Scheduled maintenance and inspection of bearing elements in industrial machinery contributes significantly to the operating costs. Savings can be made through automatic vibration-based damage detection and prognostics, to permit condition-based maintenance.However automation of the detection process is difficult due to the complexity ofvibration signals in realistic operating environments. The sensitivity of existing methods to the choice of parameters imposes a requirement for oversight from a skilled operator.This paper presents a novel approach to the removal of unwanted vibrational components from the signal: phase editing. The approach uses a computationally efficient full band demodulation and requires very little oversight. Its effectiveness is tested on experimental data sets from three different test-rigs, and comparisons are made with two state of the artprocessing techniques: spectral kurtosis and cepstral pre- whitening. The results from the phase editing technique show a 10% improvement in damage detection rates comparedto the state of the art while simultaneously improving on the degree of automation. This outcome represents a significant contribution in the pursuit of fully automatic fault detection.
- Phase spectrum
- Automated diagnostics of defective bearings
- Spectral kurtosis
- Cepstrum pre-whitening;