Deep-Learning and Dynamic Time Warping-Based Approaches for the Diagnosis of Reactor Systems
The degradation of clamping force in the core support barrel, which forms the internal structure of a nuclear power plant, has the potential to significantly impact the plant’s safety and reliability. Previous studies have concentrated on the detection of clamping force degradation but have been con...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/23/7865 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850060098723905536 |
|---|---|
| author | Hoejun Jeong Jihyun Kim Doyun Jung Jangwoo Kwon |
| author_facet | Hoejun Jeong Jihyun Kim Doyun Jung Jangwoo Kwon |
| author_sort | Hoejun Jeong |
| collection | DOAJ |
| description | The degradation of clamping force in the core support barrel, which forms the internal structure of a nuclear power plant, has the potential to significantly impact the plant’s safety and reliability. Previous studies have concentrated on the detection of clamping force degradation but have been constrained in their ability to identify the precise size and position. This study proposes a novel methodology for diagnosing the size and position of clamping force degradation in core support barrels, combining deep-learning techniques and dynamic time warping (DTW) algorithms. DTW is applied to the magnitude data of the ex-core neutron noise signal obtained in the frequency domain, thereby enabling the effective learning of changes in sensor data values. Moreover, autoencoder-based (AE-based) representation learning is utilized to extract features of the data, preventing overfitting and thus enhancing the robustness of the model. The experiment results demonstrate that the size and position of clamping force degradation can be accurately predicted. It is expected that this research will contribute to enhancing the precision and efficiency of internal structure monitoring in nuclear power plants. |
| format | Article |
| id | doaj-art-6d6968c0252d48838f4bbfdacc0f4bab |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-6d6968c0252d48838f4bbfdacc0f4bab2025-08-20T02:50:41ZengMDPI AGSensors1424-82202024-12-012423786510.3390/s24237865Deep-Learning and Dynamic Time Warping-Based Approaches for the Diagnosis of Reactor SystemsHoejun Jeong0Jihyun Kim1Doyun Jung2Jangwoo Kwon3Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of KoreaDepartment of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of KoreaKorea Atomic Energy Research Institute, 111 Daedeok-daero 989-gil, Yusenong-gu, Daejeon 34057, Republic of KoreaDepartment of Computer Engineering, Inha University, Incheon 22212, Republic of KoreaThe degradation of clamping force in the core support barrel, which forms the internal structure of a nuclear power plant, has the potential to significantly impact the plant’s safety and reliability. Previous studies have concentrated on the detection of clamping force degradation but have been constrained in their ability to identify the precise size and position. This study proposes a novel methodology for diagnosing the size and position of clamping force degradation in core support barrels, combining deep-learning techniques and dynamic time warping (DTW) algorithms. DTW is applied to the magnitude data of the ex-core neutron noise signal obtained in the frequency domain, thereby enabling the effective learning of changes in sensor data values. Moreover, autoencoder-based (AE-based) representation learning is utilized to extract features of the data, preventing overfitting and thus enhancing the robustness of the model. The experiment results demonstrate that the size and position of clamping force degradation can be accurately predicted. It is expected that this research will contribute to enhancing the precision and efficiency of internal structure monitoring in nuclear power plants.https://www.mdpi.com/1424-8220/24/23/7865deep learningdynamic time warpingfault monitoringfault diagnosisreactor internals |
| spellingShingle | Hoejun Jeong Jihyun Kim Doyun Jung Jangwoo Kwon Deep-Learning and Dynamic Time Warping-Based Approaches for the Diagnosis of Reactor Systems Sensors deep learning dynamic time warping fault monitoring fault diagnosis reactor internals |
| title | Deep-Learning and Dynamic Time Warping-Based Approaches for the Diagnosis of Reactor Systems |
| title_full | Deep-Learning and Dynamic Time Warping-Based Approaches for the Diagnosis of Reactor Systems |
| title_fullStr | Deep-Learning and Dynamic Time Warping-Based Approaches for the Diagnosis of Reactor Systems |
| title_full_unstemmed | Deep-Learning and Dynamic Time Warping-Based Approaches for the Diagnosis of Reactor Systems |
| title_short | Deep-Learning and Dynamic Time Warping-Based Approaches for the Diagnosis of Reactor Systems |
| title_sort | deep learning and dynamic time warping based approaches for the diagnosis of reactor systems |
| topic | deep learning dynamic time warping fault monitoring fault diagnosis reactor internals |
| url | https://www.mdpi.com/1424-8220/24/23/7865 |
| work_keys_str_mv | AT hoejunjeong deeplearninganddynamictimewarpingbasedapproachesforthediagnosisofreactorsystems AT jihyunkim deeplearninganddynamictimewarpingbasedapproachesforthediagnosisofreactorsystems AT doyunjung deeplearninganddynamictimewarpingbasedapproachesforthediagnosisofreactorsystems AT jangwookwon deeplearninganddynamictimewarpingbasedapproachesforthediagnosisofreactorsystems |