A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning
Traditional impedance-based bolt-looseness monitoring approaches using hand-crafted impedance features can lead to difficulties in quantitative damage severity estimation. In this study, a novel method for bolt-looseness assessment with automated impedance feature extraction is developed based on th...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-04-01
|
| Series: | Developments in the Built Environment |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666165923000042 |
| _version_ | 1797820600694079488 |
|---|---|
| author | Thanh-Truong Nguyen Quoc-Bao Ta Duc-Duy Ho Jeong-Tae Kim Thanh-Canh Huynh |
| author_facet | Thanh-Truong Nguyen Quoc-Bao Ta Duc-Duy Ho Jeong-Tae Kim Thanh-Canh Huynh |
| author_sort | Thanh-Truong Nguyen |
| collection | DOAJ |
| description | Traditional impedance-based bolt-looseness monitoring approaches using hand-crafted impedance features can lead to difficulties in quantitative damage severity estimation. In this study, a novel method for bolt-looseness assessment with automated impedance feature extraction is developed based on the integration of the impedance-based technique and deep learning algorithm. 1D CNN (1-dimensional convolutional neural network) – based bolt-looseness estimation models are designed to automatically extract and learn optimal features from raw impedance signals. The experimental verification shows that the proposed method can identify the location of loosened bolts and estimate loosening degree in a girder connection with high accuracy. The best training and testing errors of the 1D CNN-based looseness prediction are 0.063 and 0.081, respectively. The proposed method does not require pre-processing impedance signals and selecting proper frequency bands, so it has great potential for real-time bolt-looseness detection applications. |
| first_indexed | 2024-03-13T09:40:42Z |
| format | Article |
| id | doaj.art-a4a5e77a197d4f1f862fee6bf203e238 |
| institution | Directory Open Access Journal |
| issn | 2666-1659 |
| language | English |
| last_indexed | 2024-03-13T09:40:42Z |
| publishDate | 2023-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Developments in the Built Environment |
| spelling | doaj.art-a4a5e77a197d4f1f862fee6bf203e2382023-05-25T04:25:07ZengElsevierDevelopments in the Built Environment2666-16592023-04-0114100122A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learningThanh-Truong Nguyen0Quoc-Bao Ta1Duc-Duy Ho2Jeong-Tae Kim3Thanh-Canh Huynh4Industrial Maintenance Training Center, Ho Chi Minh City University of Technology (HCMUT), VNU-HCM, Ho Chi Minh City, Viet NamDepartment of Ocean Engineering, Pukyong National University, Busan, 48513, South KoreaFaculty of Civil Engineering, Ho Chi Minh City University of Technology (HCMUT), VNU-HCM, Ho Chi Minh City, Viet NamDepartment of Ocean Engineering, Pukyong National University, Busan, 48513, South KoreaInstitute of Research and Development, Duy Tan University, Da Nang, 550000, Viet Nam; Corresponding author. Institute of Research and Development, Duy Tan University, Danang, 550000, Viet Nam.Traditional impedance-based bolt-looseness monitoring approaches using hand-crafted impedance features can lead to difficulties in quantitative damage severity estimation. In this study, a novel method for bolt-looseness assessment with automated impedance feature extraction is developed based on the integration of the impedance-based technique and deep learning algorithm. 1D CNN (1-dimensional convolutional neural network) – based bolt-looseness estimation models are designed to automatically extract and learn optimal features from raw impedance signals. The experimental verification shows that the proposed method can identify the location of loosened bolts and estimate loosening degree in a girder connection with high accuracy. The best training and testing errors of the 1D CNN-based looseness prediction are 0.063 and 0.081, respectively. The proposed method does not require pre-processing impedance signals and selecting proper frequency bands, so it has great potential for real-time bolt-looseness detection applications.http://www.sciencedirect.com/science/article/pii/S2666165923000042Impedance techniqueDeep learning1D CNNBolt-loosenessLooseness severityBolted connection |
| spellingShingle | Thanh-Truong Nguyen Quoc-Bao Ta Duc-Duy Ho Jeong-Tae Kim Thanh-Canh Huynh A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning Developments in the Built Environment Impedance technique Deep learning 1D CNN Bolt-looseness Looseness severity Bolted connection |
| title | A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning |
| title_full | A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning |
| title_fullStr | A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning |
| title_full_unstemmed | A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning |
| title_short | A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning |
| title_sort | method for automated bolt loosening monitoring and assessment using impedance technique and deep learning |
| topic | Impedance technique Deep learning 1D CNN Bolt-looseness Looseness severity Bolted connection |
| url | http://www.sciencedirect.com/science/article/pii/S2666165923000042 |
| work_keys_str_mv | AT thanhtruongnguyen amethodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning AT quocbaota amethodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning AT ducduyho amethodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning AT jeongtaekim amethodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning AT thanhcanhhuynh amethodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning AT thanhtruongnguyen methodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning AT quocbaota methodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning AT ducduyho methodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning AT jeongtaekim methodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning AT thanhcanhhuynh methodforautomatedboltlooseningmonitoringandassessmentusingimpedancetechniqueanddeeplearning |