Fault Diagnosis and Prognosis Modeling Methods in Predictive Maintenance: A Systematic Review

Intelligent manufacturing approaches, technologies, and procedures have grown increasingly with the emergence of Industry 4.0 and smart manufacturing. Machines and managers, in the manufacturing process, must make decisions based on a massive amount of data and customization on regular basis. One of the most essential concerns in this scope is the ability to predict the requirement for asset maintenance at a specific future time. The predictive maintenance (PdM) function helps in the early detection of flaws and errors in machinery before they progress to critical stages; reducing hence machine downtime and associated expenses. Therefore, multiple techniques have emerged as a viable tool in PdM applications for preventing problems in the equipment that makes up the factory floor's production lines. The purpose of this paper is to give a thorough literature review of PdM methods, highlighting which are currently being considered and the performance of current state-of-the-art predictive maintenance strategies. This review focuses on six scientific databases and provides a valuable foundation for PdM methodologies, their key outcomes, obstacles, potential, as well as supporting new research in the field.