New energy automobile chassis fault intelligent diagnosis method and system based on knowledge graph

Abstract

The invention provides a new energy automobile chassis fault intelligent diagnosis method and system based on a knowledge graph, and relates to the field of data processing, and the method comprises the steps: determining an initial chassis monitoring scheme according to a three-dimensional model of a new energy automobile chassis, and installing a first chassis monitoring assembly on a physical model corresponding to the new energy automobile chassis; chassis state information of a physical model corresponding to a new energy automobile chassis in multiple fault modes is obtained through a first chassis monitoring assembly, an optimal chassis monitoring scheme is determined, and a chassis fault diagnosis knowledge graph is established; according to the optimal chassis monitoring scheme, a second chassis monitoring assembly is installed on the new energy automobile chassis, and real-time chassis state information of the new energy automobile chassis is obtained; according to the real-time chassis state information of the new energy automobile chassis and the chassis fault diagnosis knowledge graph, fault diagnosis information of the new energy automobile chassis is generated, and the method has the advantage that the accuracy of fault diagnosis of the new energy automobile chassis is improved.

Description

Technical Field

[0001] The present invention relates to the field of automobile chassis fault diagnosis, and in particular to a new energy automobile chassis fault intelligent diagnosis method and system based on a knowledge graph. Background Art

[0002] Chassis is one of the important components of a car. It supports and connects various components such as the body, engine, transmission system, suspension system, etc. Chassis component failure may cause many problems, such as unstable driving, difficult steering, weak braking, loose suspension, etc., and may even seriously affect driving safety. Therefore, chassis fault diagnosis is very necessary and important, and chassis fault diagnosis can improve driving safety; the chassis is an important supporting component in the driving process of the car. If the chassis fails or is damaged, it may cause vehicle instability, unsmooth driving, and even serious consequences such as brake failure and steering difficulty. Therefore, timely detection and diagnosis of chassis faults are of great significance to improving driving safety. The chassis components are interrelated. When one component fails, it may affect the normal operation of other components and even cause further damage. Timely diagnosis and repair of chassis faults can effectively avoid the expansion of faults and secondary damage; chassis failure may cause the vehicle's driving condition to deteriorate and wear to increase, which will affect the life of the car. If chassis faults are discovered and diagnosed in time, and appropriate repairs and maintenance are carried out, the long-term normal operation of the vehicle can be guaranteed and the service life of the car can be extended.

[0003] In the prior art, chassis fault diagnosis mainly determines whether a fault occurs by simply comparing the collected data with a preset threshold value. The fault alarm method has a high false alarm rate and a low safety factor.

[0004] Therefore, it is necessary to provide an intelligent diagnosis method and system for chassis faults of new energy vehicles based on knowledge graphs to improve the accuracy of chassis fault diagnosis of new energy vehicles. Summary of the invention

[0005] The present invention provides a new energy vehicle chassis fault intelligent diagnosis method based on a knowledge graph, comprising: obtaining a three-dimensional model of the new energy vehicle chassis; determining an initial chassis monitoring scheme according to the three-dimensional model of the new energy vehicle chassis, wherein the initial chassis monitoring scheme includes multiple initial chassis monitoring positions and a monitoring feature type corresponding to each initial chassis monitoring position; obtaining a physical model corresponding to the new energy vehicle chassis; according to the initial chassis monitoring scheme, installing a first chassis monitoring component on the physical model corresponding to the new energy vehicle chassis, wherein the first chassis monitoring component has multiple sensors installed according to the initial chassis monitoring scheme; obtaining chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes through the first chassis monitoring component; determining a chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes according to the physical model corresponding to the new energy vehicle chassis The method comprises the following steps: determining an optimal chassis monitoring scheme based on the test chassis status information under multiple fault modes, wherein the optimal chassis monitoring scheme includes multiple target chassis monitoring positions and the monitoring feature type corresponding to each target chassis monitoring position; establishing a chassis fault diagnosis knowledge graph based on the test chassis status information under multiple fault modes of the physical model corresponding to the new energy vehicle chassis; installing a second chassis monitoring component on the new energy vehicle chassis according to the optimal chassis monitoring scheme, wherein the second chassis monitoring component includes multiple sensors installed according to the optimal chassis monitoring scheme; obtaining real-time chassis status information of the new energy vehicle chassis through the second chassis monitoring component; generating fault diagnosis information of the new energy vehicle chassis according to the real-time chassis status information of the new energy vehicle chassis and the chassis fault diagnosis knowledge graph.

[0006] Furthermore, an initial chassis monitoring scheme is determined based on the three-dimensional model of the new energy vehicle chassis, including: establishing a finite element model of the new energy vehicle chassis based on the three-dimensional model of the new energy vehicle chassis; and determining an initial chassis monitoring scheme based on the finite element model of the new energy vehicle chassis.

[0007] Furthermore, based on the finite element model of the new energy vehicle chassis, an initial chassis monitoring plan is determined, including: performing stress analysis based on the finite element model of the new energy vehicle chassis to determine an initial vibration monitoring position; performing heat conduction analysis based on the finite element model of the new energy vehicle chassis to determine an initial temperature monitoring position; determining candidate current monitoring positions, candidate voltage monitoring positions, and candidate sound monitoring positions; performing electromagnetic field analysis based on the finite element model of the new energy vehicle chassis to determine an initial current monitoring position, an initial voltage monitoring position, and an initial sound monitoring position from the candidate current monitoring positions, the candidate voltage monitoring positions, and the candidate sound monitoring positions, wherein the multiple initial chassis monitoring positions include at least an initial vibration monitoring position, an initial temperature monitoring position, an initial current monitoring position, an initial voltage monitoring position, and an initial sound monitoring position.

[0008] Furthermore, according to the chassis state information of the test under multiple fault modes of the physical model corresponding to the chassis of the new energy vehicle, an optimal chassis monitoring scheme is determined, including: for each fault mode, according to the chassis state information of the test under the fault mode of the physical model corresponding to the chassis of the new energy vehicle, determining the abnormal parameters of each initial chassis monitoring position corresponding to the fault mode; according to the abnormal parameters of each initial chassis monitoring position corresponding to each fault mode, screening the multiple initial chassis monitoring positions to determine multiple intermediate chassis monitoring positions; for any two intermediate chassis monitoring positions, according to the chassis state information of the test under each fault mode of the physical model corresponding to the chassis of the new energy vehicle, determining the single-mode associated parameters of each fault mode of the two intermediate chassis monitoring positions; according to the abnormal parameters of each fault mode corresponding to the two intermediate chassis monitoring positions, screening the multiple initial chassis monitoring positions to determine multiple ... The single-mode association parameters of each fault mode corresponding to the measured position are determined to determine the multi-mode association parameters of the two intermediate chassis monitoring positions; the multiple intermediate chassis monitoring positions are grouped to determine multiple intermediate chassis monitoring position groups; for each intermediate chassis monitoring position group, the multiple intermediate chassis monitoring positions included in the intermediate chassis monitoring position group are screened according to the multi-mode association parameters of any two intermediate chassis monitoring positions included in the intermediate chassis monitoring position group to determine the multiple target chassis monitoring positions corresponding to the intermediate chassis monitoring position group and the monitoring feature type corresponding to each target chassis monitoring position; the optimal chassis monitoring scheme is determined according to the multiple target chassis monitoring positions corresponding to each intermediate chassis monitoring position group and the monitoring feature type corresponding to each target chassis monitoring position.

[0009] Furthermore, the multiple intermediate chassis monitoring positions are grouped to determine multiple intermediate chassis monitoring position groups, including: determining the abnormal parameters of each intermediate chassis monitoring position corresponding to each fault mode according to the abnormal parameters of each initial chassis monitoring position corresponding to each fault mode; for any two intermediate chassis monitoring positions, calculating the abnormal similarity of the two intermediate chassis monitoring positions according to the abnormal parameters of each intermediate chassis monitoring position corresponding to each fault mode; and clustering the multiple intermediate chassis monitoring positions according to the abnormal similarity of any two intermediate chassis monitoring positions by using a K-means algorithm to determine multiple intermediate chassis monitoring position groups.

[0010] Further, according to the test chassis state information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes, a chassis fault diagnosis knowledge graph is established, including: according to the abnormal parameters of each initial chassis monitoring position corresponding to each fault mode, determining the abnormal parameters of each target chassis monitoring position corresponding to each fault mode; for each target chassis monitoring position, determining the fault mode associated with the target chassis monitoring position according to the abnormal parameters of the target chassis monitoring position corresponding to each fault mode; for each fault mode, determining the target chassis monitoring position associated with the fault mode according to the fault mode associated with each target chassis monitoring position; for each fault mode, extracting the abnormal features corresponding to the fault mode according to the target chassis monitoring position associated with the fault mode and the test chassis state information of the physical model corresponding to the new energy vehicle chassis under the fault mode; establishing a chassis fault diagnosis knowledge graph according to the association between the target chassis monitoring position and the fault mode and the abnormal features corresponding to the fault mode, wherein the chassis fault diagnosis knowledge graph includes a target chassis monitoring position node, a fault mode node and an abnormal feature node.

[0011] Furthermore, based on the target chassis monitoring position associated with the fault mode and the test chassis state information of the physical model corresponding to the new energy vehicle chassis under the fault mode, the abnormal features corresponding to the fault mode are extracted, including: for each target chassis monitoring position associated with the fault mode, extracting the test data corresponding to the target chassis monitoring position from the test chassis state information of the physical model corresponding to the new energy vehicle chassis under the fault mode, performing variational mode decomposition on the test data, and extracting the position abnormal features corresponding to the target chassis monitoring position; generating the abnormal features corresponding to the fault mode according to the position abnormal features corresponding to each target chassis monitoring position associated with the fault mode.

[0012] Furthermore, based on the real-time chassis status information of the new energy vehicle chassis and the chassis fault diagnosis knowledge graph, fault diagnosis information of the new energy vehicle chassis is generated, including: determining an abnormal target chassis monitoring position based on the real-time chassis status information of the new energy vehicle chassis; determining a candidate fault mode based on the chassis fault diagnosis knowledge graph and the abnormal target chassis monitoring position; for each candidate fault mode, determining the real-time abnormal features of the new energy vehicle chassis corresponding to the candidate fault mode based on the real-time chassis status information of the new energy vehicle chassis and the target chassis monitoring position associated with the candidate fault mode, and determining the matching degree of the candidate fault mode based on the real-time abnormal features of the new energy vehicle chassis corresponding to the candidate fault mode and the abnormal features corresponding to the fault mode; generating fault diagnosis information of the new energy vehicle chassis according to the matching degree of each candidate fault mode.

[0013] Furthermore, according to the real-time chassis status information of the new energy vehicle chassis and the target chassis monitoring position associated with the candidate fault mode, the real-time abnormal characteristics of the new energy vehicle chassis corresponding to the candidate fault mode are determined, and according to the real-time abnormal characteristics of the new energy vehicle chassis corresponding to the candidate fault mode and the abnormal characteristics corresponding to the fault mode, the matching degree of the candidate fault mode is determined, including: according to the target chassis monitoring position associated with the candidate fault mode, extracting the real-time data corresponding to the target chassis monitoring position from the real-time chassis status information of the new energy vehicle chassis, performing variational mode decomposition on the test data, and extracting the real-time position characteristics corresponding to the target chassis monitoring position; generating the real-time characteristics corresponding to the candidate fault mode according to the real-time position characteristics corresponding to each target chassis monitoring position associated with the candidate fault mode; and determining the matching degree of the candidate fault mode according to the real-time characteristics and abnormal characteristics corresponding to the candidate fault mode.

[0014] The present invention provides a new energy vehicle chassis fault intelligent diagnosis system based on knowledge graph, which applies the above-mentioned new energy vehicle chassis fault intelligent diagnosis method based on knowledge graph, including: a data acquisition module, used to obtain a three-dimensional model of the new energy vehicle chassis; a solution optimization module, used to determine an initial chassis monitoring scheme according to the three-dimensional model of the new energy vehicle chassis, wherein the initial chassis monitoring scheme includes multiple initial chassis monitoring positions and monitoring feature types corresponding to each initial chassis monitoring position; the solution optimization module is also used to obtain a physical model corresponding to the new energy vehicle chassis; the solution optimization module is also used to install a first chassis monitoring component on the physical model corresponding to the new energy vehicle chassis according to the initial chassis monitoring scheme, wherein the first chassis monitoring component is installed with multiple sensors according to the initial chassis monitoring scheme; the solution optimization module is also used to obtain chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes through the first chassis monitoring component; the method The scheme optimization module is also used to determine the optimal chassis monitoring scheme according to the test chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes, wherein the optimal chassis monitoring scheme includes multiple target chassis monitoring positions and the monitoring feature type corresponding to each target chassis monitoring position; the graph establishment module is used to establish a chassis fault diagnosis knowledge graph according to the test chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes; the state monitoring module is used to install a second chassis monitoring component on the new energy vehicle chassis according to the optimal chassis monitoring scheme, wherein the second chassis monitoring component is a plurality of sensors installed according to the optimal chassis monitoring scheme; the state monitoring module is also used to obtain the real-time chassis status information of the new energy vehicle chassis through the second chassis monitoring component; the fault diagnosis module is used to generate fault diagnosis information of the new energy vehicle chassis according to the real-time chassis status information of the new energy vehicle chassis and the chassis fault diagnosis knowledge graph.

[0015] Compared with the prior art, the intelligent diagnosis method and system for chassis faults of new energy vehicles based on knowledge graph provided by the present invention have at least the following beneficial effects:

[0016] 1. Through the formulation of the initial chassis monitoring plan and the optimal chassis monitoring plan, the key positions of the chassis of new energy vehicles can be monitored in a targeted manner, which reduces invalid monitoring and improves diagnostic efficiency. By using the chassis fault diagnosis knowledge graph, the fault characteristics can be quickly matched, accurate fault diagnosis information can be provided, and the probability of misdiagnosis and missed diagnosis can be reduced. The intelligent diagnosis method can detect chassis faults in time, avoid greater losses caused by fault deterioration, and reduce maintenance costs. Through accurate monitoring and diagnosis, maintenance plans can be optimized, unnecessary maintenance operations can be reduced, and maintenance costs can be further reduced. Real-time monitoring of the chassis status can timely detect and warn potential safety hazards and improve the driving safety of new energy vehicles. Accurate fault diagnosis information helps to repair chassis faults in time, ensure that new energy vehicles run in good condition, and reduce the risk of accidents. The intelligent diagnosis method can quickly and accurately provide users with chassis fault information, reduce user waiting time, and improve user satisfaction. Combining advanced technologies such as knowledge graphs and the Internet of Things, it has promoted technological innovation and industrial upgrading in the field of new energy vehicles. The application of intelligent diagnosis technology will help improve the overall performance and market competitiveness of new energy vehicles and promote the sustainable development of the new energy vehicle industry.

[0017] 2. By establishing a finite element model of the chassis of new energy vehicles, accurate stress analysis, heat conduction analysis and electromagnetic field analysis can be performed to determine a more accurate initial chassis monitoring position. The application of the finite element model makes the determination of the monitoring position more scientific and reasonable, reduces blindness, and improves the accuracy of diagnosis. By analyzing the test chassis status information of the chassis of new energy vehicles under multiple fault modes, the abnormal parameters corresponding to different fault modes of each initial chassis monitoring position can be determined. Further analysis of multi-mode correlation parameters can screen out more critical target chassis monitoring positions, making diagnosis more efficient and accurate. The K-means algorithm is used to cluster and group the intermediate chassis monitoring positions, and similar monitoring positions can be grouped together according to the abnormal similarity, which is convenient for subsequent analysis and processing. Intelligent screening and grouping reduce redundant information and improve the efficiency and accuracy of diagnosis. It integrates advanced technologies such as finite element analysis, knowledge graph, and K-means algorithm to promote technological innovation and industrial upgrading in the field of new energy vehicles.

[0018] 3. By establishing a chassis fault diagnosis knowledge graph, the target chassis monitoring position, fault mode and abnormal features are associated, making the diagnosis process more systematic and organized. The introduction of the knowledge graph enables fault diagnosis to be based on a large amount of historical data and experience, improving the accuracy and reliability of diagnosis. Through variational mode decomposition and other technologies, the position abnormal features of the target chassis monitoring position are extracted from the test data, making the abnormal features more accurate and significant. The accurate extraction of abnormal features helps to quickly locate faults and improve the efficiency of diagnosis. By comparing the real-time abnormal features of the new energy vehicle chassis corresponding to the candidate fault mode and the abnormal features corresponding to the fault mode, the matching degree of the candidate fault mode is determined, thereby achieving rapid and accurate identification of the fault. Since the knowledge graph contains the association between the target chassis monitoring position and the fault mode and the abnormal features corresponding to the fault mode, the fault location and type can be accurately located, reducing the possibility of false alarms and missed alarms. Through the dual verification of the knowledge graph and abnormal features, the diagnosis results are more stable and reliable, reducing the diagnostic errors caused by a single factor. It can handle multiple fault modes and dynamically adjust according to the real-time chassis status information, so it has strong adaptability. The knowledge graph can be continuously updated and improved as new data is added, allowing the diagnostic system to continue to maintain a high level of performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0020] Figure 1 It is a flow chart of a method for intelligent diagnosis of chassis faults of new energy vehicles based on knowledge graphs according to some embodiments of this specification;

[0021] Figure 2 is a schematic diagram of a process for determining an optimal chassis monitoring solution according to some embodiments of this specification;

[0022] Figure 3 is a schematic diagram of a chassis fault diagnosis knowledge graph according to some embodiments of this specification;

[0023] Figure 4 It is a module diagram of a new energy vehicle chassis fault intelligent diagnosis system based on a knowledge graph according to some embodiments of this specification. DETAILED DESCRIPTION

[0024] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0025] Figure 1 is a flow chart of a new energy vehicle chassis fault intelligent diagnosis method based on a knowledge graph according to some embodiments of this specification, such as Figure 1 As shown, the intelligent diagnosis method for chassis faults of new energy vehicles based on knowledge graph can include the following steps.

[0026] Step 110, obtaining a three-dimensional model of the chassis of the new energy vehicle.

[0027] Step 120, determining an initial chassis monitoring plan based on the three-dimensional model of the new energy vehicle chassis.

[0028] Among them, the initial chassis monitoring plan includes multiple initial chassis monitoring positions and the monitoring feature type corresponding to each initial chassis monitoring position, for example, collecting temperature features at the initial chassis monitoring position A1, collecting vibration features at the initial chassis monitoring position A2, etc.

[0029] In some embodiments, step 120 specifically includes:

[0030] According to the three-dimensional model of the new energy vehicle chassis, a finite element model of the new energy vehicle chassis is established;

[0031] Determine the initial chassis monitoring plan based on the finite element model of the new energy vehicle chassis.

[0032] Specifically, the finite element model of the new energy vehicle chassis can be established through the following process:

[0033] First, the 3D model of the new energy vehicle chassis is simplified and geometrically cleaned to remove unnecessary details and redundant information for better meshing.

[0034] Then, the grid size is determined according to the size and accuracy requirements of the three-dimensional model of the new energy vehicle chassis, and the three-dimensional model of the new energy vehicle chassis is divided using quadrilateral or triangular grids.

[0035] In the finite element model of the chassis of new energy vehicles, real material properties are given to each component of the chassis, such as density, Poisson's ratio, elastic modulus, etc. These properties will directly affect the calculation results and accuracy of the model.

[0036] Reasonable boundary conditions are set for the finite element model of the chassis of new energy vehicles. For example, the displacement of certain nodes can be fixed or certain loads and constraints can be applied to simulate the stress conditions of the chassis in actual work.

[0037] After the meshing is completed, the mesh quality is checked and adjusted. This includes checking the mesh continuity, integrity, unit shape and other aspects to ensure that the finite element model of the new energy vehicle chassis will not have errors or anomalies during the calculation process.

[0038] In some embodiments, an initial chassis monitoring scheme is determined based on a finite element model of a new energy vehicle chassis, including:

[0039] Based on the finite element model of the new energy vehicle chassis, stress analysis is performed to determine the initial vibration monitoring position;

[0040] According to the finite element model of the new energy vehicle chassis, conduct heat conduction analysis to determine the initial temperature monitoring position;

[0041] Determine candidate current monitoring positions, candidate voltage monitoring positions, and candidate sound monitoring positions. For example only, the candidate current monitoring positions, candidate voltage monitoring positions, and candidate sound monitoring positions may be determined manually or by big data analysis technology.

[0042] Based on the finite element model of the new energy vehicle chassis, an electromagnetic field analysis is performed to determine the initial current monitoring position, the initial voltage monitoring position and the initial sound monitoring position from the candidate current monitoring positions, the candidate voltage monitoring positions and the candidate sound monitoring positions, wherein the multiple initial chassis monitoring positions include at least an initial vibration monitoring position, an initial temperature monitoring position, an initial current monitoring position, an initial voltage monitoring position and an initial sound monitoring position.

[0043] Specifically, by performing stress analysis on the finite element model of the new energy vehicle chassis, we can understand the stress distribution of the new energy vehicle chassis under various working conditions. Based on the stress analysis results, we can determine the stress concentration areas and potential danger points, thereby determining the initial vibration monitoring locations. These locations are usually areas on the new energy vehicle chassis that are susceptible to vibration and prone to problems.

[0044] The chassis of new energy vehicles will generate a certain amount of heat during operation, so heat conduction analysis is needed to understand the temperature distribution of the chassis of new energy vehicles. Through the finite element model of the chassis of new energy vehicles, heat conduction analysis can be performed to determine the high-temperature areas and potential thermal failure points on the chassis of new energy vehicles, thereby determining the initial temperature monitoring locations. These locations are usually areas on the chassis of new energy vehicles that are prone to heat accumulation and are sensitive to temperature.

[0045] For new energy vehicles, electromagnetic field is an important consideration. Through the electromagnetic field analysis of the finite element model of the new energy vehicle chassis, we can understand the electromagnetic field distribution on the new energy vehicle chassis, exclude the candidate current monitoring positions, candidate voltage monitoring positions and candidate sound monitoring positions with strong electromagnetic field interference, and use the remaining candidate current monitoring positions, candidate voltage monitoring positions and candidate sound monitoring positions as the initial current monitoring positions, initial voltage monitoring positions and initial sound monitoring positions.

[0046] Step 130, obtaining a physical model corresponding to the chassis of the new energy vehicle.

[0047] Specifically, the physical model corresponding to the new energy vehicle chassis may be a model that is consistent with the structure, size, etc. of the new energy vehicle chassis.

[0048] Step 140 , according to the initial chassis monitoring solution, install a first chassis monitoring component on the physical model corresponding to the new energy vehicle chassis.

[0049] Among them, the first chassis monitoring component is a plurality of sensors installed according to the initial chassis monitoring scheme. Specifically, corresponding sensors can be installed at corresponding positions of the physical model corresponding to the new energy vehicle chassis according to multiple initial chassis monitoring positions and the monitoring feature type corresponding to each initial chassis monitoring position, and the first chassis monitoring component can include sensors arranged at each initial chassis monitoring position.

[0050] Step 150: obtaining chassis status information of a physical model corresponding to the chassis of the new energy vehicle under multiple fault modes through a first chassis monitoring component.

[0051] Merely as an example, multiple failure modes may include transmission failure (for example, transmission oil leakage, abnormal transmission noise, difficulty shifting, etc.), steering system failure (for example, loose steering wheel and steering shaft fixing nuts, excessive meshing clearance between the steering gear master and slave parts, bending and deformation of the steering shaft, lack of oil in the steering gear, deformation of the front axle or frame, different ages of the front wheel tires or inconsistent air pressure, etc.), braking system failure (for example, location of brake pipe leakage point, low brake fluid level, excessive or small brake clearance, uneven brake clearance between the left and right brakes, difference in contact area, out-of-round brake drum, too smooth surface of the brake friction pad or foreign objects stuck in it, rust on the cable or jacket, breakage or falling off of the traction spring, etc.), driving system failure (for example, uneven tire wear, suspension deformation, shock absorber failure, suspension deformation, shock absorber abnormality, etc.), etc.

[0052] Step 160 , determining an optimal chassis monitoring solution according to chassis status information tested under multiple fault modes using a physical model corresponding to the chassis of the new energy vehicle.

[0053] Among them, the optimal chassis monitoring solution includes multiple target chassis monitoring positions and the monitoring feature type corresponding to each target chassis monitoring position.

[0054] Figure 2 is a flow chart of determining the optimal chassis monitoring solution according to some embodiments of this specification, such as Figure 2 As shown, in some embodiments, step 160 specifically includes:

[0055] For each fault mode, determine the abnormal parameters corresponding to the fault mode at each initial chassis monitoring position according to the test chassis state information of the physical model corresponding to the new energy vehicle chassis in the fault mode;

[0056] Screening multiple initial chassis monitoring positions according to the abnormal parameters of each failure mode corresponding to each initial chassis monitoring position to determine multiple intermediate chassis monitoring positions;

[0057] For any two intermediate chassis monitoring positions, determine the single-mode association parameters of the two intermediate chassis monitoring positions corresponding to each fault mode according to the test chassis status information of the physical model corresponding to the new energy vehicle chassis in each fault mode, and determine the multi-mode association parameters of the two intermediate chassis monitoring positions according to the single-mode association parameters of the two intermediate chassis monitoring positions corresponding to each fault mode;

[0058] Grouping a plurality of intermediate chassis monitoring positions to determine a plurality of intermediate chassis monitoring position groups;

[0059] For each intermediate chassis monitoring position group, multiple intermediate chassis monitoring positions included in the intermediate chassis monitoring position group are screened according to multi-mode association parameters of any two intermediate chassis monitoring positions included in the intermediate chassis monitoring position group, and multiple target chassis monitoring positions corresponding to the intermediate chassis monitoring position group and a monitoring feature type corresponding to each target chassis monitoring position are determined;

[0060] An optimal chassis monitoring scheme is determined according to a plurality of target chassis monitoring positions corresponding to each intermediate chassis monitoring position group and a monitoring feature type corresponding to each target chassis monitoring position.

[0061] Specifically, the test data of each initial chassis monitoring position under a non-fault state can be acquired in advance. According to the test data of the initial chassis monitoring position under a non-fault state, the normal position characteristics corresponding to the initial chassis monitoring position under a non-fault state are determined. Specifically, the test data of the initial chassis monitoring position under a non-fault state can be subjected to variational modal decomposition to extract the normal position characteristics corresponding to the initial chassis monitoring position, wherein the normal position characteristics can include the characteristic vectors (e.g., modal center frequency, amplitude, phase, bandwidth, energy, etc.) of each inherent modal component obtained after the test data of the initial chassis monitoring position is subjected to variational modal decomposition.

[0062] For each fault mode, according to the test chassis state information of the physical model corresponding to the new energy vehicle chassis in the fault mode, the test data of each initial chassis monitoring position corresponding to the fault mode is determined, and according to the test data of the initial chassis monitoring position corresponding to the fault mode, the position abnormality feature of the initial chassis monitoring position corresponding to the fault mode is determined. Specifically, the test data of the initial chassis monitoring position corresponding to the fault mode can be subjected to variational modal decomposition to extract the position abnormality feature of the initial chassis monitoring position corresponding to the fault mode, wherein the position abnormality feature of the initial chassis monitoring position corresponding to the fault mode can include the characteristic vector (for example, modal center frequency, amplitude, phase, bandwidth, energy, etc.) of each inherent modal component obtained after the test data of the initial chassis monitoring position corresponding to the fault mode is subjected to variational modal decomposition.

[0063] The abnormal parameters of the initial chassis monitoring position corresponding to the fault mode can be calculated according to the following formula:

[0064]

[0065] Among them, η (i,g) is the abnormal parameter of the g-th fault mode corresponding to the i-th initial chassis monitoring position, ψ1 is the preset parameter, ψ1 is greater than 0, F ((normal,k),i,g) is the eigenvector of the kth natural modal component obtained by performing variational modal decomposition on the test data corresponding to the gth fault mode at the ith initial chassis monitoring position, F ((fault,k),i,g) is the eigenvector of the kth natural mode component obtained by performing variational mode decomposition on the test data corresponding to the gth fault mode at the jth initial chassis monitoring position, cos(F ((normal,k),i,g) ,F ((fault,k),i,g)) is the cosine similarity between the eigenvector of the kth inherent modal component obtained after variational modal decomposition of the test data corresponding to the gth fault mode at the ith initial chassis monitoring position and the eigenvector of the kth inherent modal component obtained after variational modal decomposition of the test data corresponding to the gth fault mode at the jth initial chassis monitoring position, and K is the total number of preset inherent modal components.

[0066] For each initial chassis monitoring position, the abnormal parameter mean and the abnormal parameter standard deviation of the abnormal parameters corresponding to each fault mode of the initial chassis monitoring position can be calculated, and the initial chassis monitoring position whose abnormal parameter mean is greater than the abnormal parameter mean threshold, and whose abnormal parameter standard deviation is less than the maximum threshold of the abnormal parameter standard deviation and greater than the minimum threshold of the abnormal parameter standard deviation is taken as the intermediate chassis monitoring position.

[0067] The single-mode correlation parameters corresponding to the fault modes at the two middle chassis monitoring positions can be calculated according to the following formula:

[0068]

[0069] Among them, γ ((i,j),g) is the single-mode correlation parameter of the i-th intermediate chassis monitoring position and the j-th intermediate chassis monitoring position corresponding to the g-th fault mode, V ((i,t),g) is the data value of the tth test time point corresponding to the gth fault mode at the i-th intermediate chassis monitoring position, V (j,t),g) is the data value of the tth test time point corresponding to the gth failure mode at the jth intermediate chassis monitoring position, and T is the total number of sampled test time points.

[0070] For any two intermediate chassis monitoring positions, the single-mode correlation parameters corresponding to each failure mode of the two intermediate chassis monitoring positions may be weighted summed to obtain the multi-mode correlation parameters of the two intermediate chassis monitoring positions.

[0071] In some embodiments, grouping a plurality of intermediate chassis monitoring positions to determine a plurality of intermediate chassis monitoring position groups includes:

[0072] Determine the abnormal parameters of each intermediate chassis monitoring position corresponding to each failure mode according to the abnormal parameters of each initial chassis monitoring position corresponding to each failure mode;

[0073] For any two intermediate chassis monitoring positions, the abnormal similarity of the two intermediate chassis monitoring positions is calculated according to the abnormal parameters of each fault mode corresponding to each intermediate chassis monitoring position;

[0074] Through the K-means algorithm, multiple intermediate chassis monitoring positions are clustered according to the abnormal similarity between any two intermediate chassis monitoring positions, and multiple intermediate chassis monitoring position groups are determined.

[0075] Specifically, the anomaly similarity of the two middle chassis monitoring positions can be calculated according to the following formula:

[0076]

[0077] Among them, S (i,j) is the abnormal similarity between the i-th intermediate chassis monitoring position and the j-th intermediate chassis monitoring position, η (j,g) is the abnormal parameter of the jth initial chassis monitoring position corresponding to the gth fault mode, ψ2 is the preset parameter, and ψ2 is greater than 0.

[0078] The following process can be used to screen multiple intermediate chassis monitoring positions included in the intermediate chassis monitoring position group according to the multi-mode association parameters of any two intermediate chassis monitoring positions included in the intermediate chassis monitoring position group:

[0079] S11. For any one of the intermediate chassis monitoring positions included in the intermediate chassis monitoring position group, calculate a mean value of multi-mode correlation parameters of the multi-mode correlation parameters of the intermediate chassis monitoring position and any other intermediate chassis monitoring position included in the intermediate chassis monitoring position group;

[0080] S12, determining whether the mean value of the multi-mode correlation parameter of any intermediate chassis monitoring position included in the intermediate chassis monitoring position group is greater than the multi-mode correlation parameter mean threshold value, if so, executing S15, if not, executing S13;

[0081] S13, determining whether the number of the intermediate chassis monitoring positions included in the intermediate chassis monitoring position group is greater than the minimum threshold of the number of intermediate chassis monitoring positions, if so, executing S14, if not, completing the screening;

[0082] S14, filtering out the intermediate chassis monitoring position with the smallest mean value of the multi-mode associated parameter from the intermediate chassis monitoring position group, updating the intermediate chassis monitoring position group, and executing S11;

[0083] S15. Determine whether the number of the intermediate chassis monitoring positions included in the intermediate chassis monitoring position group is less than the maximum threshold of the number of intermediate chassis monitoring positions. If so, complete the screening; if not, execute S14.

[0084] Step 170 , establishing a chassis fault diagnosis knowledge graph based on the test chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes.

[0085] In some embodiments, step 160 specifically includes:

[0086] Determine the abnormal parameters of each target chassis monitoring position corresponding to each failure mode according to the abnormal parameters of each initial chassis monitoring position corresponding to each failure mode;

[0087] For each target chassis monitoring position, determine the fault mode associated with the target chassis monitoring position according to the abnormal parameters of each fault mode corresponding to the target chassis monitoring position, for example, take the fault mode with abnormal parameters greater than the abnormal parameter threshold as the fault mode associated with the target chassis monitoring position;

[0088] For each fault mode, according to the fault mode associated with each target chassis monitoring position, determine the target chassis monitoring position associated with the fault mode. For example, if the fault mode associated with the target chassis monitoring position A1 includes fault modes B1 and B2, the fault mode associated with the target chassis monitoring position A2 includes fault modes B3 and B2, and the fault mode associated with the target chassis monitoring position A3 includes fault modes B1, B2, and B4, then the target chassis monitoring position associated with the fault mode B2 may include the target chassis monitoring position A1, the target chassis monitoring position A2, and the target chassis monitoring position A3;

[0089] For each fault mode, according to the target chassis monitoring position associated with the fault mode and the test chassis status information of the physical model corresponding to the new energy vehicle chassis under the fault mode, the abnormal features corresponding to the fault mode are extracted;

[0090] According to the correlation between the target chassis monitoring position and the fault mode and the abnormal characteristics corresponding to the fault mode, a chassis fault diagnosis knowledge graph is established, where: Figure 3 is a schematic diagram of a chassis fault diagnosis knowledge graph according to some embodiments of this specification, such as Figure 3 As shown, the chassis fault diagnosis knowledge graph includes the target chassis monitoring location node, fault mode node and abnormal feature node.

[0091] In some embodiments, according to the target chassis monitoring position associated with the fault mode and the test chassis state information of the physical model corresponding to the new energy vehicle chassis in the fault mode, the abnormal features corresponding to the fault mode are extracted, including:

[0092] For each target chassis monitoring position associated with the fault mode, extract the test data corresponding to the target chassis monitoring position from the test chassis state information of the physical model corresponding to the new energy vehicle chassis under the fault mode, perform variational mode decomposition on the test data, and extract the position abnormality features corresponding to the target chassis monitoring position;

[0093] According to the position abnormality feature corresponding to each target chassis monitoring position associated with the fault mode, an abnormality feature corresponding to the fault mode is generated.

[0094] Specifically, the abnormal features corresponding to the fault mode may include position abnormal features corresponding to each target chassis monitoring position associated with the fault mode. For more descriptions on performing variational mode decomposition on the test data and extracting position abnormal features corresponding to the target chassis monitoring position, please refer to the above, which will not be repeated here.

[0095] Step 180: Install a second chassis monitoring component on the chassis of the new energy vehicle according to the optimal chassis monitoring solution.

[0096] Among them, the second chassis monitoring component is equipped with multiple sensors according to the optimal chassis monitoring solution.

[0097] Specifically, corresponding sensors may be installed at corresponding positions of the new energy vehicle chassis according to the multiple target chassis monitoring positions included in the optimal chassis monitoring solution and the monitoring feature type corresponding to each target chassis monitoring position.

[0098] Step 190, obtaining real-time chassis status information of the new energy vehicle chassis through the second chassis monitoring component.

[0099] Among them, the real-time chassis status information of the new energy vehicle chassis may include data collected by sensors installed at each target chassis monitoring position at multiple consecutive time points.

[0100] Step 200, generating fault diagnosis information of the new energy vehicle chassis according to the real-time chassis status information of the new energy vehicle chassis and the chassis fault diagnosis knowledge graph.

[0101] In some embodiments, step 190 specifically includes:

[0102] According to the real-time chassis status information of the new energy vehicle chassis, determine the abnormal target chassis monitoring position;

[0103] Determine candidate fault modes based on chassis fault diagnosis knowledge graph and abnormal target chassis monitoring locations;

[0104] For each candidate fault mode, determine the real-time abnormal features of the new energy vehicle chassis corresponding to the candidate fault mode based on the real-time chassis status information of the new energy vehicle chassis and the target chassis monitoring position associated with the candidate fault mode, and determine the matching degree of the candidate fault mode based on the real-time abnormal features of the new energy vehicle chassis corresponding to the candidate fault mode and the abnormal features corresponding to the fault mode;

[0105] According to the matching degree of each candidate fault mode, the fault diagnosis information of the new energy vehicle chassis is generated.

[0106] Specifically, for each fault mode, the target chassis monitoring position associated with the fault mode is determined according to the chassis fault diagnosis knowledge graph. Based on the determination of the abnormal target chassis monitoring position, it is judged whether each target chassis monitoring position associated with the fault mode is an abnormal target chassis monitoring position. If so, the fault mode is determined to be a candidate fault mode.

[0107] In some embodiments, according to the real-time chassis status information of the new energy vehicle chassis and the target chassis monitoring position associated with the candidate fault mode, the real-time abnormal characteristics of the new energy vehicle chassis corresponding to the candidate fault mode are determined, and according to the real-time abnormal characteristics of the new energy vehicle chassis corresponding to the candidate fault mode and the abnormal characteristics corresponding to the fault mode, the matching degree of the candidate fault mode is determined, including:

[0108] According to the target chassis monitoring position associated with the candidate fault mode, the real-time data corresponding to the target chassis monitoring position is extracted from the real-time chassis status information of the new energy vehicle chassis, and the test data is subjected to variational mode decomposition to extract the position real-time features corresponding to the target chassis monitoring position. For more descriptions, please refer to the above, which will not be repeated here.

[0109] Generate a real-time feature corresponding to the candidate fault mode according to the real-time feature of the position corresponding to each target chassis monitoring position associated with the candidate fault mode;

[0110] The matching degree of the candidate fault mode is determined according to the real-time features and abnormal features corresponding to the candidate fault mode.

[0111] Specifically, the matching degree of the candidate fault mode can be determined according to the following formula:

[0112]

[0113] Among them, M g is the matching degree of the g-th candidate fault mode, F ((fault,k),h,g) is the feature vector of the kth natural mode component in the abnormal feature corresponding to the hth target chassis monitoring position associated with the gth candidate fault mode, F ((current,k),h,g) is the feature vector of the kth intrinsic modal component in the real-time abnormal feature corresponding to the hth target chassis monitoring position associated with the gth candidate fault mode, cos(F ((fault,k),h,g) ,F ((current,k),h,g) ) is the cosine similarity between the feature vector of the kth inherent modal component in the abnormal feature corresponding to the hth target chassis monitoring position associated with the gth candidate fault mode and the feature vector of the kth inherent modal component in the real-time abnormal feature corresponding to the hth target chassis monitoring position associated with the gth candidate fault mode, H is the total number of target chassis monitoring positions associated with the gth candidate fault mode, ψ3 is a preset parameter, and ψ3 is greater than 0.

[0114] The fault diagnosis model can be used to generate fault diagnosis information of the new energy vehicle chassis according to the matching degree of each candidate fault mode, wherein the fault diagnosis model can be a convolutional neural network model.

[0115] Figure 4 is a module schematic diagram of a new energy vehicle chassis fault intelligent diagnosis system based on a knowledge graph according to some embodiments of this specification, such as Figure 4 As shown, the new energy vehicle chassis fault intelligent diagnosis system based on knowledge graph can include a data acquisition module, a solution optimization module, a graph building module, a state monitoring module and a fault diagnosis module.

[0116] A data acquisition module is used to obtain a three-dimensional model of the chassis of a new energy vehicle;

[0117] A scheme optimization module is used to determine an initial chassis monitoring scheme based on a three-dimensional model of the chassis of a new energy vehicle, wherein the initial chassis monitoring scheme includes a plurality of initial chassis monitoring positions and a monitoring feature type corresponding to each initial chassis monitoring position;

[0118] The solution optimization module is also used to obtain the physical model corresponding to the chassis of new energy vehicles;

[0119] The solution optimization module is also used to install a first chassis monitoring component on a physical model corresponding to the new energy vehicle chassis according to the initial chassis monitoring solution, wherein the first chassis monitoring component includes a plurality of sensors installed according to the initial chassis monitoring solution;

[0120] The solution optimization module is also used to obtain chassis status information of a physical model corresponding to the chassis of the new energy vehicle under multiple fault modes through the first chassis monitoring component;

[0121] The scheme optimization module is also used to determine the optimal chassis monitoring scheme according to the test chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes, wherein the optimal chassis monitoring scheme includes multiple target chassis monitoring positions and the monitoring feature type corresponding to each target chassis monitoring position;

[0122] A graph building module is used to build a chassis fault diagnosis knowledge graph based on the chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes;

[0123] A state monitoring module, used to install a second chassis monitoring component on the chassis of the new energy vehicle according to the optimal chassis monitoring solution, wherein the second chassis monitoring component includes a plurality of sensors installed according to the optimal chassis monitoring solution;

[0124] The status monitoring module is also used to obtain real-time chassis status information of the new energy vehicle chassis through the second chassis monitoring component;

[0125] The fault diagnosis module is used to generate fault diagnosis information of the new energy vehicle chassis based on the real-time chassis status information of the new energy vehicle chassis and the chassis fault diagnosis knowledge graph.

[0126] The new energy vehicle chassis fault intelligent diagnosis system based on knowledge graph can be used to execute the new energy vehicle chassis fault intelligent diagnosis method based on knowledge graph, which will not be repeated here.

[0127] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. An intelligent diagnosis method for chassis faults of new energy vehicles based on knowledge graph, characterized in that: include: Obtain the 3D model of the new energy vehicle chassis; Determine an initial chassis monitoring scheme according to the three-dimensional model of the new energy vehicle chassis, wherein the initial chassis monitoring scheme includes a plurality of initial chassis monitoring positions and a monitoring feature type corresponding to each initial chassis monitoring position; Obtain the physical model corresponding to the new energy vehicle chassis; According to the initial chassis monitoring scheme, a first chassis monitoring component is installed on a physical model corresponding to the chassis of the new energy vehicle, wherein the first chassis monitoring component includes a plurality of sensors installed according to the initial chassis monitoring scheme; Acquiring chassis status information of a physical model corresponding to the chassis of the new energy vehicle under multiple fault modes through a first chassis monitoring component; Determine an optimal chassis monitoring scheme according to the test chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes, wherein the optimal chassis monitoring scheme includes multiple target chassis monitoring positions and a monitoring feature type corresponding to each target chassis monitoring position; Establish a chassis fault diagnosis knowledge graph based on the chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes; According to the optimal chassis monitoring solution, a second chassis monitoring component is installed on the chassis of the new energy vehicle, wherein the second chassis monitoring component includes a plurality of sensors installed according to the optimal chassis monitoring solution; Acquiring real-time chassis status information of the new energy vehicle chassis through the second chassis monitoring component; Fault diagnosis information of the new energy vehicle chassis is generated according to the real-time chassis status information of the new energy vehicle chassis and the chassis fault diagnosis knowledge graph.

2. The intelligent diagnosis method for chassis fault of new energy vehicles based on knowledge graph according to claim 1 is characterized in that: Based on the 3D model of the new energy vehicle chassis, determine the initial chassis monitoring plan, including: Establishing a finite element model of the new energy vehicle chassis according to the three-dimensional model of the new energy vehicle chassis; Determine the initial chassis monitoring plan based on the finite element model of the new energy vehicle chassis.

3. The intelligent diagnosis method for chassis fault of new energy vehicles based on knowledge graph according to claim 2 is characterized in that: Based on the finite element model of the new energy vehicle chassis, determine the initial chassis monitoring plan, including: Based on the finite element model of the new energy vehicle chassis, stress analysis is performed to determine the initial vibration monitoring position; According to the finite element model of the new energy vehicle chassis, conduct heat conduction analysis to determine the initial temperature monitoring position; determining candidate current monitoring positions, candidate voltage monitoring positions, and candidate sound monitoring positions; According to the finite element model of the new energy vehicle chassis, an electromagnetic field analysis is performed to determine the initial current monitoring position, the initial voltage monitoring position and the initial sound monitoring position from the candidate current monitoring positions, the candidate voltage monitoring positions and the candidate sound monitoring positions, wherein the multiple initial chassis monitoring positions include at least an initial vibration monitoring position, an initial temperature monitoring position, an initial current monitoring position, an initial voltage monitoring position and an initial sound monitoring position.

4. The intelligent diagnosis method for chassis fault of new energy vehicles based on knowledge graph according to claim 3 is characterized in that: According to the chassis status information of the physical model corresponding to the chassis of new energy vehicles under multiple fault modes, the optimal chassis monitoring solution is determined, including: For each fault mode, determine the abnormal parameters corresponding to the fault mode at each initial chassis monitoring position according to the test chassis state information of the physical model corresponding to the new energy vehicle chassis in the fault mode; Screening the plurality of initial chassis monitoring positions according to the abnormal parameters of each failure mode corresponding to each initial chassis monitoring position to determine a plurality of intermediate chassis monitoring positions; For any two intermediate chassis monitoring positions, determine the single-mode association parameters of the two intermediate chassis monitoring positions corresponding to each fault mode according to the test chassis status information of the physical model corresponding to the new energy vehicle chassis in each fault mode, and determine the multi-mode association parameters of the two intermediate chassis monitoring positions according to the single-mode association parameters of the two intermediate chassis monitoring positions corresponding to each fault mode; Grouping the plurality of intermediate chassis monitoring positions to determine a plurality of intermediate chassis monitoring position groups; For each intermediate chassis monitoring position group, based on the multi-mode association parameters of any two intermediate chassis monitoring positions included in the intermediate chassis monitoring position group, a plurality of intermediate chassis monitoring positions included in the intermediate chassis monitoring position group are screened to determine a plurality of target chassis monitoring positions corresponding to the intermediate chassis monitoring position group and a monitoring feature type corresponding to each target chassis monitoring position; The optimal chassis monitoring scheme is determined according to the multiple target chassis monitoring positions corresponding to each of the intermediate chassis monitoring position groups and the monitoring feature type corresponding to each target chassis monitoring position.

5. The intelligent diagnosis method for chassis fault of new energy vehicles based on knowledge graph according to claim 4 is characterized in that: The plurality of intermediate chassis monitoring positions are grouped to determine a plurality of intermediate chassis monitoring position groups, including: Determine the abnormal parameters of each intermediate chassis monitoring position corresponding to each failure mode according to the abnormal parameters of each initial chassis monitoring position corresponding to each failure mode; For any two intermediate chassis monitoring positions, the abnormal similarity of the two intermediate chassis monitoring positions is calculated according to the abnormal parameters of each fault mode corresponding to each intermediate chassis monitoring position; By using the K-means algorithm, the plurality of intermediate chassis monitoring positions are clustered according to the abnormal similarity between any two intermediate chassis monitoring positions, and a plurality of intermediate chassis monitoring position groups are determined.

6. The intelligent diagnosis method for chassis fault of new energy vehicles based on knowledge graph according to claim 4 or 5 is characterized in that: According to the chassis status information of the physical model corresponding to the chassis of new energy vehicles under multiple fault modes, a chassis fault diagnosis knowledge graph is established, including: Determine the abnormal parameters of each target chassis monitoring position corresponding to each failure mode according to the abnormal parameters of each initial chassis monitoring position corresponding to each failure mode; For each target chassis monitoring position, determining a fault mode associated with the target chassis monitoring position according to abnormal parameters of each fault mode corresponding to the target chassis monitoring position; For each fault mode, according to the fault mode associated with each target chassis monitoring position, determining the target chassis monitoring position associated with the fault mode; For each fault mode, extract the abnormal features corresponding to the fault mode according to the target chassis monitoring position associated with the fault mode and the test chassis state information of the physical model corresponding to the chassis of the new energy vehicle under the fault mode; According to the correlation between the target chassis monitoring position and the fault mode and the abnormal characteristics corresponding to the fault mode, a chassis fault diagnosis knowledge graph is established, wherein the chassis fault diagnosis knowledge graph includes a target chassis monitoring position node, a fault mode node and an abnormal characteristic node.

7. The intelligent diagnosis method for chassis fault of new energy vehicles based on knowledge graph according to claim 6 is characterized in that: According to the target chassis monitoring position associated with the fault mode and the test chassis state information of the physical model corresponding to the new energy vehicle chassis under the fault mode, the abnormal features corresponding to the fault mode are extracted, including: For each target chassis monitoring position associated with the fault mode, extract test data corresponding to the target chassis monitoring position from the test chassis state information of the physical model corresponding to the new energy vehicle chassis under the fault mode, perform variational mode decomposition on the test data, and extract position abnormality features corresponding to the target chassis monitoring position; According to the position abnormality feature corresponding to each target chassis monitoring position associated with the fault mode, an abnormality feature corresponding to the fault mode is generated.

8. The intelligent diagnosis method for chassis fault of new energy vehicles based on knowledge graph according to claim 7 is characterized in that: According to the real-time chassis status information of the new energy vehicle chassis and the chassis fault diagnosis knowledge graph, fault diagnosis information of the new energy vehicle chassis is generated, including: Determine an abnormal target chassis monitoring position according to the real-time chassis status information of the new energy vehicle chassis; Determining a candidate fault mode according to the chassis fault diagnosis knowledge graph and the abnormal target chassis monitoring position; For each candidate fault mode, according to the real-time chassis status information of the new energy vehicle chassis and the target chassis monitoring position associated with the candidate fault mode, determine the real-time abnormal characteristics of the new energy vehicle chassis corresponding to the candidate fault mode, and according to the real-time abnormal characteristics of the new energy vehicle chassis corresponding to the candidate fault mode and the abnormal characteristics corresponding to the fault mode, determine the matching degree of the candidate fault mode; According to the matching degree of each candidate fault mode, fault diagnosis information of the new energy vehicle chassis is generated.

9. The intelligent diagnosis method for chassis fault of new energy vehicles based on knowledge graph according to claim 8 is characterized in that: According to the real-time chassis status information of the new energy vehicle chassis and the target chassis monitoring position associated with the candidate fault mode, the real-time abnormal characteristics of the new energy vehicle chassis corresponding to the candidate fault mode are determined; according to the real-time abnormal characteristics of the new energy vehicle chassis corresponding to the candidate fault mode and the abnormal characteristics corresponding to the fault mode, the matching degree of the candidate fault mode is determined, including: According to the target chassis monitoring position associated with the candidate fault mode, extracting the real-time data corresponding to the target chassis monitoring position from the real-time chassis status information of the new energy vehicle chassis, performing variational mode decomposition on the test data, and extracting the real-time position feature corresponding to the target chassis monitoring position; Generate a real-time feature corresponding to the candidate fault mode according to the real-time feature of the position corresponding to each target chassis monitoring position associated with the candidate fault mode; The matching degree of the candidate fault mode is determined according to the real-time characteristics and abnormal characteristics corresponding to the candidate fault mode.

10. The intelligent diagnosis system for chassis faults of new energy vehicles based on knowledge graph is characterized by: The method for intelligent diagnosis of chassis faults of new energy vehicles based on knowledge graphs according to any one of claims 1 to 9 comprises: A data acquisition module is used to obtain a three-dimensional model of the chassis of a new energy vehicle; A scheme optimization module, used to determine an initial chassis monitoring scheme according to a three-dimensional model of the chassis of the new energy vehicle, wherein the initial chassis monitoring scheme includes a plurality of initial chassis monitoring positions and a monitoring feature type corresponding to each initial chassis monitoring position; The solution optimization module is also used to obtain a physical model corresponding to the new energy vehicle chassis; The scheme optimization module is also used to install a first chassis monitoring component on a physical model corresponding to the new energy vehicle chassis according to the initial chassis monitoring scheme, wherein the first chassis monitoring component includes a plurality of sensors installed according to the initial chassis monitoring scheme; The solution optimization module is also used to obtain chassis status information of a physical model corresponding to the chassis of the new energy vehicle under multiple fault modes through the first chassis monitoring component; The scheme optimization module is also used to determine the optimal chassis monitoring scheme according to the test chassis state information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes, wherein the optimal chassis monitoring scheme includes multiple target chassis monitoring positions and the monitoring feature type corresponding to each target chassis monitoring position; A graph building module is used to build a chassis fault diagnosis knowledge graph based on the chassis status information of the physical model corresponding to the new energy vehicle chassis under multiple fault modes; A state monitoring module, used for installing a second chassis monitoring component on the chassis of the new energy vehicle according to the optimal chassis monitoring solution, wherein the second chassis monitoring component includes a plurality of sensors installed according to the optimal chassis monitoring solution; The state monitoring module is also used to obtain real-time chassis state information of the new energy vehicle chassis through the second chassis monitoring component; The fault diagnosis module is used to generate fault diagnosis information of the new energy vehicle chassis according to the real-time chassis status information of the new energy vehicle chassis and the chassis fault diagnosis knowledge graph.

Images