Predictive maintenance for cyber physical systems using neural network based on deep soft sensor and industrial internet of things. (July 2022)

• Record Type: Journal Article
• Authors: Alassery, Fawaz
• Is Part Of: Computers & electrical engineering. Volume 101(2022)
• Publication Date: 2022-07
• Subjects: CPS -- Data-driven process -- Soft sensing -- Predictive maintenance -- Linear systems; CPS cyber-physical systems -- MVA multivariate analysis -- SJITNN supervisory Just-in-time neural network -- PLSKI partial least squares key indicator; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108062
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: ML (machine learning) techniques, has the potential to greatly enhance maintenance efforts on current CPS (cyber-physical systems). Soft sensors are software libraries or techniques that can estimate status and predict important performance indicators. MVA (multivariate analysis) and ML methods have been developed in data-driven process monitoring and fault detection method. This strategy is built on the detection–prediction–decision–action sequence of operational operations. Abstract: Soft sensors are software libraries or techniques that can estimate status as well as predict important performance indicators. MVA (multivariate analysis) and ML methods have been developed in data-driven monitoring as well as fault detection method. Here this research proposes supervisory Just-in-time neural network (SJITNN) based CPS monitoring and predictive maintenance integrated with partial least squares key indicator (PLSKI) in linear systems and large scale complex systems which mitigate noise, complexity and improve the network robustness, accuracy of predictive maintenance, RMSE, recall, F-1 score and precision. Furthermore, by allowing user to design analysis chains themselves, framework presents a user-friendly predictive maintenance method. Aside from this, framework is based on containerization techniques to make platform versatile, durable, and scalable in a variety of production situations. The experimental results shows that the proposed technique obtained accuracy of 91.8%, precision of 87.6%, recall of 88%, F-1 score of 72% and RMSE of 50%. Graphical abstract: Image, graphical abstract