Application of fault monitoring and diagnosis in process industry based on fourth order moment and singular value decomposition. (1st December 2019)

• Record Type: Journal Article
• Authors: Chang, Peng; Kang, Olivia; Chunhao, Ding; Lu, Ruiwei
• Is Part Of: Canadian journal of chemical engineering. Volume 98:Number 3(2020)
• Page Start: 717
• Page End: 727
• Publication Date: 2019-12-01
• Subjects: fault diagnosis -- fourth order moment -- process monitoring -- singular value decomposition; Chemical engineering -- Periodicals; Technology -- Periodicals; 660.05
• DOI: 10.1002/cjce.23670
• Languages: English
• ISSNs: 0008-4034

Abstract

Abstract: Principal component analysis (PCA) and partial least squares (PLS) have been frequently used for process industry monitoring; however, their application on industrial sites is limited because they cannot be used to process data with non‐Gaussian distribution. Independent component analysis (ICA) has become a powerful modelling method for non‐Gaussian process monitoring. However, the ICA‐based modelling method has been found to contribute to double the amount of data loss in feature extraction. There are two reasons for this. First, when the PCA algorithm is used to whiten the original data, the smaller principal component is discarded. Second, when selecting independent components, some smaller independent components will be discarded according to the evaluation index. The abovementioned two data feature extraction methods may discard useful information for fault monitoring, which will inevitably lead to inaccurate fault monitoring. To solve this problem, a fault monitoring and diagnosis method based on fourth order moment (FOM) analysis and singular value decomposition (SVD) is proposed. First, the fourth order moments of each process variable were constructed separately. Then, the data space of the fourth order moments was decomposed by singular value decomposition to establish the global monitoring statistics. Finally, the contribution diagram was drawn and the fault diagnosis was performed based on the global monitoring results. The proposed method was applied to the Tennessee Eastman (TE) simulation platform, and its effectiveness and feasibility were verified by a comparison with PCA and ICA.