Intelligent vehicle maintenance decision-making method based on digital twinning

Abstract

The invention discloses an intelligent vehicle maintenance decision-making method based on digital twinning, and relates to the technical field of intelligent maintenance decision-making, and the method comprises the steps: obtaining vehicle operation data, calculating the vibration frequency domain energy of a crankshaft and the wear ratio of a brake pad, and constructing a vehicle three-dimensional twinning body based on a Unity 3D engine; receiving a fault diagnosis result, carrying out fault type mapping, instantiating a fault description object based on the mapped fault type, injecting the fault description object into a corresponding part of the three-dimensional twin of the vehicle, executing multi-physics coupling simulation deduction, and generating a multi-physics coupling feature matrix; and inputting the obtained multi-physics field coupling characteristic matrix into a maintenance decision knowledge graph, sequentially executing similar case retrieval, prediction maintenance quotation calculation and workshop resource scheduling, and outputting a maintenance decision scheme. According to the invention, a quantitative and visual scientific basis is provided for fault mechanism analysis and positioning; and the pertinence, the economical efficiency and the workshop resource utilization efficiency of the maintenance scheme are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent maintenance decision-making technology, and in particular to a vehicle intelligent maintenance decision-making method based on digital twins. Background Art

[0002] In recent years, with the rapid development of intelligent connected vehicles, the field of vehicle operations and maintenance is transitioning from a singularly experience-driven approach to a data-driven one. On the one hand, the maturity of technologies such as on-board sensors, edge computing, and 5G V2X has enabled the real-time collection and processing of multi-source, heterogeneous time-series data, including vehicle vibration, current, temperature, and point clouds. On the other hand, the application of digital twin technology in fields such as aerospace and intelligent manufacturing has demonstrated the methodological advantages of using 3D virtual models to simultaneously reflect the operating status of physical equipment. Academia and industry have successively proposed simulation frameworks based on finite element analysis and multi-physics coupling to predict structural stress, heat conduction, and vibration propagation. Furthermore, the integration of knowledge graphs and deep learning provides end-to-end support for intelligent decision-making, from historical case retrieval to cost prediction. These research and practices have laid the technical foundation for the integration of digital twin technology into vehicle maintenance decision-making scenarios.

[0003] However, existing vehicle maintenance technologies are often limited to the following deficiencies: First, most solutions are limited to diagnostic analysis of a single data source or a single physical field, making it difficult to fully characterize the fault evolution process. They often rely on empirical working hour standards and lack a visual simulation basis for complex coupled faults. Second, static pricing and manual scheduling models are difficult to respond to price fluctuations of parts and dynamic changes in workshop resources, resulting in insufficient decision-making efficiency and economy. Third, maintenance plans are mostly presented in the form of process templates, lacking the interactive reasoning and case matching capabilities based on digital twin three-dimensional visualization models. Summary of the Invention

[0004] The present invention is proposed in view of the problems existing in existing vehicle intelligent maintenance decision-making methods based on digital twins. Therefore, the problem to be solved by the present invention is how to provide a vehicle intelligent maintenance decision-making method based on digital twins.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a vehicle intelligent maintenance decision-making method based on digital twins, which includes: Acquire vehicle operating data, calculate crankshaft vibration frequency domain energy and brake pad wear ratio, and build a 3D twin of the vehicle based on the Unity3D engine; Receive the fault diagnosis results, perform fault type mapping, instantiate a fault description object based on the mapped fault type, inject the fault description object into the corresponding component of the vehicle's three-dimensional twin, perform multi-physics field coupling simulation, and generate a multi-physics field coupling feature matrix; The obtained multi-physics field coupling feature matrix is ​​input into the maintenance decision knowledge graph, which includes a case matching layer, a cost optimization layer, and a resource scheduling layer. It sequentially performs similar case retrieval, predictive maintenance quotation calculation, and workshop resource scheduling to output a maintenance decision plan.

[0006] As a preferred solution of the vehicle intelligent maintenance decision-making method based on digital twins described in the present invention, the vehicle operation data includes crankshaft vibration data, temperature data and brake pad point cloud data.

[0007] As a preferred solution of the vehicle intelligent maintenance decision-making method based on digital twins of the present invention, the calculation of the crankshaft vibration frequency domain energy and the brake pad wear ratio includes: The crankshaft vibration frequency domain energy is calculated through the crankshaft vibration data, and the crankshaft vibration frequency domain energy is mapped to the crankshaft stress cloud map. The calculation formula of the crankshaft vibration frequency domain energy is: ; in: Frequency band The frequency domain energy of the crankshaft vibration, is the Fourier transform result of the crankshaft vibration data; and To analyze the frequency band; The brake surface profile is fitted through the brake pad point cloud data to calculate the brake pad wear ratio, which is then converted into a color heat map. The calculation formula for the brake pad wear ratio is: ; in: is the wear ratio of the brake pad, is the current thickness of the brake pad, is the nominal thickness of the brake pad.

[0008] As a preferred solution of the vehicle intelligent maintenance decision-making method based on digital twins of the present invention, the execution of multi-physics field coupling simulation includes: In the Unity3D engine, the crankshaft and brake pad models are bound to finite element meshes respectively to obtain the crankshaft mesh node set and the brake pad mesh node set; The damped wave equation is solved on the crankshaft mesh node set and is expressed as: ; in: For the moment Crankshaft mesh nodes The fault excitation source, is the displacement field, is the material density, is Young's modulus, is the damping coefficient, is the gradient; The vibration energy of each crankshaft grid node is calculated from the displacement field to identify abnormal vibration areas, which is expressed as: ; in: For the moment Vibrational energy; Crankshaft grid nodes whose vibration energy exceeds a predetermined threshold are marked as abnormal nodes. All abnormal nodes are grouped into an abnormal node coordinate set, which is rendered as arrows on the crankshaft surface of the vehicle's 3D twin, and the abnormal area is displayed with cloud coloring. Solve the steady-state heat conduction equation on the brake pad mesh node set, which is expressed as: ; in: Frictional heat source, is the thermal conductivity, is the real-time temperature field; The Unity3D engine is used to map the historical wear profile and the real-time temperature profile onto the same cross-sectional geometry to obtain the cross-sectional data and generate a multi-physics coupling characteristic matrix containing vibration energy and temperature gradient.

[0009] As a preferred solution of the vehicle intelligent maintenance decision-making method based on digital twins of the present invention, the case matching layer is used to search for similar cases based on the multi-physics field coupling feature matrix of the case, including: Project the multi-physics coupling characteristic matrix and express it as: ; in: is the multi-physics coupling characteristic matrix after projection, is the multi-physics coupling characteristic matrix, and are the encoder weights and biases respectively; The case vector is constructed for the projected multi-physics field coupling feature matrix, and the similarity between the new case vector and all historical case vectors is calculated, which is expressed as: ; in: is the similarity, is the historical case vector, is the new case vector; The historical case database is searched for cases whose similarity exceeds a predetermined similarity limit as preliminary candidate solutions.

[0010] As a preferred solution of the vehicle intelligent maintenance decision-making method based on digital twins of the present invention, the cost optimization layer is used to calculate the predictive maintenance quotation for the preliminary candidate solutions, including: Input historical parts prices and raw material indexes into the LSTM model to predict parts prices, output the predicted parts prices within a predetermined number of days in the future, and take the predicted parts prices on the current day as the real-time parts prices. Query the historical maintenance man-hour distribution of similar maintenance faults, obtain the standard deviation and maximum value of the historical maintenance man-hours, and calculate the maintenance dynamic difficulty coefficient, which is expressed as: ; in: is the maintenance dynamic difficulty coefficient, is the standard deviation of historical maintenance hours, The maximum value of historical maintenance hours; The predicted maintenance price of each preliminary candidate solution is calculated comprehensively and expressed as: ; in: To predict maintenance quotes, The base labor cost is Real-time accessories prices.

[0011] As a preferred solution of the vehicle intelligent maintenance decision-making method based on digital twins of the present invention, the resource scheduling layer is used to schedule workshop resources for vehicle maintenance, including: Obtain maintenance personnel lists, equipment status, and daily working hours limits from workshop smart terminals; Build a scheduling model to split the maintenance process steps into a set of tasks, each of which includes the required skill label, estimated working time, and priority weight; The constraints are that the maintenance personnel's skill tags match, the total working hours are less than the available working hours on the day, and the equipment can only perform one task at a time; the goal is to minimize the completion time; Using a heuristic scheduling algorithm, the highest priority task is selected in each round and assigned to the earliest available maintenance personnel and equipment with matching skill tags; The output includes maintenance decision plan including maintenance process sequence, predicted maintenance quotation and parts list.

[0012] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements the steps of a vehicle intelligent maintenance decision-making method based on digital twins.

[0013] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of a vehicle intelligent maintenance decision-making method based on digital twins are implemented.

[0014] The beneficial effects of the present invention are as follows: the present invention realizes the visualization and simulation of the status of key components with high fidelity, providing a quantitative and visual scientific basis for fault mechanism analysis and positioning; the maintenance decision-making process driven by knowledge graph and deep learning, combined with case retrieval, cost forecasting and resource scheduling, significantly improves the targetedness, economy and workshop resource utilization efficiency of maintenance plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 Flowchart of the vehicle intelligent maintenance decision-making method based on digital twins. DETAILED DESCRIPTION

[0017] To make the above-mentioned objects, features, and advantages of the present invention more easily understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, an embodiment or embodiments herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearance of "an embodiment" in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is exclusive or selectively mutually exclusive of other embodiments.

[0020] Reference Figure 1 , which is the first embodiment of the present invention, provides a vehicle intelligent maintenance decision-making method based on digital twins, including: S1: Obtain vehicle operation data, calculate crankshaft vibration frequency domain energy and brake pad wear ratio, and build a 3D twin of the vehicle based on the Unity3D engine; Specifically, a parameter-driven three-dimensional twin is built based on the Unity3D engine, in which the crankshaft stress cloud map module associates the vibration sensor data to generate a dynamic gradient shading model, and the brake pad wear module integrates the point cloud data of the three-dimensional scanner to generate a thickness attenuation heat map.

[0021] The vehicle-mounted edge computing system architecture includes edge computing devices, vibration sensors, infrared temperature sensor arrays, 3D scanners, and communication modules; Vehicle operation data includes crankshaft vibration data collected by vibration sensors, temperature data collected by infrared temperature sensor arrays, and brake pad point cloud data collected by 3D scanners; All sensor synchronization is controlled by a master clock (provided by the edge computing device), and each data point is accompanied by a UTC timestamp; Use the vehicle CAD model to predefine the spatial reference system of each sensor and project all sensor data into a unified vehicle coordinate system; Perform 3D twin modeling and build a complete vehicle 3D structure based on the Unity3D engine (focusing on modeling the crankshaft and brake pads). The twin is parameter-driven, and sensor data streams directly control model animation / texture rendering. The crankshaft vibration frequency domain energy is calculated using the crankshaft vibration data collected by the vibration sensor, and the crankshaft vibration frequency domain energy is mapped to a crankshaft stress cloud map. The calculation formula for the crankshaft vibration frequency domain energy is: ; in: Frequency band The frequency domain energy of the crankshaft vibration, is the Fourier transform result of the crankshaft vibration data; and To analyze the frequency band; The brake pad point cloud data is regularly output by a 3D scanner to fit the brake surface contour. The wear ratio of the brake pad is calculated by comparing the current thickness of the brake pad with the nominal thickness, which is expressed as: ; in: is the wear ratio of the brake pad, is the current thickness of the brake pad, is the nominal thickness of the brake pad.

[0022] The wear ratio of the brake pad is converted into a color heat map and fitted on the surface of the brake pad model.

[0023] S2: Receive the fault diagnosis results, perform fault type mapping, establish a fault description object within the twin, inject the diagnosed fault type into the 3D twin, perform multi-physics coupling simulation, and generate a multi-physics coupling feature matrix; Specifically, fault type mapping is performed, fault diagnosis results are received, a fault description object is created within the twin, the object is mounted to the corresponding module (crankshaft or brake pad), and the simulation process is triggered.

[0024] In the Unity3D engine, the crankshaft and brake pad models are bound to finite element (FEM) meshes to obtain the crankshaft mesh node set and the brake pad mesh node set. The damped wave equation is solved on the crankshaft mesh node set and is expressed as: ; in: For the moment Crankshaft mesh nodes The fault excitation source, is the displacement field, is the material density, is Young's modulus, is the damping coefficient, is the gradient; The vibration energy of each crankshaft grid node is calculated from the displacement field to identify abnormal vibration areas, which is expressed as: ; in: For the moment Vibrational energy; Crankshaft grid nodes whose vibration energy exceeds a predetermined threshold are marked as abnormal nodes. All abnormal nodes are grouped into an abnormal node coordinate set and rendered on the surface of the vehicle's three-dimensional twin crankshaft in the form of arrows, and the abnormal area is displayed with cloud map coloring.

[0025] Obtain historical wear gradients and real-time temperature fields. Historical wear gradients: Read multiple point cloud fitting results from the database and calculate the brake pad thickness change rate at the brake pad mesh nodes. Real-time temperature fields: Array interpolation to the brake pad mesh nodes results in temperature distribution.

[0026] Solve the steady-state heat conduction equation on the brake pad mesh node set, which is expressed as: ; in: Frictional heat source, is the thermal conductivity, is the real-time temperature field.

[0027] The Unity3D engine is used to map historical wear profiles and real-time temperature profiles onto the same cross-sectional geometry to obtain cross-sectional data. This data is then used to generate a multi-physics coupling feature matrix containing vibration energy and temperature gradients (each row corresponds to a grid node, and each column corresponds to a type of physical field feature, such as crankshaft vibration frequency domain energy and brake pad wear ratio).

[0028] S3: Input the obtained multi-physics field coupling feature matrix into the maintenance decision knowledge graph, perform similar case retrieval, predictive maintenance quotation calculation and workshop resource scheduling in sequence, and output the maintenance decision plan.

[0029] Specifically, the obtained multi-physics coupling feature matrix is ​​input into the maintenance decision knowledge graph, which includes a case matching layer, a cost optimization layer, and a resource scheduling layer. The case matching layer is used to retrieve similar cases; similarity retrieval is performed on the cases, and the multi-physics coupling feature matrix is ​​projected and expressed as: ; in: is the multi-physics coupling characteristic matrix after projection, is the multi-physics coupling characteristic matrix, and are the encoder weights and biases respectively; The case vector is constructed for the projected multi-physics field coupling feature matrix, and the similarity between the new case vector and all historical case vectors is calculated, which is expressed as: ; in: is the similarity, is the historical case vector, is the new case vector; The historical case database is searched for cases whose similarity exceeds a predetermined similarity limit as preliminary candidate solutions.

[0030] The cost optimization layer is used to calculate predictive repair quotations. It inputs historical parts prices, raw material indices, etc. into the LSTM model to predict parts prices, outputs the predicted prices of each part within a predetermined number of days in the future, and takes the predicted price of the part on the current day as the real-time part price.

[0031] Query the historical maintenance man-hour distribution corresponding to similar maintenance faults, obtain the standard deviation and maximum value of the historical maintenance man-hours, and calculate the maintenance dynamic difficulty coefficient, which is expressed as: ; in: is the maintenance dynamic difficulty coefficient, is the standard deviation of historical maintenance hours, is the maximum value of historical maintenance hours after removing abnormal values; The predicted maintenance price of each preliminary candidate solution is calculated comprehensively and expressed as: ; in: To predict maintenance quotes, The base labor cost is Real-time accessories prices; The resource scheduling layer is used to schedule workshop resources for vehicle maintenance, obtaining a list of maintenance personnel, equipment status (idle / occupied), and the maintenance personnel's daily working hours from the workshop's intelligent terminals; Build a scheduling model to split the maintenance process steps into a set of tasks. Each task includes the required skill label, estimated working time, and priority weight (derived from the ranking of preliminary candidate solutions by the case matching layer solution); The constraints are that the maintenance personnel's skill tags match, the total working hours are less than the available working hours on the day, and the equipment can only perform one task at a time; the goal is to minimize the completion time; Using a heuristic scheduling algorithm, the highest priority task is selected in each round and assigned to the earliest available maintenance personnel and equipment with matching skill tags; The output includes maintenance process sequence, predicted maintenance quotation and maintenance decision plan of parts list.

[0032] This embodiment also provides a computer device, which is suitable for the case of a vehicle intelligent maintenance decision-making method based on digital twins, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement all or part of the steps of the method described in the embodiment of the present invention as proposed in the above embodiment.

[0033] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, executes the method of any optional implementation of the above embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0034] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. Technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0035] In summary, the present invention achieves high-fidelity visualization and simulation of the status of key components, providing a quantitative and visual scientific basis for fault mechanism analysis and location; the maintenance decision-making process driven by knowledge graphs and deep learning, combined with case retrieval, cost forecasting and resource scheduling, significantly improves the targetedness, economy and workshop resource utilization efficiency of maintenance plans.

[0036] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A vehicle intelligent maintenance decision-making method based on digital twins, characterized by: include, Acquire vehicle operating data, calculate crankshaft vibration frequency domain energy and brake pad wear ratio, and build a 3D twin of the vehicle based on the Unity3D engine; Receive the fault diagnosis results, perform fault type mapping, instantiate a fault description object based on the mapped fault type, inject the fault description object into the corresponding component of the vehicle's three-dimensional twin, perform multi-physics field coupling simulation, and generate a multi-physics field coupling feature matrix; The obtained multi-physics field coupling feature matrix is ​​input into the maintenance decision knowledge graph, which includes a case matching layer, a cost optimization layer, and a resource scheduling layer. It sequentially performs similar case retrieval, predictive maintenance quotation calculation, and workshop resource scheduling to output a maintenance decision plan.

2. The vehicle intelligent maintenance decision-making method based on digital twins according to claim 1, characterized in that: The vehicle operation data includes crankshaft vibration data, temperature data and brake pad point cloud data.

3. The vehicle intelligent maintenance decision-making method based on digital twins according to claim 2 is characterized in that: The calculation of the crankshaft vibration frequency domain energy and the brake pad wear ratio includes: The crankshaft vibration frequency domain energy is calculated through the crankshaft vibration data, and the crankshaft vibration frequency domain energy is mapped to the crankshaft stress cloud map. The calculation formula of the crankshaft vibration frequency domain energy is: ; in: Frequency band The frequency domain energy of the crankshaft vibration, is the Fourier transform result of the crankshaft vibration data; and To analyze the frequency band; The brake surface profile is fitted through the brake pad point cloud data to calculate the brake pad wear ratio, which is then converted into a color heat map. The calculation formula for the brake pad wear ratio is: ; in: is the wear ratio of the brake pad, is the current thickness of the brake pad, is the nominal thickness of the brake pad.

4. The vehicle intelligent maintenance decision-making method based on digital twins according to claim 3 is characterized by: The performing of multi-physics field coupling simulation deduction includes: In the Unity3D engine, the crankshaft and brake pad models are bound to finite element meshes respectively to obtain the crankshaft mesh node set and the brake pad mesh node set; The damped wave equation is solved on the crankshaft mesh node set and is expressed as: ; in: For the moment Crankshaft mesh nodes The fault excitation source, is the displacement field, is the material density, is Young's modulus, is the damping coefficient, is the gradient; The vibration energy of each crankshaft grid node is calculated from the displacement field to identify abnormal vibration areas, which is expressed as: ; in: For the moment Vibrational energy; Crankshaft grid nodes whose vibration energy exceeds a predetermined threshold are marked as abnormal nodes. All abnormal nodes are grouped into an abnormal node coordinate set, which is rendered as arrows on the crankshaft surface of the vehicle's 3D twin, and the abnormal area is displayed with cloud coloring. Solve the steady-state heat conduction equation on the brake pad mesh node set, which is expressed as: ; in: Frictional heat source, is the thermal conductivity, is the real-time temperature field; The Unity3D engine is used to map the historical wear profile and the real-time temperature profile onto the same cross-sectional geometry to obtain the cross-sectional data and generate a multi-physics coupling characteristic matrix containing vibration energy and temperature gradient.

5. The vehicle intelligent maintenance decision-making method based on digital twins according to claim 4 is characterized in that: The case matching layer is used to search for similar cases based on the multi-physics coupling feature matrix of the case, including: Project the multi-physics coupling characteristic matrix and express it as: ; in: is the multi-physics coupling characteristic matrix after projection, is the multi-physics coupling characteristic matrix, and are the encoder weights and biases respectively; The case vector is constructed for the projected multi-physics field coupling feature matrix, and the similarity between the new case vector and all historical case vectors is calculated, which is expressed as: ; in: is the similarity, is the historical case vector, is the new case vector; The historical case database is searched for cases whose similarity exceeds a predetermined similarity limit as preliminary candidate solutions.

6. The vehicle intelligent maintenance decision-making method based on digital twins according to claim 5 is characterized by: The cost optimization layer is used to calculate the predictive maintenance quotation for the preliminary candidate solutions, including: Input historical parts prices and raw material indexes into the LSTM model to predict parts prices, output the predicted parts prices within a predetermined number of days in the future, and take the predicted parts prices on the current day as the real-time parts prices. Query the historical maintenance man-hour distribution of similar maintenance faults, obtain the standard deviation and maximum value of the historical maintenance man-hours, and calculate the maintenance dynamic difficulty coefficient, which is expressed as: ; in: is the maintenance dynamic difficulty coefficient, is the standard deviation of historical maintenance hours, The maximum value of historical maintenance hours; The predicted maintenance price of each preliminary candidate solution is obtained through comprehensive calculation and is expressed as: ; in: To predict maintenance quotes, The base labor cost is Real-time accessories prices.

7. The vehicle intelligent maintenance decision-making method based on digital twins according to claim 6 is characterized in that: The resource scheduling layer is used to schedule workshop resources for vehicle maintenance, including: Obtain maintenance personnel lists, equipment status, and daily working hours limits from workshop smart terminals; Build a scheduling model to split the maintenance process steps into a set of tasks, each of which includes the required skill label, estimated working time, and priority weight; The constraints are that the maintenance personnel's skill tags match, the total working hours are less than the available working hours on the day, and the equipment can only perform one task at a time; the goal is to minimize the completion time; Using a heuristic scheduling algorithm, the highest priority task is selected in each round and assigned to the earliest available maintenance personnel and equipment with matching skill tags; The output includes maintenance decision plan including maintenance process sequence, predicted maintenance quotation and parts list.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the vehicle intelligent maintenance decision-making method based on digital twins according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle intelligent maintenance decision-making method based on digital twins according to any one of claims 1 to 7 are implemented.

Images