Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak Detection
The aging of power plant pipelines has led to significant leaks worldwide, causing environmental damage, human safety risks, and economic losses. Rapid leak detection is critical for mitigating these issues, but challenges such as varying leak characteristics, ambient noise, and limited real-world d...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/490 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589248879919104 |
|---|---|
| author | Yujin Han Yourak Choi Jonghyuk Lee Ji-Hoon Bae |
| author_facet | Yujin Han Yourak Choi Jonghyuk Lee Ji-Hoon Bae |
| author_sort | Yujin Han |
| collection | DOAJ |
| description | The aging of power plant pipelines has led to significant leaks worldwide, causing environmental damage, human safety risks, and economic losses. Rapid leak detection is critical for mitigating these issues, but challenges such as varying leak characteristics, ambient noise, and limited real-world data complicate their accurate detection and model development. To address these issues, we propose a leak detection model that integrates stepwise transfer learning and an attention mechanism. The proposed model utilizes a two-stage deep learning process. In Stage 1, one-dimensional convolutional neural networks (1D CNNs) are pre-trained to extract root mean square (RMS) and frequency-domain features from acoustic signals. In Stage 2, the classifier layers of the pre-trained models are removed, and the extracted features are fused and processed using a bidirectional long short-term memory (LSTM) network. An attention mechanism is incorporated within the LSTM to prioritize critical features, enhancing the ability of the model to distinguish leak signals from noise. The model achieved an accuracy of 99.99%, significantly outperforming the traditional methods considered in this study. By effectively addressing noise interference and data scarcity, this robust approach demonstrates its potential to enhance safety, reduce risks, and improve cost efficiency in industrial pipelines and critical infrastructure. |
| format | Article |
| id | doaj-art-3d199a0fc0df4f38a7d707b877e46b03 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-3d199a0fc0df4f38a7d707b877e46b032025-01-24T13:19:33ZengMDPI AGApplied Sciences2076-34172025-01-0115249010.3390/app15020490Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak DetectionYujin Han0Yourak Choi1Jonghyuk Lee2Ji-Hoon Bae3Department of AI and Big Data Engineering, Daegu Catholic University, 13-13, Hayang-ro, Hayang-eup, Gyeongsan-si 38430, Republic of KoreaSmart Structural Safety & Prognosis Research Division, Korea Atomic Energy Research Institute (KAERI), 62, Gwahak-ro, Yuseong-gu, Daejeon 34142, Republic of KoreaDepartment of AI and Big Data Engineering, Daegu Catholic University, 13-13, Hayang-ro, Hayang-eup, Gyeongsan-si 38430, Republic of KoreaDepartment of Computer Education, Korea National University of Education, Cheongju-si 28173, Republic of KoreaThe aging of power plant pipelines has led to significant leaks worldwide, causing environmental damage, human safety risks, and economic losses. Rapid leak detection is critical for mitigating these issues, but challenges such as varying leak characteristics, ambient noise, and limited real-world data complicate their accurate detection and model development. To address these issues, we propose a leak detection model that integrates stepwise transfer learning and an attention mechanism. The proposed model utilizes a two-stage deep learning process. In Stage 1, one-dimensional convolutional neural networks (1D CNNs) are pre-trained to extract root mean square (RMS) and frequency-domain features from acoustic signals. In Stage 2, the classifier layers of the pre-trained models are removed, and the extracted features are fused and processed using a bidirectional long short-term memory (LSTM) network. An attention mechanism is incorporated within the LSTM to prioritize critical features, enhancing the ability of the model to distinguish leak signals from noise. The model achieved an accuracy of 99.99%, significantly outperforming the traditional methods considered in this study. By effectively addressing noise interference and data scarcity, this robust approach demonstrates its potential to enhance safety, reduce risks, and improve cost efficiency in industrial pipelines and critical infrastructure.https://www.mdpi.com/2076-3417/15/2/490pipeline leak detectionfeature fusiontransfer learningattention mechanismsdeep learning |
| spellingShingle | Yujin Han Yourak Choi Jonghyuk Lee Ji-Hoon Bae Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak Detection Applied Sciences pipeline leak detection feature fusion transfer learning attention mechanisms deep learning |
| title | Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak Detection |
| title_full | Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak Detection |
| title_fullStr | Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak Detection |
| title_full_unstemmed | Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak Detection |
| title_short | Feature Fusion Model Using Transfer Learning and Bidirectional Attention Mechanism for Plant Pipeline Leak Detection |
| title_sort | feature fusion model using transfer learning and bidirectional attention mechanism for plant pipeline leak detection |
| topic | pipeline leak detection feature fusion transfer learning attention mechanisms deep learning |
| url | https://www.mdpi.com/2076-3417/15/2/490 |
| work_keys_str_mv | AT yujinhan featurefusionmodelusingtransferlearningandbidirectionalattentionmechanismforplantpipelineleakdetection AT yourakchoi featurefusionmodelusingtransferlearningandbidirectionalattentionmechanismforplantpipelineleakdetection AT jonghyuklee featurefusionmodelusingtransferlearningandbidirectionalattentionmechanismforplantpipelineleakdetection AT jihoonbae featurefusionmodelusingtransferlearningandbidirectionalattentionmechanismforplantpipelineleakdetection |