International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 06 | Jun 2025
p-ISSN: 2395-0072
www.irjet.net
Artificial Intelligence-Based Technique for Fault Detection and Diagnosis of PMSM Motor Dr Sandhya Kulkarni 1, Aniket Lakhe 2, Mayuri Rajput3 1 Professor, Department of Electrical Engineering, Government College of Engineering Aurangabad,
Chhatrapati Sambhajinagar, Maharashtra, India. 2 UG Student, Department of Electrical Engineering, Government College of Engineering Aurangabad, Chhatrapati
Sambhajinagar, Maharashtra, India. 3 UG Student, Department of Electrical Engineering, Government College of Engineering Aurangabad, Chhatrapati
Sambhajinagar, Maharashtra, India. ---------------------------------------------------------------------***--------------------------------------------------------------------1.INTRODUCTION Abstract - This project presents the detection and diagnosis of stator winding short-circuit faults in Permanent Magnet Synchronous Motors (PMSM) using artificial intelligence techniques. PMSM behavior is modeled and analyzed in MATLAB Simulink to simulate both healthy and faulty operating conditions. Simulation provides insights into dynamic behavior and electromechanical interactions under fault conditions without requiring physical experimentation.
Fault Detection and Diagnosis (FDD) is an essential condition monitoring technique designed to assess the operational status of electric motors. By enabling early detection of faults and distinguishing between fault types, FDD helps in proactive decision-making to prevent potential hazards and ensure system reliability. Permanent Magnet Synchronous Motors (PMSMs) are widely used in modern electric vehicles (EVs) due to their high efficiency, high torque density, and superior performance characteristics. However, like all electrical machines, PMSMs are vulnerable to various types of faults during operation, with stator winding short-circuit faults being among the most common and critical. Early detection and accurate diagnosis of such faults are essential to ensure the reliability, safety, and longevity of EV drive systems.
The approach involves simulating PMSM performance under normal and stator winding short-circuit scenarios. Results demonstrate close alignment between simulated and expected behaviors. For fault detection, the K-Nearest Neighbours (KNN) algorithm is applied to classify motor conditions based on features extracted from current signals. For fault diagnosis and severity estimation, Decision Tree Classifier and Random Forest Regressor models are used. The analysis shows KNN effectively detects faults, while Decision Tree and Random Forest models accurately diagnose the type and extent of stator faults. The motor modeling and fault analysis system, developed in MATLAB Simulink, enables detailed study and evaluation of fault scenarios.
Traditional fault detection methods, such as thermal monitoring or vibration analysis, are often limited in terms of sensitivity and response time. With the advancement of computational tools and artificial intelligence (AI) techniques, data-driven approaches have emerged as powerful alternatives for the early detection and diagnosis of motor faults. AI-based systems can analyze complex patterns in motor signals and classify fault types with high accuracy.
Using machine learning (ML) for PMSM fault detection and diagnosis offers advantages over traditional methods. ML models can automatically learn complex patterns from large datasets, allowing for early and accurate fault detection. Once trained, these models enable real-time monitoring and predictive maintenance, enhancing system reliability and reducing costs. This data-driven approach significantly improves the efficiency and effectiveness of fault diagnosis in PMSM.
This project focuses specifically on the detection and diagnosis of stator winding short-circuit faults in PMSMs using AI techniques. The PMSM motor model is developed and simulated in MATLAB Simulink software under both healthy and faulty conditions. For fault detection, the KNearest Neighbours (KNN) algorithm is employed, which classifies the motor's operational status based on features extracted from the stator current signals. For fault diagnosis and severity estimation, Decision Tree Classifier and Random Forest Regressor models are used to further analyze and categorize the fault condition.
Key Words: AI-Based techniques, Machine Learning (ML), KNN, Decision Tree Classifier, Random Forest Regressor.
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 732