论文部分内容阅读
采用传统的神经网络逆模策略控制具有强非线性的系统,因其计算量过大导致在线实时性能不佳,本文提出一种新型快速径向基神经网络在线逆模控制策略,并利用锥度准则对控制系统的稳定性进行了理论分析,对强非线性对象的控制仿真结果表明,在保证控制精度的前提下,该算法大大提高了控制器运算的速度,且对扰动、时延、非线性及对象参数的摄动有较强的适应能力,具有较好的控制品质,适合应用于复杂工业过程控制器的设计.
Adopting the traditional neural network inverse mode strategy to control the system with strong nonlinearity, the in-line real-time performance is not good because of the computational complexity. In this paper, a new online inverse mode control strategy of fast radial basis function neural network is proposed and the taper criterion The stability of the control system is analyzed theoretically. The simulation results of the control of the strong nonlinear objects show that the proposed algorithm can greatly improve the speed of the controller operation while ensuring the control accuracy. Moreover, the control of the disturbance, delay, nonlinearity And the perturbation of the object parameters have strong adaptability, good control quality and are suitable for the design of complex industrial process controllers.