Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizer
Applying an accurate parametric prediction model to identify abnormal or false pressurizer water levels (PWLs) is critical to the safe operation of marine pressurized water reactors (PWRs). Recently, deep-learning-based models have proved to be a powerful feature extractor to perform high-accuracy p...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-07-01
|
| Series: | Nuclear Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573319304218 |
| _version_ | 1819079249396498432 |
|---|---|
| author | Jin Zhang Xiaolong Wang Cheng Zhao Wei Bai Jun Shen Yang Li Zhisong Pan Yexin Duan |
| author_facet | Jin Zhang Xiaolong Wang Cheng Zhao Wei Bai Jun Shen Yang Li Zhisong Pan Yexin Duan |
| author_sort | Jin Zhang |
| collection | DOAJ |
| description | Applying an accurate parametric prediction model to identify abnormal or false pressurizer water levels (PWLs) is critical to the safe operation of marine pressurized water reactors (PWRs). Recently, deep-learning-based models have proved to be a powerful feature extractor to perform high-accuracy prediction. However, the effectiveness of models still suffers from two issues in PWL prediction: the correlations shifting over time between PWL and other feature parameters, and the example imbalance between fluctuation examples (minority) and stable examples (majority). To address these problems, we propose a cost-sensitive mechanism to facilitate the model to learn the feature representation of later examples and fluctuation examples. By weighting the standard mean square error loss with a cost-sensitive factor, we develop a Cost-Sensitive Long Short-Term Memory (CSLSTM) model to predict the PWL of PWRs. The overall performance of the CSLSTM is assessed by a variety of evaluation metrics with the experimental data collected from a marine PWR simulator. The comparisons with the Long Short-Term Memory (LSTM) model and the Support Vector Regression (SVR) model demonstrate the effectiveness of the CSLSTM. |
| first_indexed | 2024-12-21T19:25:59Z |
| format | Article |
| id | doaj.art-0c38ea4bc4764192b9694b0c80686a83 |
| institution | Directory Open Access Journal |
| issn | 1738-5733 |
| language | English |
| last_indexed | 2024-12-21T19:25:59Z |
| publishDate | 2020-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj.art-0c38ea4bc4764192b9694b0c80686a832022-12-21T18:52:49ZengElsevierNuclear Engineering and Technology1738-57332020-07-0152714291435Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizerJin Zhang0Xiaolong Wang1Cheng Zhao2Wei Bai3Jun Shen4Yang Li5Zhisong Pan6Yexin Duan7Command and Control Engineering College, Army Engineering University of PLA, Nanjing, 210000, China; Zhenjiang Campus, Army Military Transportation University of PLA, Zhenjiang, 212003, ChinaCollege of Nuclear Science and Technology, Naval University of Engineering, Wuhan, 430033, ChinaCommand and Control Engineering College, Army Engineering University of PLA, Nanjing, 210000, China; Anhui Provincial Key Laboratory of Network and Information Security, Anhui Normal University, Wuhu, 241000, ChinaCommand and Control Engineering College, Army Engineering University of PLA, Nanjing, 210000, ChinaZhenjiang Campus, Army Military Transportation University of PLA, Zhenjiang, 212003, ChinaCommand and Control Engineering College, Army Engineering University of PLA, Nanjing, 210000, ChinaCommand and Control Engineering College, Army Engineering University of PLA, Nanjing, 210000, China; Corresponding author.Zhenjiang Campus, Army Military Transportation University of PLA, Zhenjiang, 212003, China; Corresponding author.Applying an accurate parametric prediction model to identify abnormal or false pressurizer water levels (PWLs) is critical to the safe operation of marine pressurized water reactors (PWRs). Recently, deep-learning-based models have proved to be a powerful feature extractor to perform high-accuracy prediction. However, the effectiveness of models still suffers from two issues in PWL prediction: the correlations shifting over time between PWL and other feature parameters, and the example imbalance between fluctuation examples (minority) and stable examples (majority). To address these problems, we propose a cost-sensitive mechanism to facilitate the model to learn the feature representation of later examples and fluctuation examples. By weighting the standard mean square error loss with a cost-sensitive factor, we develop a Cost-Sensitive Long Short-Term Memory (CSLSTM) model to predict the PWL of PWRs. The overall performance of the CSLSTM is assessed by a variety of evaluation metrics with the experimental data collected from a marine PWR simulator. The comparisons with the Long Short-Term Memory (LSTM) model and the Support Vector Regression (SVR) model demonstrate the effectiveness of the CSLSTM.http://www.sciencedirect.com/science/article/pii/S1738573319304218LSTMParameter predictionCost sensitivePressurizerPressurized water reactorTime series |
| spellingShingle | Jin Zhang Xiaolong Wang Cheng Zhao Wei Bai Jun Shen Yang Li Zhisong Pan Yexin Duan Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizer Nuclear Engineering and Technology LSTM Parameter prediction Cost sensitive Pressurizer Pressurized water reactor Time series |
| title | Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizer |
| title_full | Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizer |
| title_fullStr | Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizer |
| title_full_unstemmed | Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizer |
| title_short | Application of cost-sensitive LSTM in water level prediction for nuclear reactor pressurizer |
| title_sort | application of cost sensitive lstm in water level prediction for nuclear reactor pressurizer |
| topic | LSTM Parameter prediction Cost sensitive Pressurizer Pressurized water reactor Time series |
| url | http://www.sciencedirect.com/science/article/pii/S1738573319304218 |
| work_keys_str_mv | AT jinzhang applicationofcostsensitivelstminwaterlevelpredictionfornuclearreactorpressurizer AT xiaolongwang applicationofcostsensitivelstminwaterlevelpredictionfornuclearreactorpressurizer AT chengzhao applicationofcostsensitivelstminwaterlevelpredictionfornuclearreactorpressurizer AT weibai applicationofcostsensitivelstminwaterlevelpredictionfornuclearreactorpressurizer AT junshen applicationofcostsensitivelstminwaterlevelpredictionfornuclearreactorpressurizer AT yangli applicationofcostsensitivelstminwaterlevelpredictionfornuclearreactorpressurizer AT zhisongpan applicationofcostsensitivelstminwaterlevelpredictionfornuclearreactorpressurizer AT yexinduan applicationofcostsensitivelstminwaterlevelpredictionfornuclearreactorpressurizer |