543 情報の抽象化による知的制御を適用した自動車のアクティブブレーキ DYC

概要

論文の詳細を見る
Recently, Direct Yaw Moment Control (DYC) using active brake has been applied to some vehicles. Its control law is determined by the result of nonlinear simulation analysis. However, the selection of suitable inputs to DYC controller is difficult because of nonlinear characteristics of contact force at tire. The neural network (NN) can find a control law for nonlinear system. but understanding of its meaning is not easy because of its complex structure. In this paper, a rule extraction method from NN controller is presented. The NN controller is obtained from nonlinear mathematical simulation of lane change by means of genetic algorithm (GA). by adding forgetting genetic operator, the connections of NN are reduced and simplified. As a result. a simple control law of DYC is achieved. The control law can be implemented by various means because of its simplicity. The DYC control law using side slip angle and time derivative of side slip angle is achieved. This control law has good performance and uses the same output as the DYC controller achieved by a conventional method. As a result, the effectiveness of rule extraction from NN is presented.
2000-09-01