Predicting Remaining Useful Life of Ball Bearing Using an Independent Recurrent Neural Network

Abstract

Planning maintenance of facilities is an important role for production line. From preventive maintenance to predictive maintenance, the main purpose is cost down by reducing the chance of the unexpected shot down. Thus, this study intends to apply independent recurrent neural network (IndRNN), which is a kind of deep learning technique, and apply it to predict remaining useful life for the ball bearings using vibration signals. The result of the proposed method is compared with original RNN. The experimental results indicate that IndRNN is able to perform better than the other method in terms of score.