基于BP神经网络的机械臂模糊自适应PID控制

Fuzzy adaptive PID control based on BP neural network for robotic manipulator

机械臂属于强耦合多变量的典型非线性系统,常规的控制策略难以取得满意的控制效果。采用基于BP神经网络的模糊自适应PID控制策略,解决了原有PID控制的参数自适应能力弱、鲁棒性较差的问题。该方法采用BP神经网络动态调整PID控制器参数,使之能够随时满足控制精度的需要,改善系统的控制性能。仿真实验结果表明:所提的控制策策略实现简单,同时具有较高的控制精度。

For robotic manipulator with decoupling effect and strong nonlinearity, satisfied control pertormance can hardly be achieved by using traditional control methods. To deal with the control of the robotic manipulator, a kind of fuzzy adaptive PID controller based on BP neural network is presented, which solved the problem of the robustness of PID controller. The parametres of the controller are dynamically adjusted by the output of the BP neural network, so the control performance can be satisfied momentarily. The simulation results inlurstrate that the control strategy can be performed easily and has relatively high control precision.