摘要
采用改进型BP神经网络与传统PID相结合,初始运行阶段采用传统PID控制,网络学习一段时间后切换到神经网络在线自整定PID控制,仿真结果表明,系统具有良好的动态性能和稳态精度.
The combination of improved neural network and general PID controller is used in this paper. General PID controller is used in the beginning several seconds, and then self - tuning of PID based on neural network controller is converted to after training for seconds. The simulation results indicate that this control method can improve the dynamical performance and enhance its static precision.
出处
《机械与电子》
2005年第12期3-6,共4页
Machinery & Electronics
基金
上海师范大学青年基金项目(DKL412)
上海高校科研基金项目(DKL30)
关键词
BP神经网络
PID
液压加载
轴承试验台
back propagation neural network
proportional integral derivative
hydraulic loading
bearing tester
