DNN Based on MRAC of Stepping Heating Furnace

摘要：

This paper mainly introduces dynamic neural network based on random search weight regulation learning algorithm apply control algorithm in the stepping heating furnace pump-motor drive system. Through control the output flow of the variable pump, achieve the speed control of the hydraulic motor, enable the controlled motor speed fulfill the requirement of the production. By means of simulation and experiment, prove that controller with this kind of algorithm can realizes system on-line adaptive control, can automatic regulate control parameter obtain excellent synthesis control quality even when the environment variable happen great sudden change.

关键词： dynamic neural network(DNN) controlling learning algorithm model reference adaptive control(MRAC)

作者: Zeng Liangcai Chen Yangguo Shen Juan Huang Wei Zhang Qiang

作者单位: College of Machinery & Automation, Wuhan University of Science and Technology, JiansheiLu. Wuhan, Hubei, 430081, China

会议类型: 国际会议

会议名称: The Fifth International Symposium on Fluid Power Transmission and Control(ISFP2007)（2007年国际流体动力传输与控制学术会议）

会议地点: 北戴河

会议语种:英文

页码: 663-666

在线出版日期: 2007-06-06（万方平台首次上网日期，不代表论文的发表时间）