Scalable learning and probabilistic analytics of industrial big data based on parameter server: Framework, methods and applications. (June 2019)

• Record Type: Journal Article
• Authors: Yao, Le; Ge, Zhiqiang
• Is Part Of: Journal of process control. Volume 78(2019)
• Page Start: 13
• Page End: 33
• Publication Date: 2019-06
• Subjects: Distributed parallel modeling -- Stochastic Variational Inference -- Parameter Server -- Process monitoring -- Quality prediction -- Big data; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2019.03.017
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: Distributed parallel probabilistic big data analytics method is proposed upon scalable parameter server framework. Stochastic variational inference algorithm is utilized to transfer traditional probabilistic model into a scalable form. SVI-based probabilistic model is deployed on distributed Parameter Server computing framework. SVI-MFA model is proposed as an example and deployed on the PS framework for industrial applications. Numerical and industrial cases are provided for performance evaluation of the proposed modeling framework. Abstract: With the ever increasing scale of industrial data, the computational burden for process modeling and analytics has becoming tremendous, particularly for large-scale processes. In this paper, a distributed parallel probabilistic learning framework based on scalable Parameter Server (PS) architecture is proposed for big process data. Under this framework, the traditional Variational Inference (VI) probabilistic model can be transformed to a scalable form through the Stochastic Variational Inference (SVI) algorithm, which can be further deployed on the PS architecture to make a distributed and parallel model. As an example, the traditional Variational Inference Mixture Factor Analysis (VIMFA) model is converted to the SVI-MFA model and deployed on the PS architecture for process big data modeling. Then it is utilized for process monitoring and quality prediction applications. A numerical case is first generated to validate the feasibility and efficiency of the SVI-MFA modeling algorithm, and then a TE benchmark process and a real Methanation Unit process demonstrate the effectiveness of the proposed framework for big process data modeling and analytics.