Research On Personalized Control Strategy Of Electric Booster Braking System For Intelligent Electric Vehicle

Electric booster braking systems will become the mainstream development direction of intelligent electric vehicle braking systems because they do not rely on vacuum sources,respond accurately and quickly,and have high safety.Basic assist and active braking are the core functions of the electric booster braking system.These functions are closely related to vehicle safety and driving experience.However,the control strategy of the vehicle braking system is the same now,and most of them focus on the system's pressure building capability,with little or no consideration of driver factors.In fact,the driving habits of different drivers are very different,and their use requirements of the vehicle's braking system are inconsistent.Therefore,in the development of the braking system,it is necessary to fully consider the driver's factors and integrate personalized driving habits.In the braking system,a personalized control strategy is formed,and a braking system that meets the needs of different drivers is designed to achieve safe and intelligent braking behavior of the vehicle.Therefore,using machine learning and data mining theory,the driver's personalized driving habits are explored.The driver's driving habits are combined with basic assist and active braking control strategies to form a personalized set of electric booster braking systems.The control strategy has a very positive effect on improving the intelligence of the braking system,improving vehicle safety and driver satisfaction.This article relies on the national key research and development plan(2018YFB0105103),Jilin Province Science and Technology Development Plan Project(20180201056G X),Jilin Province Education Department's "Thirteenth Five-Year Plan" Science and Technology Project(JJKH20180077KJ),Jilin Province's budgetary infrastructure Funded project(2019C036-6),etc.,to carry out research on personalized control strategies for electric booster braking systems of smart electric vehicles.First build a real-car driving data collection platform and collect driving data to complete the driving habits clustering and identification;then,complete the assisted characteristic analysis,system modeling and basic assisted algorithm design of the electric assisted braking system to form a personalized basic assisted Strategy;Next,establish a personalized safety distance model and vehicle dynamics inverse model to establish a personalized active braking strategy;Finally,build a hardware-in-the-loop test tench and a real vehicle test platform to personalize the control of the electric booster braking system.Verify the effectiveness of the strategy.The research contents of this article include the following four parts:(1)Analysis and identification of driver's personalized driving habitsA real vehicle driving data acquisition platform is built based on software and hardware such as the RT3002 / RT Range inertial navigation system,MicroAutoBox1401,and dSPACE ControlDesk,and a typical following braking condition is designed to conduct real road tests and collect driving data.Subsequently,the collected data was subjected to principal component analysis and feature extraction,and the driving habits were clustered by K-means clustering method.The particle swarm optimization algorithm was used to optimize the clustering method,and the optimized clustering results were used to characterize driving habit labels.Next,a support vector machine algorithm is used to design a driving behavior identification strategy,and a genetic algorithm is used to optimize the bandwidth parameter and penalty parameter of the support vector machine.Finally,the effectiveness of the driving habits identification strategy is verified by offline simulation.(2)Personalized basic assisting strategy of electric booster braking systemFirst,the booster characteristics of the electric booster braking system were analyzed,and the system was modeled based on MATLAB / Simulink software,and the accuracy of the model was simulated and verified.Subsequently,a control strategy and a target position calculation method for a permanent magnet synchronous motor based on a three-closed-loop control are designed,and a basic assisting strategy for an electric booster braking system is designed based on this.Next,by matching the individualized driving habits and assistance characteristics mentioned above,a personalized basic assistance control strategy is designed.Finally,a simulation model of personalized basic assisted control strategy is built in MATLAB / Simulink,and the accuracy of the personalized basic assisted control strategy is verified through simulation verification.(3)Personalized active braking strategy of electric booster braking systemFirstly,based on the kinematics relationship,the vehicle's braking process and minimum safety distance are analyzed.According to the personalized driving data collected and analyzed above,the main parameters in the active braking process are personalized and the personalized safety distance model is established.Analysis of personalized active braking needs.Subsequently,a vehicle dynamics inverse model based on BP neural network was established,an active boosting algorithm for the electric booster braking system based on four closed-loop control was designed,and an active braking strategy for the entire electric booster braking system was established.Finally,in the software environment of Simulink /CarSim,the personalized active braking strategy is modeled and simulated.(4)Verification of personalized control strategy for electric booster braking systemFirst,according to the verification requirements,design and build a hardware-in-the-loop test bench for electric power-assisted braking systems,and verify the personalized basic boost and active braking control strategy based on the test bench;then,modify the braking system of the real vehicle.Design and build a real-vehicle test platform for the electric power-assisted braking system,and conduct online identification of driving habits based on the real-vehicle test platform and verification of personalized basic assisted control strategies.Through hardware-in-the-loop experiments and real vehicle experiments,the individual control strategy of the electric power-assisted braking system for smart electric vehicles proposed in this paper is fully verified.