A Piezoelectric Impedance-based Structural Fault Detection by Using Transformer

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Electromechanical impedance based (EMI) method is a nondestructive method for detecting structural faults, and the frequency response curve of EMI can effectively show the fault condition of the structure. Transformer neural network has achieved good results in natural language and other fields since it was proposed. In this paper, we simulate different fault states of cantilever beam by changing different bolt loosening and tightening states, and use EMI method to measure the amplitude frequency response curves under different fault conditions, and then use the encoder module of Transformer network and softmax to classify the amplitude data after filtering the response signal. The results show that Transformer network can efficiently classify different fault cases of cantilever beam bolts.

Original languageEnglish
Title of host publication2022 International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665492812
DOIs
StatePublished - 2022
Externally publishedYes
Event3rd International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022 - Harbin, China
Duration: 22 Dec 202224 Dec 2022

Publication series

Name2022 International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022 - Proceedings

Conference

Conference3rd International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022
Country/TerritoryChina
CityHarbin
Period22/12/2224/12/22

Keywords

  • fault detection
  • impedance-based method
  • transformer neural network

Fingerprint

Dive into the research topics of 'A Piezoelectric Impedance-based Structural Fault Detection by Using Transformer'. Together they form a unique fingerprint.

Cite this