Data-Enhanced Stacked Autoencoders for Insufficient Fault Classification of Machinery and its Understanding via Visualization

Han, Baokun; Wang, Xiaoyu; Ji, Shanshan; Zhang, Guowei; Jia, Sixiang; He, Jingtao

doi:10.1109/access.2020.2985769

Cited by 13 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To test the performance of proposed ESPDRN, three successful models are tested as comparison methods, namely conditional generative adversarial nets (CGAN) which is referenced to [6], DESAE which is referenced to [9] and ESPCN. It should be noted that the parameters set by the CGAN and DESAE are consistent with those in the [6] and [9], the model parameters of ESPCN are same as ESPDRN. In addition, the raw LR dataset and HR dataset are also added for comparison.…”

Section: Comparison Methodmentioning

confidence: 99%

“…Wang et al [8] proposed a domain adaptive efficient sub-pixel network to enhance spectral resolution, and the enhanced dataset is used to train the SAE discriminant network. Han et al [9] constructed an integrated data enhancement and fault identification system based on the encoder named data-enhanced stacked autoencoders (DESAE). Yu et al [10] utilized a three-stage semi-supervised learning approach based on data augmentation and metric learning to diagnosis the health conditions of bearings data under insufficient labeled.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent rotating machinery fault diagnosis based on super-resolution enhancement using data augmentation under large speed fluctuation

Wang¹,

Han²,

Lü³

et al. 2021

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

In the real production of industry, in order to solve the problem that it is usually difficult to obtain correctly labeled samples, data augmentation algorithms have received more and more attention. Many efficient deep learning models have been successfully applied to the intelligent fault diagnosis of rotating machinery. However, the premise of the above method is the working conditions of the machinery are constant. It is inevitable that the equipment runs under large speed fluctuation in real industries. To achieve data augmentation under the condition of variable speed, an efficient sub-pixel deep residual neural network (ESPDRN) is proposed. The ESPDRN framework is implemented as follows: utilize low resolution (LR) samples as input to the network, to effectively learn high-level and extract feature maps by constructing a deep residual network. Through sub-pixel convolution layers to arrange the LR features of multi-channels periodically and get a set of ultra high resolution features, and the data points are augmented 16 times compared to raw data. Statistical indicators and experimental results demonstrate that the proposed ESPDRN model can effectively generate data under the condition of variable speed.

show abstract

Section: Comparison Methodmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Intelligent rotating machinery fault diagnosis based on super-resolution enhancement using data augmentation under large speed fluctuation

Wang¹,

Han²,

Lü³

et al. 2021

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…SAE [22] is a deep neural network that is superimposed layer by layer of multiple pre-trained AE, that is, the hidden layer of the previous AE serves as the input of the next AE. According to this method, the AE is continuously stacked, and the deep feature extraction of the original signal is realized.…”

Section: A Dnn Based On Saementioning

confidence: 99%

A Novel Symmetric Stacked Autoencoder for Adversarial Domain Adaptation Under Variable Speed

et al. 2022

IEEE Access

View full text Add to dashboard Cite

At present, most of the fault diagnosis methods with extensive research and good diagnostic effect are based on the premise that the sample distribution is consistent. However, in reality, the sample distribution of rotating machinery is inconsistent due to variable working conditions, and most of the fault diagnosis algorithms have poor diagnostic effects or even invalid. To dispose the above problems, a novel symmetric stacked autoencoder (NSSAE) for adversarial domain adaptation is proposed. Firstly, the symmetric stacked autoencoder network with shared weights is used as the feature extractor to extract features which can better express the original signal. Secondly, adding domain discriminator that constituting adversarial with feature extractor to enhance the ability of feature extractor to extract domain invariant features, thus confusing the domain discriminator and making it unable to correctly distinguish the features of the two domains. Finally, to assist the adversarial training, the maximum mean discrepancy (MMD) is added to the last layer of the feature extractor to align the features of the two domains in the high-dimensional space. The experimental results show that, under the condition of variable speed, the NSSAE model can extract domain invariant features to achieve the transfer between domains, and the transfer diagnosis accuracy is high and the stability is strong.

show abstract

“…With the widely application in industry and academia of deep learning technology, it is possible to mine effective diagnosis knowledge from massive amounts of fault data [ 1 , 2 , 3 ]. Therefore, such methods have been extensively applied in fault diagnosis of rotating machinery [ 4 , 5 , 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

A Weighted Subdomain Adaptation Network for Partial Transfer Fault Diagnosis of Rotating Machinery

Jia

Wang

Zhang

et al. 2021

Entropy

Self Cite

View full text Add to dashboard Cite

Domain adaptation-based models for fault classification under variable working conditions have become a research focus in recent years. Previous domain adaptation approaches generally assume identical label spaces in the source and target domains, however, such an assumption may be no longer legitimate in a more realistic situation that requires adaptation from a larger and more diverse source domain to a smaller target domain with less number of fault classes. To address the above deficiencies, we propose a partial transfer fault diagnosis model based on a weighted subdomain adaptation network (WSAN) in this paper. Our method pays more attention to the local data distribution while aligning the global distribution. An auxiliary classifier is introduced to obtain the class-level weights of the source samples, so the network can avoid negative transfer caused by unique fault classes in the source domain. Furthermore, a weighted local maximum mean discrepancy (WLMMD) is proposed to capture the fine-grained transferable information and obtain sample-level weights. Finally, relevant distributions of domain-specific layer activations across different domains are aligned. Experimental results show that our method could assign appropriate weights to each source sample and realize efficient partial transfer fault diagnosis.

show abstract

Data-Enhanced Stacked Autoencoders for Insufficient Fault Classification of Machinery and its Understanding via Visualization

Cited by 13 publications

References 28 publications

Intelligent rotating machinery fault diagnosis based on super-resolution enhancement using data augmentation under large speed fluctuation

Intelligent rotating machinery fault diagnosis based on super-resolution enhancement using data augmentation under large speed fluctuation

A Novel Symmetric Stacked Autoencoder for Adversarial Domain Adaptation Under Variable Speed

A Weighted Subdomain Adaptation Network for Partial Transfer Fault Diagnosis of Rotating Machinery

Contact Info

Product

Resources

About