双电机驱动伺服系统的控制与仿真研究

摘要

研究双电机驱动伺服系统优化控制问题,双电机驱动伺服系统中存在齿隙非线性,从而降低系统跟踪响应速度、稳态精度及抗干扰能力,为了削弱齿隙非线性对系统产生的不利影响,提出了一种新的控制方法,采用遗传算法和RBF神经网络相结合.针对RBF神经网络控制器参数难以确定的问题,对RBF神经网络的隐层中心值和宽度进行了优化,用递推最小二乘法训练隐层和输出层之间的权值.最后在双电机驱动伺服系统中进行了仿真,结果表明系统跟踪响应速度快,稳态精度高,抗干扰能力强,具有较高的鲁棒性,证明所提出的控制策略是有效的.%Dual-motor driving servo system has backlash nonlinear, which reduces system response speed, steady accuracy and anti-jamming performance. In order to diminish the adverse effects of backlash, a new control method combining genetic algorithm with RBF neural network was proposed. Aiming at the problem that neural network parameters are difficult to be determined, this method was used to optimize the centers and widths of RBF hidden layer, and recursion least square method was used to train the weights between hidden layer and output layer. Finally, the simulation experiment in dual-motor driving servo system shows that the system has quick response speed, high steady accuracy, strong anti-jamming performance and better robustness, which validates the efficacy of the proposed control strategy.