0
  • DE
  • EN
  • FR
  • International Database and Gallery of Structures

Advertisement

Proposal of ultrasonic bolt axial force evaluation method using machine learning and signal processing

 Proposal of ultrasonic bolt axial force evaluation method using machine learning and signal processing
Author(s): , , , ,
Presented at IABSE Symposium: Challenges for Existing and Oncoming Structures, Prague, Czech Republic, 25-27 May 2022, published in , pp. 1140-1147
DOI: 10.2749/prague.2022.1140
Price: € 25.00 incl. VAT for PDF document  
ADD TO CART
Download preview file (PDF) 0.13 MB

It has been confirmed that bolt axial force of high-strength bolted joints decreases due to various effects. Generally, evaluating the bolt axial force of existing bolts has been an important issue...
Read more

Bibliographic Details

Author(s): (Tokyo Institute of Technology, Tokyo, JAPAN)
(Tokyo Institute of Technology, Tokyo, JAPAN)
(Tokyo Institute of Technology, Tokyo, JAPAN)
(Tokyo Institute of Technology, Tokyo, JAPAN)
(University of Fukui, Fukui, JAPAN)
(University of Fukui, Fukui, JAPAN)
Medium: conference paper
Language(s): English
Conference: IABSE Symposium: Challenges for Existing and Oncoming Structures, Prague, Czech Republic, 25-27 May 2022
Published in:
Page(s): 1140-1147 Total no. of pages: 8
Page(s): 1140-1147
Total no. of pages: 8
DOI: 10.2749/prague.2022.1140
Abstract:

It has been confirmed that bolt axial force of high-strength bolted joints decreases due to various effects. Generally, evaluating the bolt axial force of existing bolts has been an important issue. In a conventional ultrasonic bolt axial force evaluation method, bolt length change due to the change of bolt axial force is evaluated. However, bolt length can include uncertainty due to manufacturing errors. Hence, in this study, attention was paid to the deformed shape of the bolt head, which has a little dependency on the bolt length, and application of signal processing and machine learning was attempted. It was shown that the waveform data obtained from the bolt head by ultrasonic testing included characteristic signals indicating the bolt axial force. The target characteristic signal was detected by the parasitic discrete wavelet transform (P-DWT). A highly accurate bolt axial force evaluation method was proposed by applying machine learning to characteristic signals.

Keywords:
machine learning Wavelet transform Ultrasonic test bolt axial force initial time zone
Copyright: © 2022 International Association for Bridge and Structural Engineering (IABSE)
License:

This creative work is copyrighted material and may not be used without explicit approval by the author and/or copyright owner.