Fault Detection and Diagnosis for Centrifugal Pump using Intelligent Techniques

Abstract

Automatic controlled systems are susceptible to faults. A common component found in modern process plant is the centrifugal pump which is used as an important element in a closed loop control system. Fault detection and diagnosis is an important task with increasing attention in the academic and industrial fields, due to economical and safety related matters. The early detection of fault can help avoid system shutdown, breakdown and material damage. In fault detection, the discrepancies between system outputs and model outputs are called as residuals, and are used to detect and diagnose faults. In real time application several faults may occur in centrifugal pump. Inability to deliver the desired flow and head is just one of the most common conditions for taking a pump out of service. Several techniques are being investigated as an extension to the traditional fault detection and diagnosis. Computational intelligence techniques are being investigated as an extension to the traditional fault detection and diagnosis methods. This paper proposes ANFIS (Adaptive Neural Fuzzy Inference System) for fault detection and diagnosis. In ANFIS, the fuzzy logic will create the rules and membership functions whereas the neural network trains the membership function to get the best output. The training and testing data required to develop the ANFIS model were generated at different operating conditions by running the pumping system and by creating various faults in real time in a laboratory experimental model.