Fault diagnosis and classification of water pump using adaptive neuro-fuzzy inference system based on vibration signals

Abstract

This article presents a procedure to intelligent fault diagnosis of water pump using vibration monitoring and adaptive neuro-fuzzy inference system. Vibration data from a water pump with three different conditions, namely, healthy, looseness, and misalignment faults, were acquired using an accelerometer sensor. On this basis, the proposed method extracted different feature parameters from the vibration signals in the frequency-domain to establish feature vectors. Finally, these features were input into adaptive neuro-fuzzy inference system to carry out faulty pattern classification. The performance of the system was validated by applying the testing data set to the trained adaptive neuro-fuzzy inference system model. The experimental results showed that this method had a high classification accuracy for both training and testing data sets. Therefore, the proposed approach can reliably recognize different fault categories and serve as an intelligent fault diagnosis system in real applications.