Hybrid power platform heat-energy integrated simulation optimization method

Abstract

The invention belongs to the technical field of hybrid electric vehicles, and particularly relates to a hybrid power platform heat-energy integrated simulation optimization method which comprises the following steps: step 1, collecting heat energy data, determining a heat system architecture, arranging detection equipment at a vehicle working position, and collecting multiple groups of heat energy data at each position of a vehicle by utilizing the detection equipment; step 2, data preprocessing: classifying each group of collected heat energy data according to vehicle positions, and marking each group of data; step 3, data integration: different simulation models of the relation between the heat and the energy of the power platform are established according to each group of data, and each group of simulation model data is corrected; a plurality of groups of simulation models are adopted for contrastive analysis, the data accuracy is improved, a deep learning model is utilized for path optimization, the required time is shortened, the optimization efficiency is improved, and finally the actual requirements are met by manually determining the requirements.

Description

Technical Field

[0001] The invention relates to the technical field of hybrid electric vehicles, and in particular to a hybrid electric vehicle platform heat-energy integration simulation optimization method. Background Art

[0002] In a broad sense, a hybrid vehicle (HybridVehicle) refers to a vehicle whose vehicle drive system is composed of two or more single drive systems that can operate simultaneously. The vehicle's driving power is provided by a single drive system alone or together according to the actual vehicle driving state. The vehicle drive system is composed of two or more single drive systems that can operate simultaneously. The vehicle's driving power is provided by a single drive system alone or together according to the actual vehicle driving state. Due to the differences in various components, layout methods and control strategies, a variety of classification forms have been formed. The energy-saving and low-emission characteristics of hybrid vehicles have attracted great attention from the automotive industry and have become a focus of automotive research and development. The hybrid device not only plays the advantages of the engine's long continuous working time and good power, but also plays the advantages of the motor's pollution-free and low-noise. The two "fight side by side" and learn from each other's strengths to make up for each other's weaknesses. The thermal efficiency of the car can be increased by more than 10%, and the exhaust emissions can be improved by more than 30%.

[0003] Hybrid vehicles use engines, motors, and power batteries as power units to provide energy for vehicle operation, and perform heat management through air-conditioning systems and cooling systems. Optimizing the energy consumption control of the power unit has become the core task of optimizing the energy consumption of the entire hybrid vehicle. How to achieve a balance between the energy consumption and output of the power unit needs to be optimized. To this end, this application proposes a hybrid platform thermal-energy integrated simulation optimization method. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above problems and / or problems existing in the existing vehicle thermal system architecture, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a hybrid platform thermal-energy integrated simulation optimization method, in which an inappropriate optimization path is substituted into a deep learning model for further optimization, the optimization result is brought back into the simulation model, and the optimization path is output. Multiple groups of simulation models are used for comparative analysis to improve data accuracy, and a deep learning model is used for path optimization to reduce the time required and improve optimization efficiency. Ultimately, the needs are determined manually to meet actual needs.

[0007] To solve the above technical problems, according to one aspect of the present invention, the present invention provides the following technical solutions:

[0008] A hybrid platform heat-energy integration simulation optimization method includes the following steps:

[0009] Step 1: Thermal data collection: determine the thermal system architecture, set up detection equipment at the working position of the vehicle, and use the detection equipment to collect multiple sets of thermal data at various positions of the vehicle;

[0010] Step 2: Data preprocessing: classify each set of thermal energy data collected according to the vehicle position and mark each set of data;

[0011] Step 3: Data integration: establishing simulation models of the relationship between heat and energy of different power platforms based on each set of data, and correcting each set of simulation model data;

[0012] Step 4: Data comparison and analysis: analyze the energy consumption of each model group and the performance of the thermal management system, and compare the difference data between each group of performance;

[0013] Step 5: Establish a deep learning model, bring the analysis results into the deep learning algorithm model, and bring each group of different simulation model data into it to improve the accuracy of deep learning;

[0014] Step 6: Manual control: Based on the deep learning model, determine the optimization path of the simulation model, add manual requirements, and perform intelligent control;

[0015] Step 7: Optimization path test: manually select the required optimization path, and bring the manually selected result back into the simulation model to determine the optimization effect;

[0016] Step 8: Output the optimization path, confirm the test results, substitute the inappropriate optimization path into the deep learning model for further optimization, bring the optimization results back into the simulation model, and output the optimization path.

[0017] As a preferred solution of the hybrid platform heat-energy integration simulation optimization method described in the present invention, in the step one, the thermal system architecture includes an engine, a battery, an air-conditioning system, vents and transmission parts.

[0018] As a preferred solution of the hybrid platform thermal-energy integrated simulation optimization method described in the present invention, wherein: in the step one, the thermal energy data is collected in units of time nodes, the thermal energy data of each position in the thermal system architecture at the same time is determined, and the data at different time nodes are grouped and collected.

[0019] As a preferred solution of the hybrid platform heat-energy integration simulation optimization method described in the present invention, in the step one, the detection equipment uses a temperature sensor to collect and upload the temperatures at different locations in the thermal system architecture in real time.

[0020] As a preferred solution of the hybrid platform thermal-energy integration simulation optimization method described in the present invention, in the step 2, each set of labeled data is backed up as reference data for subsequent simulation models and deep learning models to improve the optimization speed.

[0021] As a preferred solution of the hybrid platform thermal-energy integrated simulation optimization method described in the present invention, in the step three, in the correction of the simulation model data, the changed data is uncontrollable, the changed data caused by external environmental interference is eliminated, and the vehicle's own thermal energy data is retained.

[0022] As a preferred solution of the hybrid platform thermal-energy integration simulation optimization method described in the present invention, in the step four, the obvious differences in the change trends between each group of simulation models are determined, and the reasons for the differences are found to facilitate subsequent optimization processing.

[0023] As a preferred solution of the hybrid platform thermal-energy integration simulation optimization method described in the present invention, in the step five, historical test data is substituted into the deep learning model to expand the recognition range and realize the prediction and fine-tuning of the change trend of the simulation model.

[0024] As a preferred solution of the hybrid platform thermal-energy integrated simulation optimization method described in the present invention, in step six, the artificial demand is mainly based on the change time, energy consumption and hardware life, and is regulated by personal needs.

[0025] As a preferred solution of the hybrid platform thermal-energy integrated simulation optimization method described in the present invention, in the step eight, if the output optimization path does not meet the manual requirements, the optimization is re-introduced until the output optimization path meets the manual requirements.

[0026] Compared with the prior art: the present invention detects different working positions in the vehicle thermal system architecture, classifies each group of thermal energy data according to the vehicle position, and marks each group of data, establishes simulation models of the relationship between heat and energy of different power platforms, and corrects each group of simulation model data, analyzes the energy consumption of each group of models and the performance of the thermal management system, compares the difference data between each group of performance, brings the analysis results into the deep learning algorithm model, and respectively brings in each group of different simulation model data to improve the accuracy of deep learning, determine the optimization path of the simulation model, and add artificial requirements for intelligent regulation, manually select the required optimization path, and bring the manually selected results back into the simulation model to determine the optimization effect, determine the test results, substitute the inappropriate optimization path into the deep learning model for continued optimization, bring the optimization results back into the simulation model, output the optimization path, use multiple groups of simulation models for comparative analysis, improve data accuracy, and use the deep learning model to optimize the path, reduce the required time, improve the optimization efficiency, and finally determine the requirements manually to meet actual needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the present invention will be described in detail below in combination with the accompanying drawings and detailed embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0028] Figure 1 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0029] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0031] Secondly, the present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0032] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0033] The present invention provides a hybrid platform heat-energy integration simulation optimization method, which uses multiple groups of simulation models for comparative analysis to improve data accuracy, and uses deep learning models for path optimization to reduce the required time and improve optimization efficiency. Finally, the needs are determined manually to meet actual needs. Please refer to Figure 1 , including the following steps:

[0034] Step 1: Thermal data collection: determine the thermal system architecture, set up detection equipment at the working position of the vehicle, and use the detection equipment to collect multiple sets of thermal data at various positions of the vehicle;

[0035] Among them, in step one, the thermal system architecture includes the engine, battery, air-conditioning system, vents and transmission parts, which are mainly the power output and energy output ends of the car, realizing the inlet and outlet temperatures of each component, cooling cycle flow and pressure, wind temperature changes and wind speed on the wind side, and energy consumption monitoring of each energy-consuming component of the power unit.

[0036] In step 1, thermal energy data is collected in units of time nodes, the thermal energy data of each location in the thermal system architecture at the same time is determined, and the data at different time nodes are grouped and collected.

[0037] In step 1, the detection equipment uses a temperature sensor to collect and upload the temperature of different locations in the thermal system architecture in real time.

[0038] Step 2: data preprocessing: classify each set of thermal energy data collected according to the vehicle location and mark each set of data; in step 2, back up each set of marked data as reference data for subsequent simulation models and deep learning models to improve optimization speed.

[0039] Step three, data integration, establish a simulation model of the relationship between heat and energy of different power platforms based on each set of data, and correct each set of simulation model data; in step three, during the correction of the simulation model data, the changed data is uncontrollable, and the changed data caused by external environmental interference is eliminated, and the vehicle's own thermal energy data is retained.

[0040] The simulation model data includes the dynamic model and the energy consumption model mathematical model, determines the cooling system architecture of the hybrid system, and collects the performance data of each component in the cooling system architecture, including the engine cooling performance data, the generator performance data, the water pump, the pipeline data, etc. Establish a thermal management system simulation model of the hybrid system.

[0041] Step 4: Data comparison and analysis: analyze the energy consumption of each group of models and the performance of the thermal management system, and compare the difference data between each group of performance; in step 4, determine the obvious differences in the change trends between each group of simulation models, find the reasons for the differences, and facilitate subsequent optimization processing.

[0042] Step 5: Establish a deep learning model, bring the analysis results into the deep learning algorithm model, and bring in each group of different simulation model data to improve the accuracy of deep learning; In step 5, historical test data is substituted into the deep learning model to expand the recognition range and realize the prediction and fine-tuning of the change trend of the simulation model;

[0043] Among them, deep learning uses a gradient descent optimization algorithm to update the weights of the model to minimize the loss function.

[0044] Its basic form is:

[0045] Among them, Δz is the change in the loss function, and are the partial derivatives of the loss function with respect to the input (x) and (y), respectively.

[0046] Step six, manual control, based on the deep learning model, determine the optimization path of the simulation model, and add manual demand for intelligent control; in step six, manual demand is mainly based on change time, energy consumption and hardware life, supplemented by personal needs for control.

[0047] Step 7: Optimization path test: manually select the required optimization path, and bring the manually selected result back into the simulation model to determine the optimization effect;

[0048] Step eight, output the optimization path, confirm the test results, substitute the inappropriate optimization path into the deep learning model for further optimization, bring the optimization results back into the simulation model, and output the optimization path; in step eight, if the output optimization path does not meet the manual requirements, it is brought back into the optimization until the output optimizes the path that meets the manual requirements.

[0049] In specific use, the above-mentioned step process of step one to step eight is adopted to detect different working positions in the vehicle thermal system architecture, each group of thermal energy data is classified according to the vehicle position, and each group of data is marked, and a simulation model of the relationship between heat and energy of different power platforms is established, and each group of simulation model data is corrected, the energy consumption of each group of models and the performance of the thermal management system are analyzed, and the difference data between each group of performance is compared. The analysis results are brought into the deep learning algorithm model, and each group of different simulation model data is brought into respectively to improve the accuracy of deep learning, determine the optimization path of the simulation model, and add artificial requirements for intelligent regulation. The required optimization path is manually selected, and the manually selected results are brought back into the simulation model to determine the optimization effect, determine the test results, substitute the inappropriate optimization path into the deep learning model for further optimization, and bring the optimization results back into the simulation model to output the optimization path. Multiple groups of simulation models are used for comparative analysis to improve data accuracy, and the deep learning model is used for path optimization to reduce the time required and improve the optimization efficiency. Finally, the requirements are manually determined to meet actual needs.

[0050] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced by equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed in the present invention may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A hybrid platform heat-energy integration simulation optimization method, characterized in that: The process includes the following steps: Step 1: Thermal data collection: determine the thermal system architecture, set up detection equipment at the working position of the vehicle, and use the detection equipment to collect multiple sets of thermal data at various positions of the vehicle; Step 2: Data preprocessing: classify each set of thermal energy data collected according to the vehicle position and mark each set of data; Step 3: Data integration: establishing simulation models of the relationship between heat and energy of different power platforms based on each set of data, and correcting each set of simulation model data; Step 4: Data comparison and analysis: analyze the energy consumption of each model group and the performance of the thermal management system, and compare the difference data between each group of performance; Step 5: Establish a deep learning model, bring the analysis results into the deep learning algorithm model, and bring each group of different simulation model data into it to improve the accuracy of deep learning; Step 6: Manual control: Based on the deep learning model, determine the optimization path of the simulation model, add manual requirements, and perform intelligent control; Step 7: Optimization path test: manually select the required optimization path, and bring the manually selected result back into the simulation model to determine the optimization effect; Step 8: Output the optimization path, confirm the test results, substitute the inappropriate optimization path into the deep learning model for further optimization, bring the optimization results back into the simulation model, and output the optimization path.

2. A hybrid platform heat-energy integration simulation optimization method according to claim 1, characterized in that: In step 1, the thermal system architecture includes an engine, a battery, an air conditioning system, vents, and transmission components.

3. A hybrid platform heat-energy integration simulation optimization method according to claim 1, characterized in that: In the step 1, the thermal energy data is collected in units of time nodes, the thermal energy data of each position in the thermal system architecture at the same time is determined, and the data at different time nodes are grouped and collected.

4. A hybrid platform heat-energy integration simulation optimization method according to claim 1, characterized in that: In the step 1, the detection device uses a temperature sensor to collect and upload the temperatures at different locations in the thermal system architecture in real time.

5. The hybrid platform heat-energy integration simulation optimization method according to claim 1, characterized in that: In the step 2, each set of labeled data is backed up as reference data for subsequent simulation models and deep learning models to improve the optimization speed.

6. A hybrid platform heat-energy integration simulation optimization method according to claim 1, characterized in that: In the step three, in the simulation model data correction, the changed data is uncontrollable, and the changed data caused by external environmental interference is eliminated, and the thermal energy data of the vehicle itself is retained.

7. A hybrid platform heat-energy integration simulation optimization method according to claim 1, characterized in that: In the step 4, the obvious differences in the change trends between each group of simulation models are determined, and the causes of the differences are found to facilitate subsequent optimization processing.

8. The hybrid platform heat-energy integration simulation optimization method according to claim 1, characterized in that: In step five, historical test data is substituted into the deep learning model to expand the recognition range and realize the prediction and fine-tuning of the change trend of the simulation model.

9. The hybrid platform heat-energy integration simulation optimization method according to claim 1, characterized in that: In step six, the artificial demand is mainly based on the change time, energy consumption and hardware life, and is regulated by personal needs.

10. The hybrid platform heat-energy integration simulation optimization method according to claim 1, characterized in that: In the step eight, if the outputted optimization path does not meet the manual requirements, the optimization is re-entered until the outputted optimization path meets the manual requirements.

Images