Magneto-rheological seat fault diagnosis method and system and vehicle

Abstract

The invention relates to the technical field of vehicle control, and discloses a magnetorheological seat fault diagnosis method and system and a vehicle. The method comprises the steps of obtaining a first data set; performing feature extraction on each piece of data in the first data set to obtain frequency domain data and time domain data; principal component analysis is carried out on the frequency domain data and the time domain data, and variable characteristics associated with different fault types of the magnetorheological seat are determined; clustering the variable features associated with each fault type, and determining a feature cluster formed by the variable features associated with different fault types under each road condition; inputting the feature clusters associated with different fault types under each road condition into a preset support vector machine for training, and constructing a fault diagnosis model; and detecting the current vehicle data and the seat data of the vehicle by using the fault diagnosis model, and determining whether the magnetorheological seat fault diagnosis has a fault or not. Therefore, the fault can be identified even in a complex road working condition, and the diagnosis efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a magnetorheological seat fault diagnosis method, system and vehicle. Background Art

[0002] As an important part of the shock and vibration protection system in transportation vehicles, magnetorheological seats can minimize the possibility of equipment damage and / or personal injury during shock and vibration loading. It is very important for transportation vehicles and can be widely used in aircraft, ground vehicles, marine vehicles, etc.

[0003] In the related art, the fault diagnosis methods for conventional seats are divided into quantitative analysis and qualitative analysis. However, there is a lack of solutions for diagnosing magnetorheological seat faults. As a result, when the vehicle is driving on complex roads, bumpy roads or sharp turns, it is impossible to determine whether the magnetorheological seat has a fault, which can easily lead to misjudgment. Therefore, a magnetorheological seat fault diagnosis is urgently needed to improve the judgment accuracy. Summary of the invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] In view of the above-mentioned shortcomings of the prior art, the present application provides a magnetorheological seat fault diagnosis method, system and vehicle to solve the problem of low accuracy in magnetorheological seat fault diagnosis.

[0006] The first aspect of the present application provides a magnetorheological seat fault diagnosis method, comprising: obtaining a first data set, the first data set comprising vehicle data and seat data corresponding to a vehicle under a variety of road conditions; performing feature extraction on each data in the first data set to obtain frequency domain data and time domain data; performing principal component analysis on the frequency domain data and the time domain data to determine variable features associated with different fault types of the magnetorheological seat, wherein the variable features include the vehicle speed, steering wheel angle, steering wheel speed, throttle opening, brake pedal opening, vehicle height, and at least one of the pressure, displacement, and magnetic field strength of the seat; performing clustering processing on the variable features associated with each fault type to determine a feature cluster formed by the variable features associated with different fault types under each road condition; inputting the feature cluster associated with different fault types under each road condition into a preset support vector machine for training to construct a fault diagnosis model; and using the fault diagnosis model to detect the current vehicle data and seat data of the vehicle to determine whether the magnetorheological seat fault diagnosis is a fault.

[0007] In some possible embodiments of the present application, before performing feature extraction on each data in the first data set, it also includes: preprocessing the first data set to obtain a second data set, and using the second data set as the first data set to be extracted and processed, and the preprocessing includes at least one of noise processing, missing value processing, outlier processing, data integration processing, and data discretization processing.

[0008] In some possible embodiments of the present application, before preprocessing the first data set, it also includes: dividing the first data set into a first data subset representing the seat fault and a second data subset representing the seat fault-free according to the magnetorheological seat fault, and using the first data subset and the second data subset as the first data set to be preprocessed.

[0009] In some possible embodiments of the present application, feature extraction is performed on each data in the first data set to obtain frequency domain data and time domain data, including: feature extraction is performed on the vehicle data and seat data in the first data set based on the time domain and frequency domain dimensions respectively to obtain time domain data containing time domain features and frequency domain data containing frequency domain features, the time domain features include at least one of mean, variance, peak, and skewness, the time domain features include at least one of main frequency, frequency band energy, and frequency centroid, and the variable features are part of the data determined in the first data set.

[0010] In some possible embodiments of the present application, principal component analysis is performed on the frequency domain data and the time domain data to determine the variable characteristics associated with different fault types of the magnetorheological seat, including: standardizing the frequency domain data and the time domain data respectively and converting them into different feature matrices; calculating the covariance matrix of each feature matrix, and calculating the correlation coefficient between each type of eigenvector and different faults based on the covariance matrix; calculating the eigenroots in the covariance matrix based on the correlation coefficient, and calculating the principal components of each type of eigenvector according to the number of the eigenroots and the preset contribution rate; based on the principal components corresponding to each type of eigenvector, determining the variable characteristics associated with different fault types of the magnetorheological seat.

[0011] In some possible embodiments of the present application, the variable features associated with each fault type are clustered to determine a feature cluster formed by the variable features associated with different fault types under each road condition, including: selecting multiple clustering centers, assigning each of the variable features associated with each fault type under different road conditions to the nearest clustering center among the multiple clustering centers; re-clustering the assigned clustering centers until a preset number of clustering times is reached, to obtain a feature cluster formed by the variable features associated with different fault types under each road condition.

[0012] In some possible embodiments of the present application, the feature clusters associated with different fault types under each road condition are input into a preset support vector machine for training to construct a fault diagnosis model, including: presetting the value range of the support vector machine; initializing the mathematical optimizer acceleration function, determining the current number of iterations, the maximum number of iterations and the acceleration function value; randomly generating an initial population and the initial population position in each of the feature clusters; using each of the feature clusters to train the support vector machine, calculating the current fitness value, selecting the current best fitness value to determine the current optimal population position; based on the comparison result between the initial population and the acceleration function value, determining whether the search phase starts from the exploration phase or the development phase, updating the population position in different search phases, and calculating the fitness values ​​of all individuals to find the global optimal population position; if the global optimal population position reaches the maximum number of iterations, outputting the current Lagrange multiplier and constant as optimal parameters to obtain a fault diagnosis model.

[0013] In some possible embodiments of the present application, the expression of the fault diagnosis model is:

[0014]

[0015] Where f(x) is the fault diagnosis model, K(x i ,x) is the kernel function of the support vector machine, y i is the label of the i-th sample, a i ' is the Lagrange multiplier, b' is the constant, and P is the total number of samples.

[0016] In some possible embodiments of the present application, the fault diagnosis model is used to detect the current vehicle data and seat data of the vehicle to determine whether the magnetorheological seat fault diagnosis is faulty, including: inputting the current vehicle data and seat data of the vehicle into the fault diagnosis model to obtain a loss function value; comparing the loss function value with a preset fault threshold; if the loss function value is greater than or equal to the preset fault threshold, determining that the magnetorheological seat is faulty; if the loss function value is less than the preset fault threshold, determining that the magnetorheological seat is normal.

[0017] The second aspect of the present application also provides a magnetorheological seat fault diagnosis system, including: an acquisition module for acquiring a first data set, wherein the first data set includes vehicle data and seat data corresponding to the vehicle under various road conditions; a feature extraction module for performing feature extraction on each data in the first data set to obtain frequency domain data and time domain data; a component analysis module for performing principal component analysis on the frequency domain data and the time domain data to determine variable features associated with the magnetorheological seat in different fault types, wherein the variable features include the vehicle speed, steering wheel angle, steering wheel speed, throttle opening, brake The opening and closing degree of the dynamic pedal, the height of the vehicle body, and at least one of the pressure, displacement, and magnetic field strength of the seat; a clustering module, used to cluster the variable features associated with each fault type, and determine the feature clusters formed by the variable features associated with different fault types under each road condition; a model building module, used to input the feature clusters associated with different fault types under each road condition into a preset support vector machine for training, and build a fault diagnosis model; a fault diagnosis module, using the fault diagnosis model to detect the current vehicle data and seat data of the vehicle, and determine whether the magnetorheological seat fault diagnosis is a fault.

[0018] The third aspect of the present application also provides an electronic device, including: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the above method.

[0019] Beneficial effects of this application:

[0020] By acquiring a first data set, the first data set includes vehicle data and seat data corresponding to the vehicle under various road conditions, determining data diversity based on multi-source data, extracting features from each data in the first data set, and obtaining frequency domain data and time domain data; performing principal component analysis on the frequency domain data and the time domain data to determine the variable features associated with different fault types of the magnetorheological seat, covering the associated potential features, which is conducive to subsequent accurate judgment; performing clustering processing on the variable features associated with each fault type to determine the feature clusters formed by the variable features associated with different fault types under each road condition, thereby ensuring the integrity and diversity of the features; inputting the feature clusters associated with different fault types under each road condition into a preset support vector machine for training to construct a fault diagnosis model; using the fault diagnosis model to perform detection to determine whether the magnetorheological seat fault diagnosis is a fault, so that the fault can be identified even in complex road conditions, thereby improving the efficiency and accuracy of diagnosis; by accurately diagnosing the fault of the magnetorheological seat, it is helpful to prevent potential safety hazards and reduce the risk of traffic accidents caused by seat failures; at the same time, it also improves the reliability and service life of the seat and reduces maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a flow chart of a magnetorheological seat fault diagnosis method in an embodiment of the present application;

[0022] Figure 2 It is a schematic diagram of a data cleaning process in a magnetorheological seat fault diagnosis method in an embodiment of the present application;

[0023] Figure 3 It is a schematic diagram of the principle flow of a magnetorheological seat fault diagnosis method in an embodiment of the present application;

[0024] Figure 4 is a structural schematic diagram of a magnetorheological seat fault diagnosis system in an embodiment of the present application;

[0025] Figure 5 It is a structural schematic diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and sub-samples in the embodiments can be combined with each other without conflict.

[0027] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0028] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0029] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0030] Unless otherwise stated, the term "plurality" means two or more.

[0031] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0032] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0033] Combination Figure 1 FIG. 1 is a flow chart of a magnetorheological seat fault diagnosis method according to an embodiment of the present application, comprising:

[0034] Step S101, obtaining a first data set, wherein the first data set includes vehicle data and seat data corresponding to the vehicle under various road conditions;

[0035] Among them, the vehicles are new energy vehicles and fuel vehicles. New energy vehicles include but are not limited to plug-in hybrid vehicles, extended-range electric vehicles, fuel cell vehicles, fuel cell vehicles, oil-electric hybrid vehicles, and pure electric vehicles. Fuel vehicles include but are not limited to sedans, SUVs (sport utility vehicles), MPVs (multi-purpose vehicles), pickup trucks, sports cars, trucks, buses, and special-purpose vehicles.

[0036] Exemplarily, vehicle data and seat data of the vehicle under various road conditions are collected through data collection methods such as on-board sensors and controller local area network bus. The vehicle data includes but is not limited to GPS (Global Positioning System) time, vehicle geographic location, vehicle speed, steering wheel angle, steering wheel speed, throttle opening and closing, brake pedal opening and closing, and vehicle height. The seat data includes but is not limited to seat pressure, displacement, magnetic field strength, etc. It should be noted that different sensors are used for collection according to different data types, which will not be repeated here.

[0037] For example, various road conditions include turning, straight driving, bumps, uphill, etc., and various types of data are preprocessed to obtain a processed first data set A={A D |D=1,2,…M}, where A D Represents the data of the Dth vehicle.

[0038] Step S102, performing feature extraction on each data in the first data set to obtain frequency domain data and time domain data;

[0039] Exemplarily, signal processing techniques such as Fourier transform and wavelet transform are used to convert various types of data in the first data set (i.e., vehicle data and seat data) into frequency domain data; at the same time, statistical analysis methods such as mean, variance, standard deviation, etc. are used to extract time domain data. Through feature extraction, information useful for fault diagnosis, such as frequency components, amplitude changes, etc., can be extracted from the first data set, providing a basis for subsequent principal component analysis.

[0040] Step S103, performing principal component analysis on the frequency domain data and the time domain data to determine variable features associated with different fault types of the magnetorheological seat, wherein the variable features include the vehicle speed, steering wheel angle, steering wheel speed, throttle opening and closing, brake pedal opening and closing, vehicle height, and at least one of the pressure, displacement, and magnetic field strength of the seat;

[0041] Exemplarily, principal component analysis converts data into a new coordinate system through a linear transformation, so that the first principal component in the new data set has the largest variance (i.e., the most information), and subsequent principal components decrease in turn; in this way, the dimension of the data is reduced by retaining fewer principal components while retaining most of the information.

[0042] For example, the principal component analysis (PCA) algorithm is used to perform dimensionality reduction processing on the extracted frequency domain data and time domain data to determine the variable characteristics associated with different fault types of magnetorheological seats. Of course, other dimensionality reduction algorithms, such as linear discriminant analysis and independent component analysis, can also be used to obtain different dimensionality reduction effects.

[0043] Step S104, clustering the variable features associated with each fault type to determine a feature cluster formed by the variable features associated with different fault types under each road condition;

[0044] Exemplarily, the clustering algorithm divides the data points into different clusters (feature clusters) by calculating the distance or similarity between the data points, so that the fault types with similar characteristics can be classified together. For example, clustering algorithms such as K-means algorithm, hierarchical clustering, etc. are used to cluster the variable features associated with each fault type to form feature clusters. In addition, other clustering algorithms, such as spatial clustering methods with noise, spectral clustering, etc., can also be used to adapt to different data distributions and characteristics.

[0045] Step S105, inputting the feature clusters associated with different fault types under each road condition into a preset support vector machine for training to construct a fault diagnosis model;

[0046] Among them, support vector machine is a binary classification algorithm based on the maximum margin principle, which separates data points of different categories by finding a hyperplane. During the training process, SVM (support vector machine) will find an optimal hyperplane to maximize the interval between two types of data points.

[0047] Exemplarily, the feature clusters associated with different fault types under each road condition are used as training samples and input into a preset (SVM) support vector machine for training to build a fault diagnosis model. Of course, other machine learning algorithms, such as decision trees, neural networks, etc., can also be sampled to build different fault diagnosis models.

[0048] Step S106, using the fault diagnosis model to detect the current vehicle data and seat data of the vehicle to determine whether the magnetorheological seat fault diagnosis is a fault.

[0049] Among them, the fault diagnosis model can determine whether the data belongs to a known fault type by analyzing and processing the input data.

[0050] Exemplarily, the current vehicle data and seat data of the vehicle are collected in real time, and the data is detected using a fault diagnosis model to determine whether there is a fault in the magnetorheological seat.

[0051] In the above manner, useful information for fault diagnosis is extracted from the original data (the first dataset) through feature extraction, principal component analysis, clustering processing, etc., and an accurate fault diagnosis model is constructed. By constructing a fault diagnosis model based on machine learning to replace the traditional diagnosis method based on experience and rules, the labor cost and time cost of fault diagnosis are reduced. This application can not only detect and handle faults of the magnetorheological seat in a timely manner, but also ensure the riding comfort and safety of passengers, and improve the overall performance and quality of the vehicle.

[0052] Optionally, in some embodiments, before performing feature extraction on each data in the first dataset, it further includes:

[0053] Preprocessing the first dataset to obtain a second dataset, where the second dataset is the dataset to be processed by feature extraction, that is, the original dataset, and the preprocessing includes at least one of noise processing, missing value processing, outlier processing, data integration processing, and data discretization processing.

[0054] Exemplarily, please refer to Figure 2 , which is a schematic diagram of the data cleaning process in a magnetorheological seat fault diagnosis method according to an embodiment of this application. From top to bottom, it includes noise processing, missing value processing, outlier processing, and data discretization processing respectively.

[0055] For example, for noise processing, the moving average method is used to remove noise.

[0056] Assume that the existing signal sequence is x1,…x T , the moving average calculation window size is N, N < T, and T is the data length. Then the value at time t is calculated as shown in formula (1):

[0057]

[0058] For example, for missing value processing, different methods can be adopted for filling different data types, such as mean filling, mode filling, or fixed value filling.

[0059] For example, for outlier processing, outliers are detected and processed using statistical methods, such as the 3σ principle and the box plot method. According to the characteristics of outliers, its processing includes 3 cases: deleting outliers; treating them as missing values and then using missing value filling; average value correction, that is, using methods such as the mean method and the interpolation method to replace the outlier with the previous and next two observed values and treating it as a missing value.

[0060] Apply an advanced data cleaning algorithm based on machine learning to automatically identify and remove complex noise and outliers. Use the characterization score normalization method to standardize the data, and at the same time use principal component analysis for feature extraction and selection to extract M high-dimensional features, effectively reducing the data dimension and retaining key information.

[0061] For example, data discretization divides the data value range into intervals of equal width.

[0062] For example, data integration processing cleans, transforms, and merges data to form a unified data set.

[0063] Through the above preprocessing method, the quality and availability of sample data are significantly improved, and the error of the fault diagnosis model caused by sample data quality problems is reduced.

[0064] Optionally, in some embodiments, before preprocessing the first data set, the method further includes:

[0065] The first data set is divided into a first data subset representing the seat fault and a second data subset representing the seat fault-free according to the magnetorheological seat fault, and the first data subset and the second data subset are used as the first data set to be preprocessed.

[0066] Exemplarily, the data collected from each vehicle is divided into a faulty seat data set A′ and a non-faulty seat data set A″ according to the seat diagnosis standard. In this embodiment, the division of the first data set is based on the label or feature of the data. In this example, the label of the data is the fault state of the magnetorheological seat. By checking the label of each data point, it can be assigned to the corresponding data subset.

[0067] In the above way, data points with similar characteristics are grouped together by dividing the data, which facilitates subsequent data analysis and modeling; at the same time, it also helps to reduce data redundancy and noise, and improves the accuracy and efficiency of data analysis.

[0068] Optionally, in some embodiments, performing feature extraction on each data in the first data set to obtain frequency domain data and time domain data includes:

[0069] The vehicle data and seat data in the first data set are subjected to feature extraction based on the time domain and frequency domain dimensions respectively, so as to obtain time domain data containing time domain features and frequency domain data containing frequency domain features. The time domain features include at least one of mean, variance, peak and skewness; the time domain features include at least one of main frequency, frequency band energy and frequency centroid; the variable features are partial data determined in the first data set. In other words, by determining partial data in the first data set, it is possible to determine which of the following parts are variable features: vehicle speed, steering wheel angle, steering wheel speed, throttle opening and closing, brake pedal opening and closing, vehicle height, and pressure, displacement and magnetic field strength of the seat.

[0070] For example, the mean is calculated by calculating the average value of a certain type of signal to reflect the overall level of the signal. The variance is calculated by calculating the dispersion of a certain type of signal value to reflect the volatility of the signal. The peak is determined by calculating the maximum value of a certain type of signal to indicate the strongest part of the signal. The skewness is calculated to measure the asymmetry of the distribution of a certain type of signal around the mean.

[0071] It should be noted that the mean, variance, and peak are features that are calculated from the signal data, while the calculation of the skewness is relatively complex and requires the use of the signal's distribution function or probability density function. By extracting time domain features, the overall characteristics and changing trends of the signal over time are revealed. The extracted time domain features come from vehicle data and seat data.

[0072] Exemplarily, Fourier transform is used to convert the signal from the time domain to the frequency domain to obtain its spectrum information. The main frequency is calculated to find the frequency component with the largest energy, that is, the main frequency. The frequency band energy is calculated to calculate the energy of the signal within a specific frequency band. The frequency center of gravity is determined to calculate the frequency center of gravity of the signal based on the spectrum information to reflect the overall distribution characteristics of the signal in the frequency domain.

[0073] It should also be noted that the calculation of the main frequency, frequency band energy and frequency center of gravity needs to be based on the signal's spectral information, which is obtained through Fourier transform. By extracting frequency domain features, the overall characteristics and change trends of the signal in the frequency domain are revealed. The extracted frequency domain features also come from vehicle data and seat data.

[0074] Optionally, in some embodiments, principal component analysis is performed on the frequency domain data and the time domain data to determine variable features associated with different fault types of the magnetorheological seat, including:

[0075] The frequency domain data and the time domain data are respectively standardized and converted into different feature matrices;

[0076] Calculating the covariance matrix of each of the characteristic matrices, and calculating the correlation coefficient between each type of characteristic vector and different faults according to the covariance matrix;

[0077] Calculating the characteristic roots in the covariance matrix according to the correlation coefficient, and calculating the principal components of each type of characteristic vector according to the number of the characteristic roots and the preset contribution rate;

[0078] Based on the principal components corresponding to each type of the characteristic vectors, variable characteristics associated with different fault types of the magnetorheological seat are determined.

[0079] Exemplarily, frequency domain data and time domain data are obtained, and the frequency domain data and the time domain data are standardized to eliminate the dimension differences and numerical range differences between different features. The standardization process generally includes converting the data into normally distributed data with a mean of 0 and a standard deviation of 1, or scaling the data to a specific range. The standardized data is converted into a feature matrix, where each row of the feature matrix represents a data sample, and each column represents a feature (i.e., a frequency domain feature or a time domain feature).

[0080] For each feature matrix, calculate its covariance matrix, which reflects the correlation between features. According to the covariance matrix, calculate the correlation coefficient between each type of eigenvector and different faults, or the mutual information, Pearson correlation coefficient, etc., where the correlation coefficient is used to measure the linear relationship between the eigenvector and the fault. According to the covariance matrix, calculate its characteristic roots, where the characteristic roots reflect the contribution of the eigenvector in the covariance matrix. According to the number of characteristic roots and the preset contribution rate (such as 80%, etc.), calculate the principal components of each type of eigenvector. Based on the principal components corresponding to each type of eigenvector, analyze the performance under different fault types, and determine the variable characteristics associated with different fault types based on the analysis results of the principal components.

[0081] Through the above method, standardization processing and feature matrix conversion are used to eliminate the dimensional differences and numerical range differences in the original data. The linear relationship between the eigenvector and the fault is determined by calculating the covariance matrix and correlation coefficient. The principal components are obtained through PCA analysis, which reduces the dimension of the data and simplifies the subsequent analysis and processing procedures. At the same time, the accuracy and reliability of the model are improved by determining the characteristics of the associated variables.

[0082] Optionally, in some embodiments, clustering is performed on the variable features associated with each fault type to determine a feature cluster formed by the variable features associated with different fault types under each road condition, including:

[0083] Selecting a plurality of cluster centers, and assigning each of the variable features associated with each fault type under different road conditions to the nearest cluster center among the plurality of cluster centers;

[0084] The allocated cluster centers are clustered again until a preset number of clustering times is reached, so as to obtain a feature cluster formed by the variable features associated with different fault types under each road condition.

[0085] Exemplarily, according to the characteristics of the data and the expected number of clusters, multiple initial cluster centers are selected randomly or based on a certain strategy, for example, using K-Means++ to calculate the distance from each variable feature to each cluster center, for example, the Euclidean distance. Each variable feature is assigned to the cluster center closest to it to form a preliminary clustering result. Based on the preliminary clustering result, the cluster center of each cluster is recalculated, for example, the mean, median, etc. The above steps are repeated until the preset number of clustering times is reached or the cluster center no longer changes significantly. Through iterative optimization, the accuracy and stability of the clustering results are improved. After reaching the preset number of clustering times, the final clustering result is output, that is, the feature cluster formed by the variable features associated with different fault types under each road condition.

[0086] Through the above method, the accuracy and stability of the clustering results are ensured, and at the same time, the computational efficiency of the entire clustering process is improved.

[0087] Optionally, in some embodiments, the feature clusters associated with different fault types under each road condition are input into a preset support vector machine for training to construct a fault diagnosis model, including:

[0088] Presetting a value range of the support vector machine;

[0089] Initialize the mathematical optimizer acceleration function, determine the current number of iterations, the maximum number of iterations and the acceleration function value;

[0090] Randomly generating an initial population and the initial population position in each of the feature clusters;

[0091] Using each of the feature clusters to train the support vector machine, calculate the current fitness value, and select the current best fitness value to determine the current optimal population position;

[0092] According to the comparison result between the initial population and the acceleration function value, determining whether the search phase starts from the exploration phase or the development phase, updating the population position in different search phases, and calculating the fitness values ​​of all individuals to find the global optimal population position;

[0093] If the global optimal population position reaches the maximum number of iterations, the current Lagrange multiplier and constant are output as optimal parameters to obtain a fault diagnosis model.

[0094] Exemplarily, before training the support vector machine, the range of values ​​of parameters in the SVM (such as Lagrange multiplier α, penalty parameter C, kernel function parameter γ, etc.) is pre-set based on experience or data range, wherein the above parameters will affect the classification effect and performance of the SVM. A mathematical optimizer acceleration function is selected, such as momentum, root mean square optimizer, adaptive moment estimation, etc., and its parameters are initialized, for example, the current number of iterations is set, the maximum number of iterations is set to a preset value, and related parameters of the acceleration function, such as learning rate, momentum coefficient, etc.

[0095] According to the obtained feature clusters, a certain number of initial populations are randomly generated in each feature cluster, and the initial position is determined. In each feature cluster, the parameter combination in the current population is used to train the SVM, and its fitness value, such as classification accuracy, recall rate, etc., is calculated. The individual with the best fitness value is selected as the current optimal population position. According to the fitness value and acceleration function value of the individual in the initial population, it is determined whether the current search stage should be the exploration stage or the development stage. The exploration stage focuses on searching for new solution spaces in a larger range, while the development stage focuses on fine searching near the better solutions that have been found.

[0096] In the exploration phase, the population position is updated by random or heuristic methods; in the development phase, the population position is updated by gradient descent or local search, and the fitness values ​​of the updated individuals are calculated at different search stages, and the global optimal population position is selected. When the global optimal population position reaches the preset maximum number of iterations, the search process is stopped, and the current optimal Lagrange multiplier and constant are output as the optimal parameters of the SVM, thereby obtaining a fault diagnosis model.

[0097] Through the above method, combined with feature clusters, acceleration functions and dynamic search strategies, the optimal SVM parameter combination can be found efficiently, improving the classification performance and generalization ability of the model; at the same time, by optimizing SVM parameters and training an accurate fault diagnosis model, the fault type can be accurately classified and diagnosed, improving the stability and reliability of fault diagnosis. The use of intelligent fault diagnosis methods can reduce dependence on manual experience, reduce the cost and time of fault diagnosis, and combine optimization strategies such as feature clusters and acceleration functions to achieve rapid identification and diagnosis of fault types, improving the real-time and accuracy of fault diagnosis.

[0098] Optionally, in some embodiments, the fault diagnosis model is expressed as:

[0099]

[0100] In formula (1), f(x) is the fault diagnosis model, K(x i ,x) is the kernel function of the support vector machine, y iis the label of the i-th sample, a i ' is the Lagrange multiplier, b' is the constant, and P is the total number of samples.

[0101] Among them, the fault diagnosis model is obtained by solving the following formula:

[0102]

[0103] In formula (2), L is the Lagrangian function, ω is the normal vector of the hyperplane; b is a constant term, and the penalty function C and slack variable ξ are used to improve the performance of SVM and increase the fault tolerance of SVM; α i ≥0,μ i ≥0 is the Lagrange multiplier; ξ i ≥0; C is a constant greater than 0. The value of the penalty function C is positively correlated with the penalty degree of the function. The larger the penalty parameter, the smaller the value of the slack variable is required, which mainly plays a trade-off role. The set is represented by A={(x i ,y i )|i=1,,2,…,n},xi∈Rn,y i ∈{+1,-1}.

[0104] Optionally, in some embodiments, using the fault diagnosis model to detect current vehicle data and seat data of the vehicle to determine whether the magnetorheological seat fault diagnosis is a fault includes:

[0105] Inputting the current vehicle data and seat data of the vehicle into the fault diagnosis model to obtain a loss function value;

[0106] Comparing the loss function value with a preset fault threshold;

[0107] If the loss function value is greater than or equal to a preset fault threshold, determining that the magnetorheological seat is faulty;

[0108] If the loss function value is less than a preset fault threshold, it is determined that the magnetorheological seat is normal.

[0109] Exemplarily, the loss function value reflects the difference between the current state and the normal state learned by the model. When the loss function value exceeds the set fault threshold, it indicates that the difference between the current state and the normal state learned by the model is too large, and the seat is determined to be faulty; when the loss function value does not exceed the set fault threshold, it indicates that the difference between the current state and the normal state learned by the model is too large or too small, and the seat is determined to be normal.

[0110] Through the above method, the fault status of the magnetorheological seat can be detected in real time, improving the timeliness and accuracy of fault detection. The fault diagnosis model based on machine learning and statistical methods can intelligently judge the seat status and reduce the possibility of manual intervention and misjudgment. This solution can be easily extended to fault detection of other vehicles and components to improve the reliability and safety of the entire vehicle. In addition, by timely detecting faults and outputting relevant information, maintenance personnel can be guided to quickly locate and repair problems, thereby reducing maintenance costs and time.

[0111] See also Figure 3 , is a schematic diagram of the principle flow of a magnetorheological seat fault diagnosis method in an embodiment of the present application, which is described in detail as follows:

[0112] Step 1: collect vehicle data and seat data fault information under different working conditions, such as turning, straight driving, bumping, uphill and other working conditions, and perform preprocessing to obtain the processed M vehicle data sets A = {A D |D=1,2,…M}, where M is the number of vehicles, A D Represents the data of the Dth vehicle, including but not limited to GPS time, vehicle geographic location, vehicle speed, steering angle or throttle opening and closing, etc. The magnetorheological seat dataset collects seat data through sensors on the seat, including but not limited to pressure sensors, displacement sensors or magnetic field strength sensors.

[0113] Step 2: The collected data of each vehicle is divided into a faulty seat data set A′ and a non-faulty seat data set A″ according to the seat diagnosis standard.

[0114] Step 3: preprocess the collected data set, including data cleaning, feature value extraction, etc., as described above, which will not be repeated here.

[0115] Step 4, feature extraction and selection, for time domain data, for example, the time series of vibration signals, extract statistical features such as mean, variance, peak, skewness, etc. For example, the peak of the vibration signal may be related to abnormal impact of the equipment. For frequency domain data, for example, the time domain data is converted to the frequency domain through Fourier transform, and features such as main frequency, frequency band energy, and frequency center of gravity are extracted. In fault diagnosis, different fault types may lead to changes in specific frequency components. For multivariate data, features such as correlation and covariance between variables can be calculated to reflect the relationship between different parameters.

[0116] Specifically, the principal component analysis method is used to extract the feature vector F = {f D |D=1,2,…,M}, where f D represents the feature vector of the D-th vehicle, and represents the n-th dimension data of the D-th vehicle, where n represents the number of data types collected for each vehicle. The specific steps of feature selection are as follows:

[0117] Step 4.1: convert the original data f D Standardization is performed to eliminate the influence of dimension and value on the analysis results. The standardized data matrix is ​​recorded as Among them, N is the number of data types and T is the total time.

[0118] Step 4.2, calculate the correlation coefficient matrix of the standardized data Among them, r ij Represents the correlation coefficient between the data in the i-th column and the j-th column, calculated according to formula (3):

[0119]

[0120] Among them, k is the current time, T is the total time, x ki is the data matrix of the i-th column at time k, x kj is the data matrix of the jth column at time k, is the mean of the data matrix in column i, is the mean of the j-th column of the data matrix, and there exists r ij =r ji and r ii =1.

[0121] Step 4.3, find the characteristic root λ1≥λ2≥…≥λ of the characteristic equation of R det(R-λE)=0 N >0, where R is the correlation coefficient matrix of formula (3), E is the unit matrix, and λ N is the Nth characteristic root.

[0122] Step 4.4, determine the number of principal components m: α is the cumulative contribution rate, generally 80%, λ b is the bth characteristic root, and N is the number of data types.

[0123] Step 4.5, calculate m corresponding unit eigenvectors and principal components.

[0124] Step 4.6, data conversion: convert the original data into a new coordinate system consisting of the first m principal components to obtain a new test sample of the Dth vehicle after dimensionality reduction And the new eigenvector F′={f′ D |D=1,2,…,M}.

[0125] Step 5: Use an improved clustering algorithm (such as K-means clustering) to transform F′={f′ D |D=1,2,…,M} are clustered into different categories.

[0126] (1) Initialization: Random Q initial cluster center coordinates

[0127]

[0128] in, represents the qth cluster center, Represents the qth cluster center The coordinate value of the Nth dimension.

[0129] (2) Calculation: Calculate the distance of each data sample

[0130] For each data point in the data set, calculate its distance from each cluster center and assign it to the cluster center closest to it. For example, use Euclidean distance as the distance metric and calculate it according to formula (5):

[0131]

[0132] in, is the sample f′ to be tested of the D-th vehicle series D The n-th eigenvalue in is the nth cluster center The n-th dimension coordinate value of .

[0133] (3) Allocation: According to the new sample to be tested f′ D The distance to each cluster center is the distance between the new sample f′ D Assign the M vehicles to the nearest cluster, thereby assigning the test samples to the nearest cluster, obtaining Q clusters, and obtaining the data feature set of the vehicles in each cluster represents the data feature vector of the Jth vehicle in the qth cluster, and represents the n-th dimension feature of the J-th vehicle in the q-th cluster, S q represents the number of vehicles in the qth cluster.

[0134] (4) Update: Recalculate the center of each cluster using formula (6) And assign it to

[0135]

[0136] (5) Iteration: Repeat the assignment and update steps until the cluster center remains unchanged, and output the final cluster center, so that data with similar data features are clustered into one category, and obtain

[0137] Step 6: Build a fault diagnosis model: transform the data processed in step 5 into As input, a support vector machine (SVM) based on intelligent optimization algorithm is used to build a fault diagnosis model, such as Figure 3 As shown, the details are as follows:

[0138] Step 6.1: Calculate the decision function by formula (7) to determine whether a fault occurs. If If the fault occurs, it is determined to be normal.

[0139]

[0140] in, is the kernel function of SVM, is the data feature vector representing the J-th vehicle in the q-th cluster, is the n-th dimension feature of the J-th vehicle in the q-th cluster, p is the data type, and y n is the label of the nth dimension, with a value of 1 or -1, α n is the Lagrange multiplier of support vector machine, b is a constant, and sgn is the sign function.

[0141] Step 6.2, initialize the parameters of the mathematical optimizer acceleration function. Min and Max are the minimum and maximum values ​​of the acceleration function, which are 0.2 and 1 respectively. Iter is the number of iterations, and the maximum number of iterations is iter. max , and initialize the current i-th search stage by equation (8):

[0142] MOA(i)=Min+iter*(Max-Min) / iter max (8)

[0143] Step 6.3, initialize the population number npop and the population position X = [α1α2,…,α n ,b], and randomly generate r1∈[0,1];

[0144] If r1>MOA(iter) value, proceed to step 6.4 exploration phase; otherwise, proceed to step 6.5 development phase.

[0145] Step 6.4, exploration phase: randomly generate r2∈[0,1], and the position update is calculated according to formula (9):

[0146]

[0147] Among them, μ is the control parameter for adjusting the search process, X i,j (iter+1) represents the solution in iter+1 iterations, best(X j ) is the current best position, ε is the minimum value to avoid the denominator being 0, UB j and LB jare the search upper and lower limits, MOP is the coefficient, calculated according to formula (10):

[0148]

[0149] Among them, η is a sensitive parameter that defines the development accuracy of the iterative process, and MOP(i) represents the coefficient of the i-th time.

[0150] Step 6.5, development phase, randomly generate r3∈[0,1], and the position update is calculated according to formula (11):

[0151]

[0152] Among them, μ is the control parameter for adjusting the search process, X i,j (iter+1) represents the solution in iter+1 iterations, best(X j ) is the current best position, ε is the minimum value to avoid the denominator being 0, UB j and LB j are the search limits, and MOP is the coefficient.

[0153] Step 6.6, calculate the fitness value and record the optimal solution.

[0154] Step 6.7, determine whether i meets the end condition. If iter <iter max , repeat steps 6.2-6.7, otherwise, output the optimal parameters of the SVM model, that is, by obtaining a i ' is the Lagrange multiplier, b' is the constant, and the optimal detection model is established.

[0155] Compared with the prior art, this application has the following technical effects:

[0156] First, by building a machine learning model, it is possible to effectively integrate multiple vehicle data, utilize the correlation between data, fully explore the potential information of multi-source data, and improve the comprehensiveness and accuracy of seat fault diagnosis.

[0157] Second, through machine learning methods, it is possible to diagnose seat failures under different operating conditions. When vehicle operation changes over time, the machine learning model can adapt to dynamic changes by retraining by updating the training data set to maintain the effectiveness of fault diagnosis.

[0158] Third, through training with a large amount of labeled data, the complex mapping relationship between the normal state and fault state of the seat is learned, the information is mapped to a high-dimensional feature space, and the optimal model parameters are selected through an intelligent optimization algorithm to improve the accuracy of fault diagnosis. At the same time, compared with traditional fault diagnosis, the diagnosis time is greatly shortened, the deterioration of faults is avoided, and the efficiency and quality of fault resolution are improved.

[0159] Fourth, by providing early warning of failures, users can better plan equipment maintenance time and resources. Users no longer have to passively respond to failures and perform emergency repairs. They can rationally arrange maintenance personnel, reduce the inconvenience caused by equipment failures, reduce the impact on users' daily work and life, and improve user satisfaction and trust.

[0160] See also Figure 4 , is a schematic diagram of the structure of a magnetorheological seat fault diagnosis system in an embodiment of the present application, comprising:

[0161] An acquisition module 401 is used to acquire a first data set, wherein the first data set includes vehicle data and seat data corresponding to the vehicle under various road conditions;

[0162] A feature extraction module 402 is used to extract features from each data in the first data set to obtain frequency domain data and time domain data;

[0163] The component analysis module 403 is used to perform principal component analysis on the frequency domain data and the time domain data to determine variable features associated with different fault types of the magnetorheological seat, wherein the variable features include the vehicle speed, steering wheel angle, steering wheel speed, throttle opening and closing, brake pedal opening and closing, vehicle height, and at least one of the pressure, displacement, and magnetic field strength of the seat;

[0164] A clustering module 404 is used to perform clustering processing on the variable features associated with each fault type, and determine a feature cluster formed by the variable features associated with different fault types under each road condition;

[0165] A model building module 405 is used to input the feature clusters associated with different fault types under each road condition into a preset support vector machine for training to build a fault diagnosis model;

[0166] The fault diagnosis module 406 uses the fault diagnosis model to detect the current vehicle data and seat data of the vehicle to determine whether the magnetorheological seat fault diagnosis is a fault.

[0167] Among them, the acquisition module 401 is used to execute the aforementioned step 101, the feature extraction module 402 is used to execute the aforementioned step 102, the component analysis module 403 is used to execute the aforementioned step 103, the clustering module 404 is used to execute the aforementioned step 104, the model construction module 405 is used to execute the aforementioned step 105, and the fault diagnosis module 406 is used to execute the aforementioned step 106. The above modules correspond to the steps of the magnetorheological seat fault diagnosis method, and their execution process corresponds to the corresponding steps, which will not be described in detail here.

[0168] The magnetorheological seat fault diagnosis system provided by the embodiment of the present disclosure is adopted, by obtaining a first data set, the first data set includes vehicle data and seat data corresponding to the vehicle under various road conditions, determining data diversity based on multi-source data, performing feature extraction on each data in the first data set, and obtaining frequency domain data and time domain data; performing principal component analysis on the frequency domain data and the time domain data to determine variable features associated with the magnetorheological seat in different fault types, covering associated potential features, which is conducive to subsequent accurate judgment; performing clustering processing on the variable features associated with each fault type to determine different fault types under each road condition The feature cluster formed by the associated variable features ensures the integrity and diversity of the features; the feature cluster associated with different fault types under each road condition is input into a preset support vector machine for training to construct a fault diagnosis model; the fault diagnosis model is used to perform detection to determine whether the magnetorheological seat fault diagnosis is a fault, so that the fault can be identified even in complex road conditions, thereby improving the efficiency and accuracy of diagnosis; by accurately diagnosing the fault of the magnetorheological seat, it helps to prevent potential safety hazards and reduce the risk of traffic accidents caused by seat failures; at the same time, it also improves the reliability and service life of the seat and reduces maintenance costs.

[0169] In another embodiment, the present application also provides a vehicle, which includes the magnetorheological seat fault diagnosis system provided by any of the above embodiments.

[0170] For the specific definition of the vehicle, please refer to the definition of the magnetorheological seat fault diagnosis method mentioned above, which will not be repeated here. Each module in the above-mentioned vehicle can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0171] An embodiment of the present disclosure further provides an electronic device, including: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the above method.

[0172] Figure 5 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 5 The computer system 500 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0173] like Figure 5As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 to the random access memory (RAM) 503, such as executing the method in the above embodiment. In RAM503, various programs and data required for system operation are also stored. CPU501, ROM502 and RAM503 are connected to each other through a bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0174] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0175] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. Technicians can clearly understand that for the convenience and simplicity of description, the specific working process of the systems, devices and units described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0176] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A magnetorheological seat fault diagnosis method, characterized in that: include: Acquire a first data set, wherein the first data set includes vehicle data and seat data corresponding to the vehicle under various road conditions; Extracting features from each data in the first data set to obtain frequency domain data and time domain data; Performing principal component analysis on the frequency domain data and the time domain data to determine variable features associated with different fault types of the magnetorheological seat, wherein the variable features include the vehicle speed, steering wheel angle, steering wheel speed, throttle opening and closing, brake pedal opening and closing, vehicle height, and at least one of the pressure, displacement, and magnetic field strength of the seat; Performing clustering processing on the variable features associated with each fault type to determine a feature cluster formed by the variable features associated with different fault types under each road condition; Input the feature clusters associated with different fault types under each road condition into a preset support vector machine for training to construct a fault diagnosis model; The fault diagnosis model is used to detect the current vehicle data and seat data of the vehicle to determine whether the magnetorheological seat fault diagnosis is a fault.

2. The method according to claim 1, characterized in that: Before extracting features from each data in the first data set, the method further includes: The first data set is preprocessed to obtain a second data set, and the second data set is used as the first data set to be extracted and processed, wherein the preprocessing includes at least one of noise processing, missing value processing, outlier processing, data integration processing, and data discretization processing.

3. The method according to claim 2, characterized in that Before preprocessing the first data set, the method further includes: The first data set is divided into a first data subset representing the seat fault and a second data subset representing the seat fault-free according to the magnetorheological seat fault, and the first data subset and the second data subset are used as the first data set to be preprocessed.

4. The method according to claim 1, characterized in that Extracting features from each data in the first data set to obtain frequency domain data and time domain data includes: Feature extraction is performed on the vehicle data and seat data in the first data set based on the time domain and frequency domain dimensions respectively, to obtain time domain data containing time domain features and frequency domain data containing frequency domain features, the time domain features include at least one of mean, variance, peak, and skewness, the time domain features include at least one of main frequency, frequency band energy, and frequency centroid, and the variable features are partial data determined in the first data set.

5. The method according to claim 1, characterized in that Performing principal component analysis on the frequency domain data and the time domain data to determine variable characteristics associated with different fault types of the magnetorheological seat includes: The frequency domain data and the time domain data are respectively standardized and converted into different feature matrices; Calculating the covariance matrix of each of the characteristic matrices, and calculating the correlation coefficient between each type of characteristic vector and different faults according to the covariance matrix; Calculating the characteristic roots in the covariance matrix according to the correlation coefficient, and calculating the principal components of each type of characteristic vector according to the number of the characteristic roots and the preset contribution rate; Based on the principal components corresponding to each type of the characteristic vectors, variable characteristics associated with different fault types of the magnetorheological seat are determined.

6. The method according to claim 1, characterized in that Clustering the variable features associated with each fault type to determine a feature cluster formed by the variable features associated with different fault types under each road condition, including: Selecting a plurality of cluster centers, and assigning each of the variable features associated with each fault type under different road conditions to the nearest cluster center among the plurality of cluster centers; The allocated cluster centers are clustered again until a preset number of clustering times is reached, so as to obtain a feature cluster formed by the variable features associated with different fault types under each road condition.

7. The method according to claim 1, characterized in that The feature clusters associated with different fault types under each road condition are input into a preset support vector machine for training to construct a fault diagnosis model, including: Presetting a value range of the support vector machine; Initialize the mathematical optimizer acceleration function, determine the current number of iterations, the maximum number of iterations and the acceleration function value; Randomly generating an initial population and the initial population position in each of the feature clusters; Using each of the feature clusters to train the support vector machine, calculate the current fitness value, and select the current best fitness value to determine the current optimal population position; According to the comparison result between the initial population and the acceleration function value, determining whether the search phase starts from the exploration phase or the development phase, updating the population position in different search phases, and calculating the fitness values ​​of all individuals to find the global optimal population position; If the global optimal population position reaches the maximum number of iterations, the current Lagrange multiplier and constant are output as optimal parameters to obtain a fault diagnosis model.

8. The method according to any one of claims 1 to 7, characterized in that Using the fault diagnosis model to detect the current vehicle data and seat data of the vehicle to determine whether the magnetorheological seat fault diagnosis is a fault, including: Inputting the current vehicle data and seat data of the vehicle into the fault diagnosis model to obtain a loss function value; Comparing the loss function value with a preset fault threshold; If the loss function value is greater than or equal to a preset fault threshold, determining that the magnetorheological seat is faulty; If the loss function value is less than a preset fault threshold, it is determined that the magnetorheological seat is normal.

9. A magnetorheological seat fault diagnosis system, characterized in that: include: An acquisition module, configured to acquire a first data set, wherein the first data set includes vehicle data and seat data corresponding to the vehicle under various road conditions; A feature extraction module, used to extract features from each data in the first data set to obtain frequency domain data and time domain data; a component analysis module, configured to perform principal component analysis on the frequency domain data and the time domain data to determine variable features associated with different fault types of the magnetorheological seat, wherein the variable features include vehicle speed, steering wheel angle, steering wheel speed, throttle opening and closing, brake pedal opening and closing, vehicle height, and at least one of the pressure, displacement, and magnetic field strength of the seat; A clustering module, used for clustering the variable features associated with each fault type, and determining a feature cluster formed by the variable features associated with different fault types under each road condition; A model building module, used for inputting the feature clusters associated with different fault types under each road condition into a preset support vector machine for training to build a fault diagnosis model; The fault diagnosis module uses the fault diagnosis model to detect the current vehicle data and seat data of the vehicle to determine whether the magnetorheological seat fault diagnosis is a fault.

10. A vehicle, characterized in that: Including the magnetorheological seat fault diagnosis system as described in claim 9.

Images