A Machine Learning-Based Predictive Maintenance Model for Electrical Power Systems

Abstract

Predictive maintenance has become an essential approach for improving the reliability and efficiency of electrical power systems. This study proposes a machine learning-based predictive maintenance model that utilizes real-time and historical sensor data to detect faults and estimate the remaining useful life of critical components. The framework integrates data acquisition, preprocessing, feature extraction, and machine learning techniques, including Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM) networks. The performance of these models was evaluated using metrics such as accuracy, precision, recall, and root mean square error (RMSE). The results indicate that the LSTM model outperforms traditional machine learning models due to its ability to capture temporal dependencies in time-series data, achieving higher accuracy and improved fault detection rates. Although deep learning models require greater computational resources, they provide more reliable predictions. The proposed approach demonstrates significant potential in reducing unexpected failures, optimizing maintenance schedules, and enhancing the overall reliability of power systems, making it suitable for modern smart grid applications.