ANALYSIS OF CHARACTERISTICS FOR DIAGNOSING AXIAL FORCE OF HIGH-STRENGTH BOLTS

• TSUJI Yoshiki

  関西大学大学院 総合情報学科

• HIROKANE Michiyuki

  関西大学 総合情報学部

• HAYASHI Isao

  関西大学 総合情報学部

• KONISHI Hideyuki

  日本橋梁株式会社

Bibliographic Information

Other Title

• 高力ボルトの軸力診断のための振動波形データにおける特徴量の検討

Abstract

 Currently, the bridges which were built in period of high economic growth are accounting for about 40% of all bridges and the deterioration of the high-strength bolts has become the important problem. The impact acoustics method is one of the diagnosis methods of the axial force. The impact acoustics method is low risk, low cost and easily work. However, the impact acoustics method that rely on the experience and intuition of a skilled technician has problems such as lack of skilled technician, establishment of a method that can accurately efficiently diagnosed in unskilled technician is required.<br> In this study, we hit a high-strength bolt with a hammer, to obtain the frequency data from the waveform data of impact vibration. Moreover, we obtain attenuation rate from the original sound waveform data. To diagnose the axial force of the high-strength bolts by using the Machine learning, and compared the recognition accuracy.

Journal

• Journal of Japan Society of Civil Engineers, Ser. F6 (Safety Problem)

  Journal of Japan Society of Civil Engineers, Ser. F6 (Safety Problem) 72 (2), I_177-I_182, 2016

  Japan Society of Civil Engineers

Keywords

• high-strength bolt
• axial force
• pattern recognition
• FFT
• Neural Network
• attenuation rate

Details

• CRID: 1390001205354615040
• NII Article ID: 130005243660
• DOI: 10.2208/jscejsp.72.i_177
• ISSN: 21856621
• Web Site: https://www.jstage.jst.go.jp/article/jscejsp/72/2/72_I_177/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed