Most manufacturing companies utilize the overall equipment effectiveness (OEE) metric to monitor performance. Its computation provides managers with the opportunity to identify significant losses resulting from reduced machine effectiveness and make informed decisions to rectify the situation. This paper developed a systematic framework based on the reliability-centered maintenance (RCM) approach and an artificial neural network (ANN) to identify the primary losses and minimize the high downtime of production machines and product defects, thus increasing their OEE. The framework consists of five main implementation phases, which are. System description and critical system selection, critical machine analysis and evaluation, defect assessment, and assessment of idling and stoppage losses. An ANN technique is suggested to assess the hazard degree of the failure modes from critical components, determine maintenance mode decisions, calculate maintenance interval cycles, and perform OEE calculations. The developed framework was applied to the selected real case study as a maintenance and quality controller to minimize the downtime and defect rate. The results demonstrate that Availability and OEE improved from 87% to 97% and 57% to 85%, respectively. Moreover, the results indicate that the applied framework is more accurate and exhibits better performance in predicting overall equipment effectiveness in the selected case study.