上海交通大学学报

上海交通大学学报（自然版） ›› 2012, Vol. 46 ›› Issue (12): 1907-1913.

• 自动化技术、计算机技术 • 上一篇    下一篇

基于T-S模型的高炉煤气系统模糊建模

盛春阳，赵珺，王伟，刘颖   

  1. （大连理工大学 控制科学与工程学院，大连 116023）
  • 收稿日期:2012-05-28 出版日期:2012-12-29 发布日期:2012-12-29
  • 基金资助:

    国家自然科学基金资助项目（61034003;61104157）

     

A Fuzzy Modeling Method Based on T-S Model　for Blast Furnace Gas System

 SHENG  Chun-Yang, ZHAO  Jun, WANG  Wei, LIU  Ying   

  1. (College of Control Science and Engineering, Dalian University of Technology, Dalian 116023, China)
  • Received:2012-05-28 Online:2012-12-29 Published:2012-12-29

摘要： 针对钢铁企业高炉煤气系统这一复杂非线性系统的建模问题，提出一种基于数据的高炉煤气系统模糊建模方法.基于TS模糊模型的高炉煤气系统辨识模型，考虑系统中煤气调节用户的人为干扰特性，采用条件模糊聚类的方法来对输入/输出空间进行划分.引入模糊思想，使模型能够更好地适应工业噪声的干扰.利用贝叶斯线性回归方法求解模糊模型的后件参数，避免了后件参数求解过程中常出现的异常解问题.通过对实际企业高炉煤气系统的实验验证，结果表明了所提出的高炉煤气系统模糊建模方法的有效性，可进一步用于实施高炉煤气系统的优化与调度工作.  

关键词: 高炉煤气系统, 非线性, 系统建模, 模糊聚类

Abstract: Aiming at the modeling problem for blast furnace gas system in steel industry, a class of complex non-linear system, a data-based fuzzy modeling method was proposed. Firstly, the proposed method establishes the identification model based on T-S fuzzy model. Considering the manual interference from the adjustable gas users, a conditional fuzzy clustering is adopted to partition the input and output space. With the introduction of fuzzy concept, the proposed model is adaptive for industrial noises. Then, a Bayesian linear regression is proposed to determine the parameters of the consequent part in this study, which can effectively avoid the ill-conditioned phenomenon. A series of simulation verification by using the industrial data of a certain blast furnace gas system demonstrate that the proposed method exhibits well performance for identifying the blast furnace gas system, and can also be used to optimize, control and schedule the blast furnace gas system.

Key words: blast furnace gas, nonlinear, system modeling, fuzzy clustering

中图分类号: