A method and system for analyzing the maturity of a deconstruction model of a hydrogen energy vehicle

Abstract

The present invention provides a method and system for analyzing the maturity of a deconstruction model of a hydrogen energy vehicle, which relates to the technical field of vehicle model deconstruction. The comprehensive control data of a hydrogen energy vehicle is classified to obtain control data at multiple stages and multiple types of control data at each stage. A vehicle control model is trained, and the vehicle control model is subjected to a first deconstruction and a second deconstruction to obtain first deconstruction data and second deconstruction data. A first deconstruction evaluation coefficient and a second deconstruction evaluation coefficient are calculated; a comprehensive deconstruction coefficient is calculated, and a comprehensive deconstruction evaluation is performed on the vehicle control model, and then a comprehensive deconstruction maturity evaluation is performed to obtain an evaluation result. The present invention can effectively improve the evaluation level of the deconstruction performance maturity of the control system of a hydrogen energy vehicle.

Description

Technical Field

[0001] The present invention provides a method and system for analyzing the maturity of a deconstruction model of a hydrogen energy vehicle, relating to the technical field of vehicle model deconstruction, and specifically to the technical field of analyzing the maturity of a deconstruction model of a hydrogen energy vehicle. Background Art

[0002] During the development of hydrogen energy vehicles, the design and implementation of the vehicle software control system are one of the key links. To achieve the efficient, stable, and safe operation of hydrogen energy vehicles, in-depth analysis and precise control of their comprehensive control data are required. This requires classifying the comprehensive control data according to stages and stage types to obtain multiple stage control data and multiple types of control data for each stage. By establishing the mapping relationship between these data, an accurate vehicle software control system can be generated to achieve precise regulation of each control link of the hydrogen energy vehicle. However, the complexity and diversity of the vehicle control system make it particularly difficult to evaluate its performance. Traditional methods often can only generally evaluate the overall performance of the vehicle control system, and it is difficult to deeply analyze its internal control mechanism and existing problems. To more comprehensively and accurately evaluate the performance of the hydrogen energy vehicle control system, a more refined deconstruction evaluation method is needed, while traditional deconstruction methods have problems such as insufficient stability and accuracy. Summary of the Invention

[0003] The present invention provides a method and system for analyzing the maturity of a deconstruction model of a hydrogen energy vehicle to solve the problem that the complexity and diversity of the vehicle control system make it particularly difficult to evaluate its performance. Traditional methods often can only generally evaluate the overall performance of the vehicle control system, and it is difficult to deeply analyze its internal control mechanism and existing problems. To more comprehensively and accurately evaluate the performance of the hydrogen energy vehicle control system, a more refined deconstruction evaluation method is needed, while traditional deconstruction methods have problems such as insufficient stability and accuracy, etc.:

[0004] A method and system for analyzing the maturity of a deconstruction model of a hydrogen energy vehicle proposed by the present invention, the method includes:

[0005] S1. Classify the comprehensive control data of the hydrogen energy vehicle according to stages and stage types to obtain multiple stage control data and multiple types of control data for each stage, establish a mapping relationship, and generate a vehicle software control system;

[0006] S2. Train a vehicle control model, perform a first deconstruction on the vehicle control model to obtain first deconstruction data, calculate a first deconstruction evaluation coefficient, and perform a first deconstruction evaluation according to the first deconstruction evaluation coefficient to obtain a first deconstruction evaluation result;

[0007] S3. Perform a second deconstruction on the vehicle control model to obtain second deconstruction data, calculate a second deconstruction evaluation coefficient, and conduct a second deconstruction evaluation based on the second deconstruction evaluation coefficient to obtain a second deconstruction evaluation result;

[0008] S4. Calculate a comprehensive deconstruction coefficient, conduct a comprehensive deconstruction evaluation on the vehicle control model, and then conduct a comprehensive maturity evaluation to obtain an evaluation result.

[0009] Further, the S1 includes:

[0010] Obtain the comprehensive control data of the hydrogen energy vehicle, classify the comprehensive control data according to the acquisition stage of the comprehensive control data to obtain multiple stage control data; classify the control data of each stage according to the data type to obtain multiple type control data of the stage;

[0011] Obtain multiple control stages of the hydrogen energy vehicle, classify each control stage of the multiple control stages according to the control type to obtain multiple control types of the stage;

[0012] Establish a mapping relationship between the multiple type control data of each stage and the multiple control types, and obtain the mapping relationship data;

[0013] Generate the vehicle software control system corresponding to the control data according to the mapping relationship data.

[0014] Further, the S2 includes:

[0015] Obtain the comprehensive control data, multiple stage control data, multiple type control data combined with the vehicle software control system data to generate a control training set;

[0016] Train a neural network model according to the control training set to obtain a vehicle control model;

[0017] Obtain a first-level deconstruction target, perform deconstruction on the vehicle control model according to the first-level deconstruction target to obtain first deconstruction data;

[0018] Calculate a first deconstruction evaluation coefficient according to the first deconstruction data, compare the first deconstruction evaluation coefficient with a preset first coefficient threshold to obtain a first deconstruction comparison result, and conduct a first deconstruction evaluation on the vehicle control model according to the first deconstruction comparison result to obtain a first deconstruction evaluation result.

[0019] Further, the S3 includes:

[0020] Obtain a second-level deconstruction target according to the first-level deconstruction target, perform deconstruction on the first-level deconstruction target of the vehicle control model according to the second-level structure target to obtain second deconstruction data;

[0021] Calculate a second deconstruction evaluation coefficient based on the second deconstruction data, compare the second deconstruction evaluation coefficient with a preset second coefficient threshold to obtain a second deconstruction comparison result, and perform a second deconstruction evaluation on the vehicle control model according to the second deconstruction comparison result to obtain a second deconstruction evaluation result.

[0022] Further, the S4 includes:

[0023] Calculate a comprehensive deconstruction coefficient based on the data of the first deconstruction evaluation result combined with the data of the second deconstruction evaluation result;

[0024] Compare the comprehensive deconstruction coefficient with a preset comprehensive deconstruction threshold to obtain a comprehensive comparison result;

[0025] Perform a comprehensive deconstruction evaluation on the vehicle control model according to the comprehensive comparison result to obtain a comprehensive deconstruction evaluation result;

[0026] Perform a comprehensive deconstruction maturity evaluation, a first deconstruction maturity evaluation, and a second deconstruction maturity evaluation on the vehicle control model according to the comprehensive deconstruction evaluation result, the first deconstruction evaluation result, and the second deconstruction evaluation result to obtain a comprehensive deconstruction maturity evaluation result, a first deconstruction maturity evaluation result, and a second deconstruction maturity evaluation result.

[0027] Further, the system includes:

[0028] A classification mapping generation module, which is used to classify the comprehensive control data of the hydrogen energy vehicle according to stages and stage types, obtain multiple stage control data and multiple types of control data for each stage, establish a mapping relationship, and generate a vehicle software control system;

[0029] A first deconstruction evaluation module, which is used to train the vehicle control model, perform a first deconstruction on the vehicle control model to obtain first deconstruction data, calculate a first deconstruction evaluation coefficient, and perform a first deconstruction evaluation according to the first deconstruction evaluation coefficient to obtain a first deconstruction evaluation result;

[0030] A second deconstruction evaluation module, which is used to perform a second deconstruction on the vehicle control model to obtain second deconstruction data, calculate a second deconstruction evaluation coefficient, and perform a second deconstruction evaluation according to the second deconstruction evaluation coefficient to obtain a second deconstruction evaluation result;

[0031] A comprehensive deconstruction evaluation module, which is used to calculate a comprehensive deconstruction coefficient, perform a comprehensive deconstruction evaluation on the vehicle control model, and then perform a comprehensive deconstruction maturity evaluation to obtain an evaluation result.

[0032] Further, the classification mapping generation module includes:

[0033] A data stage classification module, which is used to obtain the comprehensive control data of a hydrogen energy vehicle, classify the comprehensive control data according to the acquisition stage of the comprehensive control data to obtain multiple stage control data; classify the control data of each stage according to the data type to obtain multiple type control data of the stage;

[0034] A data type classification module, which is used to obtain multiple control stages of a hydrogen energy vehicle, classify each control stage of the multiple control stages according to the control type to obtain multiple control types of the stage;

[0035] A mapping system generation module, which is used to establish the mapping relationship between the multiple type control data of each stage and the multiple control types, and obtain its mapping relationship data;

[0036] Generate the vehicle software control system corresponding to the control data according to the mapping relationship data.

[0037] Further, the first deconstruction evaluation module includes:

[0038] A model training module, which is used to obtain the comprehensive control data, multiple stage control data, multiple type control data and combine with the vehicle software control system data to generate a control training set;

[0039] Train a neural network model according to the control training set to obtain a vehicle control model;

[0040] A first deconstruction module, which is used to obtain a first-level deconstruction target, deconstruct the vehicle control model according to the first-level deconstruction target to obtain first deconstruction data;

[0041] A first evaluation module, which is used to calculate a first deconstruction evaluation coefficient according to the first deconstruction data, compare the first deconstruction evaluation coefficient with a preset first coefficient threshold to obtain a first deconstruction comparison result, and perform a first deconstruction evaluation on the vehicle control model according to the first deconstruction comparison result to obtain a first deconstruction evaluation result.

[0042] Further, the second deconstruction evaluation module includes:

[0043] A second deconstruction module, which is used to obtain a second-level deconstruction target according to the first-level deconstruction target, deconstruct the first-level deconstruction target of the vehicle control model according to the second-level structure target to obtain second deconstruction data;

[0044] A second evaluation module, which is used to calculate a second deconstruction evaluation coefficient according to the second deconstruction data, compare the second deconstruction evaluation coefficient with a preset second coefficient threshold to obtain a second deconstruction comparison result, and perform a second deconstruction evaluation on the vehicle control model according to the second deconstruction comparison result to obtain a second deconstruction evaluation result.

[0045] Further, the comprehensive deconstruction evaluation module includes:

[0046] A comprehensive deconstruction evaluation module for calculating a comprehensive deconstruction coefficient according to the data of the first deconstruction evaluation result combined with the data of the second deconstruction evaluation result;

[0047] Comparing the comprehensive deconstruction coefficient with a preset comprehensive deconstruction threshold to obtain a comprehensive comparison result;

[0048] Conducting a comprehensive deconstruction evaluation on the vehicle control model according to the comprehensive comparison result to obtain a comprehensive deconstruction evaluation result;

[0049] A maturity evaluation module for conducting a comprehensive deconstruction maturity evaluation, a first deconstruction maturity evaluation, and a second deconstruction maturity evaluation on the vehicle control model according to the comprehensive deconstruction evaluation result, the first deconstruction evaluation result, and the second deconstruction evaluation result, to obtain a comprehensive deconstruction maturity evaluation result, a first deconstruction maturity evaluation result, and a second deconstruction maturity evaluation result.

[0050] Advantages of the present invention: Through phased and categorized data classification and mapping, as well as multi-level deconstruction evaluation, it can more accurately reflect the performance and efficiency of hydrogen energy vehicles under different operating conditions, improving the accuracy of evaluation. Through deconstruction evaluation, problems and bottlenecks in the vehicle control system can be discovered. For example, the configuration of the power system can be adjusted and the battery management strategy can be optimized according to the evaluation results, improving the overall performance and efficiency of the vehicle. By optimizing the vehicle design and control strategy, the driving experience and ride comfort of hydrogen energy vehicles can be enhanced. At the same time, reducing failure rates and improving safety are also important aspects of enhancing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of a method for analyzing the maturity of a deconstruction model of a hydrogen energy vehicle;

[0052] Figure 2 It is a schematic diagram of a system for analyzing the maturity of a deconstruction model of a hydrogen energy vehicle. DETAILED DESCRIPTION OF THE INVENTION

[0053] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustration and explanation of the present invention, and are not used to limit the present invention.

[0054] In one embodiment of the present invention, a method and system for analyzing the maturity of a deconstruction model of a hydrogen energy vehicle proposed by the present invention, the method includes:

[0055] S1. Classify the comprehensive control data of hydrogen energy vehicles according to stages and stage types, obtain multiple stage control data and multiple types of control data for each stage, establish a mapping relationship, and generate a vehicle software control system.

[0056] S2. Train a vehicle control model, perform a first decomposition on the vehicle control model, obtain first decomposition data, calculate a first decomposition evaluation coefficient, and conduct a first decomposition evaluation based on the first decomposition evaluation coefficient to obtain a first decomposition evaluation result.

[0057] S3. Perform a second decomposition on the vehicle control model, obtain second decomposition data, calculate a second decomposition evaluation coefficient, and conduct a second decomposition evaluation based on the second decomposition evaluation coefficient to obtain a second decomposition evaluation result.

[0058] S4. Calculate a comprehensive decomposition coefficient, conduct a comprehensive decomposition evaluation on the vehicle control model, and then conduct a comprehensive decomposition maturity evaluation to obtain an evaluation result.

[0059] The working principle of the above technical solution is as follows: The system collects the comprehensive control data of hydrogen energy vehicles, which includes but is not limited to vehicle operating status, energy consumption, power output, battery status, etc. These data are classified according to different stages (such as startup, driving, parking, etc.) and stage types (such as normal driving, acceleration, deceleration, etc.) to form multiple stage control data and multiple types of control data for each stage. Through data analysis, a mapping relationship is established between these control data and the vehicle software control system to ensure that the control data for each stage and type can be accurately reflected in the vehicle software control system. Based on the classified data, a vehicle control model is trained to accurately simulate the actual operation of hydrogen energy vehicles. The trained vehicle control model is subjected to a first decomposition, splitting the model into smaller components (such as power system, battery management system, control system, etc.), and the first decomposition data is obtained. Based on these data, a first decomposition evaluation coefficient is calculated to evaluate the performance and efficiency of each part. On the basis of the first decomposition, a more in-depth second decomposition is carried out to further refine the sub-modules or functional units of each part, and the second decomposition data is obtained. Similarly, a second decomposition evaluation coefficient is calculated for a more detailed evaluation. The first decomposition evaluation result and the second decomposition evaluation result are weighted to calculate a comprehensive decomposition coefficient. This coefficient comprehensively reflects the performance and maturity of the vehicle control model at different levels. According to the comprehensive decomposition coefficient, a comprehensive decomposition maturity evaluation is conducted on the vehicle control model, and finally an evaluation result is obtained. The evaluation result can intuitively reflect the maturity and optimization space of hydrogen energy vehicles in terms of design, manufacturing, control, etc.

[0060] The technical effects of the above technical solution are as follows: Through phased and categorized data classification and mapping, as well as multi-level deconstruction evaluation, it can more accurately reflect the performance and efficiency of hydrogen energy vehicles under different operating conditions, improving the accuracy of evaluation. Through deconstruction evaluation, problems and bottlenecks in the vehicle control system can be discovered. For example, according to the evaluation results, the configuration of the power system can be adjusted, the battery management strategy can be optimized, etc., to improve the overall performance and efficiency of the vehicle. By optimizing the vehicle design and control strategy, the driving experience and riding comfort of hydrogen energy vehicles can be enhanced. At the same time, reducing the failure rate and improving safety are also important aspects of enhancing the user experience.

[0061] In one embodiment of the present invention, S1 includes:

[0062] Obtain the comprehensive control data of the hydrogen energy vehicle, classify the comprehensive control data according to the acquisition stage of the comprehensive control data to obtain multiple stage control data; classify the control data of each stage according to the data type to obtain multiple type control data of the stage; the stage control data includes start-up stage data, driving stage data and parking stage data, and the data types include speed data, temperature data, pressure data, battery state data, etc.;

[0063] Obtain multiple control stages of the hydrogen energy vehicle, classify each control stage of the multiple control stages according to the control type to obtain multiple control types of the stage; the control stages include start-up stage, driving stage and parking stage, and the control types include speed control, temperature control, pressure control, battery state control, etc.;

[0064] Establish the mapping relationship between multiple type control data of each stage and multiple control types, and obtain its mapping relationship data;

[0065] Generate the vehicle software control system corresponding to the control data according to the mapping relationship data.

[0066] The working principle of the above technical solution is as follows: The system obtains the comprehensive control data of the hydrogen energy vehicle in real time through devices such as sensors and in-vehicle computers. These data cover various parameters of the vehicle under different operating states. Classify the comprehensive control data according to the data acquisition phases (such as the startup phase, driving phase, and parking phase) to obtain the control data for each phase. In this way, the data can be organized in an orderly manner according to the time sequence and vehicle operating states. Within each phase, further classify according to the data types (such as speed data, temperature data, pressure data, battery status data, etc.) to obtain multiple types of control data for each phase. This classification helps with subsequent data analysis and processing. The system simultaneously identifies multiple control phases (startup, driving, parking) of the hydrogen energy vehicle, and these phases correspond to the data acquisition phases of the comprehensive control data. For each control phase, classify according to the control types (such as speed control, temperature control, pressure control, battery status control, etc.). This classification reflects various control operations that need to be performed by the vehicle in different phases. Based on the above classification results, the system establishes a mapping relationship between multiple types of control data and multiple control types for each phase. This mapping relationship clarifies the corresponding relationship between different data types and control types, providing a basis for the generation of the vehicle software control system. The mapping relationship data is usually presented in the form of a database, table, or graphical interface for subsequent software design and development. According to the mapping relationship data, the system generates a vehicle software control system that matches the actual operation of the hydrogen energy vehicle. This system can receive real-time data from sensors and precisely control and manage the vehicle according to preset control logics and algorithms. The generation of the vehicle software control system includes multiple links such as software architecture design, algorithm writing, and interface definition, aiming to achieve the efficient, safe, and stable operation of the vehicle.

[0067] The technical effects of the above technical solution are as follows: By classifying the comprehensive control data by phase and type, the organization and utilization efficiency of the data are improved. This makes subsequent data analysis and processing more convenient and efficient. Establishing a mapping relationship between control data and control types helps to optimize the vehicle's control strategy. The system can adjust control parameters according to real-time data to achieve more precise and efficient vehicle control. The generation of the vehicle software control system is based on detailed mapping relationship data, which can ensure the close matching of the system with the actual vehicle operation. This helps to improve the reliability and stability of the system and reduce the likelihood of failures. By improving the control accuracy and stability of the vehicle, the driving experience and riding comfort of users can be significantly improved. At the same time, reducing the failure rate and improving safety are also important aspects of enhancing the user experience.

[0068] In an embodiment of the present invention, S2 includes:

[0069] Obtain comprehensive control data, multiple-stage control data, and multiple types of control data, and combine them with vehicle software control system data to generate a control training set;

[0070] Train a neural network model according to the control training set to obtain a vehicle control model;

[0071] Obtain a first-level deconstruction target, and deconstruct the vehicle control model according to the first-level deconstruction target to obtain first deconstruction data; the first-level deconstruction target includes preset deconstruction targets for each control stage;

[0072] Calculate a first deconstruction evaluation coefficient according to the first deconstruction data, compare the first deconstruction evaluation coefficient with a preset first coefficient threshold to obtain a first deconstruction comparison result, and perform a first deconstruction evaluation on the vehicle control model according to the first deconstruction comparison result to obtain a first deconstruction evaluation result.

[0073] When the first deconstruction evaluation coefficient is greater than the preset first coefficient threshold, the first deconstruction of the vehicle control model is evaluated as a good deconstruction; otherwise, it is a poor deconstruction.

[0074] The calculation formula for the first deconstruction evaluation coefficient is:

[0075]

[0076] Where, G py is the first deconstruction evaluation coefficient, k is the number of control stages, m is the number of preset deconstruction targets, B sjn is the target deconstruction data of the nth preset deconstruction target, S sjsn is the actual deconstruction data of the nth preset deconstruction target, is the mean value of the deconstruction evaluation difference coefficients of the dth control stage.

[0077] The working principle of the above technical solution is as follows: Comprehensive control data is obtained from the vehicle software control system, sensors, and other data sources of a hydrogen energy vehicle. This data includes control data for multiple stages (such as start, driving, parking) and multiple types of control data (such as speed, temperature, pressure, battery status, etc.). By combining this data with information such as the operation log and parameter configuration of the vehicle software control system, a control training set is generated. This training set contains the control data of the vehicle in different operating states and their corresponding control results or effects. This training set is used to train a neural network model. Through multiple iterations and optimizations, a vehicle control model that can accurately reflect the vehicle control logic is finally obtained. Set the first-level deconstruction targets, which are usually the specific requirements and expected effects for the vehicle control model in each control stage. For example, during the driving stage, the model may be required to accurately control the vehicle speed and maintain a stable battery status. According to these preset deconstruction targets, the vehicle control model is deconstructed, that is, the performance and internal mechanism of the model in each control stage are analyzed to obtain the first deconstruction data. These data reflect the operating conditions and performance parameters of the model under specific targets. Calculate the first deconstruction evaluation coefficient using the first deconstruction data. Compare the calculated first deconstruction evaluation coefficient with the preset first coefficient threshold. If the evaluation coefficient is greater than the threshold, it is considered that the model performs well under this deconstruction target, and the deconstruction evaluation result is "good deconstruction"; otherwise, it is considered that the performance is poor, and the deconstruction evaluation result is "poor deconstruction".

[0078] The technical effects of the above technical solution are as follows: By generating a control training set and training a neural network model, a more accurate and reliable vehicle control model can be obtained. This model can more accurately reflect the actual control requirements of the vehicle, improving driving safety and comfort. The process of model deconstruction and evaluation helps to deeply understand the internal mechanism and control logic of the model. By setting deconstruction targets and calculating deconstruction evaluation coefficients, the performance of the model in different aspects can be quantified, providing strong support for the optimization and improvement of the model. The setting of the first-level deconstruction targets makes the model deconstruction and evaluation process more flexible and customizable. According to different application scenarios and requirements, different deconstruction targets and evaluation criteria can be set to meet specific control needs. The deconstruction evaluation results can provide important reference information for decision-makers. By understanding the performance of the model under different deconstruction targets, decision-makers can more accurately evaluate the applicability and reliability of the model, and thus make more informed decisions. In an embodiment of the present invention, S3 includes:

[0079] Obtain the second-level deconstruction targets according to the first-level deconstruction targets, and deconstruct the first-level deconstruction targets of the vehicle control model according to the second-level structural targets to obtain the second deconstruction data; the second-level deconstruction targets include the preset deconstruction targets for each control type in each control stage;

[0080] Calculate the second deconstruction evaluation coefficient according to the second deconstruction data, compare the second deconstruction evaluation coefficient with a preset second coefficient threshold to obtain a second deconstruction comparison result, and perform a second deconstruction evaluation on the vehicle control model according to the second deconstruction comparison result to obtain a second deconstruction evaluation result.

[0081] When the second deconstruction evaluation coefficient is greater than the preset second coefficient threshold, the second deconstruction of the vehicle control model is evaluated as a good deconstruction; otherwise, it is a poor deconstruction.

[0082] The calculation formula for the second deconstruction evaluation coefficient is:

[0083]

[0084] Where G pr is the second deconstruction evaluation coefficient, z is the total number of control types, E is the total number of preset deconstruction targets for each control type, B sji is the target deconstruction data of the i-th preset deconstruction target, S sjsi is the actual deconstruction data of the i-th preset deconstruction target, is the deconstruction evaluation difference coefficient of the i-th preset control target of the o-th control type in the d-th control stage.

[0085] The working principle of the above technical solution is as follows: After completing the first-level deconstruction evaluation, in order to further deeply analyze and optimize the vehicle control model, according to the feedback of the first-level deconstruction target and the actual needs of vehicle control, the second-level deconstruction target is set. These targets are more specific and refined, and preset deconstruction targets are set for each control type in each control stage. For example, in speed control during the driving stage, the model may be required to have different control precisions and response speeds in different speed ranges. Based on the second-level deconstruction target, a more detailed deconstruction of the performance of the vehicle control model under the first-level deconstruction target is carried out. This process involves a detailed analysis of the specific behavior of each control type within the control stage to obtain the second deconstruction data. These data provide detailed performance parameters and performance situations of the model under specific control types and stages. Using the second deconstruction data, calculate the second deconstruction evaluation coefficient according to the preset evaluation method. This coefficient comprehensively considers the performance of the model under multiple control types and stages, and compares the calculated second deconstruction evaluation coefficient with the preset second coefficient threshold. According to the comparison result, perform a second deconstruction evaluation on the vehicle control model to draw a conclusion of "good deconstruction" or "poor deconstruction". This evaluation result is more specific and comprehensive, and can more accurately reflect the performance of the model under different control types and stages.

[0086] The technical effects of the above technical solution are as follows: By refining the deconstruction objectives and evaluation methods, the second-level deconstruction evaluation improves the accuracy of the performance evaluation of the vehicle control model. It can more accurately identify the advantages and disadvantages of the model under different control types and stages, providing more detailed and specific guidance for the optimization and improvement of the model. Through the second-level deconstruction evaluation of the model, performance bottlenecks and potential problems of the model under specific control types and stages can be discovered. This helps developers to carry out targeted optimization and improvement for these problems, enhancing the overall performance and stability of the model. The second-level deconstruction evaluation method enables the vehicle control model to better adapt to different driving scenarios and control requirements. By refining the deconstruction objectives and evaluation methods, it can ensure that the model maintains high control accuracy and stability under different conditions. Through the detailed performance evaluation and optimization of the vehicle control model, the comfort and safety of driving can be significantly improved. This helps to enhance the driving experience of users and strengthen their trust and satisfaction with hydrogen energy vehicles. The second-level deconstruction evaluation promotes continuous improvement and innovation in aspects such as control algorithms and model design.

[0087] In one embodiment of the present invention, S4 includes:

[0088] Calculate the comprehensive deconstruction coefficient based on the data of the first deconstruction evaluation result and the data of the second deconstruction evaluation result;

[0089] The calculation formula of the comprehensive deconstruction coefficient is:

[0090]

[0091] Wherein, H zj is the comprehensive deconstruction coefficient;

[0092] Compare the comprehensive deconstruction coefficient with a preset comprehensive deconstruction threshold to obtain a comprehensive comparison result;

[0093] Conduct a comprehensive deconstruction evaluation on the vehicle control model according to the comprehensive comparison result to obtain a comprehensive deconstruction evaluation result;

[0094] When the comprehensive deconstruction coefficient is greater than the preset comprehensive deconstruction threshold, the comprehensive deconstruction of the vehicle control model is evaluated as good deconstruction; otherwise, it is evaluated as poor deconstruction.

[0095] Conduct a comprehensive deconstruction maturity evaluation, a first deconstruction maturity evaluation, and a second deconstruction maturity evaluation on the vehicle control model based on the comprehensive deconstruction evaluation result, the first deconstruction evaluation result, and the second deconstruction evaluation result to obtain a comprehensive deconstruction maturity evaluation result, a first deconstruction maturity evaluation result, and a second deconstruction maturity evaluation result.

[0096] The working principle of the above technical solution is as follows: The comprehensive deconstruction coefficient is a comprehensive evaluation index that combines the data of the first deconstruction evaluation result and the second deconstruction evaluation result. A comprehensive index reflecting the overall deconstruction performance of the vehicle control model is obtained through a calculation formula. The calculated comprehensive deconstruction coefficient is then compared with a preset comprehensive deconstruction threshold. This threshold is set according to the performance requirements of the vehicle control model, industry standards, or historical data, and is used to determine whether the overall deconstruction performance of the model reaches the expected level. According to the comparison result, a comprehensive deconstruction evaluation of the vehicle control model is carried out to draw a conclusion of "good deconstruction" or "poor deconstruction". This evaluation result comprehensively considers the performance of the model at different deconstruction levels and provides a comprehensive evaluation of the overall performance of the model. On the basis of the comprehensive deconstruction evaluation, the deconstruction maturity of the vehicle control model is further evaluated according to the comprehensive deconstruction evaluation result, the first deconstruction evaluation result, and the second deconstruction evaluation result. The deconstruction maturity evaluation not only focuses on the current performance level of the model but also on its development potential and improvement degree at different deconstruction levels. By analyzing the scores, improvement spaces, and comparisons with other models at different deconstruction levels of the model, the maturity levels of the model at each deconstruction level can be evaluated and corresponding evaluation results can be given.

[0097] The technical effects of the above technical solution are as follows: The comprehensive deconstruction evaluation method provides a comprehensive and accurate performance evaluation for the vehicle control model by combining the evaluation results of multiple deconstruction levels. This method can more comprehensively reflect the performance of the model in different control stages and types, avoiding the one-sidedness that may be brought by a single deconstruction level evaluation. The deconstruction maturity evaluation result provides a clear direction and basis for the optimization of the vehicle control model. By analyzing the maturity levels of the model at different deconstruction levels, the advantages and disadvantages of the model can be identified, and targeted optimization strategies and improvement measures can be formulated accordingly. Through continuous deconstruction evaluation and optimization, the quality of the vehicle control model will be improved. The adaptability, stability, and accuracy of the model in different control scenarios will be enhanced, thereby improving driving safety and comfort. The comprehensive deconstruction evaluation method promotes the continuous innovation and development of vehicle control technology. Through the comprehensive evaluation and optimization of the model performance, continuous improvement and innovation in control algorithms, model design, etc. can be promoted. By comprehensively deconstructing and evaluating and optimizing the vehicle control model, the driving experience of users can be significantly improved.

[0098] In an embodiment of the present invention, the system includes:

[0099] A classification mapping generation module, configured to classify the comprehensive control data of the hydrogen energy vehicle according to stages and stage types, obtain a plurality of stage control data and a plurality of type control data of the stages, establish a mapping relationship, and generate a vehicle software control system;

[0100] The first deconstruction evaluation module is used to train a vehicle control model, perform the first deconstruction on the vehicle control model to obtain first deconstruction data, calculate a first deconstruction evaluation coefficient, and perform a first deconstruction evaluation based on the first deconstruction evaluation coefficient to obtain a first deconstruction evaluation result;

[0101] The second deconstruction evaluation module is used to perform a second deconstruction on the vehicle control model to obtain second deconstruction data, calculate a second deconstruction evaluation coefficient, and perform a second deconstruction evaluation based on the second deconstruction evaluation coefficient to obtain a second deconstruction evaluation result;

[0102] The comprehensive deconstruction evaluation module is used to calculate a comprehensive deconstruction coefficient, perform a comprehensive deconstruction evaluation on the vehicle control model, and then perform a comprehensive deconstruction maturity evaluation to obtain an evaluation result.

[0103] The working principle of the above technical solution is as follows: The system collects comprehensive control data of a hydrogen energy vehicle, which includes but is not limited to vehicle operating status, energy consumption, power output, battery status, etc. These data are classified according to different stages (such as startup, driving, parking, etc.) and stage types (such as normal driving, acceleration, deceleration, etc.) to form multiple stage control data and multiple type control data for each stage. Through data analysis, a mapping relationship is established between these control data and the vehicle software control system to ensure that the control data for each stage and type can be accurately reflected in the vehicle software control system. Based on the classified data, a vehicle control model is trained to accurately simulate the actual operation of the hydrogen energy vehicle. The trained vehicle control model is subjected to a first deconstruction, splitting the model into smaller components (such as the power system, battery management system, control system, etc.), and the first deconstruction data is obtained. Based on this data, a first deconstruction evaluation coefficient is calculated to evaluate the performance and efficiency of each part. On the basis of the first deconstruction, a more in-depth second deconstruction is carried out to further refine the sub-modules or functional units of each part, and the second deconstruction data is obtained. Similarly, a second deconstruction evaluation coefficient is calculated for a more detailed evaluation. The first deconstruction evaluation result and the second deconstruction evaluation result are weighted to calculate a comprehensive deconstruction coefficient. This coefficient comprehensively reflects the performance and maturity of the vehicle control model at different levels. According to the comprehensive deconstruction coefficient, a comprehensive deconstruction maturity evaluation is carried out on the vehicle control model, and finally an evaluation result is obtained. The evaluation result can intuitively reflect the maturity and optimization space of the hydrogen energy vehicle in aspects such as design, manufacturing, and control.

[0104] The technical effects of the above technical solution are as follows: Through phased and categorized data classification and mapping, as well as multi-level deconstruction evaluation, it can more accurately reflect the performance and efficiency of hydrogen energy vehicles under different operating conditions, improving the accuracy of evaluation. Through deconstruction evaluation, problems and bottlenecks in the vehicle control system can be discovered. For example, the configuration of the power system can be adjusted and the battery management strategy can be optimized according to the evaluation results, improving the overall performance and efficiency of the vehicle. By optimizing the vehicle design and control strategy, the driving experience and riding comfort of hydrogen energy vehicles can be enhanced. At the same time, reducing the failure rate and improving safety are also important aspects of enhancing the user experience.

[0105] In one embodiment of the present invention, the classification and mapping generation module includes:

[0106] A data stage classification module, configured to obtain the comprehensive control data of a hydrogen energy vehicle, classify the comprehensive control data according to the acquisition stage of the comprehensive control data to obtain multiple stage control data; classify the control data of each stage according to the data type to obtain multiple type control data of the stage; the stage control data includes start stage data, driving stage data, and parking stage data, and the data types include speed data, temperature data, pressure data, battery state data, etc.;

[0107] A data type classification module, configured to obtain multiple control stages of a hydrogen energy vehicle, classify each control stage of the multiple control stages according to the control type to obtain multiple control types of the stage; the control stages include a start stage, a driving stage, and a parking stage, and the control types include speed control, temperature control, pressure control, battery state control, etc.;

[0108] A mapping system generation module, configured to establish a mapping relationship between the multiple type control data of each stage and the multiple control types, and obtain the mapping relationship data;

[0109] Generate the vehicle software control system corresponding to the control data according to the mapping relationship data.

[0110] The working principle of the above technical solution is as follows: The system obtains the comprehensive control data of the hydrogen energy vehicle in real time through devices such as sensors and in-vehicle computers. These data cover various parameters of the vehicle under different operating conditions. The comprehensive control data is classified according to the data acquisition phases (such as start-up phase, driving phase, parking phase) to obtain the control data for each phase. In this way, the data can be organized orderly according to the time sequence and the vehicle operating conditions. Within each phase, further classification is carried out according to the types of data (such as speed data, temperature data, pressure data, battery status data, etc.) to obtain multiple types of control data for each phase. This classification helps with subsequent data analysis and processing. The system simultaneously identifies multiple control phases (start-up, driving, parking) of the hydrogen energy vehicle, and these phases correspond to the data acquisition phases of the comprehensive control data. For each control phase, classification is carried out according to the control types (such as speed control, temperature control, pressure control, battery status control, etc.). This classification reflects various control operations that need to be carried out by the vehicle in different phases. Based on the above classification results, the system establishes the mapping relationship between multiple types of control data and multiple control types for each phase. This mapping relationship clarifies the corresponding relationship between different data types and control types, providing a basis for the generation of the vehicle software control system. The mapping relationship data is usually presented in the form of a database, table, or graphical interface for subsequent software design and development. According to the mapping relationship data, the system generates a vehicle software control system that matches the actual operating conditions of the hydrogen energy vehicle. This system can receive real-time data from sensors and precisely control and manage the vehicle according to preset control logics and algorithms. The generation of the vehicle software control system includes multiple links such as software architecture design, algorithm writing, and interface definition, aiming to achieve the efficient, safe, and stable operation of the vehicle.

[0111] The technical effects of the above technical solution are as follows: By classifying the comprehensive control data by phase and type, the organization and utilization efficiency of the data are improved. This makes subsequent data analysis and processing more convenient and efficient. Establishing the mapping relationship between control data and control types helps to optimize the vehicle control strategy. The system can adjust control parameters according to real-time data to achieve more precise and efficient vehicle control. The generation of the vehicle software control system is based on detailed mapping relationship data, which can ensure the close matching of the system with the actual vehicle operating conditions. This helps to improve the reliability and stability of the system and reduce the possibility of failures. By improving the control precision and stability of the vehicle, the driving experience and riding comfort of users can be significantly improved. At the same time, reducing the failure rate and improving safety are also important aspects of enhancing the user experience.

[0112] In an embodiment of the present invention, the first deconstruction evaluation module includes:

[0113] A model training module, which is used to obtain comprehensive control data, multiple-stage control data, and multiple-category control data, and combine them with vehicle software control system data to generate a control training set;

[0114] Train a neural network model according to the control training set to obtain a vehicle control model;

[0115] A first deconstruction module, which is used to obtain a first-level deconstruction target, and deconstruct the vehicle control model according to the first-level deconstruction target to obtain first deconstruction data; the first-level deconstruction target includes preset deconstruction targets for each control stage;

[0116] A first evaluation module, which is used to calculate a first deconstruction evaluation coefficient according to the first deconstruction data, compare the first deconstruction evaluation coefficient with a preset first coefficient threshold to obtain a first deconstruction comparison result, and perform a first deconstruction evaluation on the vehicle control model according to the first deconstruction comparison result to obtain a first deconstruction evaluation result.

[0117] When the first deconstruction evaluation coefficient is greater than the preset first coefficient threshold, the first deconstruction of the vehicle control model is evaluated as a good deconstruction; otherwise, it is evaluated as a poor deconstruction.

[0118] The calculation formula of the first deconstruction evaluation coefficient is:

[0119]

[0120] where G py is the first deconstruction evaluation coefficient, k is the number of control stages, m is the number of preset deconstruction targets, B sjn is the target deconstruction data of the nth preset deconstruction target, S sjsn is the actual deconstruction data of the nth preset deconstruction target, is the deconstruction evaluation difference coefficient of the dth control stage.

[0121] The working principle of the above technical solution is as follows: Comprehensive control data is obtained from the vehicle software control system, sensors, and other data sources of a hydrogen energy vehicle. This data includes control data for multiple stages (such as startup, driving, and parking) and multiple types of control data (such as speed, temperature, pressure, battery status, etc.). Combining this data with information such as the operation log and parameter configuration of the vehicle software control system, a control training set is generated. This training set contains the control data of the vehicle under different operating states and their corresponding control results or effects. Using this training set to train a neural network model, through multiple iterations and optimizations, a vehicle control model that can accurately reflect the vehicle control logic is finally obtained. Set the first-level deconstruction objectives, which are usually the specific requirements and expected effects for the vehicle control model in each control stage. For example, in the driving stage, the model may be required to accurately control the vehicle speed and maintain a stable battery status. According to these preset deconstruction objectives, the vehicle control model is deconstructed, that is, the performance and internal mechanism of the model in each control stage are analyzed to obtain the first deconstruction data. These data reflect the operating conditions and performance parameters of the model under specific objectives. Calculate the first deconstruction evaluation coefficient using the first deconstruction data. This coefficient is a quantitative indicator used to evaluate the performance of the model under specific deconstruction objectives. Its calculation formula may involve multiple aspects such as the difference between the model output and the preset objective, control accuracy, and stability. Compare the calculated first deconstruction evaluation coefficient with the preset first coefficient threshold. If the evaluation coefficient is greater than the threshold, it is considered that the model performs well under this deconstruction objective, and the deconstruction evaluation result is "good deconstruction"; otherwise, it is considered that the performance is poor, and the deconstruction evaluation result is "poor deconstruction".

[0122] The technical effects of the above technical solution are as follows: By generating a control training set and training a neural network model, a more accurate and reliable vehicle control model can be obtained. This model can more accurately reflect the actual control requirements of the vehicle, improving driving safety and comfort. The process of model deconstruction and evaluation helps to deeply understand the internal mechanism and control logic of the model. By setting deconstruction objectives and calculating deconstruction evaluation coefficients, the performance of the model in different aspects can be quantified, providing strong support for the optimization and improvement of the model. The setting of the first-level deconstruction objectives makes the model deconstruction and evaluation process more flexible and customizable. According to different application scenarios and requirements, different deconstruction objectives and evaluation criteria can be set to meet specific control needs. The deconstruction evaluation results can provide important reference information for decision-makers. By understanding the performance of the model under different deconstruction objectives, decision-makers can more accurately evaluate the applicability and reliability of the model, and thus make more informed decisions. In an embodiment of the present invention, the second deconstruction evaluation module includes:

[0123] The second deconstruction module is used to obtain the second-level deconstruction target according to the first-level deconstruction target, and deconstruct the first-level deconstruction target of the vehicle control model according to the second-level structure target to obtain the second deconstruction data; the second-level deconstruction target includes the preset deconstruction targets of each control type in each control stage.

[0124] The second evaluation module is used to calculate the second deconstruction evaluation coefficient according to the second deconstruction data, compare the second deconstruction evaluation coefficient with the preset second coefficient threshold to obtain the second deconstruction comparison result, and perform the second deconstruction evaluation on the vehicle control model according to the second deconstruction comparison result to obtain the second deconstruction evaluation result.

[0125] When the second deconstruction evaluation coefficient is greater than the preset second coefficient threshold, the second deconstruction of the vehicle control model is evaluated as a good deconstruction; otherwise, it is evaluated as a poor deconstruction.

[0126] The calculation formula for the second deconstruction evaluation coefficient is:

[0127]

[0128] Where G pr is the second deconstruction evaluation coefficient, z is the total number of control types, E is the total number of preset deconstruction targets of each control type, B sji is the target deconstruction data of the i-th preset deconstruction target, S sjsi is the actual deconstruction data of the i-th preset deconstruction target, is the deconstruction evaluation difference coefficient of the i-th preset control target of the o-th control type in the d-th control stage.

[0129] The working principle of the above technical solution is as follows: After completing the first-level deconstruction evaluation, in order to further analyze and optimize the vehicle control model in depth, according to the feedback of the first-level deconstruction target and the actual requirements of vehicle control, the second-level deconstruction target is set. These targets are more specific and refined, and preset deconstruction targets are set for each control type in each control stage. For example, in speed control during the driving stage, it may be required that the model has different control accuracies and response speeds in different speed ranges. Based on the second-level deconstruction target, a more detailed deconstruction of the performance of the vehicle control model under the first-level deconstruction target is carried out. This process involves a detailed analysis of the specific behaviors of each control type within the control stage to obtain the second deconstruction data. These data provide the detailed performance parameters and performance of the model under specific control types and stages. Using the second deconstruction data, the second deconstruction evaluation coefficient is calculated according to the preset evaluation method. This coefficient comprehensively considers the performance of the model under multiple control types and stages. The calculated second deconstruction evaluation coefficient is compared with the preset second coefficient threshold. According to the comparison result, a second deconstruction evaluation of the vehicle control model is carried out to obtain a conclusion of "good deconstruction" or "poor deconstruction". This evaluation result is more specific and comprehensive and can more accurately reflect the performance of the model under different control types and stages.

[0130] The technical effects of the above technical solution are as follows: The second-level deconstruction evaluation improves the accuracy of the performance evaluation of the vehicle control model by refining the deconstruction target and evaluation method. It can more accurately identify the advantages and disadvantages of the model under different control types and stages, providing more detailed and specific guidance for the optimization and improvement of the model. By conducting a second-level deconstruction evaluation of the model, performance bottlenecks and potential problems of the model under specific control types and stages can be discovered. This helps developers to optimize and improve targeted at these problems, enhancing the overall performance and stability of the model. The second-level deconstruction evaluation method enables the vehicle control model to better adapt to different driving scenarios and control requirements. By refining the deconstruction target and evaluation method, it can ensure that the model maintains a high control accuracy and stability under different conditions. Through detailed performance evaluation and optimization of the vehicle control model, the comfort and safety of driving can be significantly improved. This helps to enhance the driving experience of users and strengthen the trust and satisfaction of users in hydrogen energy vehicles. The second-level deconstruction evaluation promotes continuous improvement and innovation in aspects such as control algorithms and model design.

[0131] In an embodiment of the present invention, the comprehensive deconstruction evaluation module includes:

[0132] A comprehensive deconstruction evaluation module for calculating a comprehensive deconstruction coefficient according to the data of the first deconstruction evaluation result combined with the data of the second deconstruction evaluation result;

[0133] The calculation formula of the comprehensive deconstruction coefficient is:

[0134]

[0135] Among them, H zj is the comprehensive deconstruction coefficient;

[0136] Compare the comprehensive deconstruction coefficient with a preset comprehensive deconstruction threshold to obtain a comprehensive comparison result;

[0137] According to the comprehensive comparison result, conduct a comprehensive deconstruction evaluation on the vehicle control model to obtain a comprehensive deconstruction evaluation result;

[0138] When the comprehensive deconstruction coefficient is greater than the preset comprehensive deconstruction threshold, the comprehensive deconstruction of the vehicle control model is evaluated as good deconstruction; otherwise, it is evaluated as poor deconstruction.

[0139] A maturity evaluation module is used to conduct a comprehensive deconstruction maturity evaluation, a first deconstruction maturity evaluation, and a second deconstruction maturity evaluation on the vehicle control model according to the comprehensive deconstruction evaluation result, the first deconstruction evaluation result, and the second deconstruction evaluation result, so as to obtain a comprehensive deconstruction maturity evaluation result, a first deconstruction maturity evaluation result, and a second deconstruction maturity evaluation result.

[0140] The working principle of the above technical solution is as follows: The comprehensive deconstruction coefficient is a comprehensive evaluation index that combines the data of the first deconstruction evaluation result and the second deconstruction evaluation result. A comprehensive index reflecting the overall deconstruction performance of the vehicle control model is obtained through a calculation formula. The calculated comprehensive deconstruction coefficient is then compared with a preset comprehensive deconstruction threshold. This threshold is set according to the performance requirements of the vehicle control model, industry standards, or historical data, and is used to determine whether the overall deconstruction performance of the model meets the expected level. According to the comparison result, a comprehensive deconstruction evaluation is conducted on the vehicle control model, and a conclusion of "good deconstruction" or "poor deconstruction" is drawn. This evaluation result comprehensively considers the performance of the model at different deconstruction levels and provides a comprehensive evaluation of the overall performance of the model. On the basis of the comprehensive deconstruction evaluation, a deconstruction maturity evaluation is further conducted on the vehicle control model according to the comprehensive deconstruction evaluation result, the first deconstruction evaluation result, and the second deconstruction evaluation result. The deconstruction maturity evaluation not only focuses on the current performance level of the model but also on its development potential and improvement degree at different deconstruction levels. By analyzing the scores, improvement space, and comparison with other models at different deconstruction levels of the model, the maturity level of the model at each deconstruction level can be evaluated and the corresponding evaluation results can be given.

[0141] The technical effects of the above technical solution are as follows: The comprehensive deconstruction evaluation method provides a comprehensive and accurate performance evaluation for the vehicle control model by combining the evaluation results of multiple deconstruction levels. This method can more comprehensively reflect the performance of the model in different control stages and types, avoiding the one-sidedness that may be brought about by the evaluation of a single deconstruction level. The deconstruction maturity evaluation results provide a clear direction and basis for the optimization of the vehicle control model. By analyzing the maturity levels of the model at different deconstruction levels, the advantages and disadvantages of the model can be identified, and targeted optimization strategies and improvement measures can be formulated accordingly. Through continuous deconstruction evaluation and optimization, the quality of the vehicle control model will be improved. The adaptability, stability, and accuracy of the model in different control scenarios will be enhanced, thereby improving driving safety and comfort. The comprehensive deconstruction evaluation method promotes the continuous innovation and development of vehicle control technology. Through the comprehensive evaluation and optimization of the model performance, continuous improvement and innovation in control algorithms, model design, etc. can be promoted. By comprehensively deconstructing, evaluating, and optimizing the vehicle control model, the driving experience of users can be significantly improved.

[0142] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A method for analyzing the maturity of the deconstruction model of a hydrogen energy vehicle, characterized in that The method includes: S1. Classify the comprehensive control data of the hydrogen energy vehicle according to stages and stage types, obtain multiple stage control data and multiple type control data of the stages, establish a mapping relationship, and generate a vehicle software control system; S2. Train a vehicle control model, perform a first deconstruction on the vehicle control model to obtain first deconstruction data, calculate a first deconstruction evaluation coefficient, and perform a first deconstruction evaluation based on the first deconstruction evaluation coefficient to obtain a first deconstruction evaluation result; Among them, S2 includes: Obtain comprehensive control data, multiple stage control data, multiple type control data, and combine them with the vehicle software control system data to generate a control training set; Train a neural network model according to the control training set to obtain a vehicle control model; Obtain a first-level deconstruction target, deconstruct the vehicle control model according to the first-level deconstruction target to obtain first deconstruction data; Calculate a first deconstruction evaluation coefficient according to the first deconstruction data, compare the first deconstruction evaluation coefficient with a preset first coefficient threshold to obtain a first deconstruction comparison result, and perform a first deconstruction evaluation on the vehicle control model according to the first deconstruction comparison result to obtain a first deconstruction evaluation result; The calculation formula of the first deconstruction evaluation coefficient is: Among them, G py is the first deconstruction evaluation coefficient, k is the number of control phases, m is the number of preset deconstruction targets, B sjn is the target deconstruction data of the nth preset deconstruction target, S sjsn is the actual deconstruction data of the nth preset deconstruction target, is the average value of the deconstruction evaluation difference coefficients of the dth control phase; S3. Perform a second deconstruction on the vehicle control model to obtain second deconstruction data, calculate a second deconstruction evaluation coefficient, and perform a second deconstruction evaluation based on the second deconstruction evaluation coefficient to obtain a second deconstruction evaluation result; Among them, S3 includes: Obtain a second-level deconstruction target according to the first-level deconstruction target, deconstruct the first-level deconstruction target of the vehicle control model according to the second-level structure target to obtain second deconstruction data; Calculate a second deconstruction evaluation coefficient according to the second deconstruction data, compare the second deconstruction evaluation coefficient with a preset second coefficient threshold to obtain a second deconstruction comparison result, and perform a second deconstruction evaluation on the vehicle control model according to the second deconstruction comparison result to obtain a second deconstruction evaluation result; The calculation formula of the second deconstruction evaluation coefficient is: Among them, G pr is the second deconstruction evaluation coefficient, z is the total number of control types, E is the total number of preset deconstruction targets for each control type, B sji is the target deconstruction data of the i-th preset deconstruction target, S sjsi is the actual deconstruction data of the i-th preset deconstruction target, is the deconstruction evaluation difference coefficient of the i-th preset control target of the o-th control type in the d-th control stage; S4. Calculate a comprehensive deconstruction coefficient, perform a comprehensive deconstruction evaluation on the vehicle control model, and then perform a comprehensive deconstruction maturity evaluation to obtain an evaluation result; Among them, S4 includes: Calculate a comprehensive deconstruction coefficient according to the data of the first deconstruction evaluation result combined with the data of the second deconstruction evaluation result; The calculation formula of the comprehensive deconstruction coefficient is: Among them, H zj is the comprehensive deconstruction coefficient; Compare the comprehensive deconstruction coefficient with a preset comprehensive deconstruction threshold to obtain a comprehensive comparison result; Perform a comprehensive deconstruction evaluation on the vehicle control model according to the comprehensive comparison result to obtain a comprehensive deconstruction evaluation result; Perform a comprehensive deconstruction maturity evaluation, a first deconstruction maturity evaluation, and a second deconstruction maturity evaluation on the vehicle control model according to the comprehensive deconstruction evaluation result, the first deconstruction evaluation result, and the second deconstruction evaluation result to obtain a comprehensive deconstruction maturity evaluation result, a first deconstruction maturity evaluation result, and a second deconstruction maturity evaluation result.

2. The method for analyzing the maturity of the deconstruction model of a hydrogen energy vehicle according to claim 1, characterized in that, S1 includes: Obtain the comprehensive control data of a hydrogen energy vehicle, classify the comprehensive control data according to the acquisition stage of the comprehensive control data to obtain multiple stage control data; classify the control data of each stage according to the data type to obtain multiple type control data of the stage; Obtain multiple control stages of a hydrogen energy vehicle, classify each control stage of the multiple control stages according to the control type to obtain multiple control types of the stage; Establish the mapping relationship between multiple type control data of each stage and multiple control types, and obtain the mapping relationship data; Generate the vehicle software control system corresponding to the control data according to the mapping relationship data.

3. A deconstruction model maturity analysis system for a hydrogen energy vehicle, characterized in that, The system includes: A classification mapping generation module, configured to classify the comprehensive control data of a hydrogen energy vehicle according to the stage and stage type to obtain multiple stage control data and multiple type control data of the stage, establish a mapping relationship, and generate a vehicle software control system; A first deconstruction evaluation module, configured to train a vehicle control model, perform a first deconstruction on the vehicle control model to obtain first deconstruction data, calculate a first deconstruction evaluation coefficient, and perform a first deconstruction evaluation according to the first deconstruction evaluation coefficient to obtain a first deconstruction evaluation result; Among them, the first deconstruction evaluation module includes: A model training module, configured to obtain comprehensive control data, multiple stage control data, multiple type control data combined with vehicle software control system data to generate a control training set; Train a neural network model according to the control training set to obtain a vehicle control model; A first deconstruction module, configured to obtain a first-level deconstruction target, and deconstruct the vehicle control model according to the first-level deconstruction target to obtain first deconstruction data; A first evaluation module, configured to calculate a first deconstruction evaluation coefficient according to the first deconstruction data, compare the first deconstruction evaluation coefficient with a preset first coefficient threshold to obtain a first deconstruction comparison result, and perform a first deconstruction evaluation on the vehicle control model according to the first deconstruction comparison result to obtain a first deconstruction evaluation result; The calculation formula of the first deconstruction evaluation coefficient is: Among them, G py is the first deconstruction evaluation coefficient, k is the number of control phases, m is the number of preset deconstruction targets, B sjn is the target deconstruction data of the nth preset deconstruction target, S sjsn is the actual deconstruction data of the nth preset deconstruction target, is the mean value of the deconstruction evaluation difference coefficient of the dth control phase; A second deconstruction evaluation module, configured to perform a second deconstruction on the vehicle control model to obtain second deconstruction data, calculate a second deconstruction evaluation coefficient, and perform a second deconstruction evaluation according to the second deconstruction evaluation coefficient to obtain a second deconstruction evaluation result; Among them, the second deconstruction evaluation module includes: A second deconstruction module, configured to obtain a second-level deconstruction target according to the first-level deconstruction target, and deconstruct the first-level deconstruction target of the vehicle control model according to the second-level structure target to obtain second deconstruction data; A second evaluation module, configured to calculate a second deconstruction evaluation coefficient according to the second deconstruction data, compare the second deconstruction evaluation coefficient with a preset second coefficient threshold to obtain a second deconstruction comparison result, and perform a second deconstruction evaluation on the vehicle control model according to the second deconstruction comparison result to obtain a second deconstruction evaluation result; The calculation formula of the second deconstruction evaluation coefficient is: Among them, G pr is the second deconstruction evaluation coefficient, z is the total number of control types, E is the total number of preset deconstruction targets for each control type, B sji is the target deconstruction data of the i-th preset deconstruction target, S sjsi is the actual deconstruction data of the i-th preset deconstruction target, and is the deconstruction evaluation difference coefficient of the i-th preset control target of the o-th control type in the d-th control stage; A comprehensive deconstruction evaluation module, configured to calculate a comprehensive deconstruction coefficient, perform a comprehensive deconstruction evaluation on the vehicle control model, and then perform a comprehensive deconstruction maturity evaluation to obtain an evaluation result; Among them, the comprehensive deconstruction evaluation module includes: The comprehensive deconstruction evaluation module is used to calculate the comprehensive deconstruction coefficient according to the data of the first deconstruction evaluation result combined with the data of the second deconstruction evaluation result; The calculation formula of the comprehensive deconstruction coefficient is: Among them, H zj is the comprehensive deconstruction coefficient; Compare the comprehensive deconstruction coefficient with the preset comprehensive deconstruction threshold to obtain a comprehensive comparison result; Perform a comprehensive deconstruction evaluation on the vehicle control model according to the comprehensive comparison result to obtain a comprehensive deconstruction evaluation result; The maturity evaluation module is used to perform comprehensive deconstruction maturity evaluation, first deconstruction maturity evaluation, and second deconstruction maturity evaluation on the vehicle control model according to the comprehensive deconstruction evaluation result, the first deconstruction evaluation result, and the second deconstruction evaluation result, and obtain the comprehensive deconstruction maturity evaluation result, the first deconstruction maturity evaluation result, and the second deconstruction maturity evaluation result.

4. The maturity analysis system for the deconstruction model of a hydrogen energy vehicle according to claim 3, characterized in that, The classification mapping generation module includes: The data stage classification module is used to obtain the comprehensive control data of the hydrogen energy vehicle, classify the comprehensive control data according to the acquisition stage of the comprehensive control data to obtain multiple stage control data; classify the control data of each stage according to the data type to obtain multiple type control data of the stage; The data type classification module is used to obtain multiple control stages of the hydrogen energy vehicle, classify each control stage of the multiple control stages according to the control type to obtain multiple control types of the stage; The mapping system generation module is used to establish the mapping relationship between the multiple type control data of each stage and the multiple control types, and obtain its mapping relationship data; Generate the vehicle software control system corresponding to the control data according to the mapping relationship data.

Images