Remote diagnosis method for switched reluctance motor of electric vehicle

Abstract

The invention discloses a remote diagnosis method for a switched reluctance motor of an electric vehicle, and the method comprises the steps: collecting multiple groups of operation data of the switched reluctance motor, carrying out the preprocessing of the multiple groups of operation data, transmitting the preprocessed multiple groups of operation data to a remote server through a wireless communication mode, and carrying out the remote diagnosis of the switched reluctance motor. The remote server performs feature extraction on the preprocessed multiple groups of operation data by using a dual-channel mode combining an EMD algorithm and a PCA algorithm, identifies a feature vector related to a fault, and extracts a variance value in a time domain feature and a frequency component value in a frequency domain feature from the feature vector; and inputting the variance value and the frequency component value into an LASSO regression model to carry out fault diagnosis on the motor, determining the fault type of the switched reluctance motor, generating a fault early warning signal according to the fault type, and sending the fault early warning signal to a back-end platform through a network. And the operation safety and reliability of the electric automobile are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of motor fault diagnosis, and more particularly to a remote diagnosis method for a switched reluctance motor of an electric vehicle. Background Art

[0002] In the prior art, as an important part of new energy vehicles, the performance stability and reliability of electric vehicles are directly related to the driving safety of users. As one of the key components of electric vehicles, the operating state of switched reluctance motors directly affects the overall performance of electric vehicles. However, traditional motor fault diagnosis methods often rely on on-site detection and manual analysis, which are not only time-consuming and laborious, but also difficult to detect and handle potential faults in a timely manner. Therefore, there is room for improvement in the above technologies. Summary of the Invention

[0003] The present invention aims to at least solve one of the technical problems existing in the prior art. To this end, an object of the present invention is to provide a remote diagnosis method for a switched reluctance motor of an electric vehicle. According to the method of the present invention, by remotely monitoring and analyzing the operating state of the motor, potential faults can be detected and diagnosed in a timely manner, improving the operating safety and reliability of electric vehicles.

[0004] The remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention includes the following steps: S1, collecting multiple sets of operating data of the switched reluctance motor and preprocessing the multiple sets of operating data; S2, transmitting the preprocessed multiple sets of operating data to a remote server through a wireless communication method; S3, the remote server uses a dual-channel mode combining the empirical mode decomposition (EMD) algorithm and the principal component analysis (PCA) algorithm to extract features from the preprocessed multiple sets of operating data, and identify feature vectors related to faults; extracting the variance value in the time domain feature and the frequency component value in the frequency domain feature from the feature vectors, and inputting the variance value and the frequency component value into a LASSO regression model to diagnose the faults of the motor and determine the fault type of the switched reluctance motor; S4, generating a fault warning signal according to the fault type and sending it to a backend platform through a network.

[0005] According to the remote diagnosis method for a switched reluctance motor of an electric vehicle of the present invention, by remotely monitoring and analyzing the operating state of the motor, potential faults can be detected and diagnosed in a timely manner, improving the operating safety and reliability of electric vehicles.

[0006] Remote diagnostic method for switched reluctance motor of electric vehicle according to an embodiment of the present invention, using a dual-channel mode combining empirical mode decomposition (EMD) algorithm and principal component analysis (PCA) algorithm to extract features from the preprocessed multiple sets of the operating data, and identifying feature vectors related to faults, including: decomposing each of the preprocessed multiple sets of the operating data using the EMD algorithm to obtain a plurality of intrinsic mode functions and a residual term corresponding to each set of the operating data; Combining the plurality of intrinsic mode functions and the residual terms corresponding to the multiple sets of the operating data respectively to form a feature matrix, and using the PCA algorithm to perform dimensionality reduction and feature extraction on the feature matrix to obtain the feature vectors.

[0007] Remote diagnostic method for switched reluctance motor of electric vehicle according to an embodiment of the present invention, collecting multiple sets of the operating data in real time through sensors installed on the electric vehicle, and performing denoising processing on the multiple sets of the operating data by means of wavelet transform; Among them, the multiple sets of the operating data include: motor current, motor voltage, motor temperature, and motor speed.

[0008] Remote diagnostic method for switched reluctance motor of electric vehicle according to an embodiment of the present invention, encoding the obtained preprocessed multiple sets of the operating data using Huffman coding algorithm, and transmitting them to the remote server via Bluetooth.

[0009] Remote diagnostic method for switched reluctance motor of electric vehicle according to an embodiment of the present invention, preprocessing the multiple sets of the operating data includes identifying and removing abnormal operating data, and performing interpolation processing on missing operating data.

[0010] Remote diagnostic method for switched reluctance motor of electric vehicle according to an embodiment of the present invention, transmitting the preprocessed multiple sets of the operating data to the remote server via wireless communication means, including when the type of the preprocessed multiple sets of the operating data is periodic data, sending the data results within this period to the remote server; When the valid time of the data collection task expires, sending the data results collected during the valid time period to the remote server.

[0011] Remote diagnostic method for switched reluctance motor of electric vehicle according to an embodiment of the present invention, further including user feedback collection, regularizing the user's feedback on the fault diagnosis results by means of time series analysis, and sending the user's feedback on the fault diagnosis results to the backend platform via the network.

[0012] A remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention further includes fault prediction. Based on historical fault data and the current operating state, a deep learning algorithm is used to calculate the fault probability, and the fault probability is sent to the backend platform through a network.

[0013] A remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention further includes remote maintenance guidance. Based on the fault warning signal, remote maintenance suggestions are provided, and the maintenance suggestions are sent to the backend platform through a network.

[0014] In the remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention, after determining the fault type, the remote server determines a fault solution suggestion according to the fault level of the fault type, and sends the fault solution suggestion to the electric vehicle.

[0015] The remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention is applied in a remote diagnosis system. The remote diagnosis system includes a first module, a second module, a third module, and a fourth module; The first module is used to collect multiple groups of operating data of the switched reluctance motor and preprocess the multiple groups of operating data; The second module is used to transmit the preprocessed multiple groups of operating data to a remote server through a wireless communication method; The third module uses the remote server to perform feature extraction on the preprocessed multiple groups of operating data by a dual-channel mode combining the empirical mode decomposition (EMD) algorithm and the principal component analysis (PCA) algorithm, and identify the feature vectors related to faults; Extract the variance value in the time domain feature and the frequency component value in the frequency domain feature from the feature vectors, input the variance value and the frequency component value into a LASSO regression model to perform fault diagnosis on the motor, and determine the fault type of the switched reluctance motor; The fourth module is used to generate a fault warning signal according to the fault type and send it to the backend platform through a network.

[0016] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. Description of the Drawings

[0017] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 is a flowchart of a remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention; Figure 2 It is a schematic structural diagram of a remote diagnosis system for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention.

[0018] Reference numerals: 10 - Remote diagnosis system; 101 - First module; 102 - Second module; 103 - Third module; 104 - Fourth module. Detailed implementation manners

[0019] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0020] In the present invention, unless otherwise clearly defined and limited, the terms "installed", "connected", "connected", "fixed", etc. shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements or the interaction relationship between two elements, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0021] Next, refer to the attached Figure 1 and Figure 2 , and describe the remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention. For the existing technology electric vehicle mentioned in the above background technology as an important part of new energy vehicles, the stability and reliability of its performance are directly related to the driving safety of users. As one of the key components of an electric vehicle, the operating state of the switched reluctance motor directly affects the overall performance of the electric vehicle. However, the traditional motor fault diagnosis methods often rely on on-site detection and manual analysis, which are not only time-consuming and laborious, but also difficult to detect and handle potential faults in a timely manner. The present invention proposes a remote diagnosis method for a switched reluctance motor of an electric vehicle. By remotely monitoring and analyzing the operating state of the motor, potential faults can be detected and diagnosed in a timely manner, improving the operating safety and reliability of the electric vehicle.

[0022] Specifically, Figure 1 A remote diagnosis method for a switched reluctance motor of an electric vehicle provided by an embodiment of the first aspect of the present invention includes the following steps: S1, collect multiple groups of operating data of the switched reluctance motor and preprocess the multiple groups of operating data; In this application, multiple sets of operation data can be collected in real time by sensors installed on an electric vehicle. Among them, the multiple sets of operation data can include, but are not limited to, motor current, motor voltage, motor temperature, and motor speed; Exemplarily, the preprocessing can include, but is not limited to, at least one of the following: denoising processing, identifying and removing abnormal operation data, and interpolating missing operation data. For example, the multiple sets of operation data can be denoised by means of wavelet transform; In this way, through the collection and processing of data such as motor current, motor voltage, motor temperature, and motor speed, combined with advanced algorithms and analysis tools, real-time monitoring and diagnosis of motor faults can be achieved, improving the accuracy and efficiency of fault diagnosis; S2. Transmit the preprocessed multiple sets of the operation data to a remote server by means of wireless communication; S3. The remote server uses a dual-channel mode combining the EMD (Empirical Mode Decomposition) algorithm and the PCA (Principal Component Analysis) algorithm to extract features from the standardized data, identify the feature vectors related to faults, extract the variance value in the time domain features and the frequency component value in the frequency domain features from the feature vectors, input the variance value and the frequency component value into the LASSO regression model to diagnose the faults of the motor, and determine the fault type of the switched reluctance motor; Exemplarily, the EMD algorithm can be used to decompose each of the preprocessed multiple sets of operation data to obtain multiple intrinsic mode functions and a residual term corresponding to each set of operation data, and the multiple intrinsic mode functions and residual terms corresponding to the multiple sets of operation data are combined into a feature matrix. The PCA algorithm is used to reduce the dimension and extract features of the feature matrix to obtain a feature vector, and the variance value in the time domain features and the frequency component value in the frequency domain features are extracted from the feature vector. The variance value and the frequency component value are input into the LASSO regression model to diagnose the faults of the motor to determine the fault type of the switched reluctance motor.

[0023] Taking the motor current in the multiple sets of operation data as an example, in a specific embodiment, a current sensor is preset on the switched reluctance motor, and current signal data is collected from the motor by the current sensor. The collected current signal is input into the EMD algorithm, and the EMD algorithm will decompose this non-stationary current signal into a series of stationary intrinsic mode functions (IMFs). It should be noted that these IMFs represent the fluctuation modes of different frequency components in the signal. Further, the energy value of each IMF is calculated, and the energy value can be used as a characteristic parameter to describe the characteristics of the motor current signal; Furthermore, these characteristic parameters are combined into a feature vector for subsequent fault identification or classification. After the feature vector is extracted by EMD, PCA can help remove redundant information, reduce the dimension of the feature vector, and thus retain the most critical features. Specifically, EMD is used to decompose the current signal into multiple intrinsic mode functions (IMFs), and PCA is used for dimension reduction and feature extraction. Furthermore, EMD decomposes the current signal x(t) into multiple IMFs and a residual term, and the formula is as follows:

[0024] where is the i-th IMF, is the residual; Furthermore, a feature matrix is constructed, that is, the decomposed IMFs and residuals are combined into a feature matrix X, and the formula is as follows:

[0025] Furthermore, PCA processing is performed on the feature matrix X for dimension reduction and feature extraction, so as to retain the most critical eigenvalues Y, and the formula is as follows:

[0026] Furthermore, based on the extracted feature vector, the LASSO (Least Absolute Shrinkage and Selection Operator) regression model is used to diagnose the faults of the motor and determine the fault type.

[0027] For example, in a specific embodiment, the variance value in the time domain feature and the frequency component value in the frequency domain feature can be extracted from the current feature vector, and the variance value and the frequency component value are used as the input of the LASSO regression model. Furthermore, the extracted features are used as independent variables, and the motor fault type is used as the dependent variable to construct the LASSO regression model. Furthermore, during the training process, the variable coefficients are compressed. Specifically, the coefficients of some unimportant features will be compressed to zero and removed from the model to achieve feature selection. It should be noted that the LASSO regression model can also process parameters such as voltage, temperature, and speed, which will not be elaborated here. In this way, the LASSO regression model is used to diagnose the faults of the motor through the extracted feature vector.

[0028] Specifically, a data set containing multiple current features and target variables is collected; For example, in a specific embodiment, the dataset of the target variable collected can be the current value and the current stability index value. Further, necessary preprocessing is performed on the collected data, including filling in missing current values, handling abnormal current values, and verifying the normalization of current values, to ensure the quality and consistency of the current value data; Further, in constructing the LASSO model, it is necessary to set the regularization parameter λ. It should be noted that the value of λ determines the strength of regularization and thus affects the result of feature selection; Further, using the set regularization parameter λ, the training dataset is used to fit the LASSO model to obtain the regression coefficients of each current feature, where these coefficients reflect the influence degree of the feature on the target variable; Further, feature selection is performed by observing the regression coefficients, and then according to the selected parameter values, the current fault type is determined.

[0029] In some specific embodiments, the factors affecting the current value and the current stability index value may include: external temperature changes, vehicle usage frequency and load conditions, and air humidity; Specifically, the temperature changes at different times of the day, such as lower temperature in the morning and higher temperature at noon. The temperature change causes materials to expand or contract, affecting the clearance of motor components or the lubrication effect; At low temperatures, the grease may become thick, increasing bearing friction, while high temperatures may cause insulation materials to age or magnetic properties to decline, thus affecting current factors. Further, during morning and evening rush hours, the vehicle may be used more frequently, and the motor runs at high load for a long time, resulting in temperature accumulation and increasing the risk of overheating. At night, if the vehicle is stationary, condensation water may cause moisture problems, affecting electronic components or insulation, and thus affecting current factors; Further, there may be dew in the morning with high humidity, or there may be showers in the afternoon, causing the motor to get waterlogged or damp. Salt spray may be more serious in coastal areas in the morning because the temperature drops at night and humidity condenses, accelerating corrosion, thus affecting current factors; In this way, for the influence of factors such as external temperature changes, vehicle usage frequency and load conditions, and air humidity on the collected current data, by constructing a LASSO model, necessary preprocessing is performed on the collected current data to ensure the quality and consistency of the current value data. Thus, through the comprehensive analysis of environmental parameters, usage patterns, and motor status, the fault risks at different times can be predicted and prevented more accurately, so that the faults of the motor can be detected and processed in time, which helps prevent the expansion of faults and thus maintain the stable operation and efficient work of the motor.

[0030] S4. Generate a fault warning signal according to the fault type and send it to the backend platform through the network.

[0031] In this way, through the remote diagnosis method, intervention and treatment can be carried out at the initial stage of the fault, thus avoiding greater losses and repair costs caused by the fault. According to the remote diagnosis method of the switched reluctance motor of the electric vehicle of the present invention, by remotely monitoring and analyzing the operating state of the motor, potential faults can be detected and diagnosed in a timely manner, improving the operating safety and reliability of the electric vehicle.

[0032] In an embodiment of the present application, after determining the fault type of the switched reluctance motor, the remote server can also determine a fault solution suggestion according to the fault level of the fault type, and then send the fault solution suggestion to the electric vehicle. Among them, the fault levels include serious faults, minor faults, etc.

[0033] It should be noted that the fault level can be set according to actual needs and is not limited thereto.

[0034] Exemplarily, the fault solution suggestion can include but is not limited to fault solution measures, information of the nearest repair point to the electric vehicle. Among them, the repair point information can include, for example, the location of the repair point, the type of repair, evaluation information, repair volume, contact information, etc.

[0035] As an example, if the fault type is a serious fault such as winding short circuit or switch tube breakdown, resulting in the motor stopping directly, and according to the motor configuration information of the electric vehicle, it is determined that the electric vehicle does not have a spare motor, then it can be recommended that the user send it to the repair point for repair and provide the user with the information of the repair point.

[0036] As an example, if the fault type is a minor fault such as sensor error, it can be determined that the fault solution measure is for the electric vehicle to enter the power limit mode and prompt the user to repair as soon as possible.

[0037] According to the remote diagnosis method of the switched reluctance motor of the electric vehicle according to an embodiment of the present invention, the Huffman coding algorithm is used to encode the obtained multiple sets of preprocessed operation data, and further, it is transmitted to the remote server through Bluetooth. It should be noted that in other embodiments, the encoded data can also be transmitted through other wireless communication technology methods, such as 4G, 5G, Wi-Fi, etc. For example, in a specific embodiment, through the lightweight data transmission protocol, it automatically switches to the compressed transmission mode when the 4G / 5G network fluctuates, such as only transmitting the abnormal feature vector, ensuring the real-time nature of the key data. Further, the data is encrypted and transmitted through the blockchain technology, which can ensure the communication security between the cloud and the vehicle.

[0038] A remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention preprocesses multiple sets of operation data, including identifying and eliminating abnormal operation data, and interpolating missing operation data; thus, by interpolating the missing operation data, the accuracy of real-time collection and analysis of motor operation data is ensured, so that the fault type and location of the motor can be judged more accurately, potential faults can be detected and diagnosed in time, and the operation safety and reliability of the electric vehicle are improved.

[0039] A remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention transmits the multiple sets of the preprocessed operation data to a remote server through a wireless communication method, and further includes that when the type of the multiple sets of the preprocessed operation data is periodic data, the data result in this period is sent to the remote server; Furthermore, when the valid time of the data acquisition task expires, the data result acquired during the valid time period is sent to the remote server. For example, in a specific embodiment, the characteristic data and key original data are uploaded to the cloud diagnosis platform through an in-vehicle T-BOX module. Specifically, the MQTT protocol can be used to achieve low-latency communication, and a high-priority transmission channel is triggered in an abnormal state.

[0040] A remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention further includes user feedback collection. Furthermore, the feedback of the user on the fault diagnosis result is regularized by a time series analysis method, and the feedback of the user on the fault diagnosis result is sent to the backend platform through the network. That is, through the remote diagnosis method, intervention and processing can be carried out at the initial stage of the fault, so as to avoid greater losses and maintenance costs caused by the fault.

[0041] A remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention further includes fault prediction. Furthermore, according to historical fault data and the current operation state, a deep learning algorithm is used to calculate the fault probability, and the fault probability is sent to the backend platform through the network, which is beneficial to optimizing the fault diagnosis algorithm and improving the diagnosis accuracy.

[0042] A remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention further includes remote maintenance guidance. Furthermore, remote maintenance suggestions are provided according to the fault warning signal, and the maintenance suggestions are sent to the backend platform through the network, which is beneficial to improving the efficiency of fault handling.

[0043] A remote diagnosis method for a switched reluctance motor of an electric vehicle according to an embodiment of the present invention is applied in a remote diagnosis system 10. Specifically, as Figure 2As shown in the figure, the remote diagnosis system includes a first module 101, a second module 102, a third module 103, and a fourth module 104; Further, the first module 101 is used to collect multiple sets of operating data of the switched reluctance motor and preprocess the multiple sets of operating data; further, the second module 102 is used to transmit the preprocessed multiple sets of operating data to the remote server through wireless communication; Further, the third module 103 is used for the remote server to extract features from the preprocessed multiple sets of operating data by using a dual-channel mode combining the empirical mode decomposition (EMD) algorithm and the principal component analysis (PCA) algorithm, and identify the feature vectors related to faults; Further, extract the variance value in the time-domain feature and the frequency component value in the frequency-domain feature from the feature vectors, input the variance value and the frequency component value into the LASSO regression model to diagnose the faults of the motor, and determine the fault type of the switched reluctance motor; further, the fourth module 104 is used to generate a fault warning signal according to the fault type and send it to the back-end platform through the network.

[0044] In summary, according to the remote diagnosis method of the switched reluctance motor of the electric vehicle of the present invention, by remotely monitoring and analyzing the operating state of the motor, potential faults can be discovered and diagnosed in time, and the operating safety and reliability of the electric vehicle can be improved; specifically, the advantages are as follows: First, by collecting and analyzing the operating data of the motor in real time, the fault type and location of the motor can be judged more accurately; Second, discovering and dealing with the faults of the motor in time helps to prevent the expansion of the faults, thereby maintaining the stable operation and efficient work of the motor; Third, through the remote diagnosis method, intervention and treatment can be carried out at the initial stage of the fault, thereby avoiding greater losses and maintenance costs caused by the fault.

[0045] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without conflict, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0046] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.

[0047] In addition, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0048] Any process or method description shown in a flowchart or described in other ways herein may be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of the present invention includes additional implementations, where the functions may be executed in a manner substantially simultaneous with or in the reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0049] The logic and / or steps represented in the flowchart or otherwise described herein can, for example, be considered as a definitional sequence list of executable instructions for implementing logical functions, and can be embodied specifically in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic device) having one or N wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0050] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0051] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0052] In addition, each functional unit in various embodiments of the present invention may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0053] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A remote diagnosis method for a switched reluctance motor of an electric vehicle, characterized in that, Including the following steps: S1, collect multiple groups of operation data of the switched reluctance motor, and preprocess the multiple groups of the operation data; S2, transmit the preprocessed multiple groups of the operation data to a remote server through a wireless communication method; S3, the remote server uses a dual-channel mode combining the empirical mode decomposition (EMD) algorithm and the principal component analysis (PCA) algorithm to extract features from the preprocessed multiple groups of the operation data, and identify feature vectors related to faults; extract the variance value in the time domain features and the frequency component value in the frequency domain features from the feature vectors, and input the variance value and the frequency component value into a LASSO regression model to perform fault diagnosis on the motor, and determine the fault type of the switched reluctance motor; S4, generate a fault warning signal according to the fault type, and send it to a backend platform through a network.

2. The remote diagnosis method for the switched reluctance motor of an electric vehicle according to claim 1, characterized in that The using of the dual-channel mode combining the empirical mode decomposition (EMD) algorithm and the principal component analysis (PCA) algorithm to extract features from the preprocessed multiple groups of the operation data and identify feature vectors related to faults includes: Use the EMD algorithm to decompose each of the preprocessed multiple groups of the operation data respectively, and obtain multiple intrinsic mode functions and a residual term corresponding to each group of the operation data; Form a feature matrix with the multiple intrinsic mode functions and residual terms corresponding to the multiple groups of the operation data respectively, and use the PCA algorithm to perform dimensionality reduction and feature extraction on the feature matrix to obtain the feature vectors.

3. The remote diagnosis method of the switched reluctance motor for an electric vehicle according to claim 1, characterized in that, The collecting of multiple groups of operation data of the switched reluctance motor and preprocessing the multiple groups of the operation data includes: Real-time collect multiple groups of the operation data through sensors installed on an electric vehicle, and perform denoising processing on the multiple groups of the operation data through a wavelet transform method; Among them, the multiple groups of the operation data include: motor current, motor voltage, motor temperature, and motor speed.

4. The remote diagnosis method for the switched reluctance motor of an electric vehicle according to claim 1, wherein The transmitting of the preprocessed multiple groups of the operation data to a remote server through a wireless communication method includes: Use the Huffman coding algorithm to encode the obtained preprocessed multiple groups of the operation data, and transmit them to the remote server through Bluetooth.

5. The remote diagnosis method for the switched reluctance motor of an electric vehicle according to claim 1, characterized in that, The preprocessing of the multiple groups of the operation data includes: Identify and eliminate abnormal operation data, and perform interpolation processing on missing operation data.

6. The remote diagnosis method for the switched reluctance motor of an electric vehicle according to claim 1, characterized in that, The transmitting of the preprocessed multiple groups of the operation data to a remote server through a wireless communication method includes: When the type of the preprocessed multiple groups of the operation data is periodic data, send the data result within this period to the remote server; When the valid time of a data collection task expires, send the data result collected during the valid time period to the remote server.

7. The remote diagnosis method for the switched reluctance motor of an electric vehicle according to claim 1, characterized in that It also includes user feedback collection, regularize the feedback of users on the fault diagnosis results through a time series analysis method, and send the feedback of the users on the fault diagnosis results to a backend platform through a network.

8. The remote diagnosis method for the switched reluctance motor of an electric vehicle according to claim 1, wherein, It also includes fault prediction, calculate the fault probability using a deep learning algorithm according to historical fault data and the current operation status, and send the fault probability to a backend platform through a network.

9. The remote diagnosis method for the switched reluctance motor of an electric vehicle according to claim 1, characterized in that It also includes: After determining the fault type of the switched reluctance motor, the remote server determines a fault solution suggestion according to the fault level of the fault type and sends the fault solution suggestion to the electric vehicle.

10. The remote diagnosis method for the switched reluctance motor of an electric vehicle according to any one of claims 1-9, characterized in that, The method is applied in a remote diagnosis system, and the remote diagnosis system includes a first module, a second module, a third module, and a fourth module; wherein, The first module is used to collect multiple groups of operation data of the switched reluctance motor and preprocess the multiple groups of operation data; The second module is used to transmit the preprocessed multiple groups of operation data to the remote server by wireless communication; The third module is used for the remote server to extract features from the preprocessed multiple groups of operation data by using a dual-channel mode combining the empirical mode decomposition (EMD) algorithm and the principal component analysis (PCA) algorithm, and identify the feature vectors related to faults; extract the variance value in the time domain features and the frequency component value in the frequency domain features from the feature vectors, and input the variance value and the frequency component value into the LASSO regression model to diagnose the faults of the motor and determine the fault type of the switched reluctance motor; The fourth module is used to generate a fault warning signal according to the fault type and send it to the backend platform through the network.

Images