Improved algorithms for on-line oil analysis have been suggested. They utilize measurements of multiple oil properties of interest and detect faults induced by transients in the acquired signals. Transient detection is based on the cumulative sum of errors (CUSUM) technique. Performance capabilities are tested on laboratory conditions.
COBISS.SI-ID: 13160219
Premature bearing failures can be caused by a large number of factors were one of the most common causes is an inadequate lubrication. Improperly lubricated bearings detection from vibration patterns is yet a difficult task, especially when records from short operating periods are available. This problem has been addressed by applying recently introduced wavelet bispectral analysis, a technique for revealing time-phase relationships. The experimental results reveal that bispectral absolute value is not enough sensitive to reveal the lubricant deficiency fault. However by further extraction and treatment of the biphase phase information one can gain better insight into the fault bearing state. Improper lubrication is expressed in different phase coupling length and bifrequency region in the bispectrum domain.
COBISS.SI-ID: 10015817
Almost all known methods for vibration-based diagnosis of bearings stand on some sort of analysis of amplitude spectra of the acquired signal. This analysis can be agravated by presence of fluctuations in the operating conditions. We developed an alternative approach which models the occurrences of localized bearing fault patterns as a realization of random point process whose inter-event time intervals are governed by inverse Gaussian mixture. Hence the approach turns much more robust to fluctuations in operating conditions. The applicability of the model was evaluated on vibrational signals generated by bearing models with localized surface fault.
COBISS.SI-ID: 27178535