Interpretable sparse learned weights and their entropy based quantification for online machine health monitoring

Yan, Tongtong; Wang, Dong; Zheng, Meimei; Shen, Changqing; Xia, Tangbin; Peng, Z.K.

doi:10.1016/j.ymssp.2023.110493

Cited by 7 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, the envelope spectral kurtosis contains more abundant fault information than the time-domain kurtosis. It has been demonstrated that the shifting from the time domain signal to the frequency domain signal facilitates the robustness of the indicator to random impulse [34]. A healthy bearing displays a randomized pattern in its envelope spectrum across the entire frequency spectrum.…”

Section: Assisted Indicatormentioning

confidence: 99%

An adaptive Morlet wavelet-based iterative filtering method for locating informative frequency band

Shi,

Miao,

Xia

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Locating the informative frequency band of rolling bearing fault signals is of great significance for feature extraction and fault diagnosis. Benefiting from the adjustable center frequency and bandwidth as well as the similarity to impulse-like characteristics induced by bearing failures, Morlet wavelets are commonly used in resonance demodulation. However, the fault impulses are completely masked by the noise at a very low signal-to-noise ratio (SNR), which imposes many limitations on the existing wavelet parameter selection strategies and frequency band optimization methods. In this paper, an adaptive Morlet wavelet-based iterative filtering (AMIF) method is proposed for frequency band optimization under low SNR. The resonance frequency band is pinpointed based on adaptive Morlet wavelet filter banks, with off-band noise being canceled and fault features being refined during the filtering process. Additional iterative operations are leveraged to enhance fault features of in-band signals to facilitate the optimization of the filtering parameters. The effectiveness of the proposed AMIF method and its superiority over the WPT-based Kurtogram are verified through simulation and experimental analysis. According to the results, AMIF can effectively isolate the impulsive fault features even from overwhelming background noise.

show abstract

Section: Assisted Indicatormentioning

confidence: 99%