PT-Informer: A Deep Learning Framework for Nuclear Steam Turbine Fault Diagnosis and Prediction
The health status of equipment is of paramount importance during the operation of nuclear power plants. The occurrence of faults not only leads to significant economic losses but also poses risks of casualties and even major accidents, with unimaginable consequences. This paper proposed a deep learn...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/11/8/846 |
| _version_ | 1797584020269170688 |
|---|---|
| author | Jiajing Zhou Zhao An Zhile Yang Yanhui Zhang Huanlin Chen Weihua Chen Yalin Luo Yuanjun Guo |
| author_facet | Jiajing Zhou Zhao An Zhile Yang Yanhui Zhang Huanlin Chen Weihua Chen Yalin Luo Yuanjun Guo |
| author_sort | Jiajing Zhou |
| collection | DOAJ |
| description | The health status of equipment is of paramount importance during the operation of nuclear power plants. The occurrence of faults not only leads to significant economic losses but also poses risks of casualties and even major accidents, with unimaginable consequences. This paper proposed a deep learning framework called PT-Informer for fault prediction, detection, and localization in order to address the challenges of online monitoring of the operating health of nuclear steam turbines. Unlike traditional approaches that involve separate design and execution of feature extraction for fault diagnosis, classification, and prediction, PT-Informer aims to extract fault features from the raw vibration signal and perform ultra-real-time fault prediction prior to their occurrence. Specifically, the encoding and decoding structure in PT-Informer ensures the capture of temporal dependencies between input features, enabling accurate time series prediction. Subsequently, the predicted data are utilized for fault detection using PCA in the PT-Informer framework, aiming to assess the likelihood of equipment failure in the near future. In the event of potential future failures, t-SNE is utilized to project high-dimensional data into a lower-dimensional space, facilitating the identification of clusters or groups associated with different fault types or operational conditions, thereby achieving precise fault localization. Experimental results on a nuclear steam turbine rotor demonstrate that PT-Informer outperformed the traditional GRU with a 4.94% improvement in R2 performance for prediction. Furthermore, compared to the conventional model, the proposed PT-Informer enhanced the fault classification accuracy of the nuclear steam turbine rotor from 97.4% to 99.6%. Various comparative experiments provide strong evidence for the effectiveness of PT-Informer framework in the diagnosis and prediction of nuclear steam turbine. |
| first_indexed | 2024-03-10T23:47:18Z |
| format | Article |
| id | doaj.art-3465328f0291474a9952f7f5d1062f6a |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-10T23:47:18Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-3465328f0291474a9952f7f5d1062f6a2023-11-19T01:57:31ZengMDPI AGMachines2075-17022023-08-0111884610.3390/machines11080846PT-Informer: A Deep Learning Framework for Nuclear Steam Turbine Fault Diagnosis and PredictionJiajing Zhou0Zhao An1Zhile Yang2Yanhui Zhang3Huanlin Chen4Weihua Chen5Yalin Luo6Yuanjun Guo7State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment, Shenzhen 518172, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaState Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment, Shenzhen 518172, ChinaState Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment, Shenzhen 518172, ChinaState Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment, Shenzhen 518172, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, ChinaThe health status of equipment is of paramount importance during the operation of nuclear power plants. The occurrence of faults not only leads to significant economic losses but also poses risks of casualties and even major accidents, with unimaginable consequences. This paper proposed a deep learning framework called PT-Informer for fault prediction, detection, and localization in order to address the challenges of online monitoring of the operating health of nuclear steam turbines. Unlike traditional approaches that involve separate design and execution of feature extraction for fault diagnosis, classification, and prediction, PT-Informer aims to extract fault features from the raw vibration signal and perform ultra-real-time fault prediction prior to their occurrence. Specifically, the encoding and decoding structure in PT-Informer ensures the capture of temporal dependencies between input features, enabling accurate time series prediction. Subsequently, the predicted data are utilized for fault detection using PCA in the PT-Informer framework, aiming to assess the likelihood of equipment failure in the near future. In the event of potential future failures, t-SNE is utilized to project high-dimensional data into a lower-dimensional space, facilitating the identification of clusters or groups associated with different fault types or operational conditions, thereby achieving precise fault localization. Experimental results on a nuclear steam turbine rotor demonstrate that PT-Informer outperformed the traditional GRU with a 4.94% improvement in R2 performance for prediction. Furthermore, compared to the conventional model, the proposed PT-Informer enhanced the fault classification accuracy of the nuclear steam turbine rotor from 97.4% to 99.6%. Various comparative experiments provide strong evidence for the effectiveness of PT-Informer framework in the diagnosis and prediction of nuclear steam turbine.https://www.mdpi.com/2075-1702/11/8/846fault diagnosisfault predictionPCAt-SNEdeep learningnuclear steam turbine |
| spellingShingle | Jiajing Zhou Zhao An Zhile Yang Yanhui Zhang Huanlin Chen Weihua Chen Yalin Luo Yuanjun Guo PT-Informer: A Deep Learning Framework for Nuclear Steam Turbine Fault Diagnosis and Prediction Machines fault diagnosis fault prediction PCA t-SNE deep learning nuclear steam turbine |
| title | PT-Informer: A Deep Learning Framework for Nuclear Steam Turbine Fault Diagnosis and Prediction |
| title_full | PT-Informer: A Deep Learning Framework for Nuclear Steam Turbine Fault Diagnosis and Prediction |
| title_fullStr | PT-Informer: A Deep Learning Framework for Nuclear Steam Turbine Fault Diagnosis and Prediction |
| title_full_unstemmed | PT-Informer: A Deep Learning Framework for Nuclear Steam Turbine Fault Diagnosis and Prediction |
| title_short | PT-Informer: A Deep Learning Framework for Nuclear Steam Turbine Fault Diagnosis and Prediction |
| title_sort | pt informer a deep learning framework for nuclear steam turbine fault diagnosis and prediction |
| topic | fault diagnosis fault prediction PCA t-SNE deep learning nuclear steam turbine |
| url | https://www.mdpi.com/2075-1702/11/8/846 |
| work_keys_str_mv | AT jiajingzhou ptinformeradeeplearningframeworkfornuclearsteamturbinefaultdiagnosisandprediction AT zhaoan ptinformeradeeplearningframeworkfornuclearsteamturbinefaultdiagnosisandprediction AT zhileyang ptinformeradeeplearningframeworkfornuclearsteamturbinefaultdiagnosisandprediction AT yanhuizhang ptinformeradeeplearningframeworkfornuclearsteamturbinefaultdiagnosisandprediction AT huanlinchen ptinformeradeeplearningframeworkfornuclearsteamturbinefaultdiagnosisandprediction AT weihuachen ptinformeradeeplearningframeworkfornuclearsteamturbinefaultdiagnosisandprediction AT yalinluo ptinformeradeeplearningframeworkfornuclearsteamturbinefaultdiagnosisandprediction AT yuanjunguo ptinformeradeeplearningframeworkfornuclearsteamturbinefaultdiagnosisandprediction |