Bearing Condition Prediction Using Enhanced Online Learning Fuzzy Neural Networks

Abstract

Machine health condition (MHC) prediction is useful for preventing unexpected failures and minimizing overall maintenance costs since it provides decision-making information for condition-based maintenance (CBM). This paper presents a novel bearing health condition prediction approach based on enhanced online sequential learning fuzzy neural networks (EOSL-FNNs). Based on extreme learning machine (ELM) theory, an online sequential learning strategy is developed to train the FNN. Taking advantage of the proposed learning strategy, a multi-step time-series direct prediction scheme is presented to forecast bearing health condition online. The proposed approach not only keeps all salient features of the ELM, including extremely fast learning speed, good generalization ability and elimination of tedious parameter design, but also solves the singular and ill-posed problems caused by the situation that the number of training data is smaller than the number of hidden nodes. Simulation studies using real-world data from the accelerated bearing life have demonstrated the effectiveness and superiority of the proposed approach.