In recent years proactive diagnostic strategies have gained more significance. Due to the need of reduction of production costs, machine downtime must be held at the lowest possible limits. This forces maintenance services to predict possible failures and plan repairs in advance. Rolling bearing faults are among the major reasons for breakdown of industrial machinery and bearing diagnosing is one of the most important topics in machine condition monitoring. Vibration signals offer great opportunity to provide reliable information about machine condition. However, in complex industrial environments the vibration signal of the rolling bearing may be covered or concealed by other vibration sources, such as gears. In case of masking the informative bearing signal by machine noise, extraction of useful diagnostic information from vibration signals becomes very difficult. The following paper presents two rolling bearing diagnosing approaches enabling early detection of rolling bearing faults at the low-energy stage of their development. By using empirical signal decomposition methods a raw vibration signal is divided into two parts: an informative bearing signal and a signal emitted from other machinery elements. For further bearing fault-related feature extraction from the informative bearing signal, the spectral analysis of the empirically determined local amplitude is applied. To test the operational effectiveness of the developed signal decomposition methods, raw vibration signals generated by complex mechanical systems employed in the industry are used. The test results show that the developed methods allow early identification of bearing fault in case of masking the informative bearing signal by signals derived from other sources.
CITATION STYLE
Dybała, J., & Komoda, J. (2018). Empirical signal decomposition methods as a tool of early detection of bearing fault. In Applied Condition Monitoring (Vol. 9, pp. 147–156). Springer. https://doi.org/10.1007/978-3-319-61927-9_14
Mendeley helps you to discover research relevant for your work.