FAULT FEATURES OF LARGE ROTATING MACHINERY AND DIAGNOSIS USING SENSORFUSION

Large rotating machinery such as turbines and compressors are the key equipment in oil refineries, power plants, and chemical engineering pl ants. To minimize the economic loss incurred because of the defects or malfunctions of these machines, diagnosis is very important. Currentl y, diagnosis is carried out mainly using spectral analysis. In spite o f being effective in detecting the faults (monitoring), spectral analy sis is often ineffective in pin-pointing what the fault is (diagnosis) . This is due to the fact that it cannot clarify the spatial and tempo ral features in the sensor signals that are correlated to different ty pes of faults. In this paper, phase spectra, holospectra, purified orb it diagrams, and filtered orbit diagrams are used in searching for fau lt features. From the data obtained from more than 50 practical machin es, distinct fault features and diagnostic indices are found for 11 di fferent types of faults including unbalance, cracks, misalignment, rub , loose bearing caps, oil whirl, surge, fluid excitation, rotating sta ll, electric power supply fluctuation, and pipe excitation. Accordingl y, a diagnostic procedure is proposed. (C) 1995 Academic Press Limited .