Open AccessUltrasonic Guided Wave Damage Detection Method for Stiffened Plates Based on Deep Learning
Author(s) -
Qing Shen,
Shengyao Yue,
Wei Lu,
Guidong Xu,
Chunming Xu,
Bo Xu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1894/1/012069
Subject(s) - convolutional neural network , ultrasonic sensor , finite element method , wavelet , wavelet transform , computer science , artificial neural network , matrix (chemical analysis) , acoustics , structural engineering , artificial intelligence , materials science , engineering , physics , composite material
In order to solve the problem of debonding damage detection commonly exists in stiffened plates, we propose an ultrasonic guided wave damage detection method based on deep learning and conduct a numerical study of the method. The guided wave signal get from a Finite-Element-Model (FEM) is pre-processed through wavelet transform to obtain the wavelet coefficient matrix (WCM), which is input into Convolutional Neural Network (CNN) in the form of gray image to obtain the neural weights. The detection accuracy of debonding damage in the stiffened plate has reached nearly 99%.