Comparing ANFIS and ANN Models for Fault Series Prediction in Industrial Systems

Abstract:

The objective of this paper is the application of two models for predicting faults in industrial equipment systems by using Artificial Neural networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) as well as the interpretation of joint network outputs. Currently, an extended and effective operation of production systems is a vital demand. Soon the necessity to get to know and control any possible faults that might compromise the production mission is a must. The target becomes the extension of the system activity at full load and in a continuous manner, at the required timing, without it being affected by defects of its integral parts.