Industrial process fault detection based on deep highly-sensitive feature capture. (June 2021)

• Record Type: Journal Article
• Authors: Liu, Bowen; Chai, Yi; Liu, Yuhu; Huang, Chenghong; Wang, Yiming; Tang, Qiu
• Is Part Of: Journal of process control. Volume 102(2021)
• Page Start: 54
• Page End: 65
• Publication Date: 2021-06
• Subjects: Deep learning -- Feature extraction -- Fault detection -- Deep belief network -- Deep highly-sensitive features; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2021.04.003
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: With the rapid development of sensor and computer technology, deep learning has received extensive attention in the field of fault detection with powerful nonlinear feature extraction capabilities. However, the feature extracted by deep learning contains different fault information volume. Fault detection performance would be affected by features with less fault information. Motivated by this, the deep high-dimensional features extracted from the deep belief network are analyzed, and an index for measuring fault information volume is proposed to select the deep highly-sensitive feature (DHSF) with a large amount of fault information volume as the feature to be detected. Based on DHSFs, Euclidean distance is used for fault detection, and the moving average window function is used to reduce burst noise interference and improve detection performance. Finally, a numerical case and Tennessee Eastman process demonstrate the advantage of the proposed method in fault detection results compared with other methods. Graphical abstract: Highlights: GRBM is used to replace the traditional binary RBM, keeping most informations. An index of measuring the fault information volume is proposed to select deep highly-sensitive features. The Euclidean distance and the moving average are used for fault detection.