Fault Diagnosis of Rolling Element Bearing with Operationally Developed Defects Using Various Convolutional Neural Networks

Rolling element bearings are critical building blocks of any rotating machine. Achieving effective and precise fault diagnosis through various neural network models plays a pivotal role in ensuring the accuracy of rolling element bearing fault diagnosis. This research paper represented comparative study of artificial neural network (ANN), 1-D CNN, multi-input 1-D CNN, and 2-D CNN in fault diagnosis of rolling element bearings. The experiment was conducted on a roller bearing test rig over 2000 hours at constant speed of 800 rpm along with radial load of 1.5 kN till the development of naturally occurring operational surface defects on the bearing components. The proposed neural network architecture utilized multiple parallel convolutional layers to effectively extract rich and complementary fault features. The model was configured by implementing the categorical crossentropy loss function and Adam optimizer. Evaluation of the neural network models was performed using a confusion matrix and t-SNE visualization to ensure accurate fault identification. Comparative analysis among the convolutional neural network techniques was conducted to show their effectiveness toward fault diagnosis. The multi-input 1-D CNN achieved 97% prediction accuracy. The results demonstrate that multi-input 1-D CNN model provides better accuracy in fault diagnosis compared to the other models.