Prediction of Remaining Useful Life of Equipment based on Condition Monitoring and Expert Knowledge Using Neuro-Fuzzy Inference System

Prediction of equipment remaining useful life (RUL) is essential for efficient maintenance decision making to decrease the maintenance cost. The failure history data and the expert knowledge are two important information sources for RUL prediction. Although there are lots of methods in literature that have used the history data to predict the equipment RUL, the hybrid methods has received less attention in this field. Therefore, this paper aims to present a new method based on a Takagi-Sugeno-Kang (TSK) inference system combined with information gathered from both condition monitoring process and expert knowledge to predict RUL of the equipment. In this paper the rule base for fuzzy inference system is prepared in two stages. At the first stage three basic rules are tuned with history data using a neuro-fuzzy (NF) network and in the second stage the rule base is completed by rules extracted under experts’ supervision. The performance of new hybrid method is evaluated in different real conditions to compare with traditional datadependent methods. Also, in this work a simulating algorithm is presented in order to generate different conditions that really could happen. Simulating parameters are estimated from real data related to bearing failures. The experimental results show that the efficiency of proposed method is higher than traditional data-dependent method.