Application of Internal Model Control Based on Neural Network for CSTR System

摘要：

Nonlinear and time-delay axe phenomenon during many industrial processes, especially in petroleum, chemical industry and metallurgy. Nonlinear and time-delay are phenomenon during CSTR（Continuous Stirred-Tank Reactor)system, in this paper at first, it discusses on the basic structure and theories of IMC and proposes the idea that IMC based on neural network. After analyze CSTR system, it constructs IMC controller based upon neural network. Both the CSTR internal model and the controller were constructed via BP neural network. LMBP algorithm was used to train the weights of the neural network online. In order to confirm this article the design proposal, in MPCE-1000 multifunction process control experiment platform, carries on the simulation analysis to the CSTR system. The simulation of CSTR system demonstrates the algorithms good performance and better than PID algorithm. Have good dynamic and static properties, solving the impact of nonlinear and time-delay.

关键词： Internal model control(IMC) Neural network(NN) Continuous stirred-tank reactor(CSTR)

作者: Lu Shuping Ma Liang Li Changpeng

作者单位: College of Automation, Harbin Engineering University, Harbin 150001, China

会议类型: 国际会议

会议名称: ISSNP2008、CSEPC、ISOFIC2008(第二届21世纪和谐核电系统国际会议、第四届电厂控制中认知系统工程方法国际会议暨第三届未来核电厂仪表与控制国际会议)

会议地点: 哈尔滨

会议语种:英文

页码: 82-86

在线出版日期: 2008-09-08（万方平台首次上网日期，不代表论文的发表时间）