神经网络在细纱机中的应用  

The Application of Neural Network Control on Spinning Frame

作　　者：许敏[1] 黄斌[1] 

机构地区：[1]桂林电子科技大学机电工程学院,桂林541004

出　　处：《微计算机信息》2008年第21期212-214,共3页Control & Automation

基　　金：广西区研究生教育创新计划项目"基于模糊理论和神经网络的水轮机调节系统的研究"(2006105950802M09)

摘　　要：介绍了一种基于PLC和DSP的细纱机控制系统。该系统针对细纱机控制系统的非线性与传统PID控制方法的不足,提出了一种改进型基于RBF神经网络在线辨识的单神经元PID自适应控制方法。该方法构造了一个RBF网络对系统进行在线辨识,建立起在线参考模型,由单神经元控制器完成控制器参数的学习,从而实现控制器参数的在线调整。仿真试验结果表明,该控制器控制精度高,动态性能好,其控制效果优于传统的PID控制器。A spinning frame control system based on PLC and DSP is introduced in this article. This paper presents a single neural self-adaptive control method based on RBF network on-line recognition in virtue of the disadvantage of conventional PID control and nonlinear effects of the system. A RBF network is built to identify the system on-line, and then constructs the on-line reference model ,implements self-learning of controller parameters by single neuron controller. The simulation result showes that control effect of the controller is better than that of the conventional PID control arithmetic . It can achieve on-line control with high control accuracy and good dynamic characteristics.

关 键 词：细纱机 RBF神经网络 在线辨识 单神经元 

分 类 号：TP273.2[自动化与计算机技术—检测技术与自动化装置]