[go: up one dir, main page]

CN114400940B - Permanent magnet driving motor demagnetizing fault diagnosis method for electric automobile and electric automobile - Google Patents

Permanent magnet driving motor demagnetizing fault diagnosis method for electric automobile and electric automobile Download PDF

Info

Publication number
CN114400940B
CN114400940B CN202111547348.9A CN202111547348A CN114400940B CN 114400940 B CN114400940 B CN 114400940B CN 202111547348 A CN202111547348 A CN 202111547348A CN 114400940 B CN114400940 B CN 114400940B
Authority
CN
China
Prior art keywords
network
permanent magnet
electric automobile
dimensional wavelet
wavelet time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111547348.9A
Other languages
Chinese (zh)
Other versions
CN114400940A (en
Inventor
张晓飞
黄凤琴
谢金平
黄守道
周俊鸿
龙卓
唐瑶
唐镜博
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University
Original Assignee
Hunan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hunan University filed Critical Hunan University
Priority to CN202111547348.9A priority Critical patent/CN114400940B/en
Publication of CN114400940A publication Critical patent/CN114400940A/en
Application granted granted Critical
Publication of CN114400940B publication Critical patent/CN114400940B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
    • H02P21/0003—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control
    • H02P21/0014—Control strategies in general, e.g. linear type, e.g. P, PI, PID, using robust control using neural networks
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/005—Testing of electric installations on transport means
    • G01R31/006—Testing of electric installations on transport means on road vehicles, e.g. automobiles or trucks
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/34—Testing dynamo-electric machines
    • G01R31/343—Testing dynamo-electric machines in operation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P21/00—Arrangements or methods for the control of electric machines by vector control, e.g. by control of field orientation
    • H02P21/14—Estimation or adaptation of machine parameters, e.g. flux, current or voltage
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
    • H02P25/00—Arrangements or methods for the control of AC motors characterised by the kind of AC motor or by structural details
    • H02P25/02—Arrangements or methods for the control of AC motors characterised by the kind of AC motor or by structural details characterised by the kind of motor
    • H02P25/022—Synchronous motors
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/60—Other road transportation technologies with climate change mitigation effect
    • Y02T10/64—Electric machine technologies in electromobility

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Power Engineering (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Control Of Electric Motors In General (AREA)

Abstract

The invention discloses a method for diagnosing demagnetization faults of a permanent magnet driving motor for an electric automobile and the electric automobile, wherein the method comprises the steps of collecting magnetic leakage signals of the permanent magnet driving motor for the electric automobile; converting the magnetic leakage signal into a two-dimensional wavelet time-frequency diagram through wavelet transformation; extracting self-coding features of the two-dimensional wavelet time-frequency diagram to obtain a feature vector 1, and extracting features of a maximum stable extremum region of the two-dimensional wavelet time-frequency diagram to obtain a feature vector 2; and inputting the feature vector 1 and the feature vector 2 into a pre-trained machine learning model to obtain a demagnetization fault diagnosis result of the permanent magnet driving motor for the electric automobile. The invention can extract more effective fault high-dimensional characteristics, convert the demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile into more visual image processing, and can improve the comprehensiveness and the accuracy of the fault high-dimensional characteristics and the accuracy of the demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile through the fusion of the two types of characteristics.

Description

Permanent magnet driving motor demagnetizing fault diagnosis method for electric automobile and electric automobile
Technical Field
The invention relates to an electric automobile fault diagnosis technology, in particular to a permanent magnet driving motor demagnetizing fault diagnosis method for an electric automobile and the electric automobile.
Background
Since the major technological project of electric vehicles was started in 2001, the new energy vehicle industry in China has gone through the development process for 20 years, and China has become the production country and the consumption country of the largest new energy vehicles in the world, wherein the scale of the pure electric vehicles accounts for more than 50% of the world, and the pure electric vehicles are the first world and the overall level is internationally advanced. Along with the continuous improvement of the intellectualization and integration of new energy automobiles, the internal structure of the new energy automobiles is increasingly complex. In recent two years, the safety accident of the new energy automobile presents an increased situation, the industry is gradually changed from mileage anxiety into safety anxiety, and the safety problem becomes one of the core problems to be solved in the development of the new energy automobile.
The center of the power of the electric automobile is an electric motor. The permanent magnet driving motor adopts the permanent magnet to generate the motor magnetic field, has simple structure and high efficiency and control precision, and is widely applied to the fields of electric automobiles, aerospace, wind power generation and the like. The power of domestic and international electric automobiles is mostly provided by permanent magnet synchronous motors. Most of the magnetic steel sheets of the permanent magnet driving motor are made of neodymium iron boron permanent magnet materials, and the Curie temperature of the magnetic steel sheets is low. Therefore, overload of the motor, damage of a heat dissipation system and the like can cause magnetic loss of the permanent magnet, and demagnetization of the permanent magnet is extremely easy to occur. The demagnetizing faults can aggravate torque pulsation and motor loss, seriously reduce the performance of the automobile, and cause property loss and casualties when serious. Therefore, the demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile has important practical significance.
There are few studies on the diagnosis of demagnetization faults of a permanent magnet drive motor for an electric vehicle, and particularly, there are few diagnostic methods for practical applications. Related researches are carried out, and only the diagnosis of the demagnetization faults of the permanent magnet motor without considering the application field can be referred to. The existing permanent magnet motor demagnetizing fault diagnosis method has achieved a series of results, and some results exist in both a data-driven diagnosis method and a model-based diagnosis method. For example, data-based diagnostic methods have mostly focused on fault diagnosis on intelligent algorithms or neural network algorithms. However, most data-driven diagnostic methods require a large amount of data to train the classifier, while model-based methods require the establishment of an accurate fault model. In addition, the existing method mainly focuses on fault diagnosis under one-dimensional signals, and does not consider rich fault high-dimensional characteristics. In the data-based demagnetization fault diagnosis, the diagnosis network under the convolutional neural network algorithm is generally deeper, and the calculation cost is high. However, in an actual electric vehicle application environment, the fault signal is susceptible to noise in a complex environment, resulting in difficulty in extracting fault features. Meanwhile, as the permanent magnet driving motor for the electric automobile is in a normal state for a long time, actual fault signals in different states are difficult to acquire. In addition, the complex working condition and the complex environment are the tests facing the practical application of the electric automobile, the fault signals obtained under the two conditions are complex, and the diagnosis effect of the traditional single-layer and single-layer diagnosis algorithm is poor. Therefore, how to realize the demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile has become a key technical problem to be solved urgently.
Disclosure of Invention
The invention aims to solve the technical problems: aiming at the problems in the prior art, the invention provides a method for diagnosing the demagnetization fault of the permanent magnet driving motor for the electric automobile and the electric automobile, which can extract more effective fault high-dimensional characteristics, convert the demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile into more visual image processing, and can improve the comprehensiveness and the accuracy of the fault high-dimensional characteristics and the accuracy of the demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile through the fusion of the two types of characteristics.
In order to solve the technical problems, the invention adopts the following technical scheme:
a permanent magnet driving motor demagnetizing fault diagnosis method for an electric automobile comprises the following steps:
1) Collecting a magnetic leakage signal of a permanent magnet driving motor for an electric automobile;
2) Converting the magnetic leakage signal into a two-dimensional wavelet time-frequency diagram through wavelet transformation;
3) Extracting self-coding features of the two-dimensional wavelet time-frequency diagram to obtain a feature vector 1, and extracting features of a maximum stable extremum region of the two-dimensional wavelet time-frequency diagram to obtain a feature vector 2;
4) And inputting the feature vector 1 and the feature vector 2 into a pre-trained machine learning model to obtain a demagnetization fault diagnosis result of the permanent magnet driving motor for the electric automobile.
Optionally, in step 2), when the magnetic leakage signal is converted into the two-dimensional wavelet time-frequency chart through wavelet transformation, a functional expression of the wavelet transformation is shown as follows:
Figure BDA0003416108640000021
in the above formula, WT (alpha, tau) is the wavelet transformation result, alpha is the scale, tau is the translation amount, f (t) is the one-dimensional magnetic leakage signal,
Figure BDA0003416108640000022
is a mother wave function, t is time.
Optionally, in step 3), performing self-coding feature extraction on the two-dimensional wavelet time-frequency diagram to obtain a feature vector 1 includes: converting the two-dimensional wavelet time-frequency diagram into a gray-scale diagram, inputting the gray-scale diagram into a pre-trained double-layer self-encoder network, and extracting global features of the gray-scale diagram obtained after the conversion of the two-dimensional wavelet time-frequency diagram through the double-layer self-encoder network to serve as feature vectors 1; the double-layer self-encoder comprises two stacked self-encoders, wherein each self-encoder comprises an encoding layer and a decoding layer which are two network layers, the first self-encoder is used for extracting features to obtain shallow features, and the second self-encoder is used for extracting features of the shallow features to obtain depth features and taking the depth features as final obtained global features.
Optionally, in step 3), performing maximum stable extremum region feature extraction on the two-dimensional wavelet time-frequency diagram to obtain the feature vector 2 includes: sequentially binarizing the two-dimensional wavelet time-frequency diagram by using a group of binarization thresholds, and calculating a variable V (i) according to the following formula:
Figure BDA0003416108640000023
in the above, Q i Representing the area of the ith connected area in the binary area obtained by the current binary threshold, delta represents the preset change quantity of the binary threshold, and Q i+Δ Representing the area of the ith connected area in the binary area obtained by increasing the current binary threshold by a preset binary threshold change delta, Q i-Δ Representing the area of an ith connected area in a binary area obtained after the current binary threshold value is reduced by a preset binary threshold value change delta; if the variable V (i) is smaller than the set value, taking the binary region obtained by the current binary threshold value as the obtained maximum stable extremum region feature and converting the binary region into a vector as a feature vector 2.
Optionally, the machine learning model in step 4) includes a softmax classifier 1, a softmax classifier 2, and a comprehensive classifier, where the softmax classifier 1 is used for obtaining a classification probability value 1 according to the feature vector 1, the softmax classifier 2 is used for obtaining a classification probability value 2 according to the feature vector 2, and the comprehensive classifier is used for obtaining a final demagnetization fault diagnosis result of the permanent magnet driving motor for the electric automobile according to the classification probability value 1 and the classification probability value 2.
Optionally, the integrated classifier is a support vector machine classifier.
Optionally, step 4) is preceded by the step of training the machine learning model with the data samples, and the step of training the machine learning model with the data samples includes the step of expanding the data samples with the generation countermeasure network:
s1) inputting a group of random numbers and corresponding sample labels into a generator for generating an countermeasure network, generating a virtual two-dimensional wavelet time-frequency diagram with the labels, and inputting a real two-dimensional wavelet time-frequency diagram with the labels and the virtual two-dimensional wavelet time-frequency diagram into a discriminator for generating the countermeasure network;
s2) respectively calculating the network loss and the network accuracy of the generator and the network loss and the network accuracy of the discriminator in the generated countermeasure network, and if one or all of the network loss and the network accuracy of the generator and the discriminator meet the requirements, judging that the training of the generated countermeasure network is completed, and jumping to the step S3); otherwise, adjusting parameters of a generator and a discriminator for generating the countermeasure network, and jumping to the step S1) to continue training to generate the countermeasure network;
s3) generating a virtual two-dimensional wavelet time-frequency diagram with labels by using a generator for generating an countermeasure network after training, wherein the virtual two-dimensional wavelet time-frequency diagram is used as a two-dimensional wavelet time-frequency diagram in a data sample.
Optionally, the functional expression of the network loss and the network accuracy of the generator in step S2) is:
Figure BDA0003416108640000031
Figure BDA0003416108640000032
in the above, L g Network loss of generator, S g The network accuracy of the generator, mean is the average calculation,
Figure BDA0003416108640000033
the probability that the virtual two-dimensional wavelet time-frequency diagram is identified as a real two-dimensional wavelet time-frequency diagram in the discriminator; the functional expression of the network loss and network accuracy of the arbiter in step S2) is:
Figure BDA0003416108640000034
Figure BDA0003416108640000035
in the above, L D For the loss of the discriminator network, S D For the network accuracy of the arbiter,
Figure BDA0003416108640000036
the probability of outputting the true two-dimensional wavelet time-frequency diagram in the discriminator network is +.>
Figure BDA0003416108640000037
The probability that the true two-dimensional wavelet time-frequency diagram is identified by the discriminator as a virtual two-dimensional wavelet time-frequency diagram.
In addition, the invention also provides an electric automobile, which comprises an electric automobile body with a control unit and adopting the permanent magnet driving motor, wherein the control unit comprises a microprocessor and a memory which are connected with each other, the microprocessor is connected with a magnetic leakage signal sensor for collecting magnetic leakage signals, and the microprocessor is programmed or configured to execute the steps of the permanent magnet driving motor demagnetization fault diagnosis method for the electric automobile.
In addition, the invention also provides a computer readable storage medium, which stores a computer program executed by a computer device to implement the method for diagnosing the demagnetization fault of the permanent magnet driving motor for the electric automobile
Compared with the prior art, the invention has the following advantages:
1. the method comprises the steps of collecting magnetic leakage signals of the permanent magnet driving motor for the electric automobile, converting the magnetic leakage signals into a two-dimensional wavelet time-frequency diagram through wavelet transformation, displaying more effective fault high-dimensional characteristics, and converting demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile into more visual image processing.
2. According to the invention, the two-dimensional wavelet time-frequency diagram is subjected to self-coding feature extraction to obtain the feature vector 1, the two-dimensional wavelet time-frequency diagram is subjected to maximum stable extremum region feature extraction to obtain the feature vector 2, and the comprehensiveness and accuracy of fault high-dimensional features can be improved through fusion of the two types of features, so that the accuracy of demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile can be improved.
Drawings
FIG. 1 is a schematic diagram of a basic flow of a method according to an embodiment of the present invention.
Fig. 2 shows two-dimensional wavelet time-frequency diagrams of normal motor and occurrence of different types of demagnetization faults.
Fig. 3 is a schematic diagram of extracting self-coding features from a two-dimensional wavelet time-frequency diagram to obtain a feature vector 1 according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of extracting self-coding features from a two-dimensional wavelet time-frequency diagram to obtain feature vectors 2 according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a softmax classifier in an embodiment of the invention.
Fig. 6 is a schematic structural diagram of a functional module of an electric automobile body according to an embodiment of the invention.
Detailed Description
Embodiment one:
as shown in fig. 1, the method for diagnosing a demagnetization fault of a permanent magnet drive motor for an electric automobile according to the embodiment includes:
1) Collecting a magnetic leakage signal of a permanent magnet driving motor for an electric automobile;
2) Converting the magnetic leakage signal into a two-dimensional wavelet time-frequency diagram through wavelet transformation;
3) Extracting self-coding features of the two-dimensional wavelet time-frequency diagram to obtain a feature vector 1, and extracting features of a maximum stable extremum region of the two-dimensional wavelet time-frequency diagram to obtain a feature vector 2;
4) And inputting the feature vector 1 and the feature vector 2 into a pre-trained machine learning model to obtain a demagnetization fault diagnosis result of the permanent magnet driving motor for the electric automobile.
Fig. 2 shows two-dimensional wavelet time-frequency diagrams generated by measuring magnetic leakage signals on the surface of a motor by adopting a non-contact alternating-current magnetic sensor under 1000r/min for a normal motor and different types of demagnetization faults (namely, a demagnetization fault 1 and a demagnetization fault 2, wherein the demagnetization fault 1 is 30% and the demagnetization fault 2 is 100%), and referring to fig. 2, the two-dimensional wavelet time-frequency diagrams show more effective fault high-dimensional characteristics, and the demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile can be converted into more visual image processing.
In this embodiment, when the magnetic flux leakage signal is converted into the two-dimensional wavelet time-frequency chart by wavelet transformation in step 2), the functional expression of the wavelet transformation is as follows:
Figure BDA0003416108640000051
in the above formula, WT (alpha, tau) is the wavelet transformation result, alpha is the scale, tau is the translation amount, f (t) is the one-dimensional magnetic leakage signal,
Figure BDA0003416108640000052
is a mother wave function, t is time.
In step 3) of this embodiment, performing self-coding feature extraction on the two-dimensional wavelet time-frequency diagram to obtain a feature vector 1 includes: converting the two-dimensional wavelet time-frequency diagram into a gray-scale diagram, inputting the gray-scale diagram into a pre-trained double-layer self-encoder network, and extracting global features of the gray-scale diagram obtained after the conversion of the two-dimensional wavelet time-frequency diagram through the double-layer self-encoder network to serve as feature vectors 1; the double-layer self-encoder comprises two stacked self-encoders, wherein each self-encoder comprises an encoding layer and a decoding layer which are two network layers, the first self-encoder is used for extracting features to obtain shallow features, and the second self-encoder is used for extracting features of the shallow features to obtain depth features and taking the depth features as final obtained global features. Fig. 3 is a schematic diagram of extracting self-coding features from a two-dimensional wavelet time-frequency diagram to obtain a feature vector 1. The double-layer self-encoder network is an existing neural network, and the required settings comprise maximum convolution times, L2 network weight regularization parameters, sparse regularization controller parameters, sparse regularization term parameters and telescopic data settings.
When the maximum stable extremum region characteristic in the image is extracted, the image sample is subjected to binarization processing by using a series of gray threshold values, then a corresponding binary region is obtained at each threshold value, and finally a region which can keep stable shape within a wide gray threshold value range is the maximum stable extremum region characteristic. In this embodiment, in step 3), performing maximum stable extremum region feature extraction on the two-dimensional wavelet time-frequency diagram to obtain the feature vector 2 includes: sequentially binarizing the two-dimensional wavelet time-frequency diagram by using a group of binarization thresholds, and calculating a variable V (i) according to the following formula:
Figure BDA0003416108640000053
in the above, Q i Representing the area of the ith connected area in the binary area obtained by the current binary threshold, delta represents the preset change quantity of the binary threshold, and Q i+Δ Representing the area of the ith connected area in the binary area obtained by increasing the current binary threshold by a preset binary threshold change delta, Q i-Δ Representing the area of an ith connected area in a binary area obtained after the current binary threshold value is reduced by a preset binary threshold value change delta; if the variable V (i) is smaller than the set value, taking the binary region obtained by the current binary threshold value as the obtained maximum stable extremum region feature and converting the binary region into a vector as a feature vector 2. Fig. 4 is a schematic diagram of extracting self-coding features from a two-dimensional wavelet time-frequency diagram to obtain feature vectors 2.
Referring to fig. 1, the machine learning model in step 4) of the present embodiment includes a softmax classifier 1, a softmax classifier 2, and a comprehensive classifier, where the softmax classifier 1 is used for obtaining a classification probability value 1 according to the feature vector 1, the softmax classifier 2 is used for obtaining a classification probability value 2 according to the feature vector 2, and the comprehensive classifier is used for obtaining a final demagnetization fault diagnosis result of the permanent magnet driving motor for the electric automobile according to the classification probability value 1 and the classification probability value 2. Since the conventional softmax classifier may not perform well in some diagnostic data, the softmax classifier is improved in this embodiment, and is improved to an integrated classifier with n layers (n=1 to m, m is a positive integer) added after the conventional softmax classifier (softmax classifier 1, softmax classifier 2), and the diagnostic effect under complex working conditions and complex environments is improved by classifying again using the classification probability value output by the softmax.
The softmax classifier 1 and the softmax classifier 2 are both softmax neural networks, and the structures of the softmax neural networks are shown in figure 5. The softmax classifier 1 and the softmax classifier 2 calculate classification probability values based on a traditional softmax neural network, the sum of the classification probability values is 1, and the calculation function expression is as follows:
Figure BDA0003416108640000061
in the above formula, softmax represents the softmax classifier, y i Representing the softmax neural network classifier input, n representing the dimension of the softmax classifier. For multiple classifications, it is also necessary to determine how close the actual output is to the desired output by a cross entropy loss function, whose functional expression is:
Figure BDA0003416108640000062
in the above, loss i Represents a cross entropy loss function, t i Representing the true value, softmax represents the softmax classifier, y i Representing a softmax neural network classifier input.
It should be noted that the integrated classifier may employ a desired classifier, such as one or more layers of softmax classifier or other types of classifiers, etc., as desired. For example, as an alternative embodiment, the integrated classifier is a support vector machine classifier (SVM).
In this embodiment, step 4) further includes a step of training a machine learning model by using data samples, and the training of the softmax neural network and the support vector machine classifier (SVM) are well known methods, so they will not be described in detail herein.
In addition, the embodiment also provides an electric automobile, which comprises an electric automobile body with a control unit and adopting a permanent magnet driving motor, wherein the control unit comprises a microprocessor and a memory which are connected with each other, the microprocessor is connected with a magnetic leakage signal sensor for collecting magnetic leakage signals, and the microprocessor is programmed or configured to execute the steps of the method for diagnosing the demagnetization fault of the permanent magnet driving motor for the electric automobile. Fig. 6 is a schematic structural diagram of a functional module of an electric automobile body according to an embodiment of the invention. Referring to fig. 6, in the whole system of the electric automobile, the whole automobile monitoring system issues a control command to the automobile driving control system through can communication, and the automobile driving control system controls the driving motor so that the electric automobile runs. For fault diagnosis, the whole monitoring system integrates fault diagnosis result display, and all algorithms and calculation processes of fault diagnosis are in the automobile driving control system. The magnetic flux sensor is used for measuring the magnetic flux leakage signal on the surface of the driving motor, the signal is transmitted to the automobile driving control system, and the automobile driving control system realizes the fault diagnosis of the motor based on the method of the embodiment and displays and outputs the diagnosis result in the whole automobile monitoring system.
In addition, the present embodiment also provides a computer-readable storage medium in which a computer program executed by a computer device to implement the foregoing method for diagnosing a demagnetization failure of a permanent magnet drive motor for an electric automobile is stored.
Embodiment two:
this embodiment is a further improvement over the first embodiment. In order to realize the demagnetization fault diagnosis of the permanent magnet driving motor for the electric automobile under a small sample, the method for training the machine learning model by adopting the data sample in the embodiment comprises the steps of expanding the data sample by adopting a generated countermeasure network:
s1) inputting a group of random numbers and corresponding sample labels into a generator for generating an countermeasure network, generating a virtual two-dimensional wavelet time-frequency diagram with the labels, and inputting a real two-dimensional wavelet time-frequency diagram with the labels and the virtual two-dimensional wavelet time-frequency diagram into a discriminator for generating the countermeasure network;
s2) calculating the network loss and the network accuracy of the discriminator, if the network loss and the network accuracy of the discriminator meet the requirements (the network loss is smaller than a set value, the network accuracy is larger than the set value), judging that the training of generating the countermeasure network is completed, and jumping to the step S3); otherwise, adjusting parameters of a generator and a discriminator for generating the countermeasure network, and jumping to the step S1) to continue training to generate the countermeasure network;
s3) generating a virtual two-dimensional wavelet time-frequency diagram with labels by using a generator for generating an countermeasure network after training, wherein the virtual two-dimensional wavelet time-frequency diagram is used as a two-dimensional wavelet time-frequency diagram in a data sample.
The condition generating countermeasure network is a deep neural network that is capable of generating data having the same characteristics as the true input data. One condition generating countermeasure network is constituted of two networks: a generator and a arbiter. The goal of the generator is to generate data that the arbiter recognizes as true. In order to maximize the probability that the arbiter recognizes the image generated by the generator as a true image, the negative log likelihood function is minimized. The virtual two-dimensional wavelet time-frequency diagram is generated by using the condition generation countermeasure network, so that the problem of few fault signals in the practical application of the electric automobile is solved.
The requirement of the arbiter is determined by a loss function and a network accuracy function, and the functional expressions of the network loss and the network accuracy of the arbiter in step S2) of the present embodiment are:
Figure BDA0003416108640000071
Figure BDA0003416108640000072
in the above, L D For the loss of the discriminator network, S D For the network accuracy of the arbiter,
Figure BDA0003416108640000073
the probability of outputting the true two-dimensional wavelet time-frequency diagram in the discriminator network is +.>
Figure BDA0003416108640000074
The probability that the true two-dimensional wavelet time-frequency diagram is identified by the discriminator as a virtual two-dimensional wavelet time-frequency diagram.
In addition, the embodiment also provides an electric automobile, which comprises an electric automobile body with a control unit and adopting a permanent magnet driving motor, wherein the control unit comprises a microprocessor and a memory which are connected with each other, the microprocessor is connected with a magnetic leakage signal sensor for collecting magnetic leakage signals, and the microprocessor is programmed or configured to execute the steps of the method for diagnosing the demagnetization fault of the permanent magnet driving motor for the electric automobile.
In addition, the present embodiment also provides a computer-readable storage medium in which a computer program executed by a computer device to implement the foregoing method for diagnosing a demagnetization failure of a permanent magnet drive motor for an electric automobile is stored.
Embodiment III:
the embodiment is basically the same as the second embodiment, and the main difference is that the iterative judgment conditions in the step S2) are different, and the step S2) is to calculate the network loss and the network accuracy of the generator, if the network loss and the network accuracy of the generator meet the requirements (the network loss is smaller than the set value, the network accuracy is greater than the set value), the training of generating the countermeasure network is judged to be completed, and the step S3) is skipped; otherwise, the parameters of the generator and the discriminator for generating the countermeasure network are adjusted, and the step S1) is skipped to continue training to generate the countermeasure network.
The requirements of the generator are determined by the network loss and the network accuracy of the generator, and the functional expressions of the network loss and the network accuracy of the generator in step S2) of the present embodiment are:
Figure BDA0003416108640000081
Figure BDA0003416108640000082
in the above, L g Network loss of generator, S g The network accuracy of the generator, mean is the average calculation,
Figure BDA0003416108640000083
the probability that a virtual two-dimensional wavelet time-frequency diagram is identified in the arbiter as a real two-dimensional wavelet time-frequency diagram.
In addition, the embodiment also provides an electric automobile, which comprises an electric automobile body with a control unit and adopting a permanent magnet driving motor, wherein the control unit comprises a microprocessor and a memory which are connected with each other, the microprocessor is connected with a magnetic leakage signal sensor for collecting magnetic leakage signals, and the microprocessor is programmed or configured to execute the steps of the method for diagnosing the demagnetization fault of the permanent magnet driving motor for the electric automobile.
In addition, the present embodiment also provides a computer-readable storage medium in which a computer program executed by a computer device to implement the foregoing method for diagnosing a demagnetization failure of a permanent magnet drive motor for an electric automobile is stored.
Embodiment four:
the present embodiment is basically the same as the second embodiment, and the main difference is that the iterative judgment conditions in step S2) are different, and the present embodiment S2) is the or logic operation of the first embodiment and the second embodiment, that is: calculating the network loss and the network accuracy of the generator and the network loss and the network accuracy of the discriminator in the generated countermeasure network respectively, and if one of the network loss and the network accuracy of the generator and the discriminator meet the requirements, judging that the training of the generated countermeasure network is completed, and skipping to the step S3); otherwise, the parameters of the generator and the arbiter for generating the countermeasure network are adjusted, the step S1) is skipped to continue training for generating the countermeasure network, and the training for generating the countermeasure network can be realized in the same way.
In addition, the embodiment also provides an electric automobile, which comprises an electric automobile body with a control unit and adopting a permanent magnet driving motor, wherein the control unit comprises a microprocessor and a memory which are connected with each other, the microprocessor is connected with a magnetic leakage signal sensor for collecting magnetic leakage signals, and the microprocessor is programmed or configured to execute the steps of the method for diagnosing the demagnetization fault of the permanent magnet driving motor for the electric automobile.
In addition, the present embodiment also provides a computer-readable storage medium in which a computer program executed by a computer device to implement the foregoing method for diagnosing a demagnetization failure of a permanent magnet drive motor for an electric automobile is stored.
Fifth embodiment:
the present embodiment is basically the same as the second embodiment, and the main difference is that the iterative judgment conditions in step S2) are different, and the present embodiment S2) is the and logic operation of the first embodiment and the second embodiment, that is: calculating the network loss and the network accuracy of the generator and the network loss and the network accuracy of the discriminator in the generated countermeasure network respectively, and if all the network losses and the network accuracy in the generator and the discriminator meet the requirements, judging that the training of the generated countermeasure network is completed, and skipping to the step S3); otherwise, the parameters of the generator and the arbiter for generating the countermeasure network are adjusted, the step S1) is skipped to continue training for generating the countermeasure network, and the training for generating the countermeasure network can be realized in the same way.
In addition, the embodiment also provides an electric automobile, which comprises an electric automobile body with a control unit and adopting a permanent magnet driving motor, wherein the control unit comprises a microprocessor and a memory which are connected with each other, the microprocessor is connected with a magnetic leakage signal sensor for collecting magnetic leakage signals, and the microprocessor is programmed or configured to execute the steps of the method for diagnosing the demagnetization fault of the permanent magnet driving motor for the electric automobile.
In addition, the present embodiment also provides a computer-readable storage medium in which a computer program executed by a computer device to implement the foregoing method for diagnosing a demagnetization failure of a permanent magnet drive motor for an electric automobile is stored.
Example six:
the present embodiment is basically the same as the second embodiment, and the main difference is that the iteration judgment conditions in the step S2) are different, and the step S2) is that if the iteration number is equal to the set value, the training of generating the countermeasure network is judged to be completed, and the step S3) is skipped; otherwise, the parameters of the generator and the arbiter for generating the countermeasure network are adjusted, the step S1) is skipped to continue training for generating the countermeasure network, and the training for generating the countermeasure network can be realized in the same way.
In addition, the embodiment also provides an electric automobile, which comprises an electric automobile body with a control unit and adopting a permanent magnet driving motor, wherein the control unit comprises a microprocessor and a memory which are connected with each other, the microprocessor is connected with a magnetic leakage signal sensor for collecting magnetic leakage signals, and the microprocessor is programmed or configured to execute the steps of the method for diagnosing the demagnetization fault of the permanent magnet driving motor for the electric automobile.
In addition, the present embodiment also provides a computer-readable storage medium in which a computer program executed by a computer device to implement the foregoing method for diagnosing a demagnetization failure of a permanent magnet drive motor for an electric automobile is stored.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to the present invention may occur to one skilled in the art without departing from the principles of the present invention and are intended to be within the scope of the present invention.

Claims (9)

1.一种电动汽车用永磁驱动电机退磁故障诊断方法，其特征在于，包括：1. a permanent magnet drive motor demagnetization fault diagnosis method for electric vehicles, is characterized in that, comprising: 1)采集电动汽车用永磁驱动电机的漏磁信号；1) Collect the magnetic flux leakage signal of the permanent magnet drive motor for electric vehicles; 2)将漏磁信号通过小波变换转换为二维小波时频图；2) Transform the magnetic flux leakage signal into a two-dimensional wavelet time-frequency diagram through wavelet transform; 3)将二维小波时频图利用双层自编码器网络进行自编码特征提取得到特征向量1、将二维小波时频图进行最大稳定极值区域特征提取得到特征向量2；所述进行最大稳定极值区域特征提取得到特征向量2包括：将二维小波时频图使用一组二值化阈值依次进行二值化处理并根据下式计算变量V(i)：3) Use the two-dimensional wavelet time-frequency graph to extract the self-encoding feature using the double-layer autoencoder network to obtain the feature vector 1, and perform the feature extraction of the maximum stable extreme value region on the two-dimensional wavelet time-frequency graph to obtain the feature vector 2; The feature extraction of the stable extremum region to obtain the feature vector 2 includes: using a set of binarization thresholds to sequentially binarize the two-dimensional wavelet time-frequency map and calculate the variable V(i) according to the following formula:
Figure FDA0004203962580000011
Figure FDA0004203962580000011
 上式中，Qi表示当前二值化阈值得到的二值区域中第i个相连区域的面积，Δ表示预设的二值化阈值变化量，Qi+Δ表示当前二值化阈值增加预设的二值化阈值变化量Δ后得到的二值区域中第i个相连区域的面积，Qi-Δ表示当前二值化阈值减少预设的二值化阈值变化量Δ后得到的二值区域中第i个相连区域的面积；若变量V(i)小于设定值，将当前二值化阈值得到的二值区域作为得到的最大稳定极值区域特征并转换为向量作为特征向量2；In the above formula, Q i represents the area of the i-th connected region in the binary region obtained by the current binarization threshold, Δ represents the preset change in the binarization threshold, Q i+Δ represents the increase in the current binarization threshold The area of the i-th connected area in the binary area obtained after the set binarization threshold change amount Δ, Q i-Δ represents the binary value obtained after the current binarization threshold value is reduced by the preset binarization threshold change amount Δ The area of the i-th connected region in the region; if the variable V(i) is less than the set value, the binary region obtained by the current binarization threshold is used as the obtained maximum stable extremum region feature and converted into a vector as feature vector 2; 4)将特征向量1、特征向量2输入预先训练好的机器学习模型，得到电动汽车用永磁驱动电机的退磁故障诊断结果。4) Input eigenvector 1 and eigenvector 2 into the pre-trained machine learning model to obtain the demagnetization fault diagnosis result of the permanent magnet drive motor for electric vehicles. 2.根据权利要求1所述的电动汽车用永磁驱动电机退磁故障诊断方法，其特征在于，步骤2)中将漏磁信号通过小波变换转换为二维小波时频图时，小波变换的函数表达式如下式所示：2. electric vehicle permanent magnet drive motor demagnetization fault diagnosis method according to claim 1, is characterized in that, in step 2) when magnetic flux leakage signal is converted into two-dimensional wavelet time-frequency graph by wavelet transform, the function of wavelet transform The expression is as follows:
Figure FDA0004203962580000012
Figure FDA0004203962580000012
 上式中，WT(α,τ)为小波变换结果，α为尺度，τ为平移量，f(t)为一维漏磁信号，
Figure FDA0004203962580000013
是母波函数，t为时间。In the above formula, WT(α,τ) is the result of wavelet transformation, α is the scale, τ is the translation, f(t) is the one-dimensional magnetic flux leakage signal,
Figure FDA0004203962580000013
is the mother wave function, and t is time. 3.根据权利要求1所述的电动汽车用永磁驱动电机退磁故障诊断方法，其特征在于，步骤3)中将二维小波时频图进行自编码特征提取得到特征向量1包括：将二维小波时频图转换为灰度图后输入预先训练好的双层自编码器网络，通过双层自编码器网络提取二维小波时频图转换后得到的灰度图的全局特征作为特征向量1；所述双层自编码器包括堆叠的两个自编码器，所述自编码器包含编码层和解码层共两个网络层，第一个自编码器用于特征提取得到浅层特征，第二个自编码器用于对浅层特征进行特征提取得到深度特征并作为最终得到的全局特征。3. the permanent magnet drive motor demagnetization fault diagnosis method for electric vehicles according to claim 1, is characterized in that, in step 3), carrying out self-encoded feature extraction of two-dimensional wavelet time-frequency graph to obtain feature vector 1 comprises: two-dimensional After the wavelet time-frequency image is converted into a grayscale image, it is input into the pre-trained double-layer autoencoder network, and the global features of the grayscale image obtained after the conversion of the two-dimensional wavelet time-frequency image are extracted through the double-layer autoencoder network as the feature vector1 ; The two-layer self-encoder includes stacked two self-encoders, the self-encoder includes two network layers of encoding layer and decoding layer, the first self-encoder is used for feature extraction to obtain shallow features, and the second An autoencoder is used to perform feature extraction on shallow features to obtain deep features and serve as the final global features. 4.根据权利要求1所述的电动汽车用永磁驱动电机退磁故障诊断方法，其特征在于，步骤4)中的机器学习模型包括softmax分类器1、softmax分类器2和综合分类器，所述softmax分类器1用于根据特征向量1得到归类概率值1，所述softmax分类器2用于根据特征向量2得到归类概率值2，所述综合分类器用于根据归类概率值1和归类概率值2得到最终的电动汽车用永磁驱动电机的退磁故障诊断结果。4. electric vehicle permanent magnet drive motor demagnetization fault diagnosis method according to claim 1 is characterized in that, the machine learning model in step 4) comprises softmax classifier 1, softmax classifier 2 and comprehensive classifier, described The softmax classifier 1 is used to obtain the classification probability value 1 according to the feature vector 1, the softmax classifier 2 is used to obtain the classification probability value 2 according to the feature vector 2, and the comprehensive classifier is used to obtain the classification probability value 1 according to the classification probability value 1 and the classification probability value 2. The class probability value 2 is used to obtain the final demagnetization fault diagnosis result of the permanent magnet drive motor for electric vehicles. 5.根据权利要求4所述的电动汽车用永磁驱动电机退磁故障诊断方法，其特征在于，所述综合分类器为支持向量机分类器。5. The method for diagnosing demagnetization faults of permanent magnet drive motors for electric vehicles according to claim 4, wherein the comprehensive classifier is a support vector machine classifier. 6.根据权利要求1所述的电动汽车用永磁驱动电机退磁故障诊断方法，其特征在于，步骤4)之前还包括采用数据样本训练机器学习模型的步骤，且采用数据样本训练机器学习模型时包括采用生成对抗网络进行数据样本扩充的步骤：6. The permanent magnet drive motor demagnetization fault diagnosis method for electric vehicles according to claim 1, characterized in that, before step 4), the step of using data samples to train machine learning models is also included, and when using data samples to train machine learning models Including the steps of data sample expansion using generative confrontation network: S1)将一组随机数和对应的样本标签输入生成对抗网络的生成器，生成带有标签的虚拟二维小波时频图，将带有标签的真实二维小波时频图、虚拟二维小波时频图输入生成对抗网络的判别器；S1) Input a set of random numbers and corresponding sample labels into the generator of the generating confrontation network, generate a virtual two-dimensional wavelet time-frequency graph with labels, and convert the real two-dimensional wavelet time-frequency graph with labels, virtual two-dimensional wavelet The time-frequency map input generates the discriminator of the confrontation network; S2)分别计算生成对抗网络中生成器的网络损失以及网络准确度，以及判别器的网络损失以及网络准确度，若生成器和判别器两者中的其一或者全部的网络损失以及网络准确度满足要求，则判定完成对生成对抗网络的训练，跳转步骤S3)；否则，调整生成对抗网络的生成器和判别器的参数，跳转步骤S1)继续训练生成对抗网络；S2) Calculate the network loss and network accuracy of the generator in the generative confrontation network, and the network loss and network accuracy of the discriminator, if the network loss and network accuracy of one or both of the generator and the discriminator If the requirements are met, then it is judged that the training of the generated confrontation network is completed, and the step S3) is skipped; otherwise, the parameters of the generator and the discriminator of the generated confrontation network are adjusted, and the step S1) is continued to train the generated confrontation network; S3)利用完成训练的生成对抗网络的生成器生成带有标签的虚拟二维小波时频图作为数据样本中的二维小波时频图。S3) Using the generator of the trained GAN to generate a labeled virtual two-dimensional wavelet time-frequency graph as the two-dimensional wavelet time-frequency graph in the data sample. 7.根据权利要求6所述的电动汽车用永磁驱动电机退磁故障诊断方法，其特征在于，步骤S2)中生成器的网络损失以及网络准确度的函数表达式为：7. electric vehicle permanent magnet drive motor demagnetization fault diagnosis method according to claim 6, is characterized in that, the network loss of generator and the functional expression of network accuracy in step S2) are:
Figure FDA0004203962580000021
Figure FDA0004203962580000021
Figure FDA0004203962580000022
Figure FDA0004203962580000022
 上式中，Lg为生成器的网络损失，Sg为生成器的网络准确度，mean是取均值计算，
Figure FDA0004203962580000023
为虚拟二维小波时频图在判别器中被识别为真实二维小波时频图的概率；步骤S2)中判别器的网络损失以及网络准确度的函数表达式为：In the above formula, L g is the network loss of the generator, S g is the network accuracy of the generator, mean is calculated by taking the mean value,
Figure FDA0004203962580000023
is the probability that the virtual two-dimensional wavelet time-frequency graph is recognized as a real two-dimensional wavelet time-frequency graph in the discriminator; the functional expression of the network loss and network accuracy of the discriminator in step S2) is:
Figure FDA0004203962580000024
Figure FDA0004203962580000024
Figure FDA0004203962580000025
Figure FDA0004203962580000025
 上式中，LD为判别器网络损失，SD为判别器的网络准确度，
Figure FDA0004203962580000026
为真实二维小波时频图在判别器网络输出的概率，/>
Figure FDA0004203962580000027
为真实二维小波时频图被判别器识别为虚拟二维小波时频图的概率。In the above formula, LD is the discriminator network loss, SD is the network accuracy of the discriminator,
Figure FDA0004203962580000026
is the probability of the real two-dimensional wavelet time-frequency graph output by the discriminator network, />
Figure FDA0004203962580000027
is the probability that the real 2D wavelet time-frequency graph is recognized as a virtual 2D wavelet time-frequency graph by the discriminator. 8.一种电动汽车，包括带有控制单元且采用永磁驱动电机的电动汽车本体，所述控制单元包括相互连接的微处理器和存储器，所述微处理器连接有用于采集漏磁信号的漏磁信号传感器，其特征在于，该微处理器被编程或配置以执行权利要求1～7中任意一项所述电动汽车用永磁驱动电机退磁故障诊断方法的步骤。8. An electric vehicle, comprising an electric vehicle body with a control unit and a permanent magnet drive motor, the control unit includes a microprocessor and a memory connected to each other, and the microprocessor is connected with a device for collecting magnetic flux leakage signals The magnetic flux leakage signal sensor is characterized in that the microprocessor is programmed or configured to execute the steps of the method for diagnosing demagnetization faults of permanent magnet drive motors for electric vehicles according to any one of claims 1-7. 9.一种计算机可读存储介质，其特征在于，该计算机可读存储介质中存储有被计算机设备执行以实施权利要求1～7中任意一项所述电动汽车用永磁驱动电机退磁故障诊断方法的计算机程序。9. A computer-readable storage medium, characterized in that the computer-readable storage medium is stored in the computer-readable storage medium to be executed by a computer device to implement the demagnetization fault diagnosis of the permanent magnet drive motor for electric vehicles described in any one of claims 1 to 7. Method computer program.
CN202111547348.9A 2021-12-16 2021-12-16 Permanent magnet driving motor demagnetizing fault diagnosis method for electric automobile and electric automobile Active CN114400940B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111547348.9A CN114400940B (en) 2021-12-16 2021-12-16 Permanent magnet driving motor demagnetizing fault diagnosis method for electric automobile and electric automobile

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111547348.9A CN114400940B (en) 2021-12-16 2021-12-16 Permanent magnet driving motor demagnetizing fault diagnosis method for electric automobile and electric automobile

Publications (2)

Publication Number Publication Date
CN114400940A CN114400940A (en) 2022-04-26
CN114400940B true CN114400940B (en) 2023-06-13

Family

ID=81226097

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111547348.9A Active CN114400940B (en) 2021-12-16 2021-12-16 Permanent magnet driving motor demagnetizing fault diagnosis method for electric automobile and electric automobile

Country Status (1)

Country Link
CN (1) CN114400940B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119151014B (en) * 2024-11-13 2025-03-18 成都赛力斯科技有限公司 A vehicle fault diagnosis model and its training and use method, device and medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2518456A1 (en) * 2011-04-29 2012-10-31 ABB Technology AG Method for monitoring demagnetization
CN110823574A (en) * 2019-09-30 2020-02-21 安徽富煌科技股份有限公司 A Fault Diagnosis Method Based on Semi-Supervised Learning Deep Adversarial Networks
CN112052796A (en) * 2020-09-07 2020-12-08 电子科技大学 Permanent magnet synchronous motor fault diagnosis method based on deep learning
WO2021117303A1 (en) * 2019-12-09 2021-06-17 株式会社明電舎 Demagnetization diagnosis device for motor and demagnetization diagnosis method for motor control device
CN113526282A (en) * 2021-06-28 2021-10-22 江苏威尔曼科技有限公司 Method, device, medium and equipment for diagnosing medium and long-term aging faults of elevator

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2518456A1 (en) * 2011-04-29 2012-10-31 ABB Technology AG Method for monitoring demagnetization
CN110823574A (en) * 2019-09-30 2020-02-21 安徽富煌科技股份有限公司 A Fault Diagnosis Method Based on Semi-Supervised Learning Deep Adversarial Networks
WO2021117303A1 (en) * 2019-12-09 2021-06-17 株式会社明電舎 Demagnetization diagnosis device for motor and demagnetization diagnosis method for motor control device
CN112052796A (en) * 2020-09-07 2020-12-08 电子科技大学 Permanent magnet synchronous motor fault diagnosis method based on deep learning
CN113526282A (en) * 2021-06-28 2021-10-22 江苏威尔曼科技有限公司 Method, device, medium and equipment for diagnosing medium and long-term aging faults of elevator

Also Published As

Publication number Publication date
CN114400940A (en) 2022-04-26

Similar Documents

Publication Publication Date Title
Gong et al. A fast anomaly diagnosis approach based on modified CNN and multisensor data fusion
Yang et al. An intelligent fault diagnosis method enhanced by noise injection for machinery
CN114358077B (en) Permanent magnet synchronous motor demagnetizing fault diagnosis model construction method and fault diagnosis method and system
CN115267531B (en) A method for uniform demagnetization fault diagnosis of permanent magnet synchronous motor based on deep learning
CN117269754B (en) IPSM rotor demagnetizing and eccentric fault diagnosis method based on convolutional neural network operation
CN117388716B (en) Battery pack fault diagnosis method, system and storage medium based on time sequence data
CN114254674A (en) Method and system for demagnetization fault diagnosis of permanent magnet synchronous motor based on semi-supervised classifier
CN114400940B (en) Permanent magnet driving motor demagnetizing fault diagnosis method for electric automobile and electric automobile
CN114842085A (en) Full-scene vehicle attitude estimation method
Li et al. A novel framework for early pitting fault diagnosis of rotating machinery based on dilated CNN combined with spatial dropout
CN117911703A (en) Mine large-scale point cloud semantic segmentation method based on multi-scale feature fusion
CN112926728B (en) A small sample inter-turn short circuit fault diagnosis method for permanent magnet synchronous motor
CN117150408B (en) Motor fault diagnosis method based on multi-mode comparison learning
Mahmoud et al. Robust Multiple-Fault Diagnosis of PMSM Drives Under Variant Operations and Noisy Conditions
CN104062541A (en) Fault diagnosis method for stator turn-to-turn short circuit of fault-tolerant permanent magnet motor
Xu et al. Fault diagnosis on imbalanced data using an adaptive cost-sensitive multiscale attention network
CN115345277A (en) PMSM turn-to-turn short circuit diagnosis method based on time sequence generation countermeasure network
CN117332340A (en) PMSM fault diagnosis method and system based on multi-sensor visual feature fusion
CN118196392A (en) Point cloud three-dimensional target detection method based on local spatial information enhancement network
CN117805627A (en) Battery fault diagnosis method, device and storage medium
CN106094969A (en) The image aided diagnosis technique that a kind of maximum power point of photovoltaic power generation system is followed the trail of
CN116229228A (en) Small target detection method based on center-surrounding mechanism
CN115688553A (en) Method for diagnosing turn-to-turn short circuit fault of unbalanced sample of permanent magnet synchronous motor
Guo et al. Visualization for Explanation of Deep Learning-Based Fault Diagnosis Model Using Class Activation Map
CN113177599A (en) Enhanced sample generation method based on GAN

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant