Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network
Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-drive...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | Nuclear Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573323001092 |
| _version_ | 1827932999200538624 |
|---|---|
| author | Zhichao Wang Hong Xia Jiyu Zhang Bo Yang Wenzhe Yin |
| author_facet | Zhichao Wang Hong Xia Jiyu Zhang Bo Yang Wenzhe Yin |
| author_sort | Zhichao Wang |
| collection | DOAJ |
| description | Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs. |
| first_indexed | 2024-03-13T07:18:29Z |
| format | Article |
| id | doaj.art-d1e2730be52c43ea95a8993faf803340 |
| institution | Directory Open Access Journal |
| issn | 1738-5733 |
| language | English |
| last_indexed | 2024-03-13T07:18:29Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj.art-d1e2730be52c43ea95a8993faf8033402023-06-05T04:12:41ZengElsevierNuclear Engineering and Technology1738-57332023-06-0155620962106Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial networkZhichao Wang0Hong Xia1Jiyu Zhang2Bo Yang3Wenzhe Yin4Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University, Harbin, 150001, ChinaCorresponding author.; Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University, Harbin, 150001, ChinaFundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University, Harbin, 150001, ChinaFundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University, Harbin, 150001, ChinaFundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University, Harbin, 150001, ChinaRotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs.http://www.sciencedirect.com/science/article/pii/S1738573323001092Nuclear power plantImbalanced sample fault diagnosisDeep convolutional neural networkConditional generative adversarial networkRotating machinery |
| spellingShingle | Zhichao Wang Hong Xia Jiyu Zhang Bo Yang Wenzhe Yin Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network Nuclear Engineering and Technology Nuclear power plant Imbalanced sample fault diagnosis Deep convolutional neural network Conditional generative adversarial network Rotating machinery |
| title | Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network |
| title_full | Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network |
| title_fullStr | Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network |
| title_full_unstemmed | Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network |
| title_short | Imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network |
| title_sort | imbalanced sample fault diagnosis method for rotating machinery in nuclear power plants based on deep convolutional conditional generative adversarial network |
| topic | Nuclear power plant Imbalanced sample fault diagnosis Deep convolutional neural network Conditional generative adversarial network Rotating machinery |
| url | http://www.sciencedirect.com/science/article/pii/S1738573323001092 |
| work_keys_str_mv | AT zhichaowang imbalancedsamplefaultdiagnosismethodforrotatingmachineryinnuclearpowerplantsbasedondeepconvolutionalconditionalgenerativeadversarialnetwork AT hongxia imbalancedsamplefaultdiagnosismethodforrotatingmachineryinnuclearpowerplantsbasedondeepconvolutionalconditionalgenerativeadversarialnetwork AT jiyuzhang imbalancedsamplefaultdiagnosismethodforrotatingmachineryinnuclearpowerplantsbasedondeepconvolutionalconditionalgenerativeadversarialnetwork AT boyang imbalancedsamplefaultdiagnosismethodforrotatingmachineryinnuclearpowerplantsbasedondeepconvolutionalconditionalgenerativeadversarialnetwork AT wenzheyin imbalancedsamplefaultdiagnosismethodforrotatingmachineryinnuclearpowerplantsbasedondeepconvolutionalconditionalgenerativeadversarialnetwork |