CONTRIBUTIONS OF THE EXPERT SYSTEMS AND MACHINE LEARNING TECHNIQUES AT THE PRESCRIPTIVE MAINTENANCE LEVEL

Purpose – This paper aims to present the main factors necessary for the implementation of machine learning techniques applied to intelligent systems for the development of prescriptive maintenance systems. Methodology – Expert systems and machine learning systems have the capacity for ongoing updates and enhancements, enabling organizations to fine-tune their maintenance approaches in response to changing insights and feedback. Industry 4.0 has brought significant contributions in terms of re-engineering prescriptive maintenance systems. Findings – Expert systems and machine learning techniques complement each other in prescriptive maintenance by leveraging historical data, real-time monitoring and adaptive decision-making to enhance equipment reliability, minimize downtime and optimize maintenance strategies. Research implications – Both systems can effortlessly incorporate Internet of Things sensors for the acquisition of real-time data, improving the precision and promptness of forecasts and suggestions. Practical implications – Automated expert systems enhance efficiency, precision and prompt responsiveness in maintenance operations through the application of predetermined rules, analysis of data and decision-making, all accomplished without the need for manual input at each stage. Originality – This article highlights the significant contributions of expert systems in the context of prescriptive maintenance activities of organizations.