The extraction of early fault features from time-series data is very crucial for convolutional neural networks (CNNs) in bearing fault diagnosis. To address this problem, a CNN framework based on identity mapping and Adam optimizer is presented for learning temporal dependencies and extracting fault features. The introduction of four identity mappings allows the deep layers to directly learn the data from the shallow layers, which alleviates the gradient disappearance problem caused by the increase of network depth. A new Adam optimizer with power-exponential learning rate is proposed to control the iteration direction and step size of CNN method, which solves the problems of local minima, overshoot or oscillation caused by the fixed values of the learning rates during the updating of network parameters. Compared to existed methods, the identification accuracy of the proposed method outperformed that of other methods for bearing fault diagnosis.
As scalar neurons of traditional neural networks promote dimension reduction caused by pooling, it is a difficult task to extract the high-dimensional spatial features and long-term correlation of pure signals from the noisy vibration signal. To address the above issues, a vibration signal denoising method based on the combination of a dilated self-attention capsule network and bidirectional long short memory network (DACapsNet–BiLSTM) is proposed to extract high-dimensional spatial features and learn long-term correlations between two adjacent time steps. An improved self-attention module with spatial feature extraction ability was constructed based on the random distribution of noise, which is embedded into the capsule network for the extracted spatial features and denoising. The dilated convolution is integrated into the improved capsule network to expand the receptive field to obtain the spatial features of the vibration signal. The output of the capsule network was used as the input of the bidirectional long-term and short-term memory network to obtain the timing characteristics of the vibration signal. Numerical experiments demonstrated that DACapsNet–BiLSTM performs better than other signal denoising methods, in terms of signal-to-noise ratio, mean square error, and mean absolute error metrics.
The condition of bearings has a significant impact on the healthy operation of mechanical equipment, which leads to a tremendous attention on fault diagnosis algorithms. However, due to the complex working environment and severe noise interference, training a robust bearing fault diagnosis model is considered to be a difficult task. To address this problem, a multiscale frequency division denoising network (MFDDN) model is proposed, where the frequency division denoising modules are presented to extract the detail fault features, and multiscale convolution neural network is employed to learn and enrich the overall fault features through two-scale convolution channels communication. The stacking convolution pooling layers are adopted to deepen the large-scale convolution channel and learn abundant global features. To remove the noise in the small-scale convolution channel, the frequency division denoising layers are constructed based on wavelet analysis to acquire the features of noise, where the input feature map is separated into high frequency and low-frequency features, and a sub-network based on attention mechanism is established for adaptive denoising. The superior features of MFDDN are the fusion of important fault features at each scale and custom learning of fine-grained features for the adaptive denoising, which improves the network feature extraction capability and noise robustness. This paper compares the performance of MFDDN with several common bearing fault diagnosis models on two benchmark bearing fault datasets. Extensive experiments show the state-of-the-art performance including robustness, generalization, and accuracy compared to the other methods under complex noise environment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.