Test regulation and control method and system based on automobile thermal management system and storage medium

Abstract

The invention discloses a test regulation and control method and system based on an automobile thermal management system and a storage medium, and the method comprises the steps: collecting the historical training data of the automobile thermal management system, and training a machine learning model based on the historical circular data; performing real-time data acquisition and preliminary detection to obtain a first detection result, if any one of the feature change conditions is triggered, inputting the system feature data acquired in real time into the pre-trained machine learning model to perform second detection to obtain a second detection result, and if the second detection result is abnormal, performing real-time data acquisition and preliminary detection to obtain a second detection result. And the automobile thermal management monitoring platform collects a real-time regional temperature change data set of the to-be-detected automobile thermal management system, third detection is carried out, a third detection result is obtained, the third detection result is short circuit, and operation parameters of the thermal management system are adjusted according to the optimal regulation and control parameters. According to the test regulation and control method, the detection precision is high, the response speed is high, the regulation and control efficiency is good, and the adaptability is high.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle thermal management, and particularly to a test and regulation method, system and storage medium based on an automotive thermal management system. Background Art

[0002] With the continuous development of automotive technologies, the performance and reliability of automotive thermal management systems have become important factors affecting the overall performance of vehicles. The automotive thermal management system is responsible for maintaining the appropriate operating temperatures of the engine and other key components, ensuring that the vehicle can operate efficiently and safely under various working conditions.

[0003] However, the detection accuracy, response speed, regulation efficiency, adaptability, etc. of the thermal management systems in related technologies still need to be improved. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, an object of the present invention is to provide a test and regulation method based on an automotive thermal management system, and the test and regulation method based on the automotive thermal management system has high detection accuracy, fast response speed, good regulation efficiency and strong adaptability.

[0005] A test regulation method based on an automotive thermal management system according to an embodiment of the present invention includes: S1. Collect historical training data of the automotive thermal management system, where the historical training data includes system characteristic data and system state values. The system characteristic data includes real-time change values of coolant temperature, real-time change values of current, maximum temperature change values, coolant flow rate, and operating modes of the cooling system. Train a machine learning model based on the historical cycle data; S2. Real-time data collection and preliminary detection, including: The automotive thermal management monitoring platform collects the system characteristic data of the to-be-detected automotive thermal management system in real time and performs a first detection to obtain a first detection result. The first detection is based on preset coolant temperature change thresholds, current change thresholds, and maximum temperature change thresholds; S3. Determine whether the system characteristic data meets the characteristic change conditions. If any one of the conditions in the characteristic change conditions is triggered, output the abnormal first detection result and go to step S4; if none of the conditions is triggered, output the normal first detection result and go to step S2; S4. The machine learning model detection, including: Input the system characteristic data collected in real time into the pre-trained machine learning model for a second detection to obtain a second detection result. If the second detection result is normal, go to step S2 to continue real-time data collection and preliminary detection; if the second detection result is abnormal, go to step S5; S5. Regional temperature change data detection, where the automotive thermal management monitoring platform collects a real-time set of regional temperature change data of the to-be-detected automotive thermal management system and performs a third detection to obtain a third detection result. Each set of data corresponds to an abnormal area. The third detection is based on a preset abnormal segment quantity threshold. If the number of abnormal segments in the regional temperature change data set is greater than or equal to the abnormal segment quantity threshold, the third detection result is a short circuit, and go to step S6; if the number of abnormal segments in the regional temperature change data set is less than the abnormal segment quantity threshold, the third detection result is non-short circuit, and output the non-short circuit third detection result; S6. Adaptive adjustment, including: Adjust the operating parameters of the thermal management system according to the optimal regulation parameters.

[0006] The test regulation method based on the automotive thermal management system according to the embodiment of the present invention has high detection accuracy, fast response speed, good regulation efficiency, and strong adaptability.

[0007] Among them, the test regulation method based on the automotive thermal management system of the present invention may also have the following additional technical features:

[0008] In some embodiments of the present invention, the adaptive regulation includes: extracting the evaluation indexes of thermal management regulation, constructing a comprehensive evaluation function by using the evaluation indexes of thermal management regulation, and screening out the solution with the highest comprehensive evaluation function value from the optimal solution set of the comprehensive evaluation function as the optimal thermal management regulation parameter to adjust the vehicle thermal management system.

[0009] In some embodiments of the present invention, the adaptive regulation includes: S601. The evaluation indexes of thermal management regulation include the temperature uniformity evaluation index ω5, the system stability evaluation index ω6, and the energy consumption evaluation index ω7. The comprehensive evaluation function satisfies: E(x) = ω5U + ω6S + ω7E; where U represents the temperature uniformity; S represents the system stability; E represents the energy consumption; S602. Output the optimal regulation parameter; including: screening out the solution with the highest comprehensive evaluation function value from the optimal solution set as the optimal thermal management regulation parameter. The optimal thermal management regulation parameter includes the optimal coolant flow rate adjustment step number and the optimal total adjustment times, the optimal coolant flow rate adjustment path, and the optimal adjustment step number distribution; discretizing the optimal coolant flow rate adjustment path into M processing units, each unit corresponding to an adjustment step number, constructing an M×1 adjustment step number distribution matrix, and the matrix element represents the adjustment step number of the mth processing unit, m ∈ [1, M]; continuousizing the discrete adjustment step number distribution matrix to obtain an adjustment step number distribution surface; starting the thermal management regulation device, and adjusting the operating parameters of the thermal management system according to the optimal coolant flow rate adjustment path and the adjustment step number distribution surface.

[0010] In some embodiments of the present invention, if the number of abnormal segments in the regional temperature change data set is less than the abnormal segment number threshold, the third detection result is non-short circuit, and go to step S7. S7. Comprehensive evaluation and optimization, including extracting the evaluation indexes of the regional temperature change data, constructing a comprehensive evaluation function by using the evaluation indexes of the regional temperature change data, optimizing the thermal management regulation parameters according to the comprehensive evaluation function, and outputting the optimal thermal management regulation parameters.

[0011] In some embodiments of the present invention, the comprehensive evaluation and optimization include: S701, extracting evaluation indexes of regional temperature change data, including temperature change amplitude index, temperature change density index, temperature change distribution gradient index and temperature change aggregation index; S702, constructing a comprehensive evaluation function: constructing the comprehensive evaluation function by using the evaluation indexes of regional temperature change data; S703, optimization objective: taking the comprehensive evaluation function and the thermal management regulation parameters as the optimization objective, and taking the feasible range of the thermal management regulation parameters as the constraint condition, constructing an objective optimization model; S704, solving the optimal solution set: using the non-dominated sorting genetic algorithm to solve the objective optimization model to obtain the optimal solution set of the thermal management regulation parameters, and the optimal solution set of the thermal management regulation parameters includes the coolant flow rate adjustment step number and the total adjustment times, the coolant flow rate adjustment path and the adjustment step number distribution.

[0012] In some embodiments of the present invention, the calculation formula of the temperature change amplitude index is where ΔT i represents the temperature change value of the i-th abnormal area; M represents the number of all identified abnormal areas; the calculation formula of the temperature change density index d is where V represents the total volume of the whole system; the calculation formula of the temperature change distribution gradient index is where represents the gradient vector of the temperature change density field; represents the modulus of the gradient vector; the calculation formula of the temperature change aggregation index is where A represents the total projected area occupied by the system in space, n i and n j respectively represent the positions of the i-th and j-th abnormal areas, δ is an indicator function, when ||n i -n j || < r holds, δ is equal to 1, otherwise equal to 0; the comprehensive evaluation function is as follows: F(x) = ω1A + ω2d + ω3G + ω4C; where ω1, ω2, ω3 and ω4 are the weight coefficients of the temperature change amplitude index, the temperature change density index, the temperature change distribution gradient index and the temperature change aggregation index respectively.

[0013] In some embodiments of the present invention, the thermal management control parameters include coolant flow rate adjustment, cooling fan speed adjustment, and cooling system operating mode switching; obtaining the thermal management control parameters includes the number of coolant flow rate adjustment steps and the total number of adjustments, with the optimization objectives of minimizing the comprehensive evaluation function, minimizing the number of coolant flow rate adjustment steps, and minimizing the total number of adjustments; with the feasible range constraint, coverage constraint, and adjustment gradient constraint of the thermal management control parameters as the constraint conditions, the coverage constraint means ensuring that the thermal management control parameters cover all abnormal areas, and the adjustment gradient constraint means that the difference in the number of adjustment steps between adjacent control parameters is less than or equal to the adjustment step difference threshold. 8. The test control method based on an automotive thermal management system according to claim 1, wherein training the machine learning model based on historical cycle data includes: during the training process, according to the system state value when each set of system feature data is collected, assigning a corresponding label to each collected set of system feature data sets, the label reflecting the true state of the system, marking anomalies as 1 and normal as 0; training the model using the labeled data sets, and the objective of the model is to minimize the error rate when classifying all input data, that is, to minimize the sum of the prediction accuracies of all system feature data until the sum of the prediction accuracies converges.

[0014] The present invention also proposes a test control system for implementing the test control method based on an automotive thermal management system.

[0015] The test control system based on an automotive thermal management system according to an embodiment of the present invention includes: a data acquisition module: used to collect various feature data and status information of the automotive thermal management system in real time; a data processing and storage module: used to preprocess, store, and manage the collected data, and output the preprocessed data and label data; a model training module: trains a machine learning model based on historical training data for anomaly detection; a real-time detection module: used to collect system feature data in real time and perform preliminary detection, and output the preliminary detection result including normal or abnormal; a machine learning model detection module: used to perform more accurate anomaly detection using the trained machine learning model, and output the second detection result including normal or abnormal; a regional temperature change detection module: used to collect regional temperature change data and perform further detection, and output the third detection result including non-short circuit or short circuit; an adaptive control module: adjusts the operating parameters of the thermal management system according to the optimal control parameters, and outputs the adjusted operating parameters of the thermal management system.

[0016] In the above example, through multi-level data acquisition and processing, multi-stage anomaly detection, and adaptive control, comprehensive monitoring and precise control of the automotive thermal management system are achieved, significantly improving the safety and performance of the system, reducing energy consumption, and enhancing the control efficiency.

[0017] In some embodiments of the present invention, the test regulation system based on the vehicle thermal management system further includes: an integrated evaluation and optimization module: extracting evaluation indicators of the regional temperature change data, constructing an integrated evaluation function, optimizing the thermal management regulation parameters, and outputting the optimal thermal management regulation parameters.

[0018] The present invention also provides a storage medium.

[0019] According to the storage medium of the embodiments of the present invention, the storage medium stores a vehicle thermal management regulation program, and when the vehicle thermal management regulation program is executed, it implements the test regulation method based on the vehicle thermal management system.

[0020] The additional aspects and advantages of the present invention will be partially given in the following description, partially become apparent from the following description, or be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0022] Figure 1 is a flowchart of a test regulation method based on vehicle thermal management according to an embodiment of the present invention.

[0023] Figure 2 is a flowchart of integrated evaluation and optimization according to an embodiment.

[0024] Figure 3 is a module diagram of a test regulation system based on vehicle thermal management according to an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0026] Reference will be made below to Figure 1 - Figure 2 describe a test regulation method based on a vehicle thermal management system according to an embodiment of the present invention.

[0027] Reference is made to Figure 1 and Figure 2As shown in the figure, the test regulation method based on the vehicle thermal management system according to an embodiment of the present invention includes: S1. Collect historical training data of the vehicle thermal management system. The historical training data includes system characteristic data and system state values. The system characteristic data includes real-time change values of coolant temperature, real-time change values of current, maximum temperature change values, coolant flow rate, and operating modes of the cooling system. Train a machine learning model based on the historical cycle data; S2. Real-time data collection and preliminary detection, including: The vehicle thermal management monitoring platform collects the system characteristic data of the vehicle thermal management system to be detected in real time and performs a first detection to obtain a first detection result. The first detection is based on preset coolant temperature change thresholds, current change thresholds, and maximum temperature change thresholds; S3. Determine whether the system characteristic data meets the characteristic change conditions. If any one of the conditions in the characteristic change conditions is triggered, output an abnormal first detection result and go to step S4; if none of the conditions is triggered, output a normal first detection result and go to step S2; S4. Machine learning model detection, including: Input the system characteristic data collected in real time into the pre-trained machine learning model for a second detection to obtain a second detection result. If the second detection result is normal, go to step S2 to continue real-time data collection and preliminary detection; if the second detection result is abnormal, go to step S5; S5. Detection of regional temperature change data. The vehicle thermal management monitoring platform collects the real-time regional temperature change data set of the vehicle thermal management system to be detected and performs a third detection to obtain a third detection result. Each group of data corresponds to an abnormal area. The third detection is based on a preset abnormal segment quantity threshold. If the number of abnormal segments in the regional temperature change data set is greater than or equal to the abnormal segment quantity threshold, the third detection result is a short circuit, and go to step S6. If the number of abnormal segments in the regional temperature change data set is less than the abnormal segment quantity threshold, the third detection result is a non-short circuit, and output the third detection result of non-short circuit; S6. Adaptive adjustment, including: Adjust the operating parameters of the thermal management system according to the optimal regulation parameters.

[0028] In the above example, through multi-level data collection and processing, multi-stage anomaly detection, and adaptive regulation, it is possible to better achieve comprehensive monitoring and precise regulation of the vehicle thermal management system, significantly improve the safety and performance of the vehicle thermal management system, reduce energy consumption, and improve the regulation efficiency.

[0029] In the above example, preliminary detection is performed based on preset thresholds to quickly screen out possible abnormal situations; a trained machine learning model is used for more accurate anomaly detection to improve the accuracy and reliability of detection; further regional temperature change detection is performed based on the abnormal segment quantity threshold to distinguish between short circuit and non-short circuit anomalies and refine the anomaly types.

[0030] In the above example, the characteristic change condition means that the characteristic change conditions for the real-time change value of the coolant temperature, the real-time change value of the current, the maximum temperature change value, the coolant flow rate, and the working mode of the cooling system are set in advance. When the characteristic change condition of any one of the real-time change value of the coolant temperature, the real-time change value of the current, the maximum temperature change value, the coolant flow rate, and the working mode of the cooling system is triggered, an abnormal first detection result is output. If none of the conditions is triggered, a normal first detection result is output. Exemplarily, the characteristic change conditions are as follows: the real-time change value of the coolant temperature > T1, the real-time change value of the current > I1, and the maximum temperature change value > T2, where the values of T1, I1, and T2 are reasonably set according to the actual application scenario and system characteristics.

[0031] In the above example, the real-time change value of the coolant temperature: is obtained in real time by a temperature sensor installed in the cooling system. The real-time change value of the current: is obtained in real time by a current sensor installed in the cooling system. The maximum temperature change value: the real-time temperature of each section of the cooling system is obtained by an intelligent temperature sensor, and the maximum temperature change value is calculated. The coolant flow rate: is obtained in real time by a flow meter installed in the cooling system. The working mode of the cooling system: includes the operating state of the cooling system (such as start, stop, fault, etc.).

[0032] As can be seen from the above, according to the test regulation method based on the automotive thermal management system of the embodiments of the present invention, the detection accuracy is high, the response speed is fast, the regulation efficiency is good, and the adaptability is strong.

[0033] In some embodiments of the present invention, referring to Figure 2 As shown, the adaptive adjustment includes: extracting the thermal management regulation evaluation index, and using the thermal management regulation evaluation index to construct a comprehensive evaluation function, and screening out the solution with the highest comprehensive evaluation function value from the optimal solution set of the comprehensive evaluation function as the optimal thermal management regulation parameter to adjust the automotive thermal management system.

[0034] In the above example, the test regulation method based on the automotive thermal management system can better adjust the automotive thermal management system, so that the automotive thermal management system has better adaptability.

[0035] In some embodiments of the present invention, the adaptive regulation includes: S601. The evaluation indicators for thermal management regulation include the temperature uniformity evaluation indicator ω5, the system stability evaluation indicator ω6, and the energy consumption evaluation indicator ω7. The comprehensive evaluation function satisfies: E(x) = ω5U + ω6S + ω7E; where U represents the temperature uniformity; S represents the system stability; E represents the energy consumption; S602. Output the optimal regulation parameters; including: screening out the solution with the highest comprehensive evaluation function value from the optimal solution set as the optimal thermal management regulation parameters. The optimal thermal management regulation parameters include the optimal coolant flow rate adjustment steps and the optimal total adjustment times, the optimal coolant flow rate adjustment path, and the optimal adjustment step distribution; discretizing the optimal coolant flow rate adjustment path into M processing units, with each unit corresponding to an adjustment step, and constructing an M×1 adjustment step distribution matrix. The matrix element represents the adjustment step of the m-th processing unit, m ∈ [1, M]; continuousizing the discrete adjustment step distribution matrix to obtain an adjustment step distribution surface; starting the thermal management regulation device and adjusting the operating parameters of the thermal management system according to the optimal coolant flow rate adjustment path and the adjustment step distribution surface.

[0036] In the above example, the test regulation method based on the vehicle thermal management system can better adjust the vehicle thermal management system, so that the vehicle thermal management system has better adaptability.

[0037] In the above example, the present invention defines regulation evaluation indicators such as temperature uniformity, system stability, and energy consumption to ensure the multi-objective optimization of the regulation process; screening out the solution with the highest comprehensive evaluation function value from the optimal solution set as the optimal thermal management regulation parameters to ensure the optimization of the regulation effect; continuousizing the discrete adjustment step distribution matrix to obtain an adjustment step distribution surface to achieve a smooth regulation process.

[0038] In some embodiments of the present invention, if the number of abnormal segments in the regional temperature change data set is less than the abnormal segment number threshold, the third detection result is non-short circuit, and it proceeds to step S7. S7. Comprehensive evaluation and optimization, including extracting the evaluation indicators of the regional temperature change data, constructing a comprehensive evaluation function using the evaluation indicators of the regional temperature change data, optimizing the thermal management regulation parameters according to the comprehensive evaluation function, and outputting the optimal thermal management regulation parameters.

[0039] In the above example, through multi-level data collection and processing, multi-stage anomaly detection, comprehensive evaluation and optimization, and adaptive regulation, the comprehensive monitoring and precise regulation of the vehicle thermal management system are realized, significantly improving the safety and performance of the vehicle thermal management system, reducing energy consumption, and enhancing the regulation efficiency.

[0040] In some embodiments of the present invention, the comprehensive evaluation and optimization include: S701, extracting evaluation indicators of regional temperature change data, including temperature change amplitude index, temperature change density index, temperature change distribution gradient index, and temperature change aggregation degree index; S702, constructing a comprehensive evaluation function: constructing a comprehensive evaluation function using the evaluation indicators of regional temperature change data; S703, optimization objective: taking the comprehensive evaluation function and thermal management control parameters as the optimization objective, and taking the feasible range of thermal management control parameters as the constraint condition, constructing an objective optimization model; S704, solving the optimal solution set: using the non-dominated sorting genetic algorithm to solve the objective optimization model, obtaining the optimal solution set of thermal management control parameters, and the optimal solution set of thermal management control parameters includes the coolant flow rate adjustment step number and the total adjustment times, the coolant flow rate adjustment path, and the adjustment step number distribution.

[0041] In the above example, the present invention extracts multi-dimensional evaluation indicators such as temperature change amplitude, temperature change density, temperature change distribution gradient, and temperature change aggregation degree to comprehensively evaluate the system state; constructs a comprehensive evaluation function using the multi-dimensional evaluation indicators to quantify the quality of the system state; takes the comprehensive evaluation function and thermal management control parameters as the optimization objective to construct an objective optimization model to ensure the optimality of the control scheme; uses the non-dominated sorting genetic algorithm to solve the optimal solution set to improve the optimization efficiency and the quality of the solution.

[0042] In some embodiments of the present invention, the calculation formula of the temperature change amplitude index is where ΔT i represents the temperature change value of the i-th abnormal region; M represents the number of all identified abnormal regions; the calculation formula of the temperature change density index d is where V represents the total volume of the entire system; the calculation formula of the temperature change distribution gradient index is where represents the gradient vector of the temperature change density field; represents the modulus of the gradient vector; the calculation formula of the temperature change aggregation degree index is where A represents the total projected area occupied by the system in space, n i and n j respectively represent the positions of the i-th and j-th abnormal regions, δ is an indicator function, when ||n i -n j || < r holds, δ is equal to 1, otherwise equal to 0; the comprehensive evaluation function is as follows: F(x) = ω1A + ω2d + ω3G + ω4C; where ω1, ω2, ω3, and ω4 are the weight coefficients of the temperature change amplitude index, temperature change density index, temperature change distribution gradient index, and temperature change aggregation degree index respectively.

[0043] In some embodiments of the present invention, the thermal management control parameters include coolant flow rate adjustment, cooling fan speed adjustment, and cooling system operating mode switching; obtaining the thermal management control parameters includes the number of coolant flow rate adjustment steps and the total number of adjustments, with the optimization objectives of minimizing the comprehensive evaluation function, minimizing the number of coolant flow rate adjustment steps, and minimizing the total number of adjustments; using the feasible range constraint, coverage constraint, and adjustment gradient constraint of the thermal management control parameters as the constraint conditions, where the coverage constraint means ensuring that the thermal management control parameters cover all abnormal areas, and the adjustment gradient constraint means that the difference in the adjustment steps of adjacent control parameters is less than or equal to the adjustment step difference threshold.

[0044] In the above example, the present invention extracts multi-dimensional evaluation indicators such as the temperature change amplitude, temperature change density, temperature change distribution gradient, and temperature change aggregation degree to comprehensively evaluate the system state; constructs a comprehensive evaluation function using the multi-dimensional evaluation indicators to quantify the quality of the system state; constructs an objective optimization model with the comprehensive evaluation function and thermal management control parameters as the optimization objectives to ensure the optimality of the control scheme; and uses the non-dominated sorting genetic algorithm to solve the optimal solution set to improve the optimization efficiency and the quality of the solution.

[0045] In some embodiments of the present invention, training a machine learning model based on historical cycle data includes: during the training process, according to the system state value when each set of system feature data is collected, assigning a corresponding label to each collected set of system feature data sets, where the label reflects the true state of the system, marking abnormal as 1 and normal as 0; training the model using the labeled data set, and the goal of the model is to minimize the error rate when classifying all input data, that is, to minimize the sum of the prediction accuracies of all system feature data until the sum of the prediction accuracies converges.

[0046] The present invention also proposes a test control system based on an automotive thermal management system.

[0047] Refer to Figure 3As shown, the test and regulation system based on the vehicle thermal management system according to an embodiment of the present invention is used to implement the test and regulation method based on the vehicle thermal management system. The test and regulation system includes: a data acquisition module, a data processing and storage module, a model training module, a real-time detection module, a machine learning model detection module, a regional temperature change detection module, and an adaptive regulation module. The data acquisition module is used to collect various characteristic data and status information of the vehicle thermal management system in real time. The data processing and storage module is used to preprocess, store, and manage the collected data, and output the preprocessed data and label data. The model training module trains a machine learning model based on historical training data for anomaly detection. The real-time detection module is used to collect system characteristic data in real time and perform preliminary detection, and output a preliminary detection result including normal or abnormal. The machine learning model detection module is used to perform more accurate anomaly detection using the trained machine learning model, and output a second detection result including normal or abnormal. The regional temperature change detection module is used to collect regional temperature change data and perform further detection, and output a third detection result including non-short circuit or short circuit. The adaptive regulation module adjusts the operating parameters of the thermal management system according to the optimal regulation parameters, and outputs the adjusted operating parameters of the thermal management system.

[0048] In the above example, through multi-level data acquisition and processing, multi-stage anomaly detection, and adaptive regulation, it is possible to better achieve comprehensive monitoring and precise regulation of the vehicle thermal management system, significantly improve the safety and performance of the vehicle thermal management system, reduce energy consumption, and improve the regulation efficiency.

[0049] In some embodiments of the present invention, with reference to Figure 3 As shown, the test and regulation system based on the vehicle thermal management system further includes: a comprehensive evaluation and optimization module: extracting evaluation indicators of the regional temperature change data, constructing a comprehensive evaluation function, optimizing the thermal management regulation parameters, and outputting the optimal thermal management regulation parameters.

[0050] In the above example, through multi-level data acquisition and processing, multi-stage anomaly detection, comprehensive evaluation and optimization, and adaptive regulation, comprehensive monitoring and precise regulation of the vehicle thermal management system are achieved, significantly improving the safety and performance of the system, reducing energy consumption, and improving the regulation efficiency.

[0051] The present invention also proposes a storage medium.

[0052] The storage medium according to an embodiment of the present invention stores a vehicle thermal management regulation program, and when the vehicle thermal management regulation program is executed, it implements the test and regulation method based on the vehicle thermal management system.

[0053] Other components and operations of the vehicle thermal management system, test regulation system, and storage medium according to embodiments of the present invention are known to those of ordinary skill in the art and will not be described in detail herein.

[0054] In the description of this specification, the descriptions with reference to terms such as "some embodiments", "optionally", "further", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0055] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. A test and control method based on an automobile thermal management system, characterized in that: include: S1. Collect historical training data of the automotive thermal management system, wherein the historical training data includes system characteristic data and system status values, wherein the system characteristic data includes real-time change value of coolant temperature, real-time change value of current, maximum temperature change value, coolant flow rate, and working mode of the cooling system, and train a machine learning model based on the historical cycle data; S2, real-time data collection and preliminary detection, including: the automobile thermal management monitoring platform collects the system characteristic data of the automobile thermal management system to be detected in real time, and performs a first detection to obtain a first detection result, the first detection is based on a preset coolant temperature change threshold, a current change threshold and a maximum temperature change threshold; S3, judging whether the system characteristic data meets the characteristic change conditions, if any one of the characteristic change conditions is triggered, outputting the abnormal first detection result, and going to step S4; if none of the conditions is triggered, outputting the normal first detection result, and going to step S2; S4, the machine learning model detection includes: inputting the system feature data collected in real time into the pre-trained machine learning model to perform a second detection, obtaining a second detection result, if the second detection result is normal, turning to step S2, continuing real-time data collection and preliminary detection; if the second detection result is abnormal, turning to step S5; S5, regional temperature change data detection, the automobile thermal management monitoring platform collects the real-time regional temperature change data set of the automobile thermal management system to be detected, and performs a third detection to obtain a third detection result, each set of data corresponds to an abnormal area, the third detection is based on a preset abnormal segment number threshold, if the number of abnormal segments in the regional temperature change data set is greater than or equal to the abnormal segment number threshold, then the third detection result is a short circuit, and the process goes to step S6, if the number of abnormal segments in the regional temperature change data set is less than the abnormal segment number threshold, then the third detection result is a non-short circuit, and the non-short circuit third detection result is output; S6. Adaptive regulation, including: adjusting the operating parameters of the thermal management system according to the optimal control parameters.

2. The test and control method based on the automobile thermal management system according to claim 1 is characterized in that: The adaptive adjustment includes: Extract thermal management control evaluation indicators, and use the thermal management control evaluation indicators to construct a comprehensive evaluation function, and select the solution with the highest comprehensive evaluation function value from the optimal solution set of the comprehensive evaluation function as the optimal thermal management control parameter to adjust the vehicle thermal management system.

3. The test and control method based on the automobile thermal management system according to claim 2 is characterized in that: The adaptive adjustment includes: S601, thermal management control evaluation index, including temperature uniformity evaluation index ω5, system stability evaluation index ω6 and energy consumption evaluation index ω7, the comprehensive evaluation function satisfies: E(x) = ω5U + ω6S + ω7E; where U represents temperature uniformity; S represents system stability; and E represents energy consumption; S602, output optimal control parameters; including: selecting the solution with the highest comprehensive evaluation function value from the optimal solution set as the optimal thermal management control parameters, the optimal thermal management control parameters including the optimal coolant flow rate adjustment step number and the optimal total number of adjustments, the optimal coolant flow rate adjustment path and the optimal adjustment step number distribution; discretizing the optimal coolant flow rate adjustment path into M processing units, each unit corresponding to an adjustment step number, constructing an M×1 adjustment step number distribution matrix, the matrix elements represent the adjustment step number of the mth processing unit, m∈[1,M]; making the discrete adjustment step number distribution matrix continuous to obtain the adjustment step number distribution surface; starting the thermal management control equipment, and adjusting the operating parameters of the thermal management system according to the optimal coolant flow rate adjustment path and the adjustment step number distribution surface.

4. The test and control method based on the automobile thermal management system according to claim 1 is characterized in that: If the number of abnormal segments in the regional temperature change data set is less than the abnormal segment number threshold, the third detection result is non-short circuit, and the process goes to step S7. S7, comprehensive evaluation and optimization, including extracting evaluation indicators of the regional temperature change data, and constructing a comprehensive evaluation function using the evaluation indicators of the regional temperature change data, optimizing thermal management control parameters according to the comprehensive evaluation function, and outputting optimal thermal management control parameters.

5. The test and control method based on the automobile thermal management system according to claim 4 is characterized in that: The comprehensive evaluation and optimization includes: S701, extracting evaluation indicators of regional temperature change data, including a temperature change amplitude indicator, a temperature change density indicator, a temperature change distribution gradient indicator, and a temperature change aggregation indicator; S702, constructing a comprehensive evaluation function: constructing the comprehensive evaluation function using the evaluation index of the regional temperature change data; S703, optimization target: taking the comprehensive evaluation function and the thermal management control parameters as the optimization target, taking the feasible range of the thermal management control parameters as the constraint condition, and constructing a target optimization model; S704, solving the optimal solution set: using a non-dominated sorting genetic algorithm to solve the target optimization model to obtain an optimal solution set of thermal management control parameters, wherein the optimal solution set of thermal management control parameters includes the number of coolant flow adjustment steps and the total number of adjustments, the coolant flow adjustment path and the distribution of the number of adjustment steps.

6. The test and control method based on the automobile thermal management system according to claim 5, characterized in that: The calculation formula of the temperature variation index is: Where, ΔT i represents the temperature change value of the i-th abnormal area; M represents the number of all abnormal areas identified; The calculation formula for the temperature change density index d is where V represents the total volume of the entire system; the calculation formula for the temperature change distribution gradient index is where represents the gradient vector of the temperature change density field; represents the modulus of the gradient vector; the calculation formula for the temperature change aggregation index is where A represents the total projected area occupied by the system in space, n i and n j represent the positions of the i-th and j-th abnormal regions respectively, δ is an indicator function, when ||n i - n j || < r holds, δ is equal to 1, otherwise equal to 0; The comprehensive evaluation function is as follows: F(x)=ω1A+ω2d+ω3G+ω4C; wherein ω1, ω2, ω3 and ω4 are the weight coefficients of the temperature change amplitude index, the temperature change density index, the temperature change distribution gradient index and the temperature change aggregation index respectively.

7. The test and control method based on the automobile thermal management system according to claim 5, characterized in that: Thermal management control parameters, including coolant flow rate control, cooling fan speed control, and cooling system working mode switching; obtain thermal management control parameters, including coolant flow rate control steps and total adjustment times, with minimization of comprehensive evaluation function, minimization of coolant flow rate control steps, and minimization of total adjustment times as optimization goals; The feasible range constraint, coverage constraint and adjustment gradient constraint of the thermal management control parameters are used as constraint conditions. The coverage constraint refers to ensuring that the thermal management control parameters cover all abnormal areas, and the adjustment gradient constraint refers to that the difference in the number of adjustment steps of adjacent control parameters is less than or equal to the adjustment step difference threshold.

8. The test and control method based on the automobile thermal management system according to claim 1 is characterized in that: The training of the machine learning model based on historical cycle data includes: During the training process, each set of collected system feature data is assigned a corresponding label based on the system state value when each set of system feature data is collected. The label reflects the true state of the system, with anomalies marked as 1 and normal as 0. The model is trained using the labeled data set. The goal of the model is to minimize the error rate when classifying all input data, that is, to minimize the sum of the prediction accuracies of all system feature data until the sum of the prediction accuracies converges.

9. A test and control system based on an automobile thermal management system, used to implement the test and control method based on an automobile thermal management system as described in any one of claims 1 to 8, characterized in that: The test control system comprises: Data acquisition module: used to collect various characteristic data and status information of the automotive thermal management system in real time; Data processing and storage module: used to preprocess, store and manage the collected data, and output preprocessed data and label data; Model training module: trains machine learning models based on historical training data for anomaly detection; Real-time detection module: used to collect system feature data in real time and perform preliminary detection, and output preliminary detection results including normal or abnormal; Machine learning model detection module: used to use the trained machine learning model to perform more accurate anomaly detection and output the second detection result including normal or abnormal; Regional temperature change detection module: used to collect regional temperature change data and perform further detection, and output the third detection result including non-short circuit or short circuit; Adaptive control module: adjusts the operating parameters of the thermal management system according to the optimal control parameters, and outputs the adjusted operating parameters of the thermal management system.

10. The test and control system based on the automobile thermal management system according to claim 9, characterized in that: Also includes: Comprehensive evaluation and optimization module: extracts evaluation indicators of regional temperature change data, constructs comprehensive evaluation functions, optimizes thermal management control parameters, and outputs optimal thermal management control parameters.

11. A storage medium, characterized in that: The storage medium stores an automobile thermal management control program, which, when executed, implements a test control method based on an automobile thermal management system as described in any one of claims 1 to 8.

Images