基于粗糙集的T-S模糊神经网络在回转窑烧结过程中的应用  

A T-S Fuzzy Neural Network Based on Rough Sets and Its Application to Rotary Kiln Sintering Process

作　　者：王介生[1] 战红仁[2] 王伟 

机构地区：[1]大连理工大学信息与控制研究中心 [2]沈阳化工学院机械系,沈阳110005

出　　处：《华东理工大学学报（自然科学版）》2006年第7期796-800,848,共6页Journal of East China University of Science and Technology

基　　金：国家自然科学基金项目(60474058;60534010)

摘　　要：基于粗糙集理论的知识约简方法和T-S模糊神经网络的非线性映射理论,针对回转窑烧结过程被控对象复杂、各参数之间相互耦合及难以建立精确数学模型的特点,提出一种RS-FNN智能控制策略。采用基于一种新的聚类有效性准则函数的模糊C均值聚类算法对连续属性进行离散化;然后利用粗糙集理论由历史数据样本提取约简规则集,对应的T-S模型具有反映数据特征的良好拓扑结构;最后T-S模型参数由梯度下降混合最小二乘法进行精调。该方法应用于铁矿氧化球团回转窑生产过程控制取得了良好效果,增强了系统容错及抗干扰的能力。Based on the idea of the knowledge reduction of the rough sets （RS） theory and the nonlinearity mapping of Takagi-Sugeno fuzzy neural network （FNN）, a kind of RS-FNN control approach is presented and applied in the rotary kiln sintering process due to its nonlinearities in the dynamics and the large dimensionality of the problem. First, fuzzy C-means （FCM） clustering method based on a new cluster validity index is used to obtain the optimal discrete values of the continuous attributes. Then, RS theory is adopted to obtain the reductive rules using industrial history datum and corresponding FNN model has better topology configuration. Finally, the structure parameters of T-S fuzzy model are fine-tuned by a hybrid algorithm integrating the gradient descent method with least-squares estimation. The proposed approach was applied to control rotary kiln iron ore oxidized pellets sintering process and good results were obtained.

关 键 词：粗糙集 T-S模型 聚类有效性 模糊C均值聚类 回转窑 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]