Wavelet transform for rotary machine fault diagnosis:10 years revisited

The vibration signals recorded by the sensor reflect the operating state of bearings, and extracting recognizable features effectively from them has become a hot issue in fault diagnosis. Currently, signal processing based filtering methods have emerged as a popular approach for extracting fault-related features. However, conventional filters based on specified assumptions and theoretical models have limited adaptability to multiple types of bearings under different operating conditions, which can significantly impact the diagnostic results. Given this, a data-driven Adaptive Class (AdaClass) filter is proposed to extract the response characteristics of different categories within the latent space. The filter details are obtained by statistically analyzing the mean vectors of each class samples in the reconstructed feature subspaces. Notably, the latent feature space is mapped by linear operators LDA and class-wise PCA, where the data has a more concise feature representation and a more distinct feature structure. The low-dimensional projection operations enhance the differential information among different categories, and reorganize the internal structure within the same category. Furthermore, a bearing fault diagnosis model is developed based on the AdaClass filter banks, utilizing one-step convolution to improve the efficiency of feature extraction. Experimental results show that the proposed method outperforms the competitors in terms of accuracy, time consumption, and noise resistance, especially for small sample scenarios.

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

AdaClass filter and its application in bearing fault diagnosis

Zhang,

Li,

Zhang

et al. 2024

“…and immeasurable costs [3]. Therefore, accurately identifying the health of rolling bearings is imperative to improve the reliability and availability of equipment and to ensure the safe operation of installations [4,5].…”

Section: Introductionmentioning

confidence: 99%

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

Shi,

Miao,

Xia

et al. 2024

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.

“…To overcome the above drawbacks, the interpretable of CNNs are gradually attracting attention in the field of Interpretable Deep Learning (IDL) [15,16]. Currently, interpretable methods can be categorized as pre-methods and post-methods.…”

Section: Introductionmentioning

confidence: 99%

WBUN: an interpretable convolutional neural network with wavelet basis unit embedded for fault diagnosis

Gao,

Zhang,

Zhang

et al. 2024

Convolutional Neural Network (CNN) is extensively applied in mechanical system fault diagnosis. However, the absence of transparent decision mechanisms in CNNs hinders credibility. To address these challenges, this paper proposes an interpretable wavelet basis unit convolutional network (WBUN). This network incorporates meticulously designed wavelet basis unit (WBU) functions into convolutional layer, creating the interpretable wavelet basis unit convolutional (WBUConv) layer. Convolutional kernels with clear physical significance enable the WBUConv layer to extract fault-related features in both time and frequency domains, enhancing diagnostic performance, and interpreting the CNN's attention frequency along with the convolutional kernel's training outcomes. In this paper, three WBU functions are designed to construct the corresponding WBUNs, and their effectiveness and interpretability are verified through three sets of mechanical fault diagnosis experiments. Meanwhile, experimental results demonstrate the WBUConv layer's remarkable advantages in noise robustness, convergence speed, and strong generalization ability.