Concurrent analytics of temporal information and local correlation for meticulous quality prediction of industrial processes. (November 2021)

• Record Type: Journal Article
• Authors: Yu, Wanke; Zhao, Chunhui
• Is Part Of: Journal of process control. Volume 107(2021)
• Page Start: 47
• Page End: 57
• Publication Date: 2021-11
• Subjects: Cascaded regression network -- Quality prediction model -- Convolutional filter -- Local correlation and temporal information; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2021.09.014
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: Many conventional quality prediction models are directly developed based on the easy-to-measure variables, and thus the local information within individual unit may be buried by information of other units. In this study, a cascaded regression network (RegNet) is proposed to solve the aforementioned issue. Specifically, the features which are adopted to develop RegNet model are extracted in two steps, including variable-wise and unit-wise feature extractions. In variable-wise feature extraction, several adjacent variables and their corresponding time lags are integrated using convolutional filter. By this means, both local correlation and temporal information within each unit can be preserved. In the unit-wise feature extraction, the local information of each unit is adopted to further explore the global correlation between different operation units. Based on the obtained global features, a fully connected layer is designed to calculate the regression weight of the quality prediction model. It is noted that the architecture of RegNet can be readily generalized to many existing methods by replacing the convolutional filter and fully connected layer. The performance of the proposed method is illustrated using a simulated process and two real industrial processes, and the experimental results show that it can provide reliable prediction results for industrial applications. Highlights: The local information within each unit is adopted to develop RegNet model for achieving a better prediction performance. The prediction accuracy of RegNet method is further improved by extracting temporal information from adjacent samples. The proposed RegNet method can be extended to many other existing methods for addressing quality prediction problem.