论文部分内容阅读
针对刚性机械臂系统的控制问题,提出基于极限学习机(ELM)的自适应神经控制算法.极限学习机随机选择单隐层前馈神经网络(SLFN)的隐层节点及其参数,仅调整其网络的输出权值,以极快的学习速度获得良好的推广性.采用李亚普诺夫综合法,使所提出的ELM控制器通过输出权值的自适应调整能够逼近系统的模型不确定性部分,从而保证整个闭环控制系统的稳定性.将该自适应神经控制器应用于2自由度平面机械臂控制中,并与现有的径向基函数(RBF)神经网络自适应控制算法进行比较.实验结果表明,在同等条件下,ELM控制器具有良好的跟踪控制性能,表明了所提出控制算法的有效性.
In order to solve the control problem of rigid manipulator system, an adaptive neural control algorithm based on Extreme Learning Machine (ELM) is proposed.Extreme learning machine randomly selects the hidden nodes and their parameters of single hidden layer feedforward neural network (SLFN) The output value of the network, with a very fast learning speed to obtain a good promotion of the use of Lyapunov synthesis method, so that the proposed ELM controller through the output weight of the adaptive adjustment can approximate the system model uncertainty part, So as to ensure the stability of the whole closed-loop control system.The adaptive neural controller is applied to 2-DOF planar manipulator control and compared with the existing radial basis function (RBF) neural network adaptive control algorithm.Experiment The results show that, under the same conditions, the ELM controller has good tracking control performance, indicating the effectiveness of the proposed control algorithm.