A novel semisupervised classification framework for coupling faults in hot rolling mill process. (May 2021)

• Record Type: Journal Article
• Authors: Ma, Liang; Peng, Kaixiang; Dong, Jie; Hu, Changjun
• Is Part Of: ISA transactions. Volume 111(2021)
• Page Start: 376
• Page End: 386
• Publication Date: 2021-05
• Subjects: Coupling faults -- Fault classification -- Feature selection -- Semisupervised multi-task learning -- Hot rolling mill process; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2020.10.066
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: Compared with single fault, the occurrence and composition of coupling faults have more uncertainties and diversities, which make fault classification a challenging topic in academic research and industrial application areas. In this paper, the classification problems of coupling faults are addressed from a new perspective, which will provide diagnostic decisions for online operators to take immediate remedial measures to bring the abnormal operation back to an incontrol state. Specifically, the main innovations are: (1) a semisupervised classification scheme for coupling faults is first proposed, which combines adaptive classification with multi-task feature selection; (2) number of classifications can be learned adaptively and automatically; (3) common and specific features among single and the associated coupling faults can be captured, which are crucial for improving classification performance. A case study on hot rolling mill process is finally given to validate the effectiveness of the proposed scheme, and several competitive methods are employed to carry out the classification process. It can be observed that the obtained classification results for two different cases are more successful than the traditional methods. Highlights: To propose a semisupervised coupling fault classification method for hot rolling mill process. To develop an adaptive classification approach for coupling faults. To put forward a feature capture method among single and coupling faults.