Machine learning-based fault diagnosis for three-phase induction motors in ventilation systems

Induction motors are crucial in industrial drive systems and nuclear and radiological facilities due to their durability and ease of maintenance. Even though the systems are reliable, they have several faults. One of these faults is the instability of the facility's electrical network. This may lead to catastrophic consequences such as instability in HVAC and ventilation systems, which affects operational safety. Air instability in the HVAC system is a critical concern in the radio pharmaceutical industry. Controlled environments are vital for safety and regulatory compliance. Maintaining air quality and stability is crucial to protect radioactive materials and ensure personnel safety. A healthy and faulty motor condition dataset proposed and used in the study was generated based on a simulated actual supply of electric data. A fault diagnosis is necessary to increase reliability and minimise risks. This paper proposes a simple, reliable, and economical machine-learning-based fault classifier for induction motors. The method analyzes stator currents, motor speed, torque, and three-phase voltage supply to classify some faults resulting from high amplitude and zeros of voltage. A case study of an air handling unit with a 2 hp, 4-pole, 50 Hz three-phase induction motor was modelled and tested with the proposed dataset using various classifiers, including decision trees, logistic regression, discriminant analysis, Naive Bayes, Ensemble, and K-Nearest Neighbor (KNN).