The braking system is a vital part of vehicle safety. In order to improve the vehicle stability during emergency braking, a parameter-estimation-based emergency braking control approach is proposed to enhance vehicle stability. The state factors influencing the braking stability of the vehicle are obtained from the dynamic analysis of the constructed vehicle model, and an emergency braking control method that incorporates these state characteristics is developed. The radial basis function neural network and the extended Kalman filter method are utilised in the emergency brake control strategy to estimate the state parameters that are difficult to get directly. The simulation results indicate that the performance of parameter estimation-based emergency braking control surpasses that of conventional emergency braking control by 73.45%, with the relative error between parameter estimation and the actual state value maintained within 1%.
BiFSunHZhangL, et al.Study on 4WID vehicle active safety control strategy. J Tianjin Univ2022; 55: 158–165.
2.
DingFHanXJiangC, et al.Fuzzy dynamic output feedback force security control for hysteretic leaf spring hydro-suspension with servo valve opening predictive management under deception attack. IEEE Trans Fuzzy Syst2022; 30: 3736–3747.
3.
LiuZChengSWangS. Control strategy of automatic emergency braking system under complex road conditions. China Sci Technol Papers2022; 17: 221–227.
4.
GuoHCaoDChenH, et al.Vehicle dynamic state estimation:state of the art schemes and perspectives. IEEE/CAA J Autom Sinica2018; 5: 418–431.
5.
WielitzkaMDagenMOrtmaierT. Joint unscented Kalman filter for state and parameter estimation in vehicle dynamics. In 2015 IEEE Conference on Control Applications (CCA), 21–23 September 2015, pp. 1945–1950.
6.
SinghKBAratMATaheriS. Literature review and fundamental approaches for vehicle and tire state estimation. Veh Syst Dyn2019; 57: 1643–1665.
7.
DaweiCWenP. Vehicle state and parameter estimation based on improved extend Kalman filter. Journal of Measurements in Engineering2023; 11: 496–508.
8.
ZhangZZhangSHuangC, et al.State estimation of distributed drive electric vehicles based on adaptive extended Kalman filter. J Mech Eng2019; 55: 156–165.
9.
RodríguezAJSanjurjoEPastorinoR, et al.State, parameter and input observers based on multibody models and Kalman filters for vehicle dynamics. Mech Syst Signal Process2021; 155: 107544.
10.
ReinaGPaianoMBlanco-ClaracoJ-L. Vehicle parameter estimation using a model-based estimator. Mech Syst Signal Process2017; 87: 227–241.
11.
BoadaBLBoadaMJLVargas-MelendezL, et al.A robust observer based on H∞ filtering with parameter uncertainties combined with neural networks for estimation of vehicle roll angle. Mech Syst Signal Process2018; 99: 611–623.
12.
XingYLvC. Dynamic state estimation for the advanced brake system of electric vehicles by using deep recurrent neural networks. IEEE Trans Ind Electron2020; 67: 9536–9547.
13.
ZhaoY-QLiH-QLinF, et al.Estimation of road friction coefficient in different road conditions based on vehicle braking dynamics. Chin J Mech Eng2017; 30: 982–990.
14.
XiongLXiaXLuY, et al.IMU-based automated vehicle slip angle and attitude estimation aided by vehicle dynamics. Sensors2019; 19: 1930.
15.
LiWLiHXuK, et al.Estimation of vehicle dynamic parameters based on the two-stage estimation method. Sensors2021; 21: 3711.
16.
JiangKVictorinoACChararaA. Adaptive estimation of vehicle dynamics through RLS and Kalman filter approaches. In 2015 IEEE 18th International Conference on Intelligent Transportation Systems, 15–18 September 2015, pp. 1741–1746.
17.
LaiFHuangCJiangCZhangY. Simulation analysis of automatic emergency braking system under constant steer conditions. SAE Int J Vehicle Dyn, Stab NVH2022; 6(4): 461–476. doi:10.4271/10-06-04-0030.
18.
DuFGuanZGaoB, et al.Vehicle stability control by synergistic action of active steering and differential braking. Autom Safety Energy Conser J2018; 9: 65–73.
19.
GuoqingXWangYYangY, et al.Research on adhesion state recognition and stability control strategy of electric wheel on complex dynamic pavement. J Mech Eng2019; 55: 113–122.
20.
BadieSA. Genetic fuzzy self-tuning PID controllers for antilock braking systems. Eng Appl Artif Intell2010; 23: 1041–1052.
21.
AbreuRBothaTHamersmaH. Model-free intelligent control for antilock braking systems on rough roads. SAE Int J Veh Dyn Stab NVH2023; 7(3): 269–285. doi:10.4271/10-07-03-0017.
22.
AksjonovAKyrkiV. A safety-critical decision-making and control framework combining machine-learning-based and rule-based algorithms. SAE Int J Vehicle Dyn Stab NVH2023; 7(3): 287–299. doi:10.4271/10-07-03-0018.
23.
ZhaoQZhengHKakuCChengF, et al.Safety spacing control of truck platoon based on emergency braking under different road conditions. SAE Int J Vehicle Dyn Stab NVH2023; 7(1): 69–81. doi:10.4271/10-07-01-0005.
24.
LiuYPeiXGuoX. Redundancy control of anti-lock braking system based on electro-hydraulic braking system. SAE Int J Vehicle Dyn Stab NVH2023; 7(1): 53–67. doi:10.4271/10-07-01-0004.
25.
HanKChoiSBLeeJ, et al.Accurate brake torque estimation with adaptive uncertainty compensation using a brake force distribution characteristic. IEEE Trans Veh Technol2017; 66: 10830–10840.
26.
LiH. Research and simulation on control strategy of automatic emergency braking system based on driving characteristics and road adhesion coefficient. Master. Xian: Chang’an University, 2021.
27.
LiS. Research on steering stability control based on limit speed. Master. Beijing: Beijing Institute of Technology, 2016.
28.
GuoHChenHZhaoHYangS. Research progress and prospect of vehicle driving state parameter estimation. Control Theory Appl2013; 30(6): 661–672.
29.
FerrariSBellocchioFPiuriV, et al.A hierarchical RBF online learning algorithm for real-time 3-D scanner. IEEE Trans Neural Network2009; 21: 275–285.
30.
KokshenevIPaduaBA. An efficient multi-objective learning algorithm for RBF neural network. Neurocomputing2010; 73: 2799–2808.
31.
LiuYZhaoJXiaoY. C-RBFNN: a user retweet behavior prediction method for hotspot topics based on improved RBF neural network. Neurocomputing2018; 275: 733–746.
32.
LiLLuYWangR, et al.A three-dimensional dynamics control framework of vehicle lateral stability and rollover prevention via active braking with MPC. IEEE Trans Ind Electron2016; 64: 3389–3401.
33.
LinCWangGCaoV, et al.State estimation of distributed drive electric vehicles based on LO-EKF algorithm. Automot Eng2014; 36: 1316–1320.
34.
HeYXuQYangS, et al.Probabilistic density prediction method of power load based on quantile regression of RBF neural network. Chinese J Elec Eng2013; 33: 93–98.
35.
ZhangSPengZDuJ, et al.RBF neural network and NSGA-II hybrid algorithm for 3D electric field simulation and internal shield structure optimization of ±1 100 kV wall casing. High Voltage Technology2014; 40: 1847–1857.
36.
KratschSWahlströmM. Preprocessing of min ones problems: a Dichotomy. In International Colloquium on Automata, Languages, and Programming. Heidelberg, Germany, 2010, pp. 653–665.
37.
ZhaYLiuXMaF, et al.Estimation of pavement adhesion coefficient based on EKF and RBF. J Fujian Univ Tech2022; 20: 1–6+34.
38.
YunFZhengXLiuX, et al.Research on electronic hydraulic braking system for intelligent vehicles. Autom Tech2021; (6): 25–32. doi:10.19620/j.cnki.1000-3703.20210085.
39.
LiSYuBFengX. Research on braking energy recovery strategy of electric vehicle based on ECE regulation and I curve. Sci Prog2020; 103: 0036850419877762.
40.
NantaisNMinakerB. Active four wheel brake proportioning for improved performance and safety. SAE Technical Paper2008. doi:10.4271/2008-01-1224.
41.
LiuXWangF. Interpretation of the revised content of GB7258-2017 Motor Vehicle Operation Safety Technical Conditions [J]. Autom Prac Tech2018; (15): 275–278. doi:10.16638/j.cnki.1671-7988.2018.15.102.
