Multi-module detection method and system applied to integrated hydrogen storage chassis and medium

Abstract

The invention relates to a multi-module detection method and system applied to an integrated hydrogen storage chassis and a medium, and the method comprises the steps: Q1, obtaining the operation data information of each module of the hydrogen storage chassis in real time based on a vehicle-mounted multi-sensor when a vehicle provided with the integrated hydrogen storage chassis runs on a road, historical operation data information of each module of the hydrogen storage chassis is collected; and Q2, based on the operation data information of each module of the hydrogen storage chassis and the historical operation data information of each module of the hydrogen storage chassis, predicting the operation data information of each module of the hydrogen storage chassis by adopting an improved random forest regression prediction algorithm integrated with random weight, and obtaining the predicted operation data information of each module of the hydrogen storage chassis. According to the method, the hydrogen storage chassis can be detected in real time to guarantee normal operation of the vehicle, the operation data information of the hydrogen storage chassis is predicted in combination with the historical operation data information of the hydrogen storage chassis, the safety of the vehicle is further guaranteed, and the driving experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated hydrogen storage chassis detection, and in particular to a multi-module detection method, system and medium applied to an integrated hydrogen storage chassis. Background Art

[0002] With the rapid development of science and technology, hydrogen energy, as a new energy source, has attracted more and more attention. However, the storage and use of hydrogen have become problems for us to solve. Among them, in terms of hydrogen application, with the focus of the industry and the development of technology, the expectation is high that hydrogen fuel cells will drive the transformation of applications in the transportation field. In various chemical fields that require hydrogen, such as oil refining, synthetic ammonia, methanol production and steelmaking industries, green hydrogen will gradually replace gray hydrogen. In many other traditional energy-intensive industries, hydrogen energy will also replace fossil energy as an energy carrier for energy supply. In the field of construction, the use of distributed combined cooling, heating and power systems with green hydrogen energy is also an important way to save energy and reduce emissions. At the same time, more hydrogen energy application scenarios will be gradually developed. The effective use of hydrogen energy can not only reduce carbon emissions, but also reduce dependence on fossil energy. It has rich application scenarios, including four major fields: transportation, electricity and construction.

[0003] At the same time, the integrated hydrogen storage chassis used in vehicles is not only simple in structure but also space-saving. However, during the operation of the vehicle, how to conduct real-time detection of the hydrogen storage chassis to ensure the normal operation of the vehicle has become an urgent problem to be solved. Summary of the invention

[0004] In view of the above problems, the present invention provides a multi-module detection method, system and medium applied to an integrated hydrogen storage chassis, which can not only perform real-time detection of the hydrogen storage chassis to ensure the normal operation of the vehicle, but also predict the operating data information of the hydrogen storage chassis in combination with the historical operating data information of the hydrogen storage chassis, thereby further ensuring the safety of the vehicle and improving the driving experience.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows: a multi-module detection method applied to an integrated hydrogen storage chassis, the method comprising:

[0006] Q1. When a vehicle equipped with an integrated hydrogen storage chassis is driving on the road, the vehicle obtains the operating data information of each module of the hydrogen storage chassis in real time based on the on-board multi-sensors, and collects the historical operating data information of each module of the hydrogen storage chassis;

[0007] Q2. Based on the operation data information of each module of the hydrogen storage chassis and the historical operation data information of each module of the hydrogen storage chassis, the operation data information of each module of the hydrogen storage chassis is predicted by using an improved random forest regression prediction algorithm with integrated random weights to obtain the predicted operation data information of each module of the hydrogen storage chassis;

[0008] Q3. Based on the predicted operating data information of each module of the hydrogen storage chassis, the hydrogen storage chassis multi-module detection algorithm based on the random walk matrix is ​​used to detect abnormal points of each module of the hydrogen storage chassis, and the abnormal data information of the hydrogen storage chassis is output;

[0009] Q4. Based on the abnormal data information of the hydrogen storage chassis, an abnormal evaluation function H of the hydrogen storage chassis is constructed, and the abnormal data of the hydrogen storage chassis is evaluated to obtain multi-module detection data information of the hydrogen storage chassis.

[0010] Furthermore, in step Q2, the use of the improved random forest regression prediction algorithm with integrated random weights to predict the operating data information of each module of the hydrogen storage chassis includes:

[0011] Q21. Input the operating data information of each module of the hydrogen storage chassis and the historical operating data information of each module of the hydrogen storage chassis into the trained hierarchical clustering optimization model to perform hierarchical clustering processing on the operating data, and output the processed operating data information and historical operating data information of each module of the hydrogen storage chassis;

[0012] Q22. Based on the processed operating data information and historical operating data information of each module of the hydrogen storage chassis, a random forest regression prediction function G of the operating data of the hydrogen storage chassis is established.

[0013]

[0014] Among them, L is the decision tree function of the hydrogen storage chassis, x i is the processed operating data information of the i-th module of the hydrogen storage chassis, y i is the historical operation data information of the i-th module of the hydrogen storage chassis after processing, t is different time, f t is the node function of the hydrogen storage chassis at time t, W is the function of the integrated random weight of the hydrogen storage chassis, and n is the sample capacity;

[0015] Q23. Based on the random forest regression prediction function G of the operating data of the hydrogen storage chassis, the operating data information of each module of the hydrogen storage chassis is predicted to obtain the predicted operating data information of each module of the hydrogen storage chassis.

[0016] Furthermore, the function W of the integrated random weight of the hydrogen storage chassis is,

[0017]

[0018] Among them, α and β are the state transition probability parameter factors of the hydrogen storage chassis, T is the total number of nodes of the operating data of each module of the hydrogen storage chassis, ω jis the score data information of the jth node of the hydrogen storage chassis, n is the sample size, x ji The running data information of the jth data node of the i-th module of the hydrogen storage chassis, y ji is the operating data information of the jth data node of the i-th module of the hydrogen storage chassis, δ ji is the score weight coefficient of the hydrogen storage chassis.

[0019] Furthermore, the score weight coefficient δ of the hydrogen storage chassis ji The constraints are:

[0020]

[0021] Where n is the sample size.

[0022] Furthermore, in step Q21, the trained hierarchical clustering optimization model includes:

[0023] Q211. Collect the operating data information of each module of the hydrogen storage chassis;

[0024] Q212. Input the operating data information of each module of the hydrogen storage chassis into the hierarchical clustering optimization model for training and learning, determine the network parameters, and obtain a trained hierarchical clustering optimization model.

[0025] Further, in step Q3, the use of a hydrogen storage chassis multi-module detection algorithm based on a random walk matrix to detect abnormal points of each module of the hydrogen storage chassis includes:

[0026] Q31. Based on the predicted operating data information of each module of the hydrogen storage chassis, establish a random walk matrix function M of each module of the hydrogen storage chassis i ,

[0027]

[0028] Among them, z i is the predicted operating data information of the i-th module of the hydrogen storage chassis, η and σ are the mean factors of the multiple modules of the hydrogen storage chassis, and the random walk matrix of each module of the hydrogen storage chassis is characterized to obtain the data information of the random walk matrix of each module of the hydrogen storage chassis;

[0029] Q32. Based on the data information of the random walk matrix of each module of the hydrogen storage chassis, a multi-module detection function M of the hydrogen storage chassis is constructed.

[0030]

[0031] Among them, a is the data information of the random walk matrix of each module of the hydrogen storage chassis, θ 1 ,θ 2 and θ3 The detection factors of each module of the hydrogen storage chassis are used to detect each module of the hydrogen storage chassis to obtain data information of the detection values ​​of each module of the hydrogen storage chassis;

[0032] Q33. Based on the data information of the detection values ​​of each module of the hydrogen storage chassis, a preset threshold is set. If the detection value of each module of the hydrogen storage chassis is less than the preset threshold, it is not an abnormal module. If the detection value of each module of the hydrogen storage chassis is greater than the preset threshold, it is an abnormal module.

[0033] Furthermore, in step Q4, the abnormality evaluation function H of the hydrogen storage chassis is constructed.

[0034]

[0035] Among them, ρ 1 , ρ 2 and ρ 3 is the abnormal evaluation parameter of the hydrogen storage chassis, and h is the abnormal data information of the hydrogen storage chassis.

[0036] In order to achieve the above-mentioned object and other related objects, the present invention also provides a system for implementing any of the multi-module detection methods for an integrated hydrogen storage chassis, the system comprising:

[0037] The hydrogen storage chassis data acquisition module is used to obtain the operating data information of each module of the hydrogen storage chassis, and collect the historical operating data information of each module of the hydrogen storage chassis;

[0038] A hydrogen storage chassis data prediction module is connected to the hydrogen storage chassis data acquisition module and is used to predict the operating data information of each module of the hydrogen storage chassis by using an improved random forest regression prediction algorithm with integrated random weights;

[0039] A hydrogen storage chassis data abnormal point detection module is connected to the hydrogen storage chassis data prediction module and is used to detect abnormal points of each module of the hydrogen storage chassis using a hydrogen storage chassis multi-module detection algorithm based on a random walk matrix;

[0040] The hydrogen storage chassis data abnormal point evaluation module is connected to the hydrogen storage chassis data abnormal point detection module and is used to construct an abnormal evaluation function H of the hydrogen storage chassis to evaluate the abnormal data of the hydrogen storage chassis.

[0041] Furthermore, the system also includes an early warning module, which is connected to the hydrogen storage chassis data abnormal point evaluation module and is used to warn or remind the vehicle driver.

[0042] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the multi-module detection methods applied to an integrated hydrogen storage chassis.

[0043] The present invention has the following positive effects:

[0044] 1. The present invention predicts the operating data information of each module of the hydrogen storage chassis by inputting the operating data information of each module of the hydrogen storage chassis and the historical operating data information of each module of the hydrogen storage chassis into an improved random forest regression prediction algorithm with integrated random weights. This can not only ensure the detection of the overall chassis operating data information of the vehicle, but also make advance estimates of the operating abnormal point data of the vehicle's hydrogen storage chassis, thereby ensuring the safety of the vehicle and improving the driving experience.

[0045] 2. The present invention detects abnormal points of each module of the hydrogen storage chassis by adopting a hydrogen storage chassis multi-module detection algorithm based on a random walk matrix, and combines the abnormal evaluation function of the hydrogen storage chassis to accurately analyze and detect each module of the hydrogen storage chassis to ensure the normal operation of the vehicle. At the same time, it provides accurate data support for the daily maintenance and overhaul of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0047] Figure 2 A schematic diagram of the process flow of the improved random forest regression prediction algorithm with integrated random weights of the present invention;

[0048] Figure 3 It is a flow chart of a multi-module detection algorithm for a hydrogen storage chassis based on a random walk matrix of the present invention;

[0049] Figure 4 It is a schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0050] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0051] Example 1: Figure 1 As shown, a multi-module detection method applied to an integrated hydrogen storage chassis, the method comprising:

[0052] Q1. When a vehicle equipped with an integrated hydrogen storage chassis is driving on the road, the vehicle obtains the operating data information of each module of the hydrogen storage chassis in real time based on the on-board multi-sensors, and collects the historical operating data information of each module of the hydrogen storage chassis;

[0053] Q2. Based on the operation data information of each module of the hydrogen storage chassis and the historical operation data information of each module of the hydrogen storage chassis, the operation data information of each module of the hydrogen storage chassis is predicted by using an improved random forest regression prediction algorithm with integrated random weights to obtain the predicted operation data information of each module of the hydrogen storage chassis;

[0054] Q3. Based on the predicted operating data information of each module of the hydrogen storage chassis, the hydrogen storage chassis multi-module detection algorithm based on the random walk matrix is ​​used to detect abnormal points of each module of the hydrogen storage chassis, and the abnormal data information of the hydrogen storage chassis is output;

[0055] Q4. Based on the abnormal data information of the hydrogen storage chassis, an abnormal evaluation function H of the hydrogen storage chassis is constructed, and the abnormal data of the hydrogen storage chassis is evaluated to obtain multi-module detection data information of the hydrogen storage chassis.

[0056] In this embodiment, if Figure 2 As shown, in step Q2, the use of the improved random forest regression prediction algorithm with integrated random weights to predict the operating data information of each module of the hydrogen storage chassis includes:

[0057] Q21. Input the operating data information of each module of the hydrogen storage chassis and the historical operating data information of each module of the hydrogen storage chassis into the trained hierarchical clustering optimization model to perform hierarchical clustering processing on the operating data, and output the processed operating data information and historical operating data information of each module of the hydrogen storage chassis;

[0058] Q22. Based on the processed operating data information and historical operating data information of each module of the hydrogen storage chassis, a random forest regression prediction function G of the operating data of the hydrogen storage chassis is established.

[0059]

[0060] Among them, L is the decision tree function of the hydrogen storage chassis, x i is the processed operating data information of the i-th module of the hydrogen storage chassis, y i is the historical operation data information of the i-th module of the hydrogen storage chassis after processing, t is different time, f t is the node function of the hydrogen storage chassis at time t, W is the function of the integrated random weight of the hydrogen storage chassis, and n is the sample capacity;

[0061] Q23. Based on the random forest regression prediction function G of the operating data of the hydrogen storage chassis, the operating data information of each module of the hydrogen storage chassis is predicted to obtain the predicted operating data information of each module of the hydrogen storage chassis.

[0062] In this embodiment, the function W of the integrated random weight of the hydrogen storage chassis is,

[0063]

[0064] Among them, α and β are the state transition probability parameter factors of the hydrogen storage chassis, T is the total number of nodes of the operating data of each module of the hydrogen storage chassis, ω j is the score data information of the jth node of the hydrogen storage chassis, n is the sample size, x ji The running data information of the jth data node of the i-th module of the hydrogen storage chassis, y ji is the operating data information of the jth data node of the i-th module of the hydrogen storage chassis, δ ji is the score weight coefficient of the hydrogen storage chassis.

[0065] In this embodiment, the score weight coefficient δ of the hydrogen storage chassis is ji The constraints are:

[0066] Where n is the sample size.

[0067] In this embodiment, in step Q21, the trained hierarchical clustering optimization model includes:

[0068] Q211. Collect the operating data information of each module of the hydrogen storage chassis;

[0069] Q212. Input the operating data information of each module of the hydrogen storage chassis into the hierarchical clustering optimization model for training and learning, determine the network parameters, and obtain a trained hierarchical clustering optimization model.

[0070] Example 2: Based on the multi-module detection method applied to an integrated hydrogen storage chassis in Example 1, the present invention is further illustrated and described below.

[0071] like Figure 1 As shown, Figure 1 As shown, a multi-module detection method applied to an integrated hydrogen storage chassis, the method comprising:

[0072] Q1. When a vehicle equipped with an integrated hydrogen storage chassis is driving on the road, the vehicle obtains the operating data information of each module of the hydrogen storage chassis in real time based on the on-board multi-sensors, and collects the historical operating data information of each module of the hydrogen storage chassis;

[0073] Q2. Based on the operation data information of each module of the hydrogen storage chassis and the historical operation data information of each module of the hydrogen storage chassis, the operation data information of each module of the hydrogen storage chassis is predicted by using an improved random forest regression prediction algorithm with integrated random weights to obtain the predicted operation data information of each module of the hydrogen storage chassis;

[0074] Q3. Based on the predicted operating data information of each module of the hydrogen storage chassis, the hydrogen storage chassis multi-module detection algorithm based on the random walk matrix is ​​used to detect abnormal points of each module of the hydrogen storage chassis, and the abnormal data information of the hydrogen storage chassis is output;

[0075] Q4. Based on the abnormal data information of the hydrogen storage chassis, an abnormal evaluation function H of the hydrogen storage chassis is constructed, and the abnormal data of the hydrogen storage chassis is evaluated to obtain multi-module detection data information of the hydrogen storage chassis.

[0076] In this embodiment, if Figure 3 As shown, in step Q3, the use of a hydrogen storage chassis multi-module detection algorithm based on a random walk matrix to detect abnormal points of each module of the hydrogen storage chassis includes:

[0077] Q31. Based on the predicted operating data information of each module of the hydrogen storage chassis, establish a random walk matrix function M of each module of the hydrogen storage chassis i ,

[0078]

[0079] Among them, z i is the predicted operating data information of the i-th module of the hydrogen storage chassis, η and σ are the mean factors of the multiple modules of the hydrogen storage chassis, and the random walk matrix of each module of the hydrogen storage chassis is characterized to obtain the data information of the random walk matrix of each module of the hydrogen storage chassis;

[0080] Q32. Based on the data information of the random walk matrix of each module of the hydrogen storage chassis, a multi-module detection function M of the hydrogen storage chassis is constructed.

[0081]

[0082] Among them, a is the data information of the random walk matrix of each module of the hydrogen storage chassis, θ 1 ,θ 2 and θ 3 The detection factors of each module of the hydrogen storage chassis are used to detect each module of the hydrogen storage chassis to obtain data information of the detection values ​​of each module of the hydrogen storage chassis;

[0083] Q33. Based on the data information of the detection values ​​of each module of the hydrogen storage chassis, a preset threshold is set. If the detection value of each module of the hydrogen storage chassis is less than the preset threshold, it is not an abnormal module. If the detection value of each module of the hydrogen storage chassis is greater than the preset threshold, it is an abnormal module.

[0084] In this embodiment, in step Q4, the abnormality evaluation function H of the hydrogen storage chassis is constructed.

[0085]

[0086] Among them, ρ 1 , ρ 2 and ρ 3 is the abnormal evaluation parameter of the hydrogen storage chassis, and h is the abnormal data information of the hydrogen storage chassis.

[0087] In this embodiment, if Figure 4 As shown, the present invention provides a system for implementing any of the multi-module detection methods for an integrated hydrogen storage chassis, the system comprising:

[0088] The hydrogen storage chassis data acquisition module is used to obtain the operating data information of each module of the hydrogen storage chassis, and collect the historical operating data information of each module of the hydrogen storage chassis;

[0089] A hydrogen storage chassis data prediction module is connected to the hydrogen storage chassis data acquisition module and is used to predict the operating data information of each module of the hydrogen storage chassis by using an improved random forest regression prediction algorithm with integrated random weights;

[0090] A hydrogen storage chassis data abnormal point detection module is connected to the hydrogen storage chassis data prediction module and is used to detect abnormal points of each module of the hydrogen storage chassis using a hydrogen storage chassis multi-module detection algorithm based on a random walk matrix;

[0091] The hydrogen storage chassis data abnormal point evaluation module is connected to the hydrogen storage chassis data abnormal point detection module and is used to construct an abnormal evaluation function H of the hydrogen storage chassis to evaluate the abnormal data of the hydrogen storage chassis.

[0092] In this embodiment, the system further includes an early warning module, which is connected to the hydrogen storage chassis data abnormal point assessment module and is used to warn or remind the vehicle driver.

[0093] The present invention provides a computer-readable storage medium storing a computer program programmed or configured to execute any one of the multi-module detection methods applied to an integrated hydrogen storage chassis.

[0094] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0095] In summary, the present invention can not only perform real-time detection of the hydrogen storage chassis to ensure the normal operation of the vehicle, but also predict the operating data information of the hydrogen storage chassis in combination with the historical operating data information of the hydrogen storage chassis, thereby further ensuring the safety of the vehicle and improving the driving experience.

[0096] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A multi-module detection method applied to an integrated hydrogen storage chassis, characterized in that: The method comprises: Q1. When a vehicle equipped with an integrated hydrogen storage chassis is driving on the road, the vehicle obtains the operating data information of each module of the hydrogen storage chassis in real time based on the on-board multi-sensors, and collects the historical operating data information of each module of the hydrogen storage chassis; Q2. Based on the operation data information of each module of the hydrogen storage chassis and the historical operation data information of each module of the hydrogen storage chassis, the operation data information of each module of the hydrogen storage chassis is predicted by using an improved random forest regression prediction algorithm with integrated random weights to obtain the predicted operation data information of each module of the hydrogen storage chassis; Q3. Based on the predicted operating data information of each module of the hydrogen storage chassis, the hydrogen storage chassis multi-module detection algorithm based on the random walk matrix is ​​used to detect abnormal points of each module of the hydrogen storage chassis, and the abnormal data information of the hydrogen storage chassis is output; Q4. Based on the abnormal data information of the hydrogen storage chassis, an abnormal evaluation function H of the hydrogen storage chassis is constructed, and the abnormal data of the hydrogen storage chassis is evaluated to obtain multi-module detection data information of the hydrogen storage chassis.

2. The multi-module detection method applied to the integrated hydrogen storage chassis according to claim 1, characterized in that: In step Q2, the use of the improved random forest regression prediction algorithm with integrated random weights to predict the operating data information of each module of the hydrogen storage chassis includes: Q21. Input the operating data information of each module of the hydrogen storage chassis and the historical operating data information of each module of the hydrogen storage chassis into the trained hierarchical clustering optimization model to perform hierarchical clustering processing on the operating data, and output the processed operating data information and historical operating data information of each module of the hydrogen storage chassis; Q22. Based on the processed operating data information and historical operating data information of each module of the hydrogen storage chassis, a random forest regression prediction function G of the operating data of the hydrogen storage chassis is established. Among them, L is the decision tree function of the hydrogen storage chassis, x i is the processed operating data information of the i-th module of the hydrogen storage chassis, y i is the historical operation data information of the i-th module of the hydrogen storage chassis after processing, t is different time, f t is the node function of the hydrogen storage chassis at time t, W is the function of the integrated random weight of the hydrogen storage chassis, and n is the sample capacity; Q23. Based on the random forest regression prediction function G of the operating data of the hydrogen storage chassis, the operating data information of each module of the hydrogen storage chassis is predicted to obtain the predicted operating data information of each module of the hydrogen storage chassis.

3. The multi-module detection method applied to the integrated hydrogen storage chassis according to claim 2, characterized in that: The function W of the integrated random weight of the hydrogen storage chassis is, Among them, α and β are the state transition probability parameter factors of the hydrogen storage chassis, T is the total number of nodes of the operating data of each module of the hydrogen storage chassis, ω j is the score data information of the jth node of the hydrogen storage chassis, n is the sample size, x ji The running data information of the jth data node of the i-th module of the hydrogen storage chassis, y ji is the operating data information of the jth data node of the i-th module of the hydrogen storage chassis, δ ji is the score weight coefficient of the hydrogen storage chassis.

4. The multi-module detection method applied to the integrated hydrogen storage chassis according to claim 3, characterized in that: The score weight coefficient δ of the hydrogen storage chassis ji The constraints are: Where n is the sample size.

5. The multi-module detection method applied to an integrated hydrogen storage chassis according to claim 2, characterized in that: In step Q21, the trained hierarchical clustering optimization model includes: Q211. Collect the operating data information of each module of the hydrogen storage chassis; Q212. Input the operating data information of each module of the hydrogen storage chassis into the hierarchical clustering optimization model for training and learning, determine the network parameters, and obtain a trained hierarchical clustering optimization model.

6. The multi-module detection method applied to an integrated hydrogen storage chassis according to claim 1, characterized in that: In step Q3, the use of a hydrogen storage chassis multi-module detection algorithm based on a random walk matrix to detect abnormal points of each module of the hydrogen storage chassis includes: Q31. Based on the predicted operating data information of each module of the hydrogen storage chassis, establish a random walk matrix function M of each module of the hydrogen storage chassis i , Among them, z i is the predicted operating data information of the i-th module of the hydrogen storage chassis, η and σ are the mean factors of the multiple modules of the hydrogen storage chassis, and the random walk matrix of each module of the hydrogen storage chassis is characterized to obtain the data information of the random walk matrix of each module of the hydrogen storage chassis; Q32. Based on the data information of the random walk matrix of each module of the hydrogen storage chassis, a multi-module detection function M of the hydrogen storage chassis is constructed. Wherein, a is the data information of the random walk matrix of each module of the hydrogen storage chassis, θ1, θ2 and θ3 are the detection factors of each module of the hydrogen storage chassis, and each module of the hydrogen storage chassis is detected to obtain the data information of the detection value of each module of the hydrogen storage chassis; Q33. Based on the data information of the detection values ​​of each module of the hydrogen storage chassis, a preset threshold is set. If the detection value of each module of the hydrogen storage chassis is less than the preset threshold, it is not an abnormal module. If the detection value of each module of the hydrogen storage chassis is greater than the preset threshold, it is an abnormal module.

7. The multi-module detection method applied to an integrated hydrogen storage chassis according to claim 1, characterized in that: In step Q4, the abnormality evaluation function H of the hydrogen storage chassis is constructed. Among them, ρ1, ρ2 and ρ3 are the abnormal evaluation parameters of the hydrogen storage chassis, and h is the abnormal data information of the hydrogen storage chassis.

8. A system for implementing the multi-module detection method for an integrated hydrogen storage chassis according to any one of claims 1 to 7, characterized in that: The system comprises: The hydrogen storage chassis data acquisition module is used to obtain the operating data information of each module of the hydrogen storage chassis, and collect the historical operating data information of each module of the hydrogen storage chassis; A hydrogen storage chassis data prediction module is connected to the hydrogen storage chassis data acquisition module and is used to predict the operating data information of each module of the hydrogen storage chassis by using an improved random forest regression prediction algorithm with integrated random weights; A hydrogen storage chassis data abnormal point detection module is connected to the hydrogen storage chassis data prediction module and is used to detect abnormal points of each module of the hydrogen storage chassis using a hydrogen storage chassis multi-module detection algorithm based on a random walk matrix; The hydrogen storage chassis data abnormal point evaluation module is connected to the hydrogen storage chassis data abnormal point detection module and is used to construct an abnormal evaluation function H of the hydrogen storage chassis to evaluate the abnormal data of the hydrogen storage chassis.

9. The system according to claim 8, characterized in that: The system also includes an early warning module, which is connected to the hydrogen storage chassis data abnormal point evaluation module and is used to warn or remind the vehicle driver.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the multi-module detection method applied to an integrated hydrogen storage chassis as described in any one of claims 1 to 7.

Images