四轮转向的神经网络直接逆控制

Direct Inverse Control of Four-wheel Steering System by means of Neural Network

采用二自由度摩托车模型研究四轮转向车辆的转向特性,建立四轮转向车辆线性二自由度动力学模型和方程.着重设计BP神经网络直接逆控制系统,通过离线辨识、在线学习控制被控系统,与其他控制方法对比表明,神经网络直接逆控制系统能够更加有效的控制后轮转角以便使车辆质心侧偏角为零,并提高车辆低速机动性和高速稳定性.

The motorcycle model which has two degrees of freedom（2-DOF） was adopted to study the characteristics of four-wheel steering（4WS） vehicle,and the linear 2-DOF dynamic model and equation of 4WS vehicle were constructed in this paper.A neural network for direct inverse controller was designed to control the steering system of 4WS through the off-line identification and online learning processes.In contrast to other control methods,this controller is more effective in controlling the steering angle of rear wheel to realize the slip angle minimization and to improve both the mobility at low speed and the handling stability at high speed.