期刊
ISIJ INTERNATIONAL
卷 54, 期 11, 页码 2608-2617出版社
IRON STEEL INST JAPAN KEIDANREN KAIKAN
DOI: 10.2355/isijinternational.54.2608
关键词
flatness control; T-S cloud inference neural network; cloud model; stability; cold rolling mill; Genetic Algorithm
资金
- National Natural Science Foundation of China [61074099]
- Cultivation Program Project for Leading Talent of Innovation Team in Colleges and Universities of Hebei Province [LJRC013]
The accuracy of traditional flatness control methods are limited and it is difficult to establish a precise mathematical model of the rolling mill. In addition, the flatness control system is complex and multivariate. General model approaches can not satisfy the high precision, demand of rolling process. In this paper, T-S cloud inference neural network and its stability are proposed. It is constructed by cloud model and T-S fuzzy neural network. The stability of T-S cloud inference neural network is analyzed by Lyapunov method in details. Based on the new network, flatness recognition model and flatness predictive model are established. And they are applied for 900HC reversible cold rolling mill. The flatness control system is designed and a simple controller is developed. Initial parameters of the controller are firstly determined through offline training based on measured data, and then they are optimized online automatically. Genetic Algorithm (GA) is used as the optimizing method which is compared with particle swarm optimization (PSO). The simulation results demonstrate that the flatness control system is effective and has a better precision and robustness.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据