Roulias D., Loutas T., Kostopoulos V., 2013, A Statistical Feature Utilising Wavelet Denoising and Neighblock Method for Improved Condition Monitoring of Rolling Bearings, Chemical Engineering Transactions, 33, 1045-1050.
Rolling element bearings are of great importance in industrial applications as well as in critical applications in transport. Signal processing techniques can enhance the ability of bearings condition monitoring to identify faults during operation. In this work, state of the art signal denoising techniques are applied for condition monitoring of roller bearings. In particular wavelet denoising with NeighBlock threshold technique is applied in vibration waveforms. A standard data base for lifelong operation of roller bearings is used for the tests. The condition monitoring efficiency of a statistical feature is assessed taking into account both raw and denoised bearing vibration signals. A brief assessment shows that such a signal denoising technique can evidently improve the remaining useful life estimation as well as the change point detection of the structural health of the asset.
