Ensemble modified independent component analysis for enhanced non-Gaussian process monitoring

详细信息    查看全文

• 作者：Chudong Tong ; ^{tongchudong@nbu.edu.cn} ; Ting Lan ; Xuhua Shi
• 关键词：Modified independent component analysis ; Fault detection ; Ensemble learning
• 刊名：Control Engineering Practice
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：58
• 期：Complete
• 页码：34-41
• 全文大小：1865 K
• 卷排序：58

文摘

A novel MICA-based method is proposed for enhanced non-Gaussian process monitoring. Multiple MICA base monitoring results are combined into an ensemble decision. Robust performance is ensured regardless of the selection of non-quadratic functions. Case studies demonstrate the priority and the promise of the proposed EMICA model.