动态定量称重系统神经网络预测PID控制器研究

Neural Network Predictive PID Controller for Dynamic Quantitative Weighing System

采用神经网络预测与PID控制理论相结合,为动态定量称重系统设计了一种神经网络预测PID控制器。该控制器算法简单,通过自学习、记忆功能在线调整PID控制参数KP、KI、KD。建立了动态定量称重系统的仿真模型,将神经网络预测的PID控制与常规PID进行对比分析,神经网络预测PID控制器具有很好的控制效果。

A neural network predictive PID controller is designed by means of the neural network theory combined with the PID control theory.The designed algorithm is easy.The self-learning and memory fuction can be realized by adjusting the control parameter Kp,Kl,KD of PID online.The simulation model with neural network predictive PID controller is built.The results show the neural network predictive PID controller has more excellent control performance than PID controller.