Monitoring and prediction of big process data with deep latent variable models and parallel computing. (August 2020)

• Record Type: Journal Article
• Authors: Yang, Zeyu; Ge, Zhiqiang
• Is Part Of: Journal of process control. Volume 92(2020)
• Page Start: 19
• Page End: 34
• Publication Date: 2020-08
• Subjects: Big process data -- Process monitoring -- Quality prediction -- Deep latent variable models -- Parallel computing; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2020.05.010
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: Process monitoring and quality prediction are crucial for maintaining favorable operating conditions and have received considerable attention in previous decades. For majority complicated cases in chemical and biological industrial processes with particular nonlinear characteristics, traditional latent variable models, such as principal component analysis (PCA), principal component regression (PCR), partial least squares (PLS), may not work well. In this paper, various nonlinear latent variable models based on autoencoder (AE) are developed. In order to extract deeper nonlinear features from process data, the basic shallow AE models are extended to the deep latent variable models, which provides a deep generative structure for nonlinear process monitoring and quality prediction. Meanwhile, with the ever increasing scale of industrial data, the computational burden for process modeling and analytics has becoming more and more tremendous, particularly for large-scale processes. To handle the big data problem, the parallel computing strategy is further applied to the above model, which partitions the whole computational task into a few sub-tasks and assigns them to parallel computing nodes. Then the parallel models are utilized for process monitoring and quality prediction applications. The effectiveness of the developed methods are evaluated through the Tennessee Eastman (TE) benchmark process and a real-life industrial process in an ammonia synthesis plant (ASP). Highlights: Various nonlinear latent variable models based on autoencoder (AE) are extended to deep forms. The parallel computing strategy is applied to deep latent variable models. Parallel deep latent variable models are utilized for process monitoring and quality prediction. Two industrial examples are provided for performance evaluation.