Paradigm shift for predictive maintenance and condition monitoring from Industry 4.0 to Industry 5.0: A systematic review, challenges and case study

This paper examines the integration of Industry 5.0 principles with advanced predictive maintenance (PdM) and condition monitoring (CM) practices, based on Industry 4.0's enabling technologies. It provides a comprehensive review of the roles of Machine Learning (ML), Digital Twins (DT), the Internet of Things (IoT), and Big Data (BD) in transforming PdM and CM. The study proposes a six-layered framework designed to enhance sustainability, human-centricity, and resilience in industrial systems. This framework includes layers for data acquisition, processing, human-machine interfaces, maintenance execution, feedback, and resilience. A case study on a boiler feed-water pump is also presented which demonstrates the framework's potential benefits, such as reduced downtime, extended lifespan, real-time equipment monitoring and improved efficiency. The findings of this study emphasises the importance of integrating human intelligence with advanced technologies for a collaborative and adaptive industrial environment, and suggest areas for future research. • Research fills literature gap by integrating ML, DT, IoT, BD for PdM and CM in Industry 5.0. • Comprehensive review of technologies for RUL prediction and machine health monitoring. • Case study on boiler feed-water pump employs core tech for PdM, aligning with Industry 5.0. • Study discusses challenges in PdM and CM application, proposing future solution pathways. • Offers practical guidance for implementing PdM and CM, aiding academic and industry progress.