Fault Detection and Diagnosis using Principal Component Analysis of Vibration Data from a Reciprocating Compressor

This paper investigates the use of time domain vibration features for detection and diagnosis of different faults from a multi stage reciprocating compressor. Principal Component Analysis (PCA) is based to develop a detection and diagnosis framework in that the effective diagnostic features are selected from the PCA of 14 potential features and a PCA model based detection method using and statistics is subsequently developed to detect various faults including valve leakage, suction valve leakage, inter-cooler leakage, loose drive belt, discharge valve leakage combined with suction valve leakage, suction valve leakage combined with intercooler leakage and discharge valve leakage combined with intercooler leakage. Moreover a study of Q-contributions has found two original features: Histogram Lower Bound and Normal Negative log- likelihood which allow full classification of different simulated faults.