A New Fuzzy Clustering-Ranking Algorithm and Its Application in Process Alarm Management  

作　　者：ZHU Qunxiong（朱群雄） GENG Zhiqiang（耿志强） 

机构地区：[1]School of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

出　　处：《Chinese Journal of Chemical Engineering》2005年第4期477-483,共7页中国化学工程学报（英文版）

基　　金：Partially supported by the National Natural Science Foundation of China (No. 29976003), the Key Research Project ofScience and Technology from Ministry of Education in China (No. 01024), and Sinopec Science & Technology DevelopmentProject (No. E03007)

摘　　要：Overmany alarms of modern chemical process give the operators many difficulties to decision and diag- nosis. In order to ensure safe production and process operating, management and optimization of alarm information are challenge work that must be confronted. A new process alarm management method based on fuzzy clustering- ranking algorithm is proposed. The fuzzy clustering algorithm is used to cluster rationally the process variables, and difference driving decision algorithm ranks different clusters and process parameters in every cluster. The alarm signal of higher rank is handled preferentially to manage effectively alarms and avoid blind operation. The validity of proposed algorithm and solution is verified by the practical application of ethylene cracking furnace system. It is an effective and dependable alarm management method to improve operating safety in industrial process.Overmany alarms of modern chemical process give the operators many difficulties to decision and diagnosis. In order to ensure safe production and process operating, management and optimization of alarm information are challenge work that must be confronted. A new process alarm management method based on fuzzy clusteringranking algorithm is proposed. The fuzzy clustering algorithm is used to cluster rationally the process variables, and difference driving decision algorithm ranks different clusters and process parameters in every cluster. The alarm signal of higher rank is handled preferentially to manage effectively alarms and avoid blind operation. The validity of proposed algorithm and solution is verified by the practical application of ethylene cracking furnace system. It is an effective and dependable alarm management method to improve operating safety in industrial process.

关 键 词：process alarm management fuzzy clustering-ranking algorithm ethylene cracking furnace 

分 类 号：TQ063[化学工程] TQ086.3