On-line principal component analysis with application to process modeling

详细信息    查看全文

• 作者：Jian Tang^a ; ^{freeflytang@gmail.com}  ; [Author Vitae] ; Wen Yu^b  ; [Author Vitae] ; Tianyou Chai^a ; ^c  ; [Author Vitae] ; Lijie Zhao^a ; ^d  ; [Author Vitae]
• 关键词：Principal component analysis ; Recursive algorithm ; On-line modeling ; Process modeling
• 刊名：Neurocomputing
• 出版年：2012
• 出版时间：1 April, 2012
• 年：2012
• 卷：82
• 期：Complete
• 页码：167-178
• 全文大小：1480 K

文摘

Principal component analysis (PCA) has been widely applied in process monitoring and modeling. The time-varying property of industrial processes requires the adaptive ability of the PCA. This paper introduces a novel PCA algorithm, named on-line PCA (OLPCA). It updates the PCA model according to the process status. The approximate linear dependence (ALD) condition is used to check each new sample. A recursive algorithm is proposed to reconstruct the PCA model with selected samples. Three types of experiments, a synthetic data, a benchmark problem, and a ball mill load experimental data, are used to illustrate our modeling method. The results show that the proposed OLPCA is computationally faster, and the modeling accuracy is higher than conventional moving window PCA (MWPCA) and recursive PCA (RPCA) for time-varying process modeling.