Big data and stream processing platforms for Industry 4.0 requirements mapping for a predictive maintenance use case. (January 2020)

• Record Type: Journal Article
• Authors: Sahal, Radhya; Breslin, John G.; Ali, Muhammad Intizar
• Is Part Of: Journal of manufacturing systems. Volume 54(2020)
• Page Start: 138
• Page End: 151
• Publication Date: 2020-01
• Subjects: Industry 4.0 -- Big Data -- Stream processing -- Predictive maintenance -- Railway -- Wind turbines; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2019.11.004
• Languages: English
• ISSNs: 0278-6125

Abstract

Highlights: Literature review of the strengths and weaknesses of big data stream processing technologies for Industry 4.0. Identifying a set of requirements for predictive maintenance use cases including the railway transportation industry and the wind turbines energy industry. Providing a breadth-first mapping of predictive maintenance requirements to the strengths & weaknesses of open source Big Data streaming technologies. Abstract: Industry 4.0 is considered to be the fourth industrial revolution introducing a new paradigm of digital, autonomous, and decentralized control for manufacturing systems. Two key objectives for Industry 4.0 applications are to guarantee maximum uptime throughout the production chain and to increase productivity while reducing production cost. As the data-driven economy evolves, enterprises have started to utilize big data techniques to achieve these objectives. Big data and IoT technologies are playing a pivotal role in building data-oriented applications such as predictive maintenance. In this paper, we use a systematic methodology to review the strengths and weaknesses of existing open-source technologies for big data and stream processing to establish their usage for Industry 4.0 use cases. We identified a set of requirements for the two selected use cases of predictive maintenance in the areas of rail transportation and wind energy. We conducted a breadth-first mapping of predictive maintenance use-case requirements to the capabilities of big data streaming technologies focusing on open-source tools. Based on our research, we propose some optimal combinations of open-source big data technologies for our selected use cases.