A Long Short Term Memory Recurrent Neural Network Approach for Rotating Machinery Fault Prognosis

Abstract

System or equipment prognosis and health management (PHM) has become more important than ever as modern industry develop. Normally PHM requires abundant prior information or statistic features to predict future system states, however an expert or accurate physical model is usually unavailable in practice. As an important trend of deep neural network algorithms, long short term memory (LSTM) recurrent neural network (RNN) has been proven significantly practical and accurate in machine learning problems such as natural language processing (NLP) and time serial prediction. In this paper a novel fault prognosis approach using LSTM based on vibration signal of rotating machinery is presented. It is proven that the capacity of machinery performance prediction with LSTM algorithm is improved with limited data available in a relatively short time period. The proposed LSTM approach, compared with other prognosis methods, gives a successful outcomes that may enhance the ability of health management and machine condition monitoring. It is proven that the proposed approach is superior and more practical for machine prognosis in complex bearing systems.