Addressing imbalance of sample datasets in dissolved gas analysis by data augmentation: Generative adversarial networks

Li, Yuan; Xu, Yao-Yu; Li, Xinghui; Li, Rui; Lin, Jinshan; Zhang, Guanjun

doi:10.1049/gtd2.12610

Cited by 5 publications

(2 citation statements)

References 34 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through an adversarial process, the generator and discriminator continuously improve their abilities, with the generator trying to produce better false targets and the discriminator trying to more accurately differentiate between true and false targets. While GAN has been primarily used for image generation [30], it has also been applied to text data, as in research [31], where it was used to address the imbalance problem in a sample dataset for dissolved gas analysis through data augmentation.…”

Section: ) Neural Network Gas Recognition Classmentioning

confidence: 99%

A Research of Gas Open-Set Identification Based on Data Augmentation Algorithm

Zhu

Wang

2023

IEEE Access

View full text Add to dashboard Cite

Significant progress has been made in convolutional neural networks (CNN) based gas recognition. However, existing electronic nose (e-Nose) algorithms all use the closed-set assumption that the test and training samples are in the same label space and can only detect objects of known classes. However, in realistic scenarios, collecting data and training for every possible gas would waste much resource. Openset identification aims to actively reject samples from unknown classes by reducing the intra-class spacing and, thus, not misclassifying them as known classes. In this study, we propose a data preprocessing method to enhance the performance of closed-set recognition by augmenting the eigenvalues of each gas. We then implement the open-set recognition task for gases using an open-set recognition model. These methods contribute to improved recognition accuracy for gases and provide an effective means of handling unknown class samples. Experimental results show that our approach can identify unknown samples well while maintaining accuracy for available classes.

show abstract

Section: ) Neural Network Gas Recognition Classmentioning

confidence: 99%

A Research of Gas Open-Set Identification Based on Data Augmentation Algorithm

Zhu

Wang

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The most commonly used diagnostic method is Dissolved Gases Analysis (DGA) [1]. On this basis, many scholars have made a lot of improvements.…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of the transformer based on QPSO-SVM

Zhao

Guo

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In view of the shortcomings of traditional dissolved gas analysis technology low diagnostic veracity and low intelligence, this paper proposes to use QPSO to optimize the nuclear argument in the support vector machine (SVM), and on this basis, dissolved gas analysis (DGA) technology is used to diagnosis transformer faults. Firstly, the transformer data is preprocessed by DGA technology, and the processed data is used as the input amount of fault characteristics. Secondly, for the optimization of core parameters in SVM, the QPSO algorithm is combined with fault data for training and acquisition. Finally, five kinds of feature inputs are added to the model for training, and the trained multi-classification correlation vector machine is used to diagnose the test data. After case studies and comparative experimental analysis, the diagnostic accuracy of this method is as high as 94.74%, and relatively with SVM, PSO-SVM, and RVM methods, the accuracy is increased by 5.11%, 2.12%, and 2.12%, respectively.

show abstract

Transformer Failure Diagnosis based on VNWOA-MRVM

Zhou,

Liu,

et al. 2023

2023 3rd International Conference on Electrical Engineering and Control Science (IC2ECS)

View full text Add to dashboard Cite

Addressing imbalance of sample datasets in dissolved gas analysis by data augmentation: Generative adversarial networks

Cited by 5 publications

References 34 publications

A Research of Gas Open-Set Identification Based on Data Augmentation Algorithm

A Research of Gas Open-Set Identification Based on Data Augmentation Algorithm

Fault diagnosis of the transformer based on QPSO-SVM

Transformer Failure Diagnosis based on VNWOA-MRVM

Contact Info

Product

Resources

About