A novel model with the ability of few-shot learning and quick updating for intelligent fault diagnosis

Ren, Zhijun; Zhu, Yongjian; Yan, Ke; Chen, Kaida; Kang, Wei; Yue, Yi; Gao, Dawei

doi:10.1016/j.ymssp.2019.106608

Cited by 101 publications

(36 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recall Precision FAM Original GAN [12] 0.4973 0.6873 0.7297 MixtureGAN (ours) 0.8902 0.9427 0.9064 CaAE [40] 0.8641 0.8873 0.8619 RJAAN [27] 0.8814 0.9106 0.8653 B-SMOTE [9] 0.8452 0.6470 0.6941 EMICIL [20] 0.7723 0.9275 0.8799 EWMOTE [35] 0.7691 0.9138 0.8827 WSMOTE [36] 0.8502 0.9336 0.8993 • IMS bearing dataset 6 , is a well-known data which is provided by the Center for Intelligent Maintenance Systems (IMS), University of Cincinnati, and generated from the Prognostics Data Repository of NASA. Two different test-to-failure experiments are conducted as to achieve following datasets: outer race fault (S1 data) and ball fault (S2 data).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis

Zareapoor

Shamsolmoali

Yang

2020

Preprint

View full text Add to dashboard Cite

The collected data from industrial machines are often imbalanced, which poses a negative effect on learning algorithms. However, this problem becomes more challenging for a mixed type of data or while there is overlapping between classes. Class-imbalance problem requires a robust learning system which can timely predict and classify the data. We propose a new adversarial network for simultaneous classification and fault detection. In particular, we restore the balance in the imbalanced dataset by generating faulty samples from the proposed mixture of data distribution. We designed the discriminator of our model to handle the generated faulty samples to prevent outlier and overfitting. We empirically demonstrate that; (i) the discriminator trained with a generator to generates samples from a mixture of normal and faulty data distribution which can be considered as a fault detector; (ii), the quality of the generated faulty samples outperforms the other synthetic resampling techniques. Experimental results show that the proposed model performs well when comparing to other fault diagnosis methods across several evaluation metrics; in particular, coalescing of generative adversarial network (GAN) and feature matching function is effective at recognizing faulty samples.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Recall Precision FAM Original GAN [12] 0.6733 0.7859 0.6983 MixtureGAN (ours) 0.8531 0.8946 0.8730 CaAE [40] 0.8016 0.8236 0.8253 RJAAN [27] 0.8375 0.8514 0.8432 B-SMOTE [9] 0.8531 0.8946 0.8730 EMICIL [20] 0.8305 0.8426 0.8342 EWMOTE [35] 0.8609 0.8527 0.8667 WSMOTE [36] 0.8436 0.8709 0.8561 anced accuracy which is defined in [36] as:…”

Section: Methodsmentioning

confidence: 99%

Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis

Zareapoor

Shamsolmoali

Yang

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Forintelligent faultdiagnosis, Capsule Autoencoder (Ren et al, 2020) (CaAE) has been proposed to resolve theproblems of traditional and modern intelligent fault diagnosis:the need of a large set of samples of faults and the need of diagnosis models to possess the ability of quick updating. The ability of CaAE to extract and fuse featuresreduces the dependence on the number of samples and training time, whichmakesCaAE suitable for fewshot learning without overfitting.…”

Section: Implementationsmentioning

confidence: 99%

From Auto-encoders to Capsule Networks: A Survey

Alaoui-Elfels

Gadi

2021

E3S Web Conf.

View full text Add to dashboard Cite

Convolutional Neural Networks are a very powerful Deep Learning structure used in image processing, object classification and segmentation. They are very robust in extracting features from data and largely used in several domains. Nonetheless, they require a large number of training datasets and relations between features get lost in the Max-pooling step, which can lead to a wrong classification. Capsule Networks(CapsNets) were introduced to overcome these limitations by extracting features and their pose using capsules instead of neurons. This technique shows an impressive performance in one-dimensional, two-dimensional and three-dimensional datasets as well as in sparse datasets. In this paper, we present an initial understanding of CapsNets, their concept, structure and learning algorithm. We introduce the progress made by CapsNets from their introduction in 2011 until 2020. We compare different CapsNets series architectures to demonstrate strengths and challenges. Finally, we quote different implementations of Capsule Networks and show their robustness in a variety of domains. This survey provides the state-of-theartof Capsule Networks and allows other researchers to get a clear view of this new field. Besides, we discuss the open issues and the promising directions of future research, which may lead to a new generation of CapsNets.

show abstract

“…Furthermore, the model needs a large dataset for training. This issue could be addressed by few-shot learning (Ren et al, 2020).…”

Section: Implementationsmentioning

confidence: 99%

“…For intelligent fault diagnosis, Capsule Autoencoder (Ren et al, 2020) (CaAE) has been proposed to resolve the problems of traditional and modern intelligent fault diagnosis: the need for a large set of samples of faults and the need for diagnosis models to possess the ability of quick updating. The ability of CaAE to extract and fuse features reduces the dependence on the number of samples and training time, which makes CaAE suitable for few-shot learning without overfitting.…”

Section: Implementationsmentioning

confidence: 99%

From Auto-encoders to Capsule Networks: A Survey

Alaoui-Elfels

Gadi

2021

E3S Web Conf.

View full text Add to dashboard Cite

Convolutional Neural Networks are a very powerful Deep Learning algorithm used in image processing, object classification and segmentation. They are very robust in extracting features from data and largely used in several domains. Nonetheless, they require a large number of training datasets and relations between features get lost in the Max-pooling step, which can lead to a wrong classification. Capsule Networks (CapsNets) were introduced to overcome these limitations by extracting features and their pose using capsules instead of neurons. This technique shows an impressive performance in one-dimensional, two-dimensional and three-dimensional datasets as well as in sparse datasets. In this paper, we present an initial understanding of CapsNets, their concept, structure and learning algorithm. We introduce the progress made by CapsNets from their introduction in 2011 until 2020. We compare different CapsNets series to demonstrate strengths and challenges. Finally, we quote different implementations of Capsule Networks and show their robustness in a variety of domains. This survey provides the state-of-the-art of Capsule Networks and allows other researchers to get a clear view of this new field. Besides, we discuss the open issues and the promising directions of future research, which may lead to a new generation of CapsNets.

show abstract

A novel model with the ability of few-shot learning and quick updating for intelligent fault diagnosis

Cited by 101 publications

References 38 publications

Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis

Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis

From Auto-encoders to Capsule Networks: A Survey

From Auto-encoders to Capsule Networks: A Survey

Contact Info

Product

Resources

About