<![CDATA[The aim of this study is to estimate the vehicle dynamic parameters concerning with road safety (such as, road tire forces, longitudinal and lateral velocities, angular velocity, rolling radius of wheels, side slip, pitch and roll angle, and road friction coeffi cient which are diffi cult to be measured directly in a standard car) using neural network training on the basis of sequential extended Kalman fi lter (SEKF) and the recursive least squares (RLS). For such estimation, a fourteen degree-of-freedom (DOF) nonlinear full-vehicle dynamics model was developed to provide the simulation requirement. The simulation was performed and compared with CarSim (the interpreter for vehicle dynamics) to verify the model, which confi rms the expected results were all the state variables follow the CarSim response well. The simulation results show that the system performs reliably and fastly in estimating the parameters on different road surfaces during various vehicle manoeuvres.]]>
Copyrights © 2010
