Dilated convolutional neural network based model for bearing faults and broken rotor bar detection in squirrel cage induction motors

Deep learning can play a pivotal role in early fault detection in squirrel cage induction motors (SCIMs) and achieving Industry 4.0. SCIM finds application in industries like mining, textile, manufacturing, and many more. Early fault detection in SCIM can significantly reduce downtime and optimize productivity. This paper proposes a novel fault detection technique for bearing faults and broken rotor bar detection in SCIM using the dilated convolutional neural network-based model. A simple 1-D signal to image conversion technique is also proposed for transforming the 1-D vibration signal acquired from multiple accelerometers to images. The proposed method provides an end-to-end learning solution for fault detection. The propounded approach has accomplished an average accuracy of more than 99.50%. A comparison has also been made between different convolutional neural network (CNN) models and conventional machine learning models to show the proposed method's efficiency. The complete experimental work has been carried out on a 5 kW, 3-phase, 415 V, 50 Hz SCIM. The dilated CNN model development has been done using python software, and the packages used are Keras and TensorFlow.