1.National Engineering Research Center for Equipment & Tech of Cold Strip Rolling, Qinhuangdao, Hebei 066004, China;
2.Key Lab of Industrial Computer Control Engineering of Hebei Province,Yanshan University, Qinhuangdao, Hebei 066004, China
Abstract：Aimed at the tension variation during transforming process of "1+4" aluminum hot tandem rolling unit in one factory of Henan, the factors affecting tension variation are analyzed, the tension forming process was simulated and the control system diagrams was constructed. Due to normal PID controller could not meet the requirement of the system, so using immune clone algorithm to optimize PID controller parameters, the mixed control of radical basis function neural network coupled with PID was proposed to solve the problem of online parameters control. By simulation, it could be found that the use of immune clone algorithm and radical basis function significantly reduced surplus adjustment, transition time, and tension coupling degree among stands was also reduced.
赵新秋,孟庆刚,杨鹤,杨景明. 基于免疫克隆和径向基函数神经网络的铝热连轧张力控制研究[J]. 计量学报, 2015, 36(2): 149-153.
ZHAO Xin-qiu,MENG Qing-gang,YANG He,YANG Jing-ming. Tension Control Study of Aluminum Hot Tandem Rolling Based on Immune Clone Algorithm and Radical Basis Function Neural Network. Acta Metrologica Sinica, 2015, 36(2): 149-153.
［2］Janabi-Sharifi F. Neuro-Fuzzy Tension Controller for Tandem Rolling［C］//Proceedings of the 2002 IEEE International Symposium on Intelligent Control,Vancouver,Canada,2002,309-314.
［3］Hoshio I,Okamura Y,Kimura H.Observe-based Multivariable Tension Control of Aluminum Hot Rolling Mills［C］ // Proceedings of the 35th Conference on Decision and Control,Kobe,Japan,1996,1217-1222 .
［5］Pittner J,Simaan A M.Optimal Control of Continuous Tandem Cold Metal Rolling［C］ // 2008 American Control Conference,Seattle, Washington,USA,2008,1379-1390.
2015, Vol. 36 
