Hybrid platform heat-energy integrated simulation optimization method

Abstract

The application 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 step processes: step one, heat energy data acquisition, determining a heat system architecture, setting a detection device at a vehicle working position, and collecting multiple sets of heat energy data at each position of the vehicle by using the detection device; step two, data preprocessing, classifying each set of collected heat energy data according to the vehicle position, and marking each set of data; step three, data integration, establishing different simulation models of the relationship between heat and energy of the power platform according to each set of data, and correcting the data of each simulation model; comparing and analyzing multiple simulation models to improve data accuracy, using a deep learning model to optimize the path, reducing the required time, improving the optimization efficiency, and finally determining the demand by an artificial method to meet the actual needs.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hybrid electric vehicles, in particular to a hybrid power platform heat-energy integrated simulation optimization method. BACKGROUND

[0002] In a broad sense, a hybrid vehicle refers to a vehicle whose 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 jointly depending on the actual vehicle driving state. The vehicle's driving power is provided by a single drive system alone or jointly depending on the actual vehicle driving state. Due to the differences in various components, arrangement and control strategy, various classification forms are formed. The energy saving and low emission characteristics of hybrid vehicles have attracted great attention in the automotive industry and have become a focus of automotive research and development. Hybrid power devices can not only provide long continuous operation time and good power of engines, but also can provide the benefits of pollution-free and low-noise electric motors. Both "fight side by side", take the advantages of each other, the thermal efficiency of the vehicle can be improved by more than 10%, and the exhaust emission can be improved by more than 30%.

[0003] The hybrid electric vehicle uses an engine, a motor and a power battery as a power unit to provide energy for the operation of the vehicle, and the heat is managed through the air conditioning system and the cooling system. The optimization of the energy consumption control of the power unit is the core task of the whole vehicle operation energy consumption optimization of the hybrid electric vehicle, and how to balance the energy consumption and output of the power unit needs to be optimized. Therefore, the present application provides a hybrid power platform heat-energy integrated simulation optimization method. SUMMARY

[0004] This part aims to summarize some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part and the abstract and title of the specification of the present application to avoid obscuring the purpose of this part, the abstract and the title of the specification. Such simplifications or omissions cannot be used to limit the scope of the present application.

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

[0006] Therefore, the purpose of the present application is to provide a hybrid power platform heat-energy integrated simulation optimization method, which is not suitable for optimization path into deep learning model for further optimization, and the optimization result is brought back into the simulation model to output the optimization path. Multiple simulation models are used for comparative analysis to improve data accuracy, and a deep learning model is used for path optimization to reduce the required time and improve the optimization efficiency. Finally, the demand is determined by artificial means, which meets the actual needs.

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

[0008] A hybrid power platform heat-energy integrated simulation optimization method, comprising the following steps:

[0009] Step one, heat energy data collection, determine the heat system architecture, set up detection equipment at the vehicle working position, use the detection equipment to collect multiple sets of heat energy data at each position of the vehicle;

[0010] Step two, data preprocessing, classify each set of collected heat energy data according to the vehicle position, and label each set of data;

[0011] Step three, data integration, establish different simulation models of the relationship between heat and energy of the power platform according to each set of data, and correct each set of simulation model data;

[0012] Step four, data comparison and analysis, analyze the energy consumption and performance of the heat management system of each model, and compare the difference data between each performance;

[0013] Step five, establish a deep learning model, bring the analysis results into the deep learning algorithm model, and respectively bring each set of different simulation model data into the deep learning model to improve the accuracy of the deep learning;

[0014] Step six, artificial regulation, determine the optimization path of the simulation model on the basis of the deep learning model, and add artificial demand for intelligent regulation;

[0015] Step seven, optimization path test, manually select the required optimization path, and re-enter the artificial selection results into the simulation model to determine the optimization effect;

[0016] Step eight, output optimization path, determine the test results, and continue to optimize the inappropriate optimization path in the deep learning model, re-enter the optimization results into the simulation model, and output the optimization path.

[0017] As a preferred scheme of the hybrid power platform heat-energy integrated simulation optimization method, in the step one, the heat system architecture includes an engine, a battery, an air conditioning system, a ventilation port and a transmission part.

[0018] As a preferred scheme of the hybrid power platform heat-energy integrated simulation optimization method, in the step one, the heat energy data is collected in time nodes, the heat energy data of each position in the heat system architecture at the same time is determined, and the data of different time nodes is collected in groups.

[0019] As a preferred scheme of the hybrid power platform heat-energy integrated simulation optimization method, in the step one, the temperature sensor is used to detect the temperature of different positions in the heat system architecture and upload the real-time temperature.

[0020] As a preferred scheme of the hybrid power platform heat-energy integrated simulation optimization method, in the step two, each set of labeled data is backed up as reference data for the subsequent simulation model and deep learning model, so as to improve the optimization speed.

[0021] As a preferred scheme of the hybrid power platform heat-energy integrated simulation optimization method, in the step three, in the simulation model data correction, the change data is uncontrollable, and the change data caused by external environmental interference is removed, and the thermal energy data of the vehicle itself is retained.

[0022] As a preferred scheme of the hybrid power platform heat-energy integrated simulation optimization method, in the step four, the obvious difference points between each set of simulation models are determined, and the difference reasons are found, so as to facilitate subsequent optimization processing.

[0023] As a preferred scheme of the hybrid power platform heat-energy integrated simulation optimization method, in the step five, in the deep learning model, the historical test data is substituted, the recognition range is expanded, and the prediction and fine-tuning of the simulation model change trend are realized.

[0024] As a preferred scheme of the hybrid power platform heat-energy integrated simulation optimization method, in the step six, the artificial demand is mainly based on change time, energy consumption and hardware life, and is supplemented by personal demand for control.

[0025] As a preferred scheme of the hybrid power platform heat-energy integrated simulation optimization method, in the step eight, if the output optimization path does not meet the artificial demand, the optimization is re-input until the output optimization path meets the artificial demand.

[0026] Compared with the prior art: the present application detects different working positions in the vehicle thermal system architecture, each set of thermal energy data is classified according to the vehicle position, and each set of data is labeled, different simulation models of the relationship between the power platform and the energy are established, and each set of simulation model data is corrected, the performance of each set of model energy consumption and thermal management system is analyzed, the difference data between each set of performance is compared, the analysis result is brought into the deep learning algorithm model, and each set of different simulation model data is brought into the deep learning algorithm model, the accuracy of the deep learning is improved, the optimization path of the simulation model is determined, and the artificial demand is added, the intelligent regulation and control are carried out, the required optimization path is selected, and the result selected by the artificial is brought into the simulation model again, the optimization effect is determined, the test result is determined, the optimization path which is not suitable is substituted into the deep learning model for continuous optimization, the optimization result is brought into the simulation model again, the optimization path is output, a plurality of simulation models are compared and analyzed, the data accuracy is improved, the path optimization is carried out by using the deep learning model, the required time is reduced, the optimization efficiency is improved, and finally the demand is determined by the artificial, and the actual requirement is met. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical scheme of the embodiments of the present application, the present application will be described in detail below in combination with the drawings and detailed embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating laboriousness, wherein:

[0028] Figure 1 The structure of the present application is shown in the figure. DETAILED DESCRIPTION

[0029] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below in combination with the drawings.

[0030] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited by the specific embodiments disclosed below.

[0031] Secondly, the present application is described in detail in combination with the schematic diagram, in the detailed description of the embodiments of the present application, for the convenience of description, the cross-sectional view of the device structure will be partially enlarged without general proportion, and the schematic diagram is only an example, which should not limit the scope of protection of the present application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual manufacture.

[0032] In order to make the purpose, technical scheme and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0033] The present application provides a hybrid platform heat-energy integrated simulation optimization method, which uses multiple simulation models for comparative analysis to improve data accuracy, and uses a deep learning model for path optimization to reduce the required time and improve optimization efficiency. Ultimately, the demand is determined by artificial means, which meets the actual needs. Please refer to Figure 1 , including the following steps:

[0034] Step one, heat energy data collection, determine the heat system architecture, set up detection equipment at the vehicle working position, use the detection equipment to collect multiple sets of heat energy data at each position of the vehicle;

[0035] Among them, in step one, the heat system architecture includes engine, battery, air conditioning system, air vent and transmission parts, mainly for the power output and energy output end of the automobile, realizing the import and export temperature, cooling circulation flow, pressure, wind temperature change and wind speed of the air side, and the energy consumption monitoring of each energy consumption part of the power unit.

[0036] In step one, the heat energy data is collected in time nodes, and the heat energy data of each position in the heat system architecture at the same time is determined, and the data of different time nodes is collected in groups.

[0037] In step one, the detection equipment uses temperature sensors to collect and upload the temperature of different positions in the heat system architecture in real time.

[0038] Step two, data preprocessing, classify each group of heat energy data according to the vehicle position, and label each group of data; in step two, backup each group of labeled data as reference data for subsequent simulation model and deep learning model, to improve the optimization speed.

[0039] Step three, data integration, establish different simulation models of the relationship between heat and energy of the power platform according to each group of data, and correct each group of simulation model data; in step three, in the simulation model data correction, the change data has uncontrollability, the change data caused by external environmental interference is removed, and the heat energy data of the vehicle itself is retained.

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

[0041] Step four, data comparison analysis, analyze the energy consumption and performance of the thermal management system of each group of models, compare the difference data between each group of performance; in step four, determine the obvious difference points in the change trend between each group of simulation models, find out the difference reasons, and facilitate subsequent optimization processing.

[0042] Step five, establish a deep learning model, bring the analysis results into the deep learning algorithm model, and bring in the simulation model data of each group respectively, improve the accuracy of deep learning; in step five, in the deep learning model, substitute the historical test data to expand the recognition range and realize the prediction and fine-tuning of the change trend of the simulation model.

[0043] Among them, the deep learning adopts the gradient descent optimization algorithm, which is used to update the weight of the model to minimize the loss function.

[0044] Its basic form is:

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

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

[0047] Step seven, optimization path test, manually select the required optimization path, and re-enter the artificial selection results into the simulation model to determine the optimization effect.

[0048] Step eight, output optimization path, determine the test results, substitute the inappropriate optimization path into the deep learning model for continuous optimization, re-enter the optimization results into the simulation model, and output the optimization path; in step eight, if the output optimization path does not meet the artificial demand, re-enter the optimization until the output optimization path meets the artificial demand.

[0049] In specific use, the above steps one to step eight are used 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 labeled, different simulation models of the relationship between the power platform heat and energy are established, 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, 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 the deep learning algorithm model, the accuracy of the deep learning is improved, the optimization path of the simulation model is determined, artificial demand is added, intelligent regulation and control are carried out, the required optimization path is selected, the artificial selected result is brought into the simulation model again, the optimization effect is determined, the test result is determined, the optimization path which is not suitable is substituted into the deep learning model for continuous optimization, the optimization result is brought into the simulation model again, the optimization path is output, a plurality of simulation models are compared and analyzed, the data accuracy is improved, the path optimization is carried out by using the deep learning model, the required time is reduced, the optimization efficiency is improved, finally the demand is determined by artificial, and the actual requirement is met.

[0050] Although the present application has been described with reference to the embodiments above, various changes and modifications can be made without departing from the scope of the present application. In particular, the features of the disclosed embodiments can be used in any combination without structural conflict, and the combinations are not exhaustively described in the specification only for the purpose of brevity and resource saving. Therefore, the present application 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 thermal-energy integration simulation optimization method, characterized in that, The method comprises the following steps: Step one, heat energy data collection, determine the heat system architecture, set up detection equipment at the vehicle working position, collect multiple sets of heat energy data at each position of the vehicle using the detection equipment; Step two, data preprocessing, classify each set of collected heat energy data according to the vehicle position, and label each set of data; Step three, data integration, establish different simulation models of the relationship between the heat and energy of the power platform according to each set of data, and correct the data of each simulation model; Step four, data comparison and analysis, analyze the energy consumption and performance of the heat management system of each model, and compare the difference data between each performance; Step five, establish a deep learning model, bring the analysis results into the deep learning algorithm model, and bring each set of different simulation model data into it respectively to improve the accuracy of deep learning; Step six, artificial regulation, determine the optimization path of the simulation model on the basis of the deep learning model, and add artificial demand for intelligent regulation; Step seven, optimization path test, manually select the required optimization path, and re-enter the artificial selection results into the simulation model to determine the optimization effect; Step eight, output optimization path, determine the test results, and continue to optimize the inappropriate optimization path in the deep learning model, re-enter the optimization results into the simulation model, and output the optimization path.

2. The hybrid platform thermal-energy integrated simulation optimization method of claim 1, wherein, In step one, the heat system architecture includes an engine, a battery, an air conditioning system, a ventilation port, and a transmission component.

3. The hybrid platform thermal-energy integration simulation optimization method of claim 1, wherein, In step one, the heat energy data is collected in time nodes to determine the heat energy data of each position in the heat system architecture at the same time, and the data of different time nodes is collected in groups.

4. The hybrid platform thermal-energy integration simulation optimization method of claim 1, wherein, In step one, the detection equipment uses a temperature sensor to collect and upload the temperature of different positions in the heat system architecture in real time.

5. The hybrid platform thermal-energy integration simulation optimization method of claim 1, wherein, In step two, backup each set of labeled data as reference data for subsequent simulation models and deep learning models to improve optimization speed.

6. The hybrid platform thermal-energy integration simulation optimization method of claim 1, wherein, In step three, in the simulation model data correction, the change data is uncontrollable, and the change data caused by external environmental interference is removed, and the heat energy data of the vehicle itself is retained.

7. The hybrid platform thermal-energy integration simulation optimization method of claim 1, wherein, In step four, determine the obvious difference points between each simulation model, find the difference reasons, and facilitate subsequent optimization processing.

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

9. The hybrid platform thermal-energy integration simulation optimization method of claim 1, wherein, In step six, the artificial demand is mainly based on change time, energy consumption and hardware life, and is supplemented by individual demand for regulation.

10. The hybrid platform thermal-energy integration simulation optimization method of claim 1, wherein, In step eight, if the output optimization path does not meet the artificial demand, re-enter the optimization until the output optimization path meets the artificial demand.

Images