动态核聚类算法在乙烯生产中的优化模式识别  

Dynamic Kernel Clustering Algorithm and Its Application in Optimal Pattern Recognition of Ethylene Production

作　　者：耿志强[1] 朱群雄[1] 

机构地区：[1]北京化工大学信息科学与技术学院,北京100029

出　　处：《化工自动化及仪表》2005年第2期5-8,共4页Control and Instruments in Chemical Industry

基　　金：国家自然科学基金项目(29976003);教育部科学技术研究重点项目(01024);中石化科学技术研究开发项目(E03007)

摘　　要：针对传统的C means聚类在小样本和类别交叉空间存在样本错分问题,研究分析一种基于核函数的动态聚类方法,以广义欧式距离作为高维特征空间的相似性度量,提高聚类的准确性,仿真实例验证了算法的有效性。提出利用动态核聚类方法来识别乙烯裂解炉生产过程最优操作模式,动态调整乙烯裂解炉的操作条件以及选择油品和预测收率,实际的工业应用说明动态核聚类方法的可行性。For the false classification of feature samples by traditional clustering algorithms, such as C-means and Fuzzy C-means algorithms, a new dynamic kernel clustering algorithm is studied. It is difficult for traditional algorithms to classify the small samples and the crossing space. This algorithm uses a kernel function to project the original sample space to a high dimensional feature space and the generalized Euclidean distance is defined as similarity measurement of samples space that can be clustered or classified easily. The results of simulation experiments show the dynamic kernel clustering algorithm is feasible and effective.

关 键 词：核聚类/分类 模式识别 乙烯裂解炉 操作优化 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]