RBF-NN多模型切换的轧机液压活套控制方法研究  

Control method for hydraulic looper of rolling mill based on RBF-NN

作　　者：傅连东[1] 涂福泉[1] 陈奎生[1] 郑梁[1] 陈峰[1] 

机构地区：[1]武汉科技大学机械自动化学院,武汉430081

出　　处：《钢铁研究》2007年第4期31-33,共3页Research on Iron and Steel

摘　　要：本文对轧机液压活套系统的工作特性进行了分析。该系统为多变量非线性系统,在位置与张力变化较大时,使用传统的控制方法该系统的稳定性较差;而神经网络在控制领域的广泛应用表明,它用于多变量非线性系统较为适合。实验结果表明,当位置与张力变化较大时,采用RBF神经网络控制方式使系统仍然稳定。This paper analyzes the characteristics of hydraulic loop system of rolling mill. The system belongs to a multivariate and non-line system, therefore, it is unsuitable to use the traditional control for its tension control. Neural network control has been widely applied in the control field. It is found that the neural network control is more appropriate to the multivariate and non-line system. Experimental results show that RBF-NN control is suitable to make the system more stable even if a fast change of position and tension is being existed.

关 键 词：RBF神经网络 液压活套 非线性系统 

分 类 号：TG335[金属学及工艺—金属压力加工]