Improved Generative Adversarial Network for Rotating Component Fault Diagnosis in Scenarios With Extremely Limited Data

Miao, Jianguo; Wang, Jianyu; Zhang, Dingcheng; Miao, Qiang

doi:10.1109/tim.2021.3127636

Cited by 34 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method yielded positive outcomes for fault diagnosis with limited data. Miao et al [29] introduced an enhanced variational self-coding GAN-based data augmentation technique. This method generates diverse synthetic samples while maintaining high similarity.…”

Section: Introductionmentioning

confidence: 99%

Compound fault diagnosis of rolling bearings with few-shot based on DCGAN-RepLKNet

Zhu,

Fang

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

To guarantee the security of personnel on-site, diagnosing the malfunction of mechanical apparatus is imperative. The accomplishments within the domain of fault diagnosis have been partly attributed to the advancements in deep learning technology, which excels in feature extraction through extensive datasets. However, it is difficult to collect sufficient data to train high-precision fault diagnosis models in practice. To solve this problem, a novel method called DCGAN-RepLKNet is proposed to address the challenge of gathering enough data to train high-precision fault diagnosis models in practice. This technique involves transforming a one-dimensional time series vibration signal into a two-dimensional time-frequency map via wavelet transform technology. Subsequently, DCGAN expands the two-dimensional time-frequency map samples produced. Finally, RepLKNet is used to classify the fault samples. The proposed method has been verified in PU compound fault data set and bearing real damage data set. The results show that the accuracy of this method has been improved by 5.70%, 6.34%, 9.08%, and 16.35% compared to 2D-CNN under different sizes datasets in Case 1, and by 24.5% compared to 2D-CNN in Case 2.

show abstract

Section: Introductionmentioning

confidence: 99%

Compound fault diagnosis of rolling bearings with few-shot based on DCGAN-RepLKNet

Zhu,

Fang

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Dixit et al [28] proposed a novel conditional auxiliary classifier ACGAN framework combined with model agnostic meta-learning, which is validated by bearing and air compressor datasets. Miao et al [29] proposed an improved VAEGAN to complete the data augmentation task under the background of a few samples.…”

Section: Introductionmentioning

confidence: 99%

“…However, in the presence of extremely limited fault samples, the following problems still need to be addressed to further improve the diagnosis performance. (1) The inputs of generators applied in the GANs, as mentioned above, are mostly random noise or random noise with some labels, which fails to fully capture each training sample's information and make it hard to extract diverse and representative feature representation [24,27,29].…”

Section: Introductionmentioning

confidence: 99%

Data Augmentation and Intelligent Fault Diagnosis of Planetary Gearbox Using ILoFGAN Under Extremely Limited Samples

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Regarding the loss function, terms were incorporated to enforce the similarity of generated data to real data and the similarity of generated features to real features [47]. Moreover, researchers have employed sample similarity measures based on the Euclidean distance [48], Mahalanobis distance [48], and Pearson correlation coefficient (PCC) [49] to select high-quality generated data. However, it is important to note that current researches hava placed excessive emphasis on evaluating the quality of generated data solely in terms of their similarity to real data, often neglecting the importance of diversity in the generated data.…”

Section: Introductionmentioning

confidence: 99%

Generation of high-dimensional vibration signal and its application in fault diagnosis

Ren,

Gao,

Zhu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Imperfect data, such as data scarcity and imbalance, have a negative impact on intelligent fault diagnosis. Generative adversarial networks (GANs) have proven to be a potential method for augmenting data. However, the overall quality of data generated by GANs still requires improvement. In this study, a multiscale feature-fusion GAN was proposed for generating high-dimensional signals. A strategy that generates signals with dimensionality higher than the desired dimensionality was proposed. The generated signals were resampled to improve the phase diversity of the generated signals. To enhance the feature extraction capability of the GAN for high-dimensional signals, a multiscale feature extraction structure was designed. The integration of multiscale feature extraction and fusion was achieved without a significant increase in the computational burden. To enhance the amplitude diversity of the generated signals, a reconstruction network was designed that directly constrained the spatial distribution of the generated signals. Experimental results show that the model has advantages in terms of the similarity and diversity of the generated signals. The effectiveness of the model in fault diagnosis was verified using two motor datasets, where the fault diagnosis model using the sample set augmented by the proposed model obtained a 36.32% improvement in accuracy compared with using the original sample set. In addition, in comparison experiments, the model achieved a higher diagnostic accuracy improvement of 28.87% compared to four other published models.

show abstract

Improved Generative Adversarial Network for Rotating Component Fault Diagnosis in Scenarios With Extremely Limited Data

Cited by 34 publications

References 26 publications

Compound fault diagnosis of rolling bearings with few-shot based on DCGAN-RepLKNet

Compound fault diagnosis of rolling bearings with few-shot based on DCGAN-RepLKNet

Data Augmentation and Intelligent Fault Diagnosis of Planetary Gearbox Using ILoFGAN Under Extremely Limited Samples

Generation of high-dimensional vibration signal and its application in fault diagnosis

Contact Info

Product

Resources

About