FastICA-SVM fault diagnosis for batch process

摘要：

An ensemble fault diagnosis approach based on fast independent component analysis and support vector machine (FastlCA-SVM) for non-Gaussian complex process is presented. Firstly fast independent component analysis is used as a feature extraction step, and then classifier is constructed by SVTVI for fault diagnosis. The experimental results of benchmark of the fed-batch penicillin fermentation process indicate that FastlCA-SVM method can diagnosis faults more efficient and has better performance than the SVTVI method.

关键词： fault diagnosis fast independent component analysis support vector machine FastlCA-SVM batch process

作者: QingYang Jingran Guo Xu Zhang

作者单位: School of Information Science and Engineering, Shenyang Ligong University, Shenyang, China College o School of Resource and Environmental Science, Wuhan University, Wuhan, China School of Information Science and Engineering, Shenyang Ligong University, Shenyang, China

会议类型: 国际会议

会议名称: 2011 Seventh International Conference on Natural Computation(第七届自然计算国际会议 ICNC 2011)

会议地点: 上海

会议语种:英文

页码: 1675-1679

在线出版日期: 2011-07-26（万方平台首次上网日期，不代表论文的发表时间）