Remaining Useful Life Estimation Using ANFIS Algorithm: A Data-Driven Approcah for Prognostics

One of the important matters in every industrial process is maintaining an effective maintenance schedule. To that goal, predictive maintenance has been founded based on prognostics methods. One of the best ways to present the future state of a machine is to predict its useful remaining life (RUL). Since RUL as the output of the prognostics stage is a quantity related to how much more a machine can properly operate, it can be used to create a flexible and effective maintenance schedule. In this paper, a data-driven prognostics method using adaptive neuro-fuzzy inference system (ANFIS) algorithm is presented. This method uses a neuro-fuzzy structure that automatically provides us with optimum clustering, fuzzy rules and structural parameters. The main goal is to estimate the RUL of aircraft engines by studying the engine degradation process with only historical data provided. The effectiveness of the proposed methods is demonstrated by a implementing the method in a numerical example and providing evaluation of results.