Defect Detection of Bolts through Machine Learning ofUltrasonic Testing Signals

The structural integrity of bolts in civil structures is critical to ensuring safety and operational efficiency. Traditional visual inspection methods often fail to detect internal defects of installed bolts, necessitating more advanced approaches. On the other hand, ultrasonic testing which c...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdul Azziz Abd Talib, Chun Yee Lim, Chin Kian Liew
Format: Article
Language:deu
Published: NDT.net 2025-03-01
Series:e-Journal of Nondestructive Testing
Online Access:https://www.ndt.net/search/docs.php3?id=30801
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The structural integrity of bolts in civil structures is critical to ensuring safety and operational efficiency. Traditional visual inspection methods often fail to detect internal defects of installed bolts, necessitating more advanced approaches. On the other hand, ultrasonic testing which can detect internal defects is not as straightforward to apply with signals difficult to analyse without the relevant certified non-destructive testing personnel qualifications and experience. This paper integrates machine learning to automate ultrasonic testing signal analysis in enhancing the reliability and precision of defect detection of bolts. A-scan signals were analysed to extract key features for machine learning models, with Gradient Boosting Classifier emerging as the optimal model, achieving an accuracy of 97% in defect classification. This methodology targets bolt defects such as thinning and corrosion, utilizing normalised signal features to distinguish severity of defects while enabling automated classification.
ISSN:1435-4934