Joint Sparse Principal Component Analysis Based Roust Sparse Fault Detection
Wenlan Jiang, Tao Zhang, Huangang Wang · 2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS) · 2020
In this paper, a novel variant of PCA, joint sparse principal component analysis(JSPCA), is adopted into robust sparse fault detection. By imposing l2,1norm jointly on the loss function and the regularization term of traditional sparse PCA, the JSPCA based fault detection method achieves sparse feature selection and robust fault detection simultaneously without high computation cost. The effectiveness of the proposed method is evaluated on the Tennessee Eastman process.