AI BASED MOTOR FAULT DETECTION AND MAINTENANCE PREDICTION SYSTEM FOR SINGLE PHASE INDUCTION MOTOR

Electric motors are essential parts that power machines in the manufacturing, energy, transportation, and automation sectors. Single-phase AC induction motors, which are often used in home and light industrial applications, are one type of electric motor. Unexpected motor fai lures continue to be a significant problem despite their ubiquitous use, resulting in expensive unscheduled downtime, production losses, and considerable worker and equipment safety risks. The intelligent, AI-based system proposed in this project is intend ed to continually monitor the condition of electric motors in real time and forecast maintenance needs well in advance of any malfunction. Through the analysis of real-time sensor data, such as vibration, temperature, and current signals, the system is abl e to detect the first indications of fault development that would otherwise go undetected until a catastrophic failure takes place. The system uses a multi-phase methodology. Continuous collection of raw sensor signals techniques such as Fast Fourier Trans form (FFT), and then analyzed by machine learning models including Support Vector Machines (SVM), Random Forest, Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks to classify fault types such as bearing defects, rotor bar brea kage, stator winding faults, shaft misalignment, and overheating. A predictive model estimates the Remaining Useful Life (RUL) of the motor, enabling maintenance teams to schedule servicing at the most optimal time — avoiding both unexpected failures and unnecessary early servicing. Results and alerts are presented through a real-time monitoring dashboard that gives operators a clear view of motor health status, active fault conditions, predicted maintenance dates, and historical trends.