A method and system for monitoring operating faults of a permanent magnet synchronous motor for a vehicle

Abstract

The present application relates to the technical field of permanent magnet synchronous motor fault detection, and specifically to a method and system for monitoring operational faults of automotive permanent magnet synchronous motors. The method comprises: installing sensors on the permanent magnet synchronous motor and collecting temperature, current, and voltage during the operation of the permanent magnet synchronous motor; calculating the degree of frequency variation of the current based on the current operating state of the permanent magnet synchronous motor; obtaining the current extreme value regression degree and the permanent magnet synchronous motor's current persistent abnormality based on the variation characteristics between extreme value points during the current operation; obtaining the permanent magnet synchronous motor's voltage persistent abnormality and temperature fault recognition degree; and identifying the permanent magnet synchronous motor's operating state through a neural network. The present application aims to effectively avoid misjudgment of transient abnormalities in the permanent magnet synchronous motor due to environmental interference.

Description

Technical Field

[0001] The present application relates to the technical field of permanent magnet synchronous motor fault detection, and in particular to a method and system for monitoring operating faults of a permanent magnet synchronous motor for a vehicle. Background Art

[0002] An automotive permanent magnet synchronous motor (PMSM) is a synchronous motor with permanent magnets embedded in the rotor. It generates torque by interacting with the magnetic field generated by the permanent magnets and the induced magnetic field in the stator windings, thereby driving the vehicle. Faults in a PMSM, such as a faulty rotor position sensor or a winding short circuit, can cause abnormal motor output torque. At high speeds, this abnormal torque can cause loss of control and lead to serious traffic accidents. Real-time fault detection can promptly identify these potentially dangerous situations and enable appropriate measures, such as shutting off the motor power supply and activating the braking system, to ensure the safety of the vehicle and its passengers.

[0003] To identify operational faults in permanent magnet synchronous motors, a neural network is trained on operational status data. The neural network then identifies the type of operational fault in the motor. However, vehicles experience different driving environments, such as hills, forests, and speed bumps. These bumps can cause the operational status of the permanent magnet synchronous motor to change, leading to brief anomalies in the collected data. However, if the automotive permanent magnet synchronous motor does not exhibit any issues, direct use of real-time collected data would result in the neural network identifying this as a fault, resulting in inaccurate identification of operational faults in the motor. Summary of the Invention

[0004] In view of the above, it is necessary to provide an operating fault monitoring method and monitoring system for a vehicle permanent magnet synchronous motor to solve the above problems.

[0005] In a first aspect, the present application provides a method for monitoring operating faults of a vehicle permanent magnet synchronous motor, the method comprising:

[0006] During a preset time period, the temperature of the permanent magnet synchronous motor during operation is collected to form an operating temperature sequence; at the same time, the current and voltage of each phase are collected to form an operating current sequence and an operating voltage sequence of each phase respectively;

[0007] Decompose the operating current sequence of each phase to obtain a preset number of layers of decomposed current sequences. Compare the similarity of the frequencies of the current decomposition sequences of each layer after the current decomposition of any two phases. Combined with the distribution characteristics of the amplitude values, obtain the relative frequency difference of the current decomposition sequences of each layer after the current decomposition of any two phases. Analyze the numerical characteristics of the relative frequency difference between each phase and the other phase currents in all layers to obtain the frequency variation degree of the operating current sequence of each phase.

[0008] The extreme points in each phase's operating current sequence are extracted and sorted. Based on the variation characteristics between the extreme points, the extreme points are classified. The standard characteristic difference of each phase's current is determined based on the element mean of all classes. The current extreme value regression degree of each phase is obtained based on the distribution variation of the extreme values ​​in each phase's operating current sequence and the standard characteristic difference.

[0009] The permanent magnet synchronous motor's current persistence anomaly degree is obtained based on the frequency variation degree of all phase currents and the current extreme value regression degree. Accordingly, the operating voltage sequence of each phase is analyzed to obtain the permanent magnet synchronous motor's voltage persistence anomaly degree. The prediction results of the operating temperature sequence in time series are obtained and combined with the current persistence anomaly degree and voltage persistence anomaly degree to form an operating fault identification vector for the permanent magnet synchronous motor.

[0010] Based on the operation fault identification vector of the permanent magnet synchronous motor, the fault monitoring results of the permanent magnet synchronous motor are obtained by using the trained neural network.

[0011] The specific process of obtaining the relative frequency difference of each layer of current decomposition sequence after the decomposition of any two-phase current is as follows:

[0012] The ratio of the number of intersection elements to the number of union elements of the frequency of each layer of the current decomposition sequence after the current decomposition of any two phases is calculated; the difference between 1 and the ratio is calculated, and then multiplied by the mean of the amplitude values ​​of all non-intersection frequencies to obtain the relative frequency difference of each layer of the current decomposition sequence after the current decomposition of any two phases.

[0013] The frequency variation degree of the operating current sequence of each phase is obtained as follows:

[0014] The minimum relative frequency difference between each phase current and all other phase currents in each layer of the current decomposition sequence is obtained, and the average of the minimum relative frequency difference values ​​corresponding to each phase current in all layers is taken as the frequency variation degree of each phase operating current sequence.

[0015] The step of extracting and sorting the extreme points in the operating current sequence of each phase is specifically as follows: sorting the extreme points from small to large based on their values.

[0016] The standard characteristic difference of each phase current is specifically the minimum value of the element means of all classes.

[0017] The current extreme value regression degree of each phase is obtained as follows:

[0018] For each phase's operating current sequence, calculate the difference between two adjacent maxima, which is recorded as the first difference; record the difference between the first difference and the standard characteristic difference as the second difference; and take the average of the second differences corresponding to all two adjacent maxima in each phase's operating current sequence as the first characteristic value of each phase;

[0019] Accordingly, the second eigenvalue of each phase is calculated based on the adjacent minima;

[0020] Based on the first eigenvalue and the second eigenvalue of each phase, a current extreme value regression index of each phase current is obtained, wherein the current extreme value regression index is negatively correlated with both the first eigenvalue and the second eigenvalue.

[0021] The current extreme value regression degree is specifically: the first eigenvalue of the i-th phase is recorded as , the second eigenvalue of the i-th phase is recorded as , then the formula of the current extreme value regression degree of phase i is: ;in, Represents an exponential function with a natural constant as its base.

[0022] The method for obtaining the current persistence abnormality degree of the permanent magnet synchronous motor is as follows:

[0023] For each phase current, the difference between 1 and the current extreme value regression degree is calculated and forward fused with the frequency variation degree; the maximum forward fusion result of all phase currents is used as the current persistence abnormality degree of the permanent magnet synchronous motor.

[0024] The specific process of training the neural network is as follows:

[0025] A different label value is assigned to each fault state of the permanent magnet synchronous motor; an operating fault identification vector of the permanent magnet synchronous motor with a known fault and an operating identification vector of the permanent magnet synchronous motor without a fault are obtained as inputs to a neural network, and the output of the neural network is the label value corresponding to the fault.

[0026] In the second aspect, an embodiment of the present application also provides an operation fault monitoring system for a vehicle permanent magnet synchronous motor, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0027] This application has at least the following beneficial effects:

[0028] The present invention collects temperature, current, and voltage data during the operation of a permanent magnet synchronous motor, decomposes the current and voltage of each phase, and obtains the degree of frequency variation based on the frequency distribution characteristics, thereby identifying abnormal fluctuations and potential faults in the operation of the motor and improving the accuracy of fault diagnosis. Furthermore, the extreme points of current and voltage during operation are extracted, and the fluctuation of the same type of extreme points is analyzed to obtain the current extreme value regression degree, which helps to accurately assess the operating status of the motor and improve the response speed and accuracy of the fault warning system. Furthermore, the persistent abnormality degree of current and voltage is obtained, which can cope with data fluctuations in different environments and enable the monitoring system to operate stably under complex working conditions. This stability improves the identification of persistent abnormal states of permanent magnet synchronous motors and improves the practicality and reliability of the monitoring system. The temperature during operation is predicted to obtain the temperature fault recognition degree, which helps to identify overheating problems of motors or equipment in advance. This early warning capability can shorten the fault response time. Compared with traditional methods, it can effectively avoid the misjudgment of transient abnormal conditions caused by environmental interference, accurately identify faults, significantly improve diagnostic accuracy, and provide reliable protection for the safe operation of vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A flowchart of a method for monitoring operating faults of a permanent magnet synchronous motor for a vehicle provided in one embodiment of the present application;

[0030] Figure 2 A schematic diagram of obtaining the current persistence abnormality of a permanent magnet synchronous motor provided in one embodiment of the present application. DETAILED DESCRIPTION

[0031] In the description of the embodiments of this application, words such as "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "or," and "for example" is intended to present the relevant concepts in a concrete manner.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the art of this application. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0033] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the methods. Without departing from the scope of protection of this application, the order of executing multiple steps can be interchanged with each other, and some steps can also be deleted.

[0034] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0035] The following describes in detail a method and system for monitoring operating faults of a permanent magnet synchronous motor for a vehicle provided by the present application with reference to the accompanying drawings.

[0036] See also Figure 1 , which shows a flowchart of a method for monitoring operating faults of a permanent magnet synchronous motor for a vehicle provided by one embodiment of the present application, the method comprising the following steps:

[0037] The first step is to collect the temperature of the permanent magnet synchronous motor during operation within a preset time period to form an operating temperature sequence; at the same time, collect the current and voltage of each phase to form an operating current sequence and an operating voltage sequence of each phase respectively.

[0038] First, current sensors, voltage sensors, and temperature sensors are installed on the automotive permanent magnet synchronous motor. The acquisition frequency is 1kHz and the acquisition time is 10s. It should be noted that the operation of the permanent magnet synchronous motor depends on a three-phase power supply, so current and voltage sensors are used to collect current and voltage data for each phase respectively.

[0039] Since the collected data may be missing during the data collection process, the mean interpolation method is used in this application to interpolate the missing data. The interpolated current, voltage, and temperature data are arranged in the order of collection time. Then, the arranged data are de-noised using the mean filtering algorithm to obtain the operating current sequence, operating voltage sequence, and operating temperature sequence of the permanent magnet synchronous motor. Among them, the calculation of the mean interpolation method and mean filtering is a well-known technology, and the specific calculation steps are not repeated here.

[0040] The second step is to decompose the operating current sequence of each phase to obtain a preset number of layers of decomposed current sequences, compare the similarity of the frequencies of each layer of current decomposition sequences after the current decomposition of any two phases, and combine the distribution characteristics of the amplitude values ​​to obtain the relative frequency difference of each layer of current decomposition sequences after the current decomposition of any two phases. Analyze the numerical characteristics of the relative frequency difference between each phase and the other phase currents in all layers to obtain the frequency variation degree of the operating current sequence of each phase.

[0041] During vehicle travel, uneven road surfaces can cause bumps and vibrations, which can cause changes in various parameters of the vehicle's permanent magnet synchronous motor. For example, vehicle vibrations can cause current instability in the permanent magnet synchronous motor. Unstable currents can lead to torque and speed fluctuations, increasing mechanical stress on the motor, particularly impacting bearings, which can increase bearing wear and shorten their service life.

[0042] The input of the permanent magnet synchronous motor is three-phase alternating current obtained by orthogonal-alternating current conversion. Ideally, the current waveforms of the three-phase alternating current should be the same, and the phase angle between the two adjacent phase currents should differ by 120 degrees. Therefore, the difference in the three-phase current can reflect the stability of the current. Therefore, the operating current sequences of the three phases of the permanent magnet synchronous motor are respectively used as the input of the wavelet decomposition algorithm. For the wavelet basis function of the wavelet decomposition algorithm, the Symlets8 function is selected in this embodiment, the number of decomposition layers is 8, and the decomposed current data is recorded as the current decomposition sequence. Among them, the calculation of the wavelet decomposition algorithm is a well-known technology, and the specific calculation steps are not repeated here.

[0043] For the current decomposition sequence of the three-phase current, since the decomposition is performed in the same way, ideally, the distribution of current data should be the same for the current decomposition sequence of the same layer of the three-phase current. Therefore, the decomposition sequence of the same layer of the three-phase current is used as the input of the Fourier transform algorithm. After the transformation, the output result is the frequency of the current decomposition sequence and its corresponding amplitude. It should be noted that the amplitude value is non-zero. Among them, the calculation process of the Fourier transform is a well-known technology, and the specific calculation steps are not repeated here. Since the frequency and corresponding amplitude of the same signal should remain consistent after the Fourier transform. Therefore, when the frequency difference between the two current decomposition sequences increases, it means that there is a large difference in the current of different phases of the permanent magnet synchronous motor for a long time, which indicates that the possibility of current instability will also increase accordingly.

[0044] Based on this, the frequency variation degree of the running current sequence is calculated. First, the similarity of the frequencies of each layer of the current decomposition sequence after the current decomposition of any two phases is compared. Combined with the overall distribution of the amplitude values ​​of the non-intersecting frequencies, the relative frequency difference of each layer of the current decomposition sequence after the current decomposition of any two phases is obtained. Specifically, the ratio of the number of intersection elements to the number of union elements of the frequencies of each layer of the current decomposition sequence after the current decomposition of any two phases is calculated; the difference between 1 and the ratio is calculated, and then multiplied by the mean of the amplitude values ​​of the non-intersecting frequencies to obtain the relative frequency difference of each layer of the current decomposition sequence after the current decomposition of any two phases.

[0045] Furthermore, the minimum value of the relative frequency difference between each phase current and all other phase currents in each layer of the current decomposition sequence is obtained, and the average of the minimum values ​​corresponding to each phase current in all layers is taken as the frequency variation degree of each phase operating current sequence.

[0046] Ideally, the operating current sequences of any two phases of a permanent magnet synchronous motor have identical waveform characteristics. The same-layer data after wavelet decomposition is identical, and therefore the frequencies and corresponding amplitudes obtained through Fourier transform are also identical. A greater frequency difference between the two decomposed-layer data, i.e., the current decomposition sequences, indicates the presence of different stable currents between the two current phases. Furthermore, greater amplitude differences in the frequencies of the two current decomposition sequences indicate a longer-term difference, greater relative fluctuations between the currents, and higher instability in the current phases. Normal current phases have smaller differences, so using the minimum value minimizes the frequency variation of normal current phases, increasing the frequency variation of abnormal current phases and making them easier to identify.

[0047] The third step is to extract and sort the extreme points in the operating current sequence of each phase, classify the extreme points based on the change characteristics between the extreme points, and determine the standard characteristic difference of each phase current based on the element mean of all classes; based on the distribution change of the extreme values ​​in the operating current sequence of each phase and the said standard characteristic difference, the current extreme value regression degree of each phase is obtained.

[0048] To ensure stable operation of automotive permanent magnet synchronous motors, the current waveform provided by the DC / DC converter is typically an ideal sinusoidal wave. Under this ideal condition, the peak-to-peak differences and valley-to-valley differences of the sine wave waveform remain consistent, and the motor speed is dynamically adjusted based on the vehicle's driving requirements, achieving precise control and efficient power output. Therefore, the frequency of the three-phase AC power also changes dynamically, but the stability of the current peaks and valleys must be maintained. Therefore, the operating current sequence of each phase is used as the input to an extreme point detection algorithm, and the output is the extreme points of the operating current sequence for each phase. All the extreme points of each phase current are arranged in ascending order, denoted as an extreme value sequence. This extreme value sequence is then used as the input to a first-order difference algorithm, and the output is a sequence of extreme value differences within the extreme value sequence. This extreme value difference sequence can be used to determine the degree of current regression relative to peak and valley values, improving fault detection. The calculations for the extreme point detection algorithm and the first-order difference method are both well-known techniques, and the specific calculation process is not detailed here.

[0049] To maintain the stability of the current, the difference between peaks should be as small as possible, and the same applies to troughs. Therefore, the smaller value in the extreme value difference sequence may be the difference between peaks or the difference between troughs. Therefore, the extreme value difference sequence is used as the input of the segmentation algorithm, and the output is a segmentation set. Segmentation algorithms include OTSU, K-means, mean segmentation algorithm, and median segmentation algorithm. In this embodiment, the OTSU algorithm is used. The calculation process of the OTSU algorithm is a well-known technology, and the specific calculation is not repeated here. The set with the smallest element mean is selected, and its element mean is used as the standard feature difference.

[0050] When the peak or trough values ​​are in a state of large difference for a long time, it indicates that the possibility of failure of the permanent magnet synchronous motor is higher. Based on this, according to the distribution of extreme values ​​in the operating current sequence of each phase, combined with the standard characteristic difference, the current extreme value regression degree of each phase is calculated. Specifically: for the operating current sequence of each phase, the difference between two adjacent maximum values ​​is calculated and recorded as the first difference; the difference between the first difference and the standard characteristic difference is recorded as the second difference; the average of the second differences corresponding to all two adjacent maximum values ​​in the operating current sequence of each phase is used as the first characteristic value of each phase. Correspondingly, the difference between two adjacent minimum values ​​is calculated and recorded as the third difference; the difference between the third difference and the standard characteristic difference is recorded as the fourth difference; the average of the fourth differences corresponding to all two adjacent minimum values ​​in the operating current sequence of each phase is used as the second characteristic value of each phase; based on the first characteristic value and the second characteristic value of each phase, the current extreme value regression degree of each phase current is obtained.

[0051] In this embodiment, the difference between variables is calculated using the absolute value of the difference; the first eigenvalue of the i-th phase is recorded as , the second eigenvalue of the i-th phase is recorded as , then the formula of the current extreme value regression degree of phase i is: ;in, Represents an exponential function with a natural constant as its base.

[0052] It should be understood that the electromagnetic torque of a permanent magnet synchronous motor is closely related to the amplitude of the current. Instability in the current extremes can cause fluctuations in the electromagnetic torque. When the current peak suddenly increases, the torque increases instantaneously; when the current peak decreases, the torque decreases. Torque fluctuations can make the motor's output power unstable and affect the smooth operation of the motor. By analyzing the differences between adjacent maxima or minima in the current waveform, and the deviations between these differences and the standard characteristic differences, the current variation characteristics can be evaluated. When the difference value increases, it indicates that the possibility of problems occurring during the test is also higher. This means that the fluctuations between adjacent peaks or troughs of the current are more significant, indicating that the current amplitude of the permanent magnet synchronous motor varies significantly, causing the first and second eigenvalues ​​of the current phase to increase, and the current variation state does not conform to the stable operation state, resulting in a decrease in the current extreme value regression value of the current phase.

[0053] The fourth step: Based on the frequency variation degree of all phase currents and the current extreme value regression degree, the current persistence abnormality of the permanent magnet synchronous motor is obtained; accordingly, the operating voltage sequence of each phase is analyzed to obtain the voltage persistence abnormality of the permanent magnet synchronous motor; the prediction result of the operating temperature sequence in time series is obtained, and combined with the current persistence abnormality and voltage persistence abnormality, an operating fault identification vector of the permanent magnet synchronous motor is formed.

[0054] The currents of the three phases of the permanent magnet synchronous motor are converted from the same direct current, so that the waveforms of the currents are the same. This may cause the frequency variation of each phase current to be small when the permanent magnet synchronous motor fails, and the fault cannot be identified. However, since the peak value of the waveform will change, the current extreme value regression degree of the current phase will decrease. Based on this, the current persistence abnormality of the permanent magnet synchronous motor is obtained according to the frequency variation degree and the current extreme value regression degree of all phase currents. Specifically: for each phase current, the difference between 1 and the current extreme value regression degree is calculated, and forward fused with the frequency variation degree; the maximum forward fusion result of all phase currents is used as the current persistence abnormality of the permanent magnet synchronous motor. In this embodiment, the forward fusion of multiple variables adopts the multiplication calculation method. Among them, the schematic diagram of obtaining the current persistence abnormality of the permanent magnet synchronous motor is shown as follows: Figure 2 shown.

[0055] It should be understood that the greater the value of the permanent magnet synchronous motor's current persistence abnormality, the longer the abnormal state persists, and the more likely it is to contain faults such as winding short circuits, insulation aging, and magnet demagnetization. Furthermore, the current persistence abnormality can be used to identify different types of permanent magnet synchronous motor faults, as the abnormal state changes differently due to different fault currents.

[0056] Furthermore, the permanent magnet synchronous motor's voltage persistence anomaly is calculated using the operating voltage sequence of each phase. Next, the permanent magnet synchronous motor's operating temperature sequence is used as input to an exponentially weighted moving average (EMA) algorithm. The smoothing parameter, a necessary parameter, ranges from [0, 1] and, in this embodiment, is set to 0.9. The predicted temperature at the next moment output by the EMA algorithm is recorded as the temperature fault recognition degree. The current persistence anomaly degree, voltage persistence anomaly degree, and temperature fault recognition degree are combined to form a permanent magnet synchronous motor operating fault recognition vector. The calculation of the EMA algorithm is well known, and the specific calculation steps are not detailed here.

[0057] The fifth step: Based on the operation fault identification vector of the permanent magnet synchronous motor, the trained neural network is used to obtain the fault monitoring result of the permanent magnet synchronous motor.

[0058] Through the above steps, the operational fault identification vectors of the vehicle permanent magnet synchronous motor are collected. In this embodiment, for each fault type, 1000 operational identification vectors of the fault state are collected, and 1000 operational identification vectors of the normal state are also collected. Then, each fault state and normal state are marked separately. In this embodiment, the normal state is marked as 0, and each fault state is assigned a different label value, such as 1, 2, 3, etc. Each fault state corresponds to a unique label value, which can be set by the specific implementation personnel. The five-layer BP network is trained with the training set, and cross entropy is used as the loss function. The AdaGrad optimizer optimizes the training results. Then, the operational fault identification vectors of the vehicle permanent magnet synchronous motor are used as the input of the training model, and the output is the state label of the vehicle permanent magnet synchronous motor. The label value is used to identify the state of the permanent magnet synchronous motor during the vehicle operation. Among them, the calculation of the BP neural network algorithm is a well-known technology, and the specific calculation steps are not repeated here.

[0059] Based on the same inventive concept as the above method, an embodiment of the present application also provides an operation fault monitoring system for a vehicle permanent magnet synchronous motor, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned methods for monitoring the operation fault of a vehicle permanent magnet synchronous motor are implemented.

[0060] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions.

[0061] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, from any point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; modifications to the technical solutions described in the above embodiments, or equivalent replacement of some of the technical features therein, do not deviate from the essence of the corresponding technical solutions within the scope of the technical solutions of the embodiments of the present application, and should be included in the scope of protection of the present application.

Claims

1. A method for monitoring operating faults of a permanent magnet synchronous motor for a vehicle, characterized in that: The method comprises the following steps: During a preset time period, the temperature of the permanent magnet synchronous motor during operation is collected to form an operating temperature sequence; at the same time, the current and voltage of each phase are collected to form an operating current sequence and an operating voltage sequence of each phase respectively; Decompose the operating current sequence of each phase to obtain a decomposed current sequence of a preset number of layers, calculate the ratio of the number of intersection elements and the number of union elements of the frequency of each layer of the current decomposition sequence after the current decomposition of any two phases; calculate the difference between 1 and the ratio, and then multiply it by the average of the amplitude values ​​of all non-intersection frequencies to obtain the relative frequency difference of each layer of the current decomposition sequence after the decomposition of the current of any two phases; obtain the minimum relative frequency difference of each layer of the current decomposition sequence between each phase current and all other phase currents, and take the average of the minimum relative frequency difference values ​​corresponding to each phase current in all layers as the frequency variation degree of each phase operating current sequence; The extreme points in the operating current sequence of each phase are extracted and sorted, and the extreme points are classified based on the change characteristics between the extreme points. The minimum value of the element mean of all classes is used as the standard characteristic difference of each phase current; for the operating current sequence of each phase, the difference between two adjacent maximum values ​​is calculated and recorded as the first difference; the difference between the first difference and the standard characteristic difference is recorded as the second difference; the mean of the second differences corresponding to all two adjacent maximum values ​​in the operating current sequence of each phase is used as the first characteristic value of each phase; the second characteristic value of each phase is calculated based on all two adjacent minimum values ​​in the operating current sequence of each phase; the first characteristic value of the i-th phase is recorded as A i , the second eigenvalue of the i-th phase is recorded as B i , then the formula of the current extreme value regression degree of phase i is: exp(-(A i +B i )); where exp() represents an exponential function with a natural constant as the base; For each phase current, the difference between 1 and the current extreme value regression degree is calculated and forward-fused with the frequency variation degree; the maximum forward-fusion result of all phase currents is used as the current persistence abnormality degree of the permanent magnet synchronous motor; accordingly, the operating voltage sequence of each phase is analyzed to obtain the voltage persistence abnormality degree of the permanent magnet synchronous motor; the prediction result of the operating temperature sequence in time series is obtained, and combined with the current persistence abnormality degree and voltage persistence abnormality degree, an operating fault identification vector of the permanent magnet synchronous motor is formed; Based on the operation fault identification vector of the permanent magnet synchronous motor, the fault monitoring results of the permanent magnet synchronous motor are obtained by using the trained neural network.

2. The method for monitoring operating faults of a vehicle permanent magnet synchronous motor according to claim 1, wherein: The extracting and sorting of extreme value points in each phase operating current sequence is specifically: sorting the extreme value points from small to large based on their values.

3. The method for monitoring operating faults of a vehicle permanent magnet synchronous motor according to claim 1, wherein: The specific process of training a neural network is as follows: A different label value is assigned to each fault state of the permanent magnet synchronous motor; an operating fault identification vector of the permanent magnet synchronous motor with a known fault and an operating identification vector of the permanent magnet synchronous motor without a fault are obtained as inputs to a neural network, and the output of the neural network is the label value corresponding to the fault.

4. A system for monitoring an operating fault of a permanent magnet synchronous motor for a vehicle, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

Images