论文部分内容阅读
针对如今复杂被控对象大滞后、非线性和时变性的特点,研究把人工免疫算法和RBF神经网络相结合对PID控制器进行参数寻优,应用到矿井输送机上。利用人工免疫算法,无需事先确定隐层结点个数,设计了一种动态的RBF神经网络,并且分析基于免疫算法的RBF神经网络的PID控制器的算法结构。通过仿真实验得知:研究设计的免疫RBF神经网络的PID控制器在抗干扰性、跟随性和鲁棒性方面都表现出了良好的控制效果,非常适合用于控制模型不确定的情况。
Considering the characteristics of complex controlled objects such as large lag, nonlinearity and time-varying nowadays, combining the artificial immune algorithm and the RBF neural network, the parameters of the PID controller are optimized and applied to the mine conveyor. Using artificial immune algorithm, a dynamic RBF neural network is designed without prior determining the number of hidden layer nodes, and the algorithm structure of PID controller based on immune algorithm RBF neural network is analyzed. The simulation results show that the PID controller based on the immune RBF neural network has good controllability in terms of anti-interference, followability and robustness, and is very suitable for the control of uncertain models.