Bolt Loosening and Preload Loss Detection Technology Based on Machine Vision
Steel bridges often experience bolt loosening and even fatigue fracture due to fatigue load, forced vibration, and other factors during operation, affecting structural safety. This study proposes a high-precision bolt key point positioning and recognition method based on deep learning to address the...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/14/12/3897 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850050619329478656 |
|---|---|
| author | Zhiqiang Shang Xi Qin Zejun Zhang Hongtao Jiang |
| author_facet | Zhiqiang Shang Xi Qin Zejun Zhang Hongtao Jiang |
| author_sort | Zhiqiang Shang |
| collection | DOAJ |
| description | Steel bridges often experience bolt loosening and even fatigue fracture due to fatigue load, forced vibration, and other factors during operation, affecting structural safety. This study proposes a high-precision bolt key point positioning and recognition method based on deep learning to address the high cost, low efficiency, and poor safety of current bolt loosening identification methods. Additionally, a bolt loosening angle recognition method is proposed based on digital image processing technology. Using image recognition data, the angle-preload curve is revised. The established correlation between loosening angle and pretension for commonly utilized high-strength bolts provides a benchmark for identifying loosening angles. This finding lays a theoretical foundation for defining effective detection intervals in future bolt loosening recognition systems. Consequently, it enhances the system’s ability to deliver timely warnings, facilitating swift manual inspections and repairs. |
| format | Article |
| id | doaj-art-155be1ca96ff451ebb83a8db62b5885a |
| institution | DOAJ |
| issn | 2075-5309 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj-art-155be1ca96ff451ebb83a8db62b5885a2025-08-20T02:53:23ZengMDPI AGBuildings2075-53092024-12-011412389710.3390/buildings14123897Bolt Loosening and Preload Loss Detection Technology Based on Machine VisionZhiqiang Shang0Xi Qin1Zejun Zhang2Hongtao Jiang3Shandong Key Laboratory of Highway Technology and Safety Assessment, Jinan 250000, ChinaZhejiang Institute of Communications, Hangzhou 311112, ChinaShandong Key Laboratory of Highway Technology and Safety Assessment, Jinan 250000, ChinaShandong Key Laboratory of Highway Technology and Safety Assessment, Jinan 250000, ChinaSteel bridges often experience bolt loosening and even fatigue fracture due to fatigue load, forced vibration, and other factors during operation, affecting structural safety. This study proposes a high-precision bolt key point positioning and recognition method based on deep learning to address the high cost, low efficiency, and poor safety of current bolt loosening identification methods. Additionally, a bolt loosening angle recognition method is proposed based on digital image processing technology. Using image recognition data, the angle-preload curve is revised. The established correlation between loosening angle and pretension for commonly utilized high-strength bolts provides a benchmark for identifying loosening angles. This finding lays a theoretical foundation for defining effective detection intervals in future bolt loosening recognition systems. Consequently, it enhances the system’s ability to deliver timely warnings, facilitating swift manual inspections and repairs.https://www.mdpi.com/2075-5309/14/12/3897steel bridgeshigh-strength boltsdeep learningdigital image processingbolt loosening detection |
| spellingShingle | Zhiqiang Shang Xi Qin Zejun Zhang Hongtao Jiang Bolt Loosening and Preload Loss Detection Technology Based on Machine Vision Buildings steel bridges high-strength bolts deep learning digital image processing bolt loosening detection |
| title | Bolt Loosening and Preload Loss Detection Technology Based on Machine Vision |
| title_full | Bolt Loosening and Preload Loss Detection Technology Based on Machine Vision |
| title_fullStr | Bolt Loosening and Preload Loss Detection Technology Based on Machine Vision |
| title_full_unstemmed | Bolt Loosening and Preload Loss Detection Technology Based on Machine Vision |
| title_short | Bolt Loosening and Preload Loss Detection Technology Based on Machine Vision |
| title_sort | bolt loosening and preload loss detection technology based on machine vision |
| topic | steel bridges high-strength bolts deep learning digital image processing bolt loosening detection |
| url | https://www.mdpi.com/2075-5309/14/12/3897 |
| work_keys_str_mv | AT zhiqiangshang boltlooseningandpreloadlossdetectiontechnologybasedonmachinevision AT xiqin boltlooseningandpreloadlossdetectiontechnologybasedonmachinevision AT zejunzhang boltlooseningandpreloadlossdetectiontechnologybasedonmachinevision AT hongtaojiang boltlooseningandpreloadlossdetectiontechnologybasedonmachinevision |