Accurate vehicle state estimation using WOA-SVR algorithm: a novel approach

Accurate estimation of the state parameters of vehicles during driving has always been a focus of attention for researchers in the automotive industry. Traditional estimation methods have the problem of larger errors. For this issue, a motion state estimation algorithm based on whale optimization algorithm and support vector regression (WOA-SVR) that does not rely on accuracy of the vehicle model and vehicle parameters was proposed for estimating the yaw rate and side slip angle as well as longitudinal speed. Firstly, the dynamic characteristics of the vehicle were analyzed and a two-layer SVR estimation structure was constructed. Then, Carsim was used to collect data which was used to train SVR models on both sides of the estimation structure from various operating conditions. The WOA algorithm was used to optimize the penalty factor and kernel function parameter in the SVR algorithm to obtain the optimal algorithm parameters. Finally, the feasibility of the WOA-SVR algorithm was verified through Matlab/Simlink simulation and virtual experiments. The simulation results indicate that the root mean square error (RMSE) of the yaw rate and side slip angle as well as longitudinal speed improves 67.8 %, 63.5 %, 69.9 % respectively. The verification results indicate that the WOA-SVR algorithm has good estimation accuracy and robustness in vehicle state estimation.