Rolling bearing fault prognosis using recurrent neural network

Abstract

Rolling bearing devices are widely used in almost all industries in the world, and play a very critical role. So that once this critical device fails, the whole system will have a very serious impact. It will not only affect the performance of the entire system, but also the system reliability, security, applicability and so on. Therefore, it is very important to predict the bearing failure. Because recurrent neural network is quite effective in dealing with sequence problems, it is often used to do prediction-related problems. And in recent years, recurrent neural network has been put into great attention, so here we choose to use RNN for rolling bearing fault prognosis. Afterwards, we use the actual rolling bearing fault data to verify the effectiveness of our method.