Decision support system using artificial immune recognition system for fault classification of centrifugal pump

摘要: Centrifugal pumps are a crucial part of many industrial plants. Early detection faults in can increase their reliability, reduce energy consumption, service and maintenance costs, life-cycle safety, thus resulting significant reduction life-time costs. Vibration analysis is very popular tool for condition monitoring machinery like pumps, turbines compressors. The proposed method based on novel immune inspired supervised learning algorithm which known as artificial recognition system (AIRS). This paper compares the fault classification efficiency AIRS with hybrid systems such principle component (PCA)-Naive Bayes PCA-Bayes Net. robustness examined using its accuracy kappa statistics. It observed that AIRS-based outperforms other two methods considered present study.