Vehicle fault analysis method, device, equipment and medium

Abstract

The invention discloses a vehicle fault analysis method and device, equipment and a medium, and relates to the technical field of vehicle fault diagnosis, and the method comprises the steps: obtaining vehicle driving fault information, obtaining feature data through an improved grey wolf algorithm model according to the vehicle driving fault information, obtaining a corresponding fault type through a classifier model according to the feature data, and carrying out the fault diagnosis through the classifier model. And according to the fault type, a fault report is generated, accurate fault diagnosis is realized, and the accuracy and efficiency of fault analysis are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle fault diagnosis, and in particular to a vehicle fault analysis method, device, equipment and medium. Background Art

[0002] With the rapid development of science and technology and the improvement of global environmental awareness, the new energy vehicle industry has ushered in unprecedented growth opportunities. This is not only reflected in the rapid expansion of the market size, but also reflected in the increasing acceptance and willingness of consumers to purchase new energy vehicles. With its clean and energy-saving characteristics, new energy vehicles have become an important development direction for the future automotive industry. The promotion of government policies, technological innovation and the continuous improvement of infrastructure have jointly promoted the prosperity of this market. However, with the surge in the number of vehicles in use, the problem of new energy vehicle failure has also become prominent, which has put forward higher requirements for fault diagnosis and maintenance technology, because these problems not only affect the user's daily travel experience, but may also endanger driving safety.

[0003] At present, fault diagnosis technology for new energy vehicles mainly includes traditional methods and methods based on modern intelligent algorithms. Traditional methods rely on fault diagnosis instruments and the experience of maintenance personnel to judge faults through observation, hearing, touch and other means. This method is relatively limited when facing the complex electronic control system and power structure of new energy vehicles, and it is difficult to cope with massive nonlinear, non-convex, and noisy fault feature data. Advanced algorithms based on artificial neural networks, such as using data collection and analysis to extract fault features and identify and classify them, have made progress compared to traditional methods.

[0004] Although the existing fault diagnosis technology has made some progress in the fault diagnosis of new energy vehicles, it still has obvious shortcomings. First, traditional fault diagnosis relies too much on manual experience, lacks accuracy and efficiency, and is prone to misjudgment, especially when dealing with complex faults. Secondly, although the application of intelligent algorithms has improved the intelligence level of diagnosis, the search and optimization capabilities of existing algorithms are still limited in the face of the complexity and noise interference of fault feature data, and they are often unable to quickly and accurately extract key fault features, resulting in limited accuracy and real-time performance of diagnostic results. In addition, the algorithm parameters are highly sensitive, and fine-tuning of the algorithm parameters requires professional skills, and there are also challenges in choosing a balance between global and local searches. Therefore, the market urgently needs a more efficient, accurate and adaptable fault analysis method to meet the rapidly growing market demand for new energy vehicles and users' expectations for safe and reliable travel. Summary of the invention

[0005] The main purpose of this application is to provide a vehicle fault analysis method, device, equipment and medium, aiming to solve the technical problem of how to improve the accuracy and efficiency of vehicle fault analysis.

[0006] To achieve the above objectives, the present application proposes a vehicle fault analysis method, the method comprising:

[0007] Obtain vehicle driving fault information;

[0008] According to the vehicle running fault information, characteristic data is obtained through an improved grey wolf algorithm model;

[0009] Obtaining a corresponding fault type through a classifier model according to the feature data;

[0010] A fault report is generated according to the fault type.

[0011] Optionally, before the step of obtaining vehicle driving fault information, the step includes:

[0012] Obtain original vehicle driving fault information;

[0013] De-noising the original vehicle travel fault information according to wavelet transform to obtain de-noised fault information;

[0014] The de-noised fault information is subjected to time-frequency analysis and normalization processing to obtain the vehicle driving fault information.

[0015] Optionally, the step of optimizing the initial improved grey wolf algorithm model to obtain a preset improved grey wolf algorithm model includes:

[0016] A gray wolf population is randomly generated, and the positions, speeds, and algorithm parameters of the gray wolves in the gray wolf population are initialized, where each gray wolf represents a feature data;

[0017] The fitness of the gray wolf is calculated according to the position, speed and algorithm parameters of the gray wolf;

[0018] Determining the level of the gray wolf according to the fitness of the gray wolf;

[0019] Set the number of iterations and calculate the historical optimal value of the gray wolf;

[0020] By comparing the fitness of the gray wolves in each iteration, a global optimal value of the gray wolf population is obtained;

[0021] According to the historical optimal value and the global optimal value, updating the position and level of the gray wolf;

[0022] Determine whether the position and level of the gray wolf meet a preset range, and if not, perform boundary condition processing on the gray wolf;

[0023] If the number of iterations is reached, the improved grey wolf algorithm model is output.

[0024] Optionally, before the step of obtaining characteristic data according to the vehicle running fault information through an improved grey wolf algorithm model, the step further includes:

[0025] Performing centralization and whitening processing on the vehicle driving fault information to obtain processed fault information;

[0026] The processed fault information is solved for independent components through a preset mathematical model to obtain a column vector to be solved;

[0027] The relevant fault features are obtained according to the column vector to be determined.

[0028] Optionally, the step of obtaining characteristic data according to the vehicle running fault information through an improved grey wolf algorithm model includes:

[0029] Inputting the relevant fault features into the improved gray wolf algorithm model and updating the gray wolf position and speed in parallel to obtain the updated position and speed of the gray wolf;

[0030] Obtaining an updated fitness according to the updated position and speed;

[0031] The characteristic data is obtained by comparing the updated fitness.

[0032] Optionally, before the step of obtaining the corresponding fault type according to the feature data by using a preset classifier model, the step includes:

[0033] Obtain training set feature information and establish an initial classifier model;

[0034] The initial classifier model is trained according to the training set feature information to obtain the classifier model.

[0035] Optionally, the step of obtaining a corresponding fault type according to the feature data by using a preset classifier model includes:

[0036] Inputting the feature data into the classifier model to obtain posterior probabilities of multiple fault types;

[0037] By comparing the multiple posterior probabilities, the highest posterior probability is obtained;

[0038] According to the highest a posteriori probability, the corresponding fault type is obtained.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle fault analysis device, the vehicle fault analysis device comprising:

[0040] An acquisition module, used to acquire vehicle driving fault information;

[0041] An acquisition module, used to obtain characteristic data according to the vehicle running fault information through an improved grey wolf algorithm model;

[0042] A classification module, used to obtain a corresponding fault type through a classifier model according to the feature data;

[0043] The result module is used to generate a fault report according to the fault type.

[0044] In addition, to achieve the above-mentioned purpose, the present application also proposes a medium, which is a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the vehicle fault analysis method described above are implemented.

[0045] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the vehicle fault analysis method described above are implemented.

[0046] The present application obtains vehicle driving fault information, obtains feature data based on the vehicle driving fault information through an improved grey wolf algorithm model, obtains the corresponding fault type based on the feature data through a classifier model, generates a fault report based on the fault type, realizes accurate fault diagnosis, and improves the accuracy and efficiency of fault analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] Figure 1 This is a flow chart of the first embodiment of the vehicle fault analysis method of the present application;

[0049] Figure 2 This is a flow chart of a second embodiment of the vehicle fault analysis method of the present application;

[0050] Figure 3 This is a schematic diagram of the module structure of the vehicle fault analysis device according to an embodiment of the present application;

[0051] Figure 4 A schematic diagram of the device structure of the hardware operating environment involved in the vehicle fault analysis method in the embodiment of the present application;

[0052] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solution of the embodiment of the present application is: obtain vehicle driving fault information, obtain feature data based on the vehicle driving fault information through an improved gray wolf algorithm model, obtain the corresponding fault type based on the feature data through a classifier model, and generate a fault report based on the fault type.

[0056] Based on this, the present application embodiment provides a vehicle fault analysis method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle fault analysis method of the present application.

[0057] In this embodiment, the vehicle fault analysis method includes steps S10 to S40:

[0058] Step S10, obtaining vehicle driving fault information.

[0059] It should be noted that the fault data of new energy vehicles is collected through the data acquisition unit, and the running fault information of new energy vehicles is collected to provide a data basis for fault detection.

[0060] Furthermore, before obtaining the vehicle driving fault information, the original vehicle driving fault information is obtained, and the original vehicle driving fault information is denoised according to the wavelet transform to obtain the fault information data after denoising. It needs to go through a strict preprocessing stage, including denoising, filtering, signal smoothing and other operations to eliminate environmental interference and accidental errors and ensure data quality. For example, the use of wavelet transform or frequency domain filtering technology can effectively separate the noise components in the signal and highlight the true reflection of the equipment status. In addition, the fault information after denoising is subjected to time-frequency analysis and normalization processing to obtain the vehicle driving fault information. The data is normalized, such as normalization or standardization, to ensure that the data collected by different sensors are comparable on a unified scale, which is convenient for subsequent analysis.

[0061] Step S20, obtaining characteristic data through an improved grey wolf algorithm model according to the vehicle running fault information.

[0062] It should be noted that the core part of the improved gray wolf optimization algorithm begins to play a role. The algorithm simulates the cooperation and competition mechanism of gray wolf packs in nature, creates a gray wolf population through the initialization module, and each gray wolf represents a feature subset. The algorithm continuously adjusts the position of the gray wolf (i.e., feature weight) through global search and local search strategies, and uses the fitness evaluation module to evaluate the contribution of each feature subset to fault diagnosis. In this process, the population diversity is increased by introducing mutation and crossover operations to avoid the algorithm from falling into the local optimal solution, ensuring the globality and efficiency of the search process. In addition, the algorithm also implements parallel computing, supports the simultaneous iterative update of multiple gray wolf populations through a distributed system, and significantly improves the computing efficiency. During the iteration process, the information synchronization mechanism ensures the stability of the algorithm, and the convergence factor adjustment module dynamically adjusts the search intensity of the algorithm, balancing the contradiction between exploration and development, so that the algorithm can converge to the optimal solution of the fault feature faster.

[0063] Furthermore, before obtaining the characteristic data, the vehicle driving fault information is first subjected to centralization and whitening processing to obtain the processed fault information. The data x is centered and the average value is subtracted from the original data. The mean of x is set to 0, and then the covariance matrix of the data is converted into a unit matrix for whitening to reduce the redundancy and correlation of the data. The specific whitening formula is:

[0064]

[0065] in, represents the whitened vector, E represents Covariance matrix, d i Represents the eigenvalue.

[0066] Furthermore, the processed fault information is solved for independent components through a preset mathematical model to obtain the column vector to be solved. The ICA mathematical model is established and expressed as:

[0067] X(t)=AS(t)M+E

[0068] Among them, X(t) is a column vector consisting of m observable known data, S(t) represents the column vector to be determined consisting of n unknown data, E represents the residual matrix, M matrix is ​​used for filtering, and A represents the mixing matrix.

[0069] Furthermore, the relevant fault features are obtained according to the column vector to be determined. Let W = A -1 , by solving the inverse W of the mixing matrix, we can get the column vector S(t) to be solved. The iterative formula of W is:

[0070]

[0071] Among them, s is the gradient parameter, and the final relevant fault features are obtained through independent component analysis. The relevant fault features are passed through the improved grey wolf algorithm model to obtain feature data.

[0072] Furthermore, the construction of the improved gray wolf algorithm randomly generates a gray wolf population, initializes the position, speed and algorithm parameters of the gray wolves in the gray wolf population, where each gray wolf represents a feature data. The fitness of the gray wolf is calculated according to the position, speed and algorithm parameters of the gray wolf, and then the level of the gray wolf is determined according to the fitness of the gray wolf. The level of the gray wolf includes the leader α wolf, the auxiliary leader β wolf, the follower δ wolf and the bottom member ω wolf. The number of iterations is set to calculate the historical optimal value of the gray wolf; by comparing the fitness of the gray wolf in each iteration, the global optimal value of the gray wolf population is obtained; according to the historical optimal value and the global optimal value, the position and speed of the gray wolf are updated. The position of each gray wolf is updated by simulating the hunting action of the gray wolf to surround, chase and attack the prey. In the hunting action, the α wolf, the β wolf and the δ wolf guide the search direction, and the ω wolf follows the search, thereby updating the level and position of the gray wolf. It is judged whether the position and level of the gray wolf meet the preset range. If not, the gray wolf is subjected to boundary condition processing; if the number of iterations is reached, the improved gray wolf algorithm model is output.

[0073] Furthermore, the improved gray wolf algorithm determines the characteristics by simulating the gray wolf's search for prey. The global search simulates the hunting behavior of the wolf pack in the entire solution space, and the local search is achieved by simulating the individual wolves in the wolf pack to narrow the search range and improve the search accuracy in the potential better solution area. The inertia weight ω reflects the gray wolf's ability to inherit the speed of movement in the search space. The global search and local search capabilities of the gray wolf algorithm are balanced by the linear decrease of the inertia weight value. As the iteration proceeds, the inertia weight decreases linearly. The linear decrease weight formula is:

[0074]

[0075] where ω start represents the initial inertia weight, ω end represents the inertia weight when the iteration reaches the maximum number, k represents the current number of iterations, T max Represents the maximum number of iterations, c1 and c2 represent learning factors. As the iterations proceed, the change in inertia weight from large to small reflects the conversion of the Gray Wolf Algorithm from global search to local search. Solutions with an error of 0.01 from the optimal solution of 1.0054 are considered to be close to the optimal solution, and solutions with an error of 0.8477 and less are considered to be trapped in the local optimal solution. The run is set to 100 times, and the inertia weights with different initial weights and the maximum number of iterations are compared to compare the performance of the Gray Wolf Algorithm. Some comparison results are shown in Table 1:

[0076]

[0078] In this embodiment, the inertia weight ω can be obtained through experiments start =0.9,ω end When =0.4, the algorithm can balance the capabilities of global search and local search.

[0079] Furthermore, the mutation operation introduces new mutations to increase population diversity by randomly changing individual dimensions to increase the mutation rate, and the crossover operation generates new individuals with different characteristics from the parent individuals through multi-point crossover and uniform crossover to increase the diversity of the gray wolf population. The improved gray wolf algorithm model simulates the hunting behavior of gray wolves, including surrounding prey, chasing prey and attacking prey to find the optimal solution. The formula for the gray wolf group to gradually approach and surround the prey is:

[0080]

[0081] Where t is the current iteration number, and is the coefficient vector, is the position vector of the prey, is the position vector of the gray wolf, A is a random vector in the interval [-a, a], where a decreases linearly during the iteration process. When A is in the interval [-1, 1], the next moment position of the search agent is anywhere between the current gray wolf and the prey. and The calculation formula is:

[0082]

[0083] Where a is the convergence factor, and as the number of iterations decreases linearly from 2 to 0, r1 and r2 follow a uniform distribution between [0,1]. The prey to be pursued is the other gray wolf individuals in the wolf pack. According to the position X of α, β and δ α , X β and X δ To update their respective positions, the update position formula is:

[0084]

[0085] Among them, D α , D β , D δ Respectively represent the distances between α, β and δ and other individuals, X α , X β , X δ Represent the current positions of α, β and δ respectively, C1, C2, C3 are random vectors, X is the current position of the gray wolf, γ α , γ β , γδ Represents the weight coefficient, and the position update formula of the gray wolf individual is:

[0086]

[0087] Among them, D α , D β , D δ Respectively represent the distances between α, β and δ and other individuals, X α , X β , X δ Represent the current positions of α, β and δ respectively, A1, A2, A3 are random vectors, X is the current position of the gray wolf, and t represents the number of iterations. The mutation operation changes the bit value of the individual code in the population with a small probability to generate new individuals, and increases the diversity of the population by introducing new gene combinations in the search process. The steps of the crossover operation are to randomly select two parent individuals, randomly select a crossover position, cut the two parent individuals at the crossover point, exchange the two cut segments, and combine them into a new offspring individual, and add the new offspring individual to the population. After the mutation and crossover operations, a parallel environment is built to provide computing resources through a distributed computing system to support the simultaneous update of multiple gray wolf positions, and then the gray wolf's position, speed and fitness information are assigned to different threads, and updated in parallel iterations. Each thread independently updates the position of the gray wolf it is responsible for according to the gray wolf's social level and search strategy. Different threads regularly synchronize the position, speed, and fitness of the gray wolves to ensure that the data is consistent and correct, so that the algorithm can search based on the latest data. After the positions of all gray wolves are updated, the results of each thread are merged, the fitness of different gray wolves is compared, and the gray wolf with the best fitness is selected as the current optimal solution, that is, the best feature data.

[0088] Step S30, obtaining the corresponding fault type through a classifier model according to the feature data.

[0089] It should be understood that the process of obtaining the corresponding fault type through the classifier model based on the feature data is a key step in fault diagnosis technology. Feature data refers to a representative and diagnostically meaningful data subset extracted from the original vehicle driving fault information after preprocessing and feature extraction. These data subsets can effectively describe and distinguish different fault modes. Classifier models, such as the improved Bayesian classifier, are algorithms based on statistical learning theory. They learn the association between historical fault cases and specific feature data through a training process. In practical applications, the classifier model first receives the feature data from the feature extraction module, and then analyzes and comprehensively evaluates these features based on the fault type-feature mapping relationship pre-established in the model. The evaluation process usually includes calculating the probability distribution of the feature data under each fault category, that is, the posterior probability, and then selecting the fault category with the highest probability as the prediction result.

[0090] Furthermore, before obtaining the fault type, the training set feature information is obtained and an initial classifier model is established. The training set feature information refers to a set of known data used to train the machine learning model, which contains a large amount of observation data of new energy vehicles in different states (including normal state and various fault states). Feature information can be data collected directly from vehicle sensors, such as physical quantities such as voltage, current, temperature, pressure, etc., or it can be advanced features extracted after data processing, such as frequency characteristics, pattern recognition indicators, etc. The initial classifier model refers to a fault classification model preliminarily established based on the training set feature information before optimization and adjustment. In this embodiment, an improved Bayesian classifier is used as a classification model. The model is based on the Bayesian theorem and performs fault classification by learning the probability relationship between fault features and fault categories. The initial classifier model is trained through a sample set to obtain a perfected classifier model. Then, the improved gray wolf optimization algorithm is based on this, and by continuously optimizing feature subsets and adjusting model parameters, the prediction ability of the classifier is gradually improved, and finally a more accurate fault identification effect is achieved.

[0091] For example, if the feature data shows that the vehicle's power battery temperature is abnormally high, the battery voltage is reduced, and the current is abnormally increased, the classifier model may determine that this matches the fault type of battery overheating or internal short circuit, because these features are highly consistent with the performance of this type of fault in historical data.

[0092] In order to ensure the accuracy of classification, the classifier model usually needs to be continuously learned and optimized, which includes using a large number of known fault samples for training, and adjusting model parameters through cross-validation, grid search and other techniques to achieve the best classification performance. In addition, for complex fault modes, an integrated learning strategy may be adopted, that is, combining the judgment results of multiple weak classifiers to improve the overall diagnostic accuracy and robustness.

[0093] Step S40: Generate a fault report according to the fault type.

[0094] It should be noted that the report header will clearly list the fault types determined by the classifier model analysis, such as "Electrical System Fault-Sensor Fault", directly indicating the system and specific components where the problem is located, so as to quickly focus on the maintenance focus. Based on the comparison between the historical fault case library and the current fault characteristics, the report will try to analyze the possible causes of the fault. For example, for sensor failure, it may be due to external environmental factors (such as extreme temperature and humidity) that cause the sensor performance to deteriorate, or the internal circuit aging and poor contact cause signal transmission errors. This part of the analysis will help prevent similar failures in the future. The report will also detail the possible chain reactions that the fault may have on other vehicle systems. For example, a sensor failure may cause unstable vehicle power output, affect driving safety, or affect the normal operation of the battery management system, thereby reducing the driving range. Assessing the scope of impact helps to make comprehensive fault isolation preparations before maintenance and prevent the spread of faults. Based on the fault type and cause analysis, the report will make specific repair or replacement suggestions. For example, for sensor failure, it may be recommended to replace the damaged sensor and calibrate the system to restore normal function. At the same time, it will also prompt the necessary inspection items to ensure that the fault is completely eliminated.

[0095] The present embodiment provides a vehicle fault analysis method, which obtains vehicle running fault information, obtains feature data based on the vehicle running fault information through an improved grey wolf algorithm model, obtains the corresponding fault type based on the feature data through a classifier model, generates a fault report based on the fault type, realizes accurate fault diagnosis, and improves the accuracy and efficiency of fault analysis.

[0096] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 2 The vehicle fault analysis method step S30 further includes steps S301 to S303:

[0097] Step S301, inputting feature data into a classifier model to obtain posterior probabilities of multiple fault types.

[0098] It should be noted that before inputting the feature data into the model, the output function of the improved Bayesian classifier is:

[0099]

[0100] where x n represents the fault characteristic information of new energy vehicles, P(x1,x2,...,xn) represents the probability value of the fault characteristic information, Ck It represents the probability of a certain fault characteristic value appearing in the fault analysis of new energy vehicles, P(x i |C k ) represents the probability of a certain new energy vehicle failure feature; P(C k ) represents the probability function of a certain fault characteristic value in the new energy vehicle failure. The posterior probability, that is, the probability of a certain fault type occurring under certain characteristic data conditions, is calculated based on the Bayesian theorem. The posterior probability of the Bayesian network data information fault category is P(X|Ck)×P(Ck).

[0101] Step S302, obtaining the highest posterior probability by comparing multiple posterior probabilities.

[0102] It is important to understand that when comparing multiple posterior probabilities, the algorithm calculates the probability value for each possible fault type separately. This process is actually a quantitative assessment of the rationality of the feature data under different fault assumptions. For example, if a feature data set has historically been highly correlated with battery failures, then in the current situation, the posterior probability of battery failure will be relatively high. The algorithm compares the posterior probabilities of all fault types and identifies the one with the highest probability as the final conclusion of the fault diagnosis. The highest posterior probability is selected as the basis for the fault type because it combines prior knowledge (the frequency of faults based on historical data) and new evidence (the feature data of the current vehicle) to find the most likely explanation in uncertainty. This approach is particularly effective when faced with complex failure modes. It can help maintenance personnel quickly identify the problem, avoid blind disassembly and inspection, and save time and cost. Set the probability value C k The largest fault type corresponds to the diagnosis of new energy vehicle fault category.

[0103] Step S303: Obtain the corresponding fault type according to the highest a posteriori probability.

[0104] It should be noted that after obtaining the processed feature data, the system will use a classifier model, such as an improved Bayesian classifier, to perform a probability assessment on each feature subset. The classifier will calculate the posterior probability of each fault type under the current feature data conditions, that is, the probability of the fault type occurring under the known feature data. The posterior probabilities of all possible fault types will be calculated one by one, and then by comparing these probability values, the fault type with the highest probability will be found as the final diagnosis result.

[0105] This embodiment inputs feature data into a classifier model to obtain a plurality of posterior probabilities of fault types, obtains the highest posterior probability by comparing the plurality of posterior probabilities, and obtains the corresponding fault type based on the highest posterior probability, thereby shortening the fault detection time and improving the fault judgment efficiency.

[0106] This application also provides a vehicle fault analysis device, please refer to Figure 3 , the device comprises:

[0107] An acquisition module 10 is used to acquire vehicle driving fault information;

[0108] An acquisition module 10 is used to obtain characteristic data according to the vehicle driving fault information through an improved grey wolf algorithm model;

[0109] The classification module 20 is used to obtain the corresponding fault type through the classifier model according to the feature data;

[0110] The result module 30 is used to generate a fault report according to the fault type.

[0111] The vehicle fault analysis device provided by the present application adopts the vehicle fault analysis method in the above embodiment, which can solve the technical problem of how to improve the accuracy and efficiency of vehicle fault analysis. Compared with the prior art, the beneficial effects of the vehicle fault analysis device provided by the present application are the same as the beneficial effects of the vehicle fault analysis method provided by the above embodiment, and the other technical features in the vehicle fault analysis device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0112] In one embodiment, the acquisition module 10 is also used to obtain original vehicle travel fault information; perform denoising on the original vehicle travel fault information according to wavelet transform to obtain denoised fault information; perform time-frequency analysis and normalization on the denoised fault information to obtain vehicle travel fault information.

[0113] In one embodiment, the acquisition module 10 is also used to randomly generate a gray wolf population, initialize the position, speed and algorithm parameters of the gray wolves in the gray wolf population, wherein each gray wolf represents a feature data; calculate the fitness of the gray wolf according to the position, speed and algorithm parameters of the gray wolf; determine the level of the gray wolf according to the fitness of the gray wolf; set the number of iterations, and calculate the historical optimal value of the gray wolf; obtain the global optimal value of the gray wolf population by comparing the fitness of the gray wolf in each iteration; update the position and level of the gray wolf according to the historical optimal value and the global optimal value; determine whether the position and level of the gray wolf meet the preset range, and if not, perform boundary condition processing on the gray wolf; if the number of iterations is reached, output the improved gray wolf algorithm model.

[0114] In one embodiment, the acquisition module 10 is also used to perform centralization and whitening processing on the vehicle driving fault information to obtain processed fault information; perform independent component solving on the processed fault information through a preset mathematical model to obtain a column vector to be solved; and obtain relevant fault characteristics based on the column vector to be solved.

[0115] In one embodiment, the acquisition module 10 is also used to input relevant fault characteristics into the improved gray wolf algorithm model to update the gray wolf position and speed in parallel to obtain the updated position and speed of the gray wolf; obtain the updated fitness based on the updated position and speed; and obtain characteristic data based on the comparison of the updated fitness.

[0116] In one embodiment, the classification module 20 is further used to obtain feature information of a training set and establish an initial classifier model; the initial classifier model is trained according to the feature information of the training set to obtain a preset classifier model.

[0117] In one embodiment, the classification module 20 is further used to input the feature data into a preset classifier model to obtain a plurality of posterior probabilities of fault types; obtain the highest posterior probability by comparing the plurality of posterior probabilities; and obtain the corresponding fault type according to the highest posterior probability.

[0118] The present application provides a vehicle fault analysis device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle fault analysis method in the above-mentioned embodiment one.

[0119] Reference below Figure 4 , which shows a schematic diagram of the structure of a vehicle fault analysis device suitable for implementing an embodiment of the present application. The vehicle fault analysis device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The vehicle fault analysis device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0120] like Figure 4As shown, the vehicle fault analysis device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the vehicle fault analysis device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the vehicle fault analysis device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a vehicle fault analysis device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0121] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0122] The vehicle fault analysis device provided by the present application adopts the vehicle fault analysis method in the above embodiment, which can solve the technical problem of how to improve the accuracy and efficiency of vehicle fault analysis. Compared with the prior art, the beneficial effects of the vehicle fault analysis device provided by the present application are the same as the beneficial effects of the vehicle fault analysis method provided by the above embodiment, and the other technical features in the vehicle fault analysis device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0123] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0124] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0125] The present application provides a computer-readable medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the vehicle fault analysis method in the above-mentioned embodiment.

[0126] The computer-readable medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0127] The computer-readable medium may be included in the vehicle fault analysis device; or may exist independently without being assembled into the vehicle fault analysis device.

[0128] The computer-readable medium carries one or more programs. When the one or more programs are executed by the vehicle fault analysis device, the vehicle fault analysis device can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0129] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0130] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0131] The readable medium provided by the present application is a computer-readable medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned vehicle fault analysis method, and can solve the technical problem of how to improve the accuracy and efficiency of vehicle fault analysis. Compared with the prior art, the beneficial effects of the computer-readable medium provided by the present application are the same as the beneficial effects of the vehicle fault analysis method provided by the above-mentioned embodiment, and will not be repeated here.

[0132] The present application also provides a computer program product, including a computer program, which implements the steps of the vehicle fault analysis method as described above when executed by a processor.

[0133] The computer program product provided by the present application can solve the technical problem of how to improve the accuracy and efficiency of vehicle fault analysis. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the vehicle fault analysis method provided by the above embodiment, which will not be repeated here.

[0134] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A vehicle fault analysis method, characterized in that: The method comprises: Obtain vehicle driving fault information; According to the vehicle running fault information, characteristic data is obtained through an improved grey wolf algorithm model; Obtaining a corresponding fault type through a classifier model according to the feature data; A fault report is generated according to the fault type.

2. The method according to claim 1, characterized in that Before the step of obtaining vehicle driving fault information, the method includes: Obtain original vehicle driving fault information; De-noising the original vehicle travel fault information according to wavelet transform to obtain de-noised fault information; The de-noised fault information is subjected to time-frequency analysis and normalization processing to obtain the vehicle driving fault information.

3. The method according to claim 1, characterized in that Before the step of obtaining characteristic data according to the vehicle running fault information through the improved grey wolf algorithm model, the method includes: A gray wolf population is randomly generated, and the positions, speeds, and algorithm parameters of the gray wolves in the gray wolf population are initialized, where each gray wolf represents a feature data; The fitness of the gray wolf is calculated according to the position, speed and algorithm parameters of the gray wolf; Determining the level of the gray wolf according to the fitness of the gray wolf; Set the number of iterations and calculate the historical optimal value of the gray wolf; By comparing the fitness of the gray wolves in each iteration, a global optimal value of the gray wolf population is obtained; According to the historical optimal value and the global optimal value, updating the position and level of the gray wolf; Determine whether the position and level of the gray wolf meet a preset range, and if not, perform boundary condition processing on the gray wolf; If the number of iterations is reached, the improved grey wolf algorithm model is output.

4. The method according to claim 1, characterized in that Before the step of obtaining characteristic data through the improved grey wolf algorithm model according to the vehicle running fault information, the method further includes: Performing centralization and whitening processing on the vehicle driving fault information to obtain processed fault information; The processed fault information is solved for independent components through a preset mathematical model to obtain a column vector to be solved; The relevant fault features are obtained according to the column vector to be determined.

5. The method according to any one of claims 1 to 4, characterized in that: The step of obtaining characteristic data according to the vehicle running fault information through an improved grey wolf algorithm model comprises: Inputting the relevant fault features into the improved gray wolf algorithm model and updating the gray wolf position and speed in parallel to obtain the updated position and speed of the gray wolf; Obtaining an updated fitness according to the updated position and speed; The characteristic data is obtained by comparing the updated fitness.

6. The method according to claim 1, characterized in that Before the step of obtaining the corresponding fault type according to the feature data through a classifier model, the method includes: Obtain training set feature information and establish an initial classifier model; The initial classifier model is trained according to the training set feature information to obtain the classifier model.

7. The method according to claim 6, characterized in that The step of obtaining the corresponding fault type through a classifier model according to the feature data includes: Inputting the feature data into the classifier model to obtain posterior probabilities of multiple fault types; By comparing the multiple posterior probabilities, the highest posterior probability is obtained; According to the highest a posteriori probability, the corresponding fault type is obtained.

8. A vehicle fault analysis device, characterized in that: The device comprises: An acquisition module, used to acquire vehicle driving fault information; An acquisition module, used to obtain characteristic data according to the vehicle running fault information through an improved grey wolf algorithm model; A classification module, used to obtain a corresponding fault type through a classifier model according to the feature data; The result module is used to generate a fault report according to the fault type.

9. A vehicle fault analysis device, characterized in that: The device comprises: a memory, a processor, and a vehicle fault analysis program stored in the memory and executable on the processor, wherein the vehicle fault analysis program is configured to implement the steps of the vehicle fault analysis method according to any one of claims 1 to 7.

10. A medium, characterized in that The medium stores a vehicle fault analysis program, which, when executed by a processor, implements the steps of the vehicle fault analysis method according to any one of claims 1 to 7.

Images