An Intelligent and Robust Fault Diagnosis System for Identification of Centrifugal Pump Defects in Frequency Domain Using Corrupted Vibration and Current Signatures

摘要: Historically, fault diagnosis techniques in industries were experience based. These techniques, however, are very tedious and involve a lot of human error. Therefore, intelligent methods need to be developed for the sustained operation vital equipment like centrifugal pumps (CPs). In present investigation, multiple independent coexisting hydraulic mechanical faults CP attempted classified. The include blockages (discharge suction), dry runs, impeller cracks cover plate damages. blockage considered with varying severities. current vibration signatures collected time-domain by experimentally simulating on CP. later converted into frequency domain. Support vector machine (SVM) classifier conjunction Gaussian RBF kernel is used develop expert system diagnosis. To inspect algorithm’s robustness, noisy/corrupted data test algorithm. prediction accuracies thus obtained compared non-corrupt data’s classification performance.