Abstract & Overview
Centrifugal pumps play a vital role in many critical applications and therefore continuous availability of such mechanical components become absolutely essential. This paper focuses on a problem of vibration-based condition monitoring and fault diagnosis of centrifugal pumps. The vibration based machine condition monitoring and fault diagnosis incorporate a number of machinery fault detection and diagnostic techniques. Many machinery fault diagnostic techniques utilize automatic signal classification in order to increase accuracy and reduce errors caused by subjective human judgment. This paper presented an adaptive network fuzzy inference system (ANFIS) to diagnose the fault type of the pump. The pump conditions to be considered were healthy, broken impeller, worn impeller, leakage and cavitation. These features are extracted from vibration signals using the FFT technique. The features were fed into an adaptive neurofuzzy inference system as input vectors. Performance of the system was validated by applying the testing data set to the trained ANFIS model. According to the result, total classification accuracy was 90.67%. This shows that the system has great potential to serve as an intelligent fault diagnosis system in real applications.