Multimode Anomaly Detection Under the Multiscale Framework

摘要：

　　Multiscale characteristic of fault signals determines the necessity of multiscale analysis in multimode anomaly detection.Firstly,mode identification is implemented.Then,multiscale MSPCA detection modeling and multiscale time-varying rolling balls anomaly detection model is,respectively,established to each steady state and transition mode.Simulation result shows that the multimode monitoring method under multiscale framework can significantly reduce the missing detection rate of critical faults,which can effectively avoid major accidents.

关键词： Multimode Transition mode Multiscale Anomaly detection

作者: Funa Zhou Yu Zhang Xiaoliang Feng Chenglin Wen Juan Wang

作者单位: Institute of Advanced Control and Intelligent Information Processing,Henan University,Kaifeng,China Xiaoliang Feng College of Information Science and Technology,Henan University of Technology,Zhengzh Chenglin Wen Institute of System Modeling and Control,Hangzhou Dianzi University,Hangzhou,China

会议类型: 国际会议

会议名称: The 2015 Chinese Intelligent Automation Conference(2015中国智能自动化会议)

会议地点: 福州

会议语种:英文

页码: 483-492

在线出版日期: 2015-05-08（万方平台首次上网日期，不代表论文的发表时间）