Improving Rehabilitation And Maintenance Of Workshop Equipments Using Artificial Neural Network (Ann) Based Technique. a Case Study Of Foundry Crucible Furnace In Caritas University Amorji Nike Emene Enugu

Abstract

The effective rehabilitation and maintenance of workshop equipment are critical for ensuring optimal performance, reducing operational downtime, and extending the lifespan of machinery. This study focuses on improving the rehabilitation and maintenance process of a foundry crucible furnace in Caritas University Amorji Nike Emene, Enugu, using an Artificial Neural Network (ANN)-based technique. The research explores the application of ANN in predictive maintenance by analyzing historical operational data and identifying patterns that indicate potential faults or performance degradation.A structured methodology was adopted, involving data collection from the crucible furnace, preprocessing, and training of the ANN model. The ANN-based system was designed to predict faults and recommend maintenance actions before critical failures occur. Results from the study demonstrated that the ANN model accurately detected anomalies and provided timely alerts, significantly reducing downtime and improving operational efficiency. The findings highlight the potential of ANN-based techniques in transforming traditional maintenance practices into proactive and intelligent systems. The study recommends the integration of ANN systems into workshop maintenance frameworks, the training of technical personnel, and the adoption of sustainable practices to enhance reliability and productivity. This approach not only optimizes equipment performance but also contributes to the advancement of intelligent maintenance technologies in educational institutions.