be realized as a hardware circuit.

The determination unit 116 determines the malfunction of the motor 30 using data obtained from the sampling result by the sampling unit 113 (i.e., the analysis result by the frequency analysis unit 115) and a learning model learned in advance. The determination unit 116 is realized, for example, by an MCU110 processor that reads software (computer program) from a memory and executes the software (computer program), but may be realized as a hardware circuit. Here, the learning model is previously learned using data obtained from the sampling result of the current at the time of regeneration of the motor 30 (i.e., the analysis result by the frequency analysis unit 115) when the soundness state of the motor 30 is a predetermined state. For example, the model is a neural network, but other machine learning models may be used.

The learning model may be a model that is previously learned using the following data. The data used for learning may be: data obtained from the result of sampling of the current at the time of regeneration of the motor 30 when the health state of the motor 30 and the components connected to the motor 30 is a predetermined state. Specifically, the data obtained from the sampling result is an analysis result by the frequency analysis unit 115. In this case, the determination unit 116 determines the malfunction of the motor 30 and the components connected to the motor 30. The components connected to the motor 30 are connected to, for example, a rotating shaft of the motor 30 directly or indirectly, and specifically include, but are not limited to, bearings, gears, fan belts, and the like. According to this configuration, components related to the motor can be included as objects of the failure determination.

Here, a method of determining the sampling interval in the present embodiment will be described. During regeneration of the electric motor 30, the energy stored is determined by the inertial force and the rotational speed of the electric motor 30. Therefore, the rotation speed of the motor 30 is different immediately after the regeneration is started and after the predetermined period of time has elapsed. In other words, the rotational speed of the motor 30 gradually decreases during regeneration. Here, the rotation speed corresponds to a current frequency of the motor 30. Therefore, in the case where sampling data of a predetermined number (M) or more of currents is acquired in n cycles of the current waveform of the motor 30, an appropriate sampling interval depends on the rotation speed. Therefore, in the present embodiment, the sampling interval is determined as follows.

Fig. 5 is a diagram showing one example of the relationship between the motor rotation speed and time during regeneration. Although fig. 5 shows a graph in which the rotation speed linearly decreases, the rotation speed does not always linearly decrease in practice. For example, in the present embodiment, the change in rate is predicted as follows. The sampling interval determination unit 114 measures the rotation speed of the motor 30 at the first time point and the rotation speed of the motor 30 at the second time point while the regeneration operation continues. Here, the second time point is a speed at a time point at which a predetermined time Δ t has elapsed from the first time point. The predetermined time Δ t may be a masking time, which will be described later, or may be a time longer or shorter than the masking time. The difference between the rotational speed at the first point in time and the rotational speed at the second point in time is defined as Δ N. Therefore, it is possible to calculate a slope α (═ Δ N/Δ t) which is an estimated value of the rate of change in the rotational speed during the regenerative operation. The sampling interval determination unit 114 calculates the rate of change α of the rotation speed in advance before performing the failure diagnosis. That is, in the regeneration operation performed at any time before the regeneration operation in which the fault diagnosis is performed, the sampling interval determination unit 114 determines the sampling interval in the regeneration operation in which the fault diagnosis is performed.

The relationship between the motor rotation speed and the motor current is expressed by the following equation (1):

N＝120/P×f_e(1)

in equation (1), N is the motor rotation speed, f_eTo the synchronous frequency (i.e., current frequency), P is the number of poles of the motor 30. Thus, the sampling interval determination unit 114 may be based on the frequency f_eTo calculate the rotation rate, frequency f_eIs obtained by measuring the period of the current obtained by the detected value obtaining unit 112.

The sampling interval determination unit 114 determines the sampling interval by using the previously calculated rotational speed change rate α at the start of the regeneration operation for performing the failure diagnosis. In the present embodiment, the determination unit 116 diagnoses a fault by using the sampled data after a predetermined masking time has elapsed since the start of the regeneration operation. Therefore, the sampling interval determination unit 114 determines the sampling interval corresponding to the rotation speed after a predetermined masking time has elapsed from the start of the reproduction operation. The reason why the masking time is provided is that there is an influence of transient characteristics immediately after the regenerating operation. By not using the sampling data in the predetermined mask time for the failure diagnosis from the start of the regeneration operation to the elapse, the influence of the transient characteristics immediately after the regeneration operation can be eliminated.

Suppose that the rotational speed at the time of starting the regeneration operation is N₁And the masking time is T_estThen the estimated value N of the rotation speed after the masking time has elapsed_estExpressed by the following equation (2):

N_est＝N₁-α×T_est(2)

as described above, since there is the relationship of equation (1) between the motor rotation speed and the motor current, equation (2) can be expressed as the following equation (3):

N_est＝120/P×f₁-α×T_est(3)

wherein f is₁Is the current frequency (synchronized frequency) at which the regeneration operation in which the fault diagnosis is performed starts.

Estimation f of the current frequency after the elapse of the masking time_estCan be calculated by the following equation (4) from the above equation (1):

f_est＝N_est/120/P(4)

that is, the rotation speed N after the masking time has elapsed is estimated by the relational expression based on equation (3)_estFrequency f of the current after the masking time has elapsed_estIt can be estimated based on the relational expression of equation (4).

If the frequency f_estCan be estimated, the sampling interval T_sampCan be determined by the following equation (5). In equation (5), n is the number of current cycles that need to be sampled for fault diagnosis. M is the number of sample data required for fault diagnosis. That is, M is the number of samples required to achieve a predetermined resolution in the FFT analysis.

T_samp＝n/f_est/M (5)

The sampling interval determination unit 114 calculates the sampling interval T_sampAnd is set in the sampling unit 113. The sampling unit 113 is represented by T_sampThe time interval acquires M or more sample data.

Fig. 6 is one example of a flowchart showing the operation flow of the fault diagnosis. Referring to fig. 6, the operation flow of the fault diagnosis will be described below.

In step S100, the control unit 111 sets a target rotation speed for performing frequency control and power consumed by the resistor 104 when performing current control.

Next, in step S101, the control unit 111 switches the motor 30 to the regenerative operation so as to calculate the rate of change α of the rotational speed during the regenerative operation. Prior to switching from the power running operation to the regenerating operation in step S101, the control unit 111 may perform frequency control such that the regenerating operation is started at the rotational speed set in step S100. In step S101, the control unit 111 may perform current control such that the power set in step S100 is consumed.

Next, in step S102, the sampling interval determination unit 114 measures the rotation speed of the motor 30 at the first point in time and the rotation speed of the motor 30 at the second point in time while the regeneration operation continues. Then, the sampling interval determination unit 114 calculates the rate of change α of the rotation speed during the regeneration operation.

Next, in step S103, the control unit 111 switches the motor 30 to the power running operation. Then, the control unit 111 performs frequency control so that the rotation speed becomes the rotation speed set in step S100. Until the rotation speed of the motor 30 reaches the rotation speed set in step S100, the control unit 111 continues the power running operation (no in step S104). When the rotation speed of the motor 30 reaches the rotation speed set in step S100 (yes in step S104), the process proceeds to step S105.

In step S105, the control unit 111 switches the motor 30 to the regenerative operation to diagnose the failure. Then, the control unit 111 performs current control so that the power set in step S100 is consumed. Thereafter, the control unit 111 continues the regenerative operation of the motor 30 along with the current control.

In step S106, the sampling interval determination unit 114 measures the synchronization frequency f at the start of the regeneration operation₁And an estimated value N of the rotation speed at a point in time when the masking time has elapsed since the start of the regenerating operation is calculated based on equation (3)_estAt this time, the value calculated in step S102 is used as the change rate α, and the predetermined time is used as the masking time T_est。

In step S107, the sampling interval determination unit 114 uses the estimated value N of the rotation speed calculated in step S106_estAnd equation (4) calculating an estimated value f of the frequency of the current after the masking period has elapsed_est。

In step S108, the sampling interval determination unit 114 uses the estimated frequency f calculated in step S107_estAnd equation (5), calculating the sampling interval T_sampAnd determined for use by the sampling unit 113The sampling interval of (a). In this case, predetermined values are used as the value n of the number of cycles and the value M of the number of sample data. As described above, the sampling interval is determined. In this way, the sampling interval determination unit 114 estimates the frequency of the current of the motor 30 after a predetermined time has elapsed from the start of regeneration of the motor 30, and determines the sampling interval based on the estimated frequency. Therefore, it is possible to set an appropriate sampling interval while eliminating the influence of the transient characteristics immediately after the start of regeneration. That is, while suppressing deterioration of the failure determination accuracy, resource consumption due to oversampling can be suppressed. Since the rate of change in the number of rotations at the time of regeneration differs depending on the difference in the motor inertial force, it is necessary to set a sampling interval for each system set.

Here, the following description will supplement the value of the number n of cycles mentioned above. When performing the fault diagnosis of the motor-related component, which rotates in accordance with the rotation of the rotating shaft of the motor 30, it is necessary to perform sampling of the motor current waveform corresponding to at least one rotation of the component. This will be explained with reference to the drawings.

Fig. 7A is a schematic perspective view of a mechanism having two gears that are rotated by rotation of a motor.

Further, fig. 7B is a side view of the gear shown in fig. 7A. In the mechanism shown in fig. 7A, a gear 32 is rotated by the rotation of the rotating shaft 31 of the motor 30, and a gear 33 different in the number of teeth from the gear 32 is rotated in accordance with the rotation of the gear 32. That is, the gear 33 is a motor-related component, which is indirectly connected to the motor 30. Here, when diagnosing the gear 33, it is impossible to detect the tooth breakage 34 or the like of the gear 33 unless sampling of the motor current waveform is performed in a period covering one rotation of the gear 33. Therefore, with respect to the frequency number n, it is necessary to preset a period in which at least one rotation of the gear 33 can be covered. As described above, in order to diagnose a failure of each component directly or indirectly connected to the motor 30, it is necessary to sample the motor current waveform in a period of at least one rotation of the covering component.

The description will return to the flowchart. In step S109, the sampling interval determination unit 114 sets the sampling unit 113 to perform sampling at the sampling interval determined in step S108.

Next, in step S110, the sampling unit 113 samples the regenerative current of the motor 30. Specifically, the sampling unit 113 adopts the regenerative current at the sampling interval determined by step S108 after the masking time has elapsed from the start of the regenerative operation.

Next, in step S111, the frequency analysis unit 115 performs FFT analysis on the sampling result obtained by the sampling unit 113. Specifically, the frequency analysis unit 115 performs FFT analysis on the sample data after the masking time has elapsed from the start of the reproduction operation.

Next, in step S112, the determination unit 116 inputs the analysis result obtained in step S111 to the learning model, and performs failure determination. If the output result of the learning model indicates that the motor 30 or its related components are normal ("normal" in step S112), the diagnostic process is terminated. Otherwise ("deterioration" in step S112), the determination unit 116 outputs an alarm (step S113).

In the present embodiment, the failure diagnosis is performed using the detected value during the regenerative operation. Therefore, the following effects can also be obtained. That is, when the influence of switching noise or the like occurs during the power running operation, such influence can be eliminated during the regeneration operation. That is, when the motor regenerates, the switching of the power elements of the inverter 107 is stopped, and switching noise unique to the operation of the inverter 107 is not generated. Therefore, the signal-to-noise (S/N) ratio in the values detected at the time of regeneration can be improved as compared to that at the time of power operation, which contributes to an improvement in determination accuracy.

During the power running operation, the voltage of the electrolytic capacitor 106 contains frequency components due to external factors. External factors include, for example, an imbalance of the power supply voltage in the respective phase and an impedance change of the ac filter 102. Therefore, the frequency component of the motor current may be affected. That is, when the frequency analysis of the motor current is performed, it is necessary to consider the influence of the voltage of the electrolytic capacitor 106. Therefore, it is difficult to separate the degradation of the electrolytic capacitor 106 and the malfunction of the motor 30 for analysis. In contrast, in the diagnosis at the time of the regenerative operation, the influence of the electrolytic capacitor voltage can be eliminated.

Incidentally, if the motor is a normal motor, the voltage of each phase of the motor is output in equilibrium at the time of regeneration. Therefore, it is also possible to detect an abnormality of the motor 30 by checking the voltage unbalance degree of the motor 30 at the time of regeneration, instead of using the frequency analysis result of the current and the learning model for diagnosis. At the time of regeneration, energy is stored in the electrolytic capacitor 106, and the electrolytic capacitor 106 can be diagnosed by measuring the time constant at that time. A diagnostic flow combining these diagnostics is shown in fig. 8. Fig. 8 is one example of a flowchart showing a diagnostic operational flow including a plurality of diagnostic methods. The flowchart shown in fig. 8 differs from the flowchart shown in fig. 6 in that: step S153 is added from step S150 between step S110 and step S111. Differences from the flowchart shown in fig. 6 will be described below.

In the flowchart shown in fig. 8, in step S110, the sampling unit 113 samples the voltage of the electrolytic capacitor 106 in addition to the current from the motor 30. Note that a predetermined condition is used as a sampling condition of the voltage of the electrolytic capacitor 106.

In step S150, the determination unit 116 determines a failure of the motor 30 based on whether the voltages of the three-phase alternating currents are balanced at the time of regeneration of the motor 30. Therefore, the determination unit 116 checks the degree of unbalance of the voltage of the motor 30 at the time of regeneration. If the motor is normal, the output voltages of the motor phases at the time of regeneration should be in equilibrium. Therefore, it is possible to detect an abnormality of the motor 30 by detecting the unbalance of the output voltages of the respective phases. Specifically, the determination unit 116 confirms the equilibrium state of the output voltages of the respective phases based on the phase currents (regenerated currents). When the output voltages of the phases are in equilibrium, the total value of the phase currents is zero. Therefore, the determination unit 116 calculates the total value of the phase currents obtained as the sampling data, and determines whether the motor 30 is normal based on the calculated value. When the determination unit 116 determines that the motor 30 is normal ("normal" in step S150), the process proceeds to step S152. Otherwise ("abnormal" in step S150), the determination unit 116 outputs an alarm (step S151). After step S151, the process advances to step S152.

In step S152, the determination unit 116 determines the degradation of the electrolytic capacitor 106 based on the voltage of the electrolytic capacitor 106 during the regeneration of the motor 30. Thus, the electrolytic capacitor 106 can also be diagnosed. The internal resistance of the electrolytic capacitor 106 increases with degradation. Therefore, the degree of degradation of the electrolytic capacitor 106 can be determined by measuring the time constant when the motor voltage at the time of regeneration is charged in the electrolytic capacitor 106. Therefore, the determination unit 116 measures a time constant based on the voltage of the electrolytic capacitor 106 obtained as the sampling data, for example, and determines degradation of the electrolytic capacitor 106 based on whether the time constant exceeds a predetermined threshold. When the determination unit 116 determines that the electrolytic capacitor 106 is normal ("normal" in step S152), the process proceeds to step S111. Otherwise ("abnormal" in step S150), the determination unit 116 outputs an alarm (step S153). After step S153, the process advances to step S111. According to the diagnosis according to the flowchart shown in fig. 8, after the motor 30 and the electrolytic capacitor 106 are diagnosed, the diagnosis may be performed by the learning model.

< example 2>

Next, a second embodiment will be described. Hereinafter, those descriptions overlapping with the configuration and operation of the first embodiment will be omitted as appropriate. When all data obtained by the frequency analysis is input to a machine learning model (such as a neural network), a large amount of data causes a reduction in calculation speed and an increase in memory consumption.

Here, the frequency component f occurring at the time of motor failure_faultIs expressed as the following equation (6) (see non-patent document 1).

[ equation 1]

In equation (6), f_eIs the synchronization frequency, i.e. the fundamental frequency. Further, p is the number of poles. k is any integer of 1 or greater. I.e., k is 1, 2, 3 …. As shown in equation (6), the frequency component occurring at the time of the motor failure is a sideband (sideband) wave. That is, the result of the frequency analysis of the sideband waves is data contributing to the failure diagnosis. Therefore, in the present embodiment, data contributing to the diagnosis of a failure is extracted from data obtained by frequency analysis.

For this reason, in the present embodiment, the frequency analysis unit 115 analyzes the frequency components of the predetermined frequency band contributing to the determination of the failure, and the determination unit 116 inputs the analysis result into the learning model and performs the determination process. Therefore, before performing the FFT processing, the frequency analysis unit 115 performs preprocessing (filtering processing) using a notch (notched) filter or the like, and removes a signal component that does not contribute to the failure diagnosis.

Fig. 9 is a diagram showing one example of the analysis result by the FFT when the motor is driven. In the graph of fig. 9, the horizontal axis represents frequency, and the vertical axis represents amplitude (spectral intensity). As shown in fig. 9, the analysis result by the FFT includes not only the amplitude value of the data group 40 contributing to the failure diagnosis, but also the amplitude value of the fundamental wave 41, the amplitude value of the high-frequency wave 42 generated by the influence of the switching, and the like. In the present embodiment, on the other hand, since the FFT analysis is performed on the values detected during the reproduction operation, the amplitude of the high frequencies 42 can be excluded. The amplitude of the fundamental wave 41 can be excluded by performing the filtering process. In the present embodiment, the amplitude of the data group 40 that contributes only to the failure diagnosis is used to perform the diagnosis by machine learning. As shown in fig. 9, the amplitude value of the data group 40 contributing to the failure diagnosis is smaller than the amplitude value of the fundamental wave 41. In the case of the motor failure diagnosis, a slight difference between the amplitude in the normal state and the amplitude in the abnormal state needs to be detected, and thus the resolution needs to be sufficiently ensured. According to the present embodiment, the amplitude of the fundamental wave 41 can be removed so that sufficient resolution can be ensured.

Fig. 10 is one example of a flowchart showing an operation flow for the fault diagnosis. The flowchart shown in fig. 10 differs from the flowchart shown in fig. 6 in that the filtering process (step S200) is added before step S111. In step S200, the above-described filtering process is performed. In the flowchart shown in fig. 8, step S200 may be added before step S111.

The second embodiment has been described above. According to the present embodiment, since the filtering process is performed, the diagnosis can be performed by machine learning using only data contributing to the failure diagnosis. Therefore, data input to the model can be reduced, and a decrease in calculation speed and an increase in memory consumption can be suppressed. Moreover, the resolution required for diagnosis can be sufficiently ensured.

< example 3>

Fig. 11 is a schematic diagram showing one example of the configuration of the motor drive system. As shown in fig. 11, the motor drive system 2 is different from the above-described embodiment in that a motor and a plurality of inverters for driving the motor are provided. Specifically, the motor drive system 2 differs from the motor drive system 1 shown in fig. 1 in that a pair of the motor 30 and the inverter 107 is added. In the present embodiment, the MCU110 controls the two inverters 107.

When the fault diagnosis is performed during the motor regeneration operation, the power running operation of the motor during the fault diagnosis is impossible. Therefore, during this period, the system operated by driving the motor will be stopped. In the present embodiment, the motor drive system 2 includes a plurality of motors and a plurality of inverters corresponding to the motors. Accordingly, the control unit 111 of the MCU110 can perform power running operations of other motors while regenerating and diagnosing a fault of any motor. In other words, according to the motor drive system 2 of the present embodiment, it is possible to suppress complete stop of the system operated by driving the motor. Further, the control unit 111 of the MCU110 may control the other motors to be supplied with power by using regenerated energy from the motors during a regeneration operation. Since the power supply switch can be turned off when such control is performed, it is possible to diagnose a failure of the other motor during the regenerative operation without being affected by external factors when the motor is supplied with power. External factors are, for example, an imbalance of the power supply voltage in the respective phase, or a change in the impedance of the ac filter 102. Incidentally, not only the current control by the resistor 104, but also the current control by consuming power by the power running operation of the motor may be performed at the time of regeneration.

As a system that operates by driving a motor, any system may be targeted. For example, the system operated by the drive motor may be a hydraulic system, an elevator system, or an electric vehicle system.

In the above-described embodiment, the control device (MCU) for controlling the inverter performs the process for the fault diagnosis, but the device for performing the process for the fault diagnosis and the device for controlling the inverter may be separate devices. Fig. 12 is a schematic diagram showing an exemplary configuration of the motor drive system 3, the motor drive system 3 being provided as a device separate from the control device 120, wherein the diagnosis device (failure determination device) 130 is used to perform a process for failure diagnosis, and the control device 120 controls the inverter 107.

Fig. 12 is a schematic diagram showing an exemplary configuration of a motor drive system provided as a device other than a control system device that controls an inverter, in which a diagnostic device executes a process for diagnosing a fault.

As shown in fig. 12, the motor drive system 3 includes a motor 30, an external device 35, an inverter 107 for driving the motor 30, a control device 120, and a diagnostic device 130. The external device 35 is a device operated by driving the motor 30. That is, the external device 35 is a load of the motor 30. The control device 120 is a device for controlling the inverter 107. The device 130 is a device for performing failure diagnosis of the motor 30. Here, the control device 120 has an inverter control function among the functions of the MCU110 described above, and the diagnostic device 130 has a fault diagnosis function among the functions of the MCU110 described above. Specifically, for example, the control device 120 is a device including the above-described control unit 111. In addition, the diagnostic apparatus 130 is an apparatus including the above-described detected value acquisition unit 112, sampling interval determination unit 114, sampling unit 113, frequency analysis unit 115, and determination unit 116, for example.

If the apparatus that performs the fault diagnosis process and the apparatus that controls the inverter are separated, the diagnosis apparatus 130 cannot directly control the inverter 107. Therefore, the diagnostic device 130 requires a function of determining the operation state of the motor 30, that is, a function of determining whether the motor 30 is in the power running state or the regenerative state. To this end, for example, the diagnostic apparatus 130 further includes an operation state detection unit 131 for detecting the operation state of the motor 30 by acquiring a voltage value and a current value of the motor 30.

The operation state detection unit 131 detects a regeneration state and a power running state of the motor 30 based on the voltage value and the current value of the motor 30. The operation state detection unit 131 calculates a product (i.e., a power value) of a voltage value and a current value for each phase of the three-phase alternating current between the motor 30 and the inverter 107. Then, when the sum of the products of the voltage value and the current value is positive, the operation state detection unit 131 determines that the motor 30 is in the power running state, and if the sum is negative, it determines that it is in the regeneration state.

If it is determined that the motor 30 is in the regeneration state, the apparatus 130 performs the above-described diagnostic process. According to this configuration, even if the apparatus for performing the process for the fault diagnosis and the apparatus for controlling the inverter are different, the above-described diagnosis can be performed.

Although the invention made by the inventor has been specifically described based on the embodiments, the invention is not limited to the embodiments that have been described, and various modifications can be made without departing from the gist of the invention.