Multilocation and Multiscale Learning Framework with Skip Connection for Fault Diagnosis of Bearing under Complex Working Conditions

Ban, H.; Wang, Dazhi; Wang, Sihan; Liu, Ziming

doi:10.3390/s21093226

Cited by 2 publications

(1 citation statement)

References 40 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the bidirectional long short-term memory (BiLSTM) introduces the "gate" unit controlled. BiLSTM can extract deeper features through bidirectional training [27]. This research uses the advantages of the above two deep neural networks (CNN and BiLSTM), which facilitate the identification and assessment the performance degradation of bearing.…”

Section: Introductionmentioning

confidence: 99%

Rolling bearing performance degradation assessment based on singular value decomposition-sliding window linear regression and improved deep learning network in noisy environment

Dong¹,

Li²,

Zhu³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

It is difficult to evaluate the degradation performance and the degradation state of the rolling bearing in noisy environment. A new method is proposed to solve the problem based on singular value decomposition (SVD)-sliding window linear regression and ResNeXt - multi-attention mechanism's deep neural network (RMADNN). Firstly, the root mean square(RMS) gradient value is calculated on the basis of RMS based on SVD and linear regression of sliding window, which is used as the rolling bearing performance degradation indicator in noisy environment. Secondly, the degradation state of rolling bearing is divided by the RMS gradient. Thirdly, for the part of the deep learning network model, the soft attention mechanism is introduced into the bidirectional long short-term memory network (BiLSTM) to extract more important and deep fault features. At the same time, the ResNeXt layer is added into the convolutional neural network (CNN) to extract more fault features and merge them through multi-scale grouped convolution. Then, the hybrid domain attention mechanism (HDAM) was introduced after the ResNext layer. The HDAM can screen out more important features from the output features of the ResNext in the two dimensions of channel and spatial. Therefore, the improved deep learning network of the ResNeXt - multi-attention mechanism's deep neural network (RMADNN) in this research is established. Finally, the labeled data set is input into the improved model for training, and the Softmax classifier is used to identify the life decline state of the rolling bearing. The result shows that the indicator of RMS gradient proposed has a better characterization, and the RMADNN model can distinguish the life degradation state of rolling bearing better.

show abstract

Section: Introductionmentioning

confidence: 99%

Rolling bearing performance degradation assessment based on singular value decomposition-sliding window linear regression and improved deep learning network in noisy environment

Dong¹,

Li²,

Zhu³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Deep Subdomain Transfer Learning with Spatial Attention ConvLSTM Network for Fault Diagnosis of Wheelset Bearing in High-Speed Trains

et al. 2023

View full text Add to dashboard Cite

High-speed trains operate under varying conditions, leading to different distributions of vibration data collected from the wheel bearings. To detect bearing faults in situations where the source and target domains exhibit differing data distributions, the technique of transfer learning can be applied to move the distribution of features gleaned from unlabeled data in the source domain. However, traditional deep transfer learning techniques do not take into account the relationships between subdomains within the same class of different domains, resulting in suboptimal transfer learning performance and limiting the use of intelligent fault diagnosis for wheel bearings under various conditions. In order to tackle this problem, we have developed the Deep Subdomain Transfer Learning Network (DSTLN). This innovative approach transfers the distribution of features by harmonizing the subdomain distributions of layer activations specific to each domain through the implementation of the Local Maximum Mean Discrepancy (LMMD) method. The DSTLN consists of three modules: a feature extractor, fault category recognition, and domain adaptation. The feature extractor is constructed using a newly proposed SA-ConvLSTM model and CNNs, which aim to automatically learn features. The fault category recognition module is a classifier that categorizes the samples based on the extracted features. The domain adaptation module includes an adversarial domain classifier and subdomain distribution discrepancy metrics, making the learned features domain-invariant across both the global domain and subdomains. Through 210 transfer fault diagnosis experiments with wheel bearing data under 15 different operating conditions, the proposed method demonstrates its effectiveness.

show abstract

Multilocation and Multiscale Learning Framework with Skip Connection for Fault Diagnosis of Bearing under Complex Working Conditions

Cited by 2 publications

References 40 publications

Rolling bearing performance degradation assessment based on singular value decomposition-sliding window linear regression and improved deep learning network in noisy environment

Rolling bearing performance degradation assessment based on singular value decomposition-sliding window linear regression and improved deep learning network in noisy environment

Deep Subdomain Transfer Learning with Spatial Attention ConvLSTM Network for Fault Diagnosis of Wheelset Bearing in High-Speed Trains

Contact Info

Product

Resources

About