Method, system and equipment for monitoring operation faults of permanent magnet synchronous motors

Abstract

The present invention relates to the technical field of motor fault monitoring, and specifically to a method, system and device for monitoring operation faults of a permanent magnet synchronous motor. The method comprises: obtaining operation parameters of the permanent magnet synchronous motor in a current statistical period and a previous statistical period, obtaining the harmonic degree of each operation parameter from the number of different harmonics in each operation parameter and the abnormality of each harmonic, obtaining the correlation degree of the operation parameters of the two statistical periods according to the harmonic degree and the change of three-phase current imbalance in the two statistical periods, determining a reference weight of the harmonic degree according to the relationship between the correlation degree and the degree of change of the operation task, and training a fault monitoring model in combination with other features, thereby improving the accuracy of the motor fault monitoring model and improving the accuracy of the motor operation fault detection result.

Description

Technical Field

[0001] The present invention relates to the technical field of motor fault monitoring, and in particular to an operation fault monitoring method, system and device applicable to a permanent magnet synchronous motor. Background Art

[0002] Permanent magnet synchronous motors (PMSMs) are widely used in numerous fields, including industry and new energy vehicles, due to their high efficiency and high power density. However, real-time monitoring technology is crucial because operational faults such as permanent magnet demagnetization, bearing damage, and winding short circuits can cause equipment failure or even accidents. Currently, the industry primarily utilizes intelligent diagnostic algorithms such as online parameter identification, multi-sensor fusion monitoring, and neural networks for fault monitoring. The neural network approach involves constructing a training set based on the operational characteristics of the PMSM, training the model based on the training set to generate a fault monitoring model, and then implementing operational fault monitoring of the PMSM based on the fault monitoring model. Among them, when obtaining the training set, reference weights are usually not set for all features of the permanent magnet synchronous motor, that is, the reference weights of all features of the permanent magnet synchronous motor are 1. This fixed reference weight setting method will have the following defects: when identifying the operation faults of the permanent magnet synchronous motor, since harmonics are a relatively common feature in the fault manifestations, the more harmonics appear and the greater the degree of fluctuation, the greater the possibility of the corresponding permanent magnet synchronous motor failure. However, in addition to being caused by abnormal operation, harmonics may also be caused by other reasons, such as: changes in the operating tasks of the permanent magnet synchronous motor. If this situation is not taken into account, the various features in the training set will not be targeted, thereby reducing the accuracy of the fault monitoring model and easily causing misjudgment of the operation fault detection results of the permanent magnet synchronous motor. Summary of the Invention

[0003] In order to solve the technical problem of low accuracy in training existing fault monitoring models, the present invention aims to provide a method, system and device for monitoring operating faults of permanent magnet synchronous motors. The technical solutions adopted are as follows:

[0004] In a first aspect of the present invention, a method for monitoring operating faults of a permanent magnet synchronous motor is provided, comprising:

[0005] Obtaining operating parameters of the permanent magnet synchronous motor in a current statistical period and a previous statistical period, wherein the operating parameters include at least three-phase current and three-phase voltage;

[0006] The harmonic degree of each operating parameter is obtained from the number of different harmonics in each operating parameter and the abnormal conditions of each harmonic;

[0007] According to the change of harmonic degree between the current statistical period and the previous statistical period, and the change of the imbalance degree of the three-phase current, the correlation degree of the operating parameters between the current statistical period and the previous statistical period is obtained;

[0008] Determining a reference weight for the harmonic level based on a magnitude relationship between the correlation level corresponding to the current statistical period and a degree of change in the operating tasks of the permanent magnet synchronous motor in the current statistical period;

[0009] Based on the harmonic degree under the reference weight addition and other characteristics of the permanent magnet synchronous motor, a permanent magnet synchronous motor fault monitoring model is trained.

[0010] In an exemplary embodiment, the process of obtaining the harmonic degree of the operating parameter includes:

[0011] Acquire a data set of a fundamental wave and each harmonic of an operating parameter, wherein the data set consists of amplitude and frequency;

[0012] Obtain the Euclidean distance between the data groups of the fundamental wave and each harmonic respectively to obtain the comprehensive Euclidean distance;

[0013] The comprehensive Euclidean distance and the number of different subharmonics in the operating parameters are integrated to obtain the harmonic degree of the operating parameters, and the harmonic degree is proportional to the comprehensive Euclidean distance and the number of different subharmonics in the operating parameters.

[0014] In an exemplary embodiment, the process of obtaining the imbalance degree of three-phase current includes:

[0015] Obtaining a difference between any two-phase currents, the difference including a DTW distance and a mean difference between fluctuation curves of any two-phase currents;

[0016] By combining the differences between any two-phase currents, the imbalance of the three-phase current is obtained.

[0017] In an exemplary embodiment, the change in harmonic degree between the current statistical period and the previous statistical period is an absolute value of a comprehensive difference between the harmonic degrees of the current statistical period and the previous statistical period, and the absolute value of the comprehensive difference is obtained by fusing the absolute values ​​of the differences between the harmonic degrees of all operating parameters of the current statistical period and the previous statistical period;

[0018] The change in the unbalance degree of the three-phase current is the absolute value of the difference between the unbalance degrees of the three-phase current in the current statistical period and the previous statistical period.

[0019] In an exemplary embodiment, the process of obtaining the relevance includes:

[0020] According to the absolute value of the comprehensive difference between the harmonic levels of the current statistical period and the previous statistical period, and the absolute value of the difference between the imbalance of the three-phase current, the correlation degree between the operating parameters of the current statistical period and the previous statistical period is obtained; the correlation degree is inversely proportional to the absolute value of the comprehensive difference between the harmonic levels and the absolute value of the difference between the imbalance of the three-phase current.

[0021] In an exemplary embodiment, the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period is the type ratio of the operating tasks of the permanent magnet synchronous motor in the current statistical period, and the type ratio is the ratio of the actual number of types of operating tasks of the permanent magnet synchronous motor in the current statistical period to the total number of types of operating tasks of the permanent magnet synchronous motor.

[0022] In an exemplary embodiment, the process of obtaining the reference weight of the harmonic degree includes:

[0023] If the correlation degree corresponding to the current statistical period is greater than the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period, the reference weight of the harmonic degree is less than the first preset weight threshold, and the difference between the correlation degree corresponding to the current statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period is inversely proportional to the reference weight of the harmonic degree;

[0024] If the degree of correlation corresponding to the current statistical period is less than the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period, the reference weight of the harmonic degree is greater than the second preset weight threshold, and the difference between the degree of correlation corresponding to the current statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period is proportional to the reference weight of the harmonic degree; the first preset weight threshold is less than or equal to the second preset weight threshold.

[0025] In an exemplary embodiment, the reference weight of the other characteristics of the permanent magnet synchronous motor is equal to the difference between a value of 1 and a reference weight of the harmonic degree;

[0026] The permanent magnet synchronous motor fault monitoring model is trained based on the harmonic degree under the reference weight addition and other characteristics of the permanent magnet synchronous motor, including:

[0027] The various features of the permanent magnet synchronous motor under the corresponding reference weight addition in multiple statistical periods are obtained, and the permanent magnet synchronous motor fault monitoring model is trained based on them.

[0028] In a second aspect of the present invention, a system for monitoring operation faults of a permanent magnet synchronous motor is provided, comprising: a memory and a processor; the memory is connected to the processor; the memory is used to store program instructions; and the processor is used to implement the above-mentioned method for monitoring operation faults of a permanent magnet synchronous motor when the program instructions are executed.

[0029] In a third aspect of the present invention, an operation fault monitoring device suitable for a permanent magnet synchronous motor is provided, comprising a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the above-mentioned embodiment of the operation fault monitoring method suitable for a permanent magnet synchronous motor.

[0030] The present invention has the following beneficial effects: the present invention targets the changes in the harmonic levels of various operating parameters of the permanent magnet synchronous motor and the imbalance of the three-phase current in two adjacent statistical periods, obtains the correlation between the operating parameters of the two statistical periods, and determines the reference weight of the harmonic level based on the relationship between the correlation and the change in the degree of the operating task of the permanent magnet synchronous motor, thereby ensuring that the reference weight of the harmonic level is closely related to the change in the degree of the operating task of the permanent magnet synchronous motor and is not fixed. It takes into account the fact that harmonics may be caused by other reasons in addition to abnormal operation, so that the various features in the training set are targeted, thereby improving the accuracy of the permanent magnet synchronous motor fault monitoring model and the accuracy of the operation fault detection results of the permanent magnet synchronous motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a flowchart of a method for monitoring operating faults of a permanent magnet synchronous motor provided by one embodiment of the present invention;

[0032] Figure 2 This is a flow chart for obtaining the imbalance degree of three-phase current provided by one embodiment of the present invention;

[0033] Figure 3 This is a flow chart for obtaining the harmonic degree of an operating parameter provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following detailed description of the specific embodiments, structures, features, and effects of the present invention is provided in conjunction with the accompanying drawings and preferred embodiments. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this invention pertains. The data and information collected in this application were obtained with full consent and authorization.

[0036] This embodiment provides a method for monitoring operating faults of a permanent magnet synchronous motor. Figure 1 As shown, the following steps are included:

[0037] Step S1: obtaining operating parameters of the permanent magnet synchronous motor in the current statistical period and the previous statistical period, where the operating parameters include at least three-phase current and three-phase voltage;

[0038] Step S2: Obtaining the harmonic degree of each operating parameter based on the number of different harmonics in each operating parameter and the abnormality of each harmonic;

[0039] Step S3: Obtaining the correlation between the operating parameters of the current statistical period and the previous statistical period based on the change in the harmonic level between the current statistical period and the previous statistical period, and the change in the imbalance of the three-phase current;

[0040] Step S4: determining a reference weight of the harmonic level according to a magnitude relationship between the correlation level corresponding to the current statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period;

[0041] Step S5: Based on the harmonic degree under the reference weight addition and other characteristics of the permanent magnet synchronous motor, a permanent magnet synchronous motor fault monitoring model is trained.

[0042] Each step is described in detail below with reference to the accompanying drawings.

[0043] Step S1: obtaining operating parameters of the permanent magnet synchronous motor in the current statistical period and the previous statistical period, where the operating parameters include at least three-phase current and three-phase voltage.

[0044] A data acquisition device is provided on the permanent magnet synchronous motor to collect the required operating parameters. The operating parameters include at least the three-phase current and three-phase voltage of the permanent magnet synchronous motor. Therefore, the data acquisition device includes at least a three-phase current sensor and a three-phase voltage sensor. The three-phase current sensor and the three-phase voltage sensor are provided on the three-phase windings of the permanent magnet synchronous motor to obtain the three-phase current and three-phase voltage, respectively. In an exemplary embodiment, the operating parameters include not only the three-phase current and three-phase voltage but also the rotational speed. Accordingly, a rotational speed sensor is installed on the rotating shaft of the permanent magnet synchronous motor to collect the rotational speed signal of the permanent magnet synchronous motor.

[0045] In an exemplary embodiment, a temperature sensor is further fixed on the permanent magnet synchronous motor to collect a temperature signal of the permanent magnet synchronous motor. The temperature sensor may be arranged near the stator winding or the permanent magnet.

[0046] It should be understood that each data acquisition device is connected to a data acquisition card for converting analog signals into digital signals. Moreover, the sampling frequency of each data acquisition device is set according to actual needs.

[0047] This embodiment analyzes a permanent magnet synchronous motor using a statistical cycle as a time unit. During the operation of the permanent magnet synchronous motor, each statistical cycle is included in the analysis. Each statistical cycle has the same duration, and the specific duration is set based on actual needs, for example, half an hour. Therefore, a statistical cycle includes multiple sampling moments, and each sampling moment acquires various operating parameters of the permanent magnet synchronous motor, thereby obtaining an operating parameter sequence corresponding to each operating parameter in the statistical cycle.

[0048] For ease of explanation, two adjacent statistical cycles are set to be the current statistical cycle and the statistical cycle before the current statistical cycle. By analyzing the operating parameters of the permanent magnet synchronous motor in the current statistical cycle and the previous statistical cycle, a reference weight for the relevant characteristics of the permanent magnet synchronous motor in the current statistical cycle is obtained.

[0049] Therefore, the operating parameters of the permanent magnet synchronous motor in the current statistical period and the previous statistical period are obtained. The operating parameters of each statistical period are essentially the operating parameter fluctuation curve in the time domain.

[0050] Step S2: Obtaining the harmonic degree of each operating parameter from the number of different harmonics in each operating parameter and the abnormality of each harmonic.

[0051] When there are faults such as winding short circuit and phase loss, the three-phase current of the permanent magnet synchronous motor will be obviously unbalanced. The existing method for obtaining the imbalance of the three-phase current is to determine it by dividing the difference between the maximum and minimum currents by the average value. However, when the waveform of a phase current is offset in time due to load changes, the imbalance calculated by the existing method will deviate. Therefore, it is also necessary to analyze the difference between the currents of different phases in the three-phase current to determine the imbalance of the three-phase current. The more serious the difference, the more serious the imbalance of the three-phase current. In order to improve the accuracy of the imbalance of the three-phase current, such as Figure 2 As shown, a specific process for obtaining the unbalance degree of the three-phase current is given as follows:

[0052] Step S2-1: Obtain the difference between any two-phase currents, where the difference includes the DTW distance and the mean difference of the fluctuation curves of the any two-phase currents.

[0053] For any statistical period, obtain the fluctuation curves of any two-phase currents in the statistical period, that is, the current fluctuation curves of any two-phase currents, and then obtain the DTW (Dynamic Time Warping) distance of the current fluctuation curves of the two-phase currents. The DTW distance represents the difference between the current fluctuation curves of the two-phase currents. The larger the DTW distance, the greater the difference between the current fluctuation curves of the two-phase currents.

[0054] Furthermore, the current mean of the current fluctuation curve of each of the two phase currents is obtained to obtain two current mean values. The difference between the two current mean values ​​is then calculated. Specifically, the absolute value of the difference between the two current mean values ​​is calculated as the mean difference of the current fluctuation curves of the two phase currents. The mean difference represents the difference between the current fluctuation curves of the two phase currents. The greater the mean difference, the greater the difference in the current fluctuation curves of the two phase currents.

[0055] The difference between the two phase currents is obtained based on the DTW distance and the mean difference of the two phase currents. In an exemplary embodiment, the product of the DTW distance and the mean difference of the two phase currents is calculated as the difference between the two phase currents, thereby obtaining the difference between any two phase currents in the three-phase current.

[0056] Step S2-2: The differences between any two-phase currents are combined to obtain the imbalance degree of the three-phase currents.

[0057] By integrating all the differences between any two phase currents, the imbalance degree of the three-phase current is obtained. In an exemplary embodiment, a specific quantitative method for the imbalance degree of the three-phase current is given as follows:

[0058] ;

[0059] in, Indicates the imbalance of three-phase current. Represents the current fluctuation curve of the i-th phase current in the three-phase current, represents the current fluctuation curve of the j-th phase current in the other two phase currents except the i-th phase current, Current fluctuation curve and current fluctuation curve The DTW distance, Current fluctuation curve Current mean and current fluctuation curve The difference in the mean current. Represents a normalization function, where the normalization method can be a sigmoid function.

[0060] When a permanent magnet synchronous motor experiences an operating fault, its operating parameters will exhibit a certain degree of harmonics. For example, in a permanent magnet synchronous motor, the normal waveforms of the three-phase current and voltage generally conform to the standard sinusoidal law. Ideally, the three-phase voltage and current waveforms are sinusoidal with a fixed frequency, stable amplitude, and a phase difference of 120°. Harmonics of the three-phase voltage and current are sinusoidal components with frequencies that are integer multiples of the fundamental frequency. Depending on the fault type, the degree of harmonics is categorized as third, fifth, and seventh harmonics. (A third harmonic indicates a frequency three times the fundamental frequency. If the fundamental frequency is 50 Hz, the third harmonic has a frequency of 150 Hz.)

[0061] For any operating parameter, its harmonics are obtained. Taking three-phase current as an example, for any phase of the three-phase current, the current fluctuation curve of that phase is converted from the time domain to the frequency domain. Then, the spectrum lines corresponding to each harmonic are obtained on the frequency domain graph. Finally, the amplitude and frequency of each harmonic are determined based on the height and position of the spectrum lines corresponding to each harmonic. This results in the amplitude and frequency of each harmonic of that phase current, as well as the number of different harmonics. The currents of the other two phases are processed in the same way to obtain the amplitude and frequency of each harmonic, as well as the number of different harmonics. When the operating parameter is three-phase voltage, the amplitude and frequency of each harmonic corresponding to each phase voltage, as well as the number of different harmonics, are obtained according to the processing method described above for three-phase current. When the operating parameter is speed, the amplitude and frequency of each harmonic corresponding to the speed, as well as the number of different harmonics, are also obtained according to the processing method described above for three-phase current.

[0062] When the number of different subharmonics is smaller and the amplitude and frequency corresponding to the different subharmonics are closer to the amplitude and frequency of the fundamental wave, the harmonic degree of the operating parameter is lower. Figure 3 As shown, a specific process for obtaining the harmonic degree of the operating parameters is given as follows:

[0063] Step S2-3: Obtain a data set of the fundamental wave and each harmonic of the operating parameter, wherein the data set consists of amplitude and frequency.

[0064] For any operating parameter, obtain the data group of the fundamental wave of the operating parameter, which is composed of the amplitude and frequency of the fundamental wave, and obtain the data group of each harmonic of the operating parameter, which is composed of the amplitude and frequency of the corresponding harmonic.

[0065] For three-phase current and three-phase voltage, it is necessary to obtain the data group of the fundamental wave and each harmonic corresponding to each phase current, and the data group of the fundamental wave and each harmonic corresponding to each phase voltage respectively.

[0066] Step S2-4: respectively obtain the Euclidean distance between the data groups of the fundamental wave and each harmonic to obtain the comprehensive Euclidean distance.

[0067] The Euclidean distance between the data group of the fundamental wave of the operating parameter and the data group of each harmonic of the operating parameter is obtained to obtain the Euclidean distance corresponding to each harmonic, and then the Euclidean distance of the operating parameter corresponding to each harmonic is fused to obtain the comprehensive Euclidean distance of the operating parameter.

[0068] For three-phase current and three-phase voltage, it is necessary to obtain the integrated Euclidean distance corresponding to each phase current and the integrated Euclidean distance corresponding to each phase voltage respectively.

[0069] Step S2-5: The comprehensive Euclidean distance and the number of different harmonics in the operating parameters are integrated to obtain the harmonic degree of the operating parameters.

[0070] The comprehensive Euclidean distance represents the difference between the fundamental wave and each harmonic of the operating parameter. The larger the comprehensive Euclidean distance, the greater the difference and the greater the harmonic degree of the operating parameter. Therefore, the harmonic degree is proportional to the comprehensive Euclidean distance; the more different harmonics in the operating parameter, the greater the harmonic degree. Therefore, the harmonic degree is proportional to the number of different harmonics in the operating parameter.

[0071] Taking the harmonic level of any phase of three-phase current as an example, a specific quantification method is given below:

[0072] ;

[0073] in, Indicates the harmonic level of the k-th phase current in the three-phase current. Indicates the number of different harmonics appearing in the current fluctuation curve of the k-th phase current, represents a data set consisting of the amplitude and frequency of the rth harmonic in the current fluctuation curve of the kth phase current, represents a data set consisting of the amplitude and frequency of the fundamental wave in the current fluctuation curve of the k-th phase current, express and The Euclidean distance. Represents a normalization function, where the normalization method can be a sigmoid function.

[0074] Using the above formula, the harmonic degree of each phase current can be obtained. Similarly, the harmonic degree of each phase voltage and the harmonic degree of the speed can be obtained.

[0075] Step S3: Obtain the correlation between the operating parameters of the current statistical period and the previous statistical period based on the change in the harmonic level between the current statistical period and the previous statistical period, and the change in the imbalance of the three-phase current.

[0076] In the actual operation of permanent magnet synchronous motors, the characteristics of operating parameters vary within different statistical periods due to the changes in the motor's operating tasks. Furthermore, these changes in operating tasks can cause the number of harmonics in the operating parameters to change, typically increasing. Failure to account for these factors can lead to abnormal detection results, resulting in misjudgments or missed detections.

[0077] By adopting step S2, the harmonic degree of each operating parameter in each statistical period and the imbalance degree of the three-phase current in each statistical period can be obtained. Based on the change in the harmonic degree between the current statistical period and the previous statistical period, and the change in the imbalance degree of the three-phase current, the correlation degree of the operating parameters between the current statistical period and the previous statistical period can be obtained.

[0078] For three-phase current, step S2 obtains the harmonic degree of each phase current, then the average value of the harmonic degree of each phase current in the statistical period is calculated as the harmonic degree of the three-phase current in the statistical period. Similarly, for three-phase voltage, step S2 obtains the harmonic degree of each phase voltage, then the average value of the harmonic degree of each phase voltage in the statistical period is calculated as the harmonic degree of the three-phase voltage in the statistical period.

[0079] In an exemplary embodiment, the process of obtaining the change in harmonic degree between the current statistical period and the previous statistical period is: obtaining the absolute value of the difference between the harmonic degree of each operating parameter between the current statistical period and the previous statistical period, and then fusing the absolute value of the difference between the harmonic degree of each operating parameter between the current statistical period and the previous statistical period to obtain the comprehensive absolute value of the difference between the harmonic degree of the current statistical period and the previous statistical period.

[0080] A specific quantitative method for the change in the harmonic degree between the current statistical period and the previous statistical period is given below:

[0081] ;

[0082] in, It indicates the change of harmonic degree between the M+1th statistical period and the Mth statistical period, that is, the change of harmonic degree between the M+1th statistical period and the Mth statistical period. Indicates the harmonic degree of the e-th operating parameter in the M+1-th statistical period, It represents the harmonic degree of the e-th operating parameter in the M-th statistical period. The reason why e is equal to 3 is that there are three operating parameters, namely three-phase current, three-phase voltage and speed.

[0083] Represents a normalization function, where the normalization method can be a sigmoid function.

[0084] Obtain the change in the three-phase current imbalance between the current statistical period and the previous statistical period, which is: the absolute value of the difference between the three-phase current imbalance between the current statistical period and the previous statistical period. The calculation formula is:

[0085] ;

[0086] in, Indicates the change in the unbalance degree of the three-phase current between the M+1th statistical cycle and the Mth statistical cycle, Indicates the unbalance of the three-phase current in the M+1th statistical cycle, Indicates the unbalance of the three-phase current in the Mth statistical cycle.

[0087] Since changes in harmonic levels can exist independently of changes in three-phase current imbalance, that is, when the harmonic level changes between the current statistical cycle and the previous statistical cycle, the three-phase current imbalance may not change. In this case, the change in harmonic level may be due to factors such as power supply-side harmonic injection and nonlinear loads. Therefore, the correlation between the operating parameters of the current statistical cycle and the previous statistical cycle is determined by comprehensively considering the changes in harmonic level and three-phase current imbalance between the current statistical cycle and the previous statistical cycle.

[0088] In an exemplary embodiment, the process of obtaining the degree of correlation is specifically as follows: according to the absolute value of the comprehensive difference between the harmonic degree of the current statistical period and the previous statistical period, and the absolute value of the difference between the imbalance of the three-phase current of the current statistical period and the previous statistical period, the degree of correlation between the operating parameters of the current statistical period and the previous statistical period is obtained. The larger the absolute value of the comprehensive difference between the harmonic degree of the current statistical period and the previous statistical period, the less correlation there is between the operating parameters of the current statistical period and the previous statistical period, that is, the lower the degree of correlation, and the degree of correlation is inversely proportional to the absolute value of the comprehensive difference between the harmonic degree. The larger the absolute value of the difference between the imbalance of the three-phase current of the current statistical period and the previous statistical period, the less correlation there is between the three-phase current of the current statistical period and the previous statistical period, the lower the degree of correlation there is between the operating parameters of the current statistical period and the previous statistical period, and the degree of correlation is inversely proportional to the absolute value of the difference between the imbalance of the three-phase current.

[0089] A specific quantitative method of correlation is given below:

[0090] ;

[0091] in, Indicates the degree of correlation between the operating parameters of the M+1th statistical cycle and the Mth statistical cycle. This calculation formula comprehensively analyzes the absolute value of the comprehensive difference in harmonic levels after negative correlation and the absolute value of the difference in the imbalance of the three-phase current after negative correlation. The correlation degree is obtained by taking the average of the absolute value of the comprehensive difference in harmonic levels after negative correlation and the absolute value of the difference in the imbalance of the three-phase current. In essence, it is a weighted sum of the two, with a weight of 0.5.

[0092] Step S4: Determine a reference weight of the harmonic degree according to the magnitude relationship between the correlation degree corresponding to the current statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period.

[0093] First, the degree of change in the permanent magnet synchronous motor's task load during the current statistical period is obtained. Specifically, each time a permanent magnet synchronous motor task load changes during the current statistical period, the change process (i.e., the task load after the change) is recorded. Based on the change in the permanent magnet synchronous motor task load during the current statistical period, the actual number of permanent magnet synchronous motor task load types occurring during the current statistical period is determined. Task load changes refer to changes in the permanent magnet synchronous motor's operating mode, processing tasks, or processing materials. The total number of permanent magnet synchronous motor task load types is also determined. The total number of types represents the number of all possible permanent magnet synchronous motor task load types related to the application scenario and is a known value. The degree of change in the permanent magnet synchronous motor task load during the current statistical period is calculated as the percentage of permanent magnet synchronous motor task load types during the current statistical period. The percentage is the ratio of the actual number of permanent magnet synchronous motor task load types to the total number of permanent magnet synchronous motor task load types during the current statistical period.

[0094] The reference weight of the harmonic level is determined based on the relationship between the correlation level corresponding to the current statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period. In an exemplary embodiment, there are two cases:

[0095] If the correlation between the current statistical period and the previous statistical period is greater than the change in the operating tasks of the permanent magnet synchronous motor in the current statistical period, it means that the operating parameters in the current statistical period have not changed significantly due to the change in the operating tasks of the permanent magnet synchronous motor in the current statistical period. If there are harmonics in the current statistical period, the large change in harmonics in the current statistical period may be caused by the change in the operating tasks. For normal harmonic fluctuations caused by changes in operating tasks, the reference weight of the harmonic degree in the corresponding current statistical period needs to be set smaller to avoid misjudgment. In an exemplary embodiment, a first preset weight threshold is set, and the first preset weight threshold is a smaller weight threshold. The numerical range of the first preset weight threshold is (0.2, 0.5]. The specific numerical value of the first preset weight threshold is set according to actual needs, and the reference weight of the harmonic degree in the current statistical period is less than the first preset weight threshold, so as to limit the reference weight of the harmonic degree in the current statistical period and limit it to a small numerical range. Moreover, the gap between the degree of correlation between the current statistical period and the previous statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period is inversely proportional to the reference weight of the harmonic degree. Specifically: the greater the gap between the degree of correlation between the current statistical period and the previous statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period, that is, the greater the degree of correlation between the current statistical period and the previous statistical period is than the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period, the smaller the reference weight of the harmonic degree. In an exemplary embodiment, a specific quantification method is given to calculate a parameter :

[0096] ;

[0097] in, Indicates the degree of change in the permanent magnet synchronous motor's operating tasks in the M+1th statistical cycle.

[0098] If the correlation between the current statistical period and the previous statistical period is greater than the change in the permanent magnet synchronous motor's task in the current statistical period, then Less than 1. As a specific example, in When is equal to 1, the reference weight of the harmonic degree in the current statistical period is equal to 0.5 (that is, the first preset weight threshold is set to 0.5); When it is less than 1, the reference weight of the harmonic degree in the current statistical period is equal to 0.5 , thus making The smaller the value, the smaller the reference weight of the harmonic degree in the current statistical period. When it is less than 0.2, the reference weight of the harmonic degree in the current statistical period is set to 0.2.

[0099] If the correlation between the current statistical period and the previous statistical period is less than the change in the operating tasks of the permanent magnet synchronous motor in the current statistical period, it means that the operating parameters have changed too much due to the change in the operating tasks of the permanent magnet synchronous motor in the current statistical period, that is, the harmonic changes in the current statistical period may be affected by other factors in addition to the changes in the operating tasks. Therefore, the reference weight of the harmonic degree in the current statistical period needs to be set larger to avoid misjudgment.

[0100] In an exemplary embodiment, a second preset weight threshold is set. The second preset weight threshold is a larger weight threshold. The value range of the second preset weight threshold is [0.5, 0.7). The specific value of the second preset weight threshold is set according to actual needs. Then, the first preset weight threshold is less than or equal to the second preset weight threshold.

[0101] The reference weight of the harmonic degree in the current statistical period is greater than the second preset weight threshold, and the gap between the correlation degree corresponding to the current statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period is proportional to the reference weight of the harmonic degree, that is, the greater the gap between the correlation degree between the current statistical period and the previous statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period, the greater the reference weight of the harmonic degree.

[0102] In an exemplary embodiment, if the correlation between the current statistical period and the previous statistical period is less than the change in the task of the permanent magnet synchronous motor in the current statistical period, then Greater than 1. As a specific example, in When is equal to 1, the reference weight of the harmonic degree in the current statistical period is equal to 0.5 (that is, the second preset weight threshold is set to 0.5); When greater than 1, the reference weight of the harmonic degree in the current statistical period is equal to 0.5 , thus making The larger the value, the greater the reference weight of the harmonic degree in the current statistical period. When it is greater than 0.7, the reference weight of the harmonic degree in the current statistical period is set to 0.7.

[0103] The above process is used to obtain the reference weight of the harmonic degree in the current statistical period, wherein the harmonic degree refers to the harmonic degree corresponding to each operating parameter.

[0104] It should be understood that when training a permanent magnet synchronous motor fault monitoring model, the features of the permanent magnet synchronous motor obtained include, in addition to the harmonic level, other relevant features. The specific composition of these other features is determined based on actual training needs. In an exemplary embodiment, the other features of the permanent magnet synchronous motor include: the current mean and current variance of each phase of the three-phase current in the statistical period; the amplitude, phase, and frequency of each phase of the three-phase voltage; the speed mean, range, and variance; the number and corresponding amplitude and frequency of each harmonic of the three-phase current, three-phase voltage, and speed; and the temperature mean.

[0105] After obtaining the reference weight of the harmonic level, the reference weights of other features of the permanent magnet synchronous motor are equal to the difference between 1 and the reference weight of the harmonic level. For example, when the reference weight of the harmonic level is 0.2, the reference weights of other features of the permanent magnet synchronous motor are 0.8; when the reference weight of the harmonic level is 0.7, the reference weights of other features of the permanent magnet synchronous motor are 0.3. Thus, the reference weights of various features of the permanent magnet synchronous motor are obtained.

[0106] Step S5: Based on the harmonic degree under the reference weight addition and other characteristics of the permanent magnet synchronous motor, a permanent magnet synchronous motor fault monitoring model is trained.

[0107] Each feature of the permanent magnet synchronous motor corresponds to an input channel. Each input channel has its own reference weight. Each feature is combined with its corresponding reference weight (specifically, each feature is multiplied by its corresponding reference weight) to obtain various features under the reference weight addition, including: the harmonic degree under the reference weight addition, and other features of the permanent magnet synchronous motor under the reference weight addition.

[0108] Then, in each statistical cycle, reference weights for each feature of the permanent magnet synchronous motor are obtained. This allows us to determine the harmonic level and other features of the permanent magnet synchronous motor under the corresponding reference weights for each statistical cycle. Therefore, by obtaining the features of the permanent magnet synchronous motor under the corresponding reference weights for multiple statistical cycles, this data is used to form a training set, which is then input into the permanent magnet synchronous motor fault monitoring model for training, resulting in the final permanent magnet synchronous motor operational fault detection model. The loss function used during training is the cross-entropy loss function.

[0109] When training the permanent magnet synchronous motor fault monitoring model, each sample in the training set is manually labeled to indicate whether the permanent magnet synchronous motor has experienced a fault. If no operational fault has occurred, the output is 0; if an operational fault has occurred, the output is 1, along with the corresponding operational fault name. 20% of the training set is used as the test set.

[0110] When the permanent magnet synchronous motor fault monitoring is subsequently performed based on the trained permanent magnet synchronous motor operation fault detection model, the actual data of the permanent magnet synchronous motor collected will be input into the model, and the operating status of the permanent magnet synchronous motor will be output. If an operation fault occurs, the name of the operation fault will be output at the same time. The maintenance personnel will then stop the permanent magnet synchronous motor in time, conduct risk investigation after identifying the operation fault, and carry out targeted fault diagnosis and processing.

[0111] This embodiment also provides an operation fault monitoring system suitable for a permanent magnet synchronous motor, including: a memory and a processor; the memory is connected to the processor, and the memory is used to store program instructions; the processor is used to implement the steps in the above-mentioned operation fault monitoring method embodiment suitable for a permanent magnet synchronous motor when the program instructions are executed.

[0112] In an exemplary embodiment, the present invention provides an operation fault monitoring device suitable for a permanent magnet synchronous motor, comprising: a computer-readable storage medium, the computer-readable storage medium storing a computer program, and the computer program, when executed by a processor, implements the steps in the above-mentioned operation fault monitoring method embodiment suitable for a permanent magnet synchronous motor.

[0113] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for monitoring operating faults of a permanent magnet synchronous motor, characterized in that: include: Obtaining operating parameters of the permanent magnet synchronous motor in a current statistical period and a previous statistical period, wherein the operating parameters include at least three-phase current and three-phase voltage; The harmonic degree of each operating parameter is obtained from the number of different harmonics in each operating parameter and the abnormal conditions of each harmonic; According to the change of harmonic degree between the current statistical period and the previous statistical period, and the change of the imbalance degree of the three-phase current, the correlation degree of the operating parameters between the current statistical period and the previous statistical period is obtained; Determining a reference weight for the harmonic level based on a magnitude relationship between the correlation level corresponding to the current statistical period and a degree of change in the operating tasks of the permanent magnet synchronous motor in the current statistical period; Based on the harmonic level under the reference weight addition and other characteristics of the permanent magnet synchronous motor, a permanent magnet synchronous motor fault monitoring model is trained; The process of obtaining the reference weight of the harmonic degree includes: If the correlation degree corresponding to the current statistical period is greater than the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period, the reference weight of the harmonic degree is less than the first preset weight threshold, and the difference between the correlation degree corresponding to the current statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period is inversely proportional to the reference weight of the harmonic degree; If the degree of correlation corresponding to the current statistical period is less than the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period, the reference weight of the harmonic degree is greater than the second preset weight threshold, and the difference between the degree of correlation corresponding to the current statistical period and the degree of change of the operating tasks of the permanent magnet synchronous motor in the current statistical period is proportional to the reference weight of the harmonic degree; the first preset weight threshold is less than or equal to the second preset weight threshold.

2. The method for monitoring operating faults of a permanent magnet synchronous motor according to claim 1, wherein: The process of obtaining the harmonic degree of operating parameters includes: Acquire a data set of a fundamental wave and each harmonic of an operating parameter, wherein the data set consists of amplitude and frequency; Obtain the Euclidean distance between the data groups of the fundamental wave and each harmonic respectively to obtain the comprehensive Euclidean distance; The comprehensive Euclidean distance and the number of different subharmonics in the operating parameters are integrated to obtain the harmonic degree of the operating parameters, and the harmonic degree is proportional to the comprehensive Euclidean distance and the number of different subharmonics in the operating parameters.

3. The operating fault monitoring method for a permanent magnet synchronous motor according to claim 1, wherein: The process of obtaining the three-phase current imbalance includes: Obtaining a difference between any two-phase currents, the difference including a DTW distance and a mean difference between fluctuation curves of any two-phase currents; By combining the differences between any two-phase currents, the imbalance of the three-phase current is obtained.

4. The method for monitoring operating faults of a permanent magnet synchronous motor according to claim 1, wherein: The change in harmonic degree between the current statistical period and the previous statistical period is the comprehensive absolute value of the difference between the harmonic degrees of the current statistical period and the previous statistical period, and the comprehensive absolute value of the difference is obtained by fusing the absolute values ​​of the differences between the harmonic degrees of all operating parameters of the current statistical period and the previous statistical period; The change in the unbalance degree of the three-phase current is the absolute value of the difference between the unbalance degrees of the three-phase current in the current statistical period and the previous statistical period.

5. The operating fault monitoring method for a permanent magnet synchronous motor according to claim 4, wherein: The process of obtaining relevant degrees includes: According to the absolute value of the comprehensive difference between the harmonic levels of the current statistical period and the previous statistical period, and the absolute value of the difference between the imbalance of the three-phase current, the correlation degree between the operating parameters of the current statistical period and the previous statistical period is obtained; the correlation degree is inversely proportional to the absolute value of the comprehensive difference between the harmonic levels and the absolute value of the difference between the imbalance of the three-phase current.

6. The method for monitoring operating faults of a permanent magnet synchronous motor according to claim 1, wherein: The degree of change in the operating tasks of the permanent magnet synchronous motor in the current statistical period is the type ratio of the operating tasks of the permanent magnet synchronous motor in the current statistical period, and the type ratio is the ratio of the actual number of types of operating tasks of the permanent magnet synchronous motor in the current statistical period to the total number of types of operating tasks of the permanent magnet synchronous motor.

7. The method for monitoring operating faults of a permanent magnet synchronous motor according to claim 1, wherein: The reference weights of the other characteristics of the permanent magnet synchronous motor are equal to the difference between the value 1 and the reference weight of the harmonic degree; The permanent magnet synchronous motor fault monitoring model is trained based on the harmonic degree under the reference weight addition and other characteristics of the permanent magnet synchronous motor, including: The various features of the permanent magnet synchronous motor under the corresponding reference weight addition in multiple statistical periods are obtained, and the permanent magnet synchronous motor fault monitoring model is trained based on them.

8. An operation fault monitoring system for a permanent magnet synchronous motor, comprising: Memory and processor; The memory is connected to the processor; The memory is used to store program instructions; The processor is configured to implement the operation fault monitoring method applicable to a permanent magnet synchronous motor according to any one of claims 1 to 7 when the program instructions are executed.

9. A running fault monitoring device suitable for a permanent magnet synchronous motor, characterized in that: The invention comprises a computer-readable storage medium storing a computer program, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the embodiment of the method for monitoring operation faults of a permanent magnet synchronous motor according to any one of claims 1 to 7 are implemented.

Images