基于对角递归神经网络的控制系统  

Research and development of control system based on diagonal recurrent neural network

作　　者：宋怡霖 陈新楚[1,2] 郑松[1,2] 

机构地区：[1]福州大学电气工程与自动化学院,福建福州350116 [2]福建省工业控制信息安全技术企业重点实验室,福建福州350008

出　　处：《福州大学学报（自然科学版）》2016年第6期774-778,共5页Journal of Fuzhou University(Natural Science Edition)

基　　金：福建省科技厅高校产学合作科技重大资助项目(2013H6009)

摘　　要：针对角递归神经网络具有结构简单、收敛速度快,可广泛用于非线性系统的辨识与控制的特点.基于工业自动化通用技术平台(IAP),采用图形化控制策略组态技术开发了一套基于对角递归神经网络的控制系统,该系统具有基于参考模型跟踪的控制结构,可快速自适应地调整控制器参数.仿真实验结果表明,基于对角递归神经网络的控制系统控制精度高、稳定性好,可成为处理复杂工业过程,尤其是解决不确定和非线性领域问题的有效工具.The diagonal recurrent neural network has the advantage of simple structure and fast convergence speed. It can be widely used in the identification and control of nonlinear systems. A set of control systems based on diagonal recurrent neural network is developed using graphical control strategy configuration technology based on IAP in this paper. The system has a control structure based on the reference model and can adjust the controller parameters quickly. Simulation experiment results shows that the control system based on diagonal recurrent neural network has high control accuracy and good stability,which can be an effective tool to deal with complex industrial processes,especially to solve the problems in the field of uncertainty and nonlinearity.

关 键 词：对角递归神经网络 控制策略 组态 控制器 辨识器 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]