Rolling element bearing fault detection using acoustic emission signal analyzed by envelope analysis with discrete wavelet transform

Multi-feature entropy distance approach with vibration and acoustic emission signals for process feature recognition of rolling element bearing faults

“…The MFED approach is promising in the use of one kind of vibration or AE signal in fault diagnosis. 35–40 Sometimes, multiple types of signals are simultaneously required, however, to master the characters of faults more accurately. Under the circumstances, based on the thought of the MFED method, the four MFED values of each fault from one kind of signals may be regarded as the feature indexes of the fault signals.…”

“…Along with ever increasing on the accuracy of fault diagnosis, feature extraction technique is increasingly valued and thereby leads to the prevalence of information entropy, 30 and in consequence emerges various entropy methods by combining singular spectrum in time domain, power spectrum in frequency domain, wavelet space spectrum and wavelet energy spectrum in time–frequency domain, which are defined by singular spectrum entropy, 31 power spectrum entropy, 32 wavelet space spectrum entropy 33 and wavelet energy spectrum entropy, 34 respectively. Due to the complicacy of rolling bearing signals of rotating machinery herein accompanying with a lot of ambient noise and other superfluous signals, the fault diagnosis techniques based on information entropy still confront with unavoidable questions: (a) the signal characters of rolling bearing faults are insufficiently reflected by the extracted information features; (b) the real fault features of rolling bearings are hardly described by single type of fault signal like vibration signals 35–37 or acoustic emission (AE) signals, 38–40 in spite of a large amounts of works studied by single type of fault signal for the related machinery; and (c) the process features of rolling bearing signals cannot be reasonably expressed and reflected in fault diagnosis so that the diagnostic precision is unacceptable. Therefore, it is obviously urgent to require proposing an effective method to innovatively address the above issues and thereby improve the effect of rolling bearing fault diagnosis.…”

Robust condition monitoring of rolling element bearings using de-noising and envelope analysis with signal decomposition techniques

“…Recently, WT-based envelope analysis has been used to address these issues (Gu, Kim, Kelimu, Huh, & Choi, 2012;Kim, Gu, Kim, Kim, & Choi, 2010). Although Gu et al (2012) and Kim et al (2010) achieved satisfactory performance in terms of capturing the defect frequencies (or characteristic frequencies) of low-speed rolling element bearing failures, they did not consider the impact of sub-bands. Hence, this study quantitatively explores the effect of a set of subbands with regard to condition monitoring performance.…”

Condition Monitoring of Cooling Tower Fans using the Envelope Technique

“…al. [4], the envelope analysis was enhanced with the addition of discrete wavelet transform (DWT) to reduce the noise level in AE signals. And then, the PR was calculated and compared with general envelope analysis result and the result of envelope analysis added DWT.…”