AI-Based Predictive Maintenance System for Bearings

Bearing failures in rotating machinery can lead to unplanned downtime, increased maintenance costs, and reduced operational reliability. To address these challenges, this paper proposes an artificial intelligence (AI)-based predictive maintenance framework for bearing condition monitoring using temperature, vibration, and electrical-current measurements. The proposed methodology comprises sensor-data acquisition, preprocessing, feature extraction, machine-learning model development, and condition classification. Candidate machine-learning algorithms will be evaluated using labelled data to distinguish normal bearing operation from abnormal conditions. Performance will be assessed using accuracy, precision, recall, F1-score, and confusion-matrix analysis. Where suitable datasets are available, individual sensor inputs will be compared with combined sensor inputs to investigate the potential benefits of sensor fusion. The framework is intended to support condition monitoring by presenting the estimated bearing status and providing a basis for maintenance decisions. Its effectiveness will depend on data quality, representative operating conditions, reliable fault labelsand independent model validation. This work establishes a proposed methodology for investigating the feasibility of integrating multiple sensor measurements with machine learning for bearing predictive maintenance.