Estimation of centroid sideslip angle and roll angle of multi-axle special vehicle based on neural network

Abstract

Aiming at the problems of high test cost, nonlinear dynamics and uncertainty in the direct measurement of the side-slip angle and roll angle of the center of mass by the on-board sensors of multi-axis heavy-duty special vehicles, in order to realize the observation of steering instability under high maneuvering conditions, Neural Network (NN) is used to estimate the side-slip angle and roll angle of the vehicle center of mass., and use the Trucksim model verified by real vehicle experiments to obtain the data set required by the neural network. The neural network estimates the sideslip angle and roll angle through easily measurable variables. Finally, the effectiveness and reliability of the algorithm are further verified by simulation experiments.