Autonomous Decision Support Based on Artificial Intelligence Techniques for Maintenance Processes

Through the recent digitalization of the industry and the use of technologies and ideas from Industry 4.0, maintenance tasks have altered. Companies are now able to develop knowledge about the production system’s present and future health state by connecting to and talking with it, which enables more effective control over the machinery. Predictive maintenance is a technique whose objective is to minimize unscheduled downtimes and efficiently arrange maintenance tasks before faults and stoppages occur. Several Artificial Intelligence (AI) data analysis tools have been presented in recent decades to construct a prescriptive maintenance system that will aid with the autonomous choice in order to better assist this work. In order to comprehend how artificial intelligence algorithms are affecting maintenance policies and to analyze their implications in strategies, we investigate the state-of-the-art technologies in the prescriptive maintenance system in this study. The findings are compiled in a thorough database that offers illustrations of how to adopt maintenance policies based on descriptive, predictive, and prescriptive analytics using concepts and empirical evidence from the literature. The goal of this study, which is the first in-depth inquiry of these research subjects, is to provide a deeper understanding and awareness of current trends and major challenges while highlighting important aspects and barriers to the adoption of novel policies.