Crack Profile Reconstruction from Eddy Current Signals with an Encoder-Decoder Convolutional Neural Network

2019 ◽  
Author(s):  
Shaohua Li ◽  
Ayesha Anees ◽  
Yu Zhong ◽  
Zaifeng Yang ◽  
Yong Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Eddy Current ◽  
Profile Reconstruction ◽  
Crack Profile

scholarly journals Defect Image Recognition and Classification for Eddy Current Testing of Titanium Plate Based on Convolutional Neural Network

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Weiquan Deng ◽  
Jun Bao ◽  
Bo Ye
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Recognition ◽  
Eddy Current ◽  
Structural Characteristics ◽  
Eddy Current Testing ◽  
Production Environment ◽  
Titanium Plate ◽  
Noise Interference ◽  
Current Testing

In the actual production environment, the eddy current imaging inspection of titanium plate defects is prone to scan shift, scale distortion, and noise interference in varying degrees, which leads to the defect false detection and even missed inspection. In view of this problem, a novel image recognition and classification method based on convolutional neural network (CNN) for eddy current detection of titanium plate defects is proposed. By constructing a variety of experimental conditions and collecting defect signals, the characteristics of eddy current testing (ECT) signals for titanium plate defects are analyzed, and then the convolution structure and learning parameters are set. The structural characteristics of local connectivity and shared weights of CNN have better feature learning and characterization capabilities for titanium plate defect images under scan shift, scale distortion, and strong noise interference. The results prove that, compared with other deep learning and classical machine learning methods, the CNN has a higher recognition and classification accuracy for the defect eddy current image of the titanium plate in the complex detection environment.

Fast crack profile reconstruction using pulsed eddy current signals

2013 ◽  
Vol 54 ◽  
pp. 37-44 ◽  
Author(s):  
Libing Bai ◽  
Gui Yun Tian ◽  
Anthony Simm ◽  
Shulin Tian ◽  
Yuhua Cheng
Keyword(s):  
Eddy Current ◽  
Pulsed Eddy Current ◽  
Profile Reconstruction ◽  
Crack Profile

CONVOLUTIONAL NEURAL NETWORK BASED ALGORITHM FOR CECUM ACHIEVEMENT CONFIRMATION

2020 ◽  
Author(s):  
S Kashin ◽  
D Zavyalov ◽  
A Rusakov ◽  
V Khryashchev ◽  
A Lebedev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network

Reconstruction of complex shaped crack from ECT signals based on a fast forward solver using an advanced multi-media element

2020 ◽  
Vol 64 (1-4) ◽  
pp. 621-629
Author(s):  
Yingsong Zhao ◽  
Cherdpong Jomdecha ◽  
Shejuan Xie ◽  
Zhenmao Chen ◽  
Pan Qi ◽  
...  
Keyword(s):  
Coefficient Matrix ◽  
Crack Edge ◽  
Numerical Accuracy ◽  
Gauss Point ◽  
Current Testing ◽  
Efficient Simulation ◽  
Shaped Crack ◽  
Multi Media ◽  
Profile Reconstruction ◽  
Crack Profile

In this paper, the conventional database type fast forward solver for efficient simulation of eddy current testing (ECT) signals is upgraded by using an advanced multi-media finite element (MME) at the crack edge for treating inversion of complex shaped crack. Because the analysis domain is limited at the crack region, the fast forward solver can significantly improve the numerical accuracy and efficiency once the coefficient matrices of the MME can be properly calculated. Instead of the Gauss point classification, a new scheme to calculate the coefficient matrix of the MME is proposed and implemented to upgrade the ECT fast forward solver. To verify its efficiency and the feasibility for reconstruction of complex shaped crack, several cracks were reconstructed through inverse analysis using the new MME scheme. The numerical results proved that the upgraded fast forward solver can give better accuracy for simulating ECT signals, and consequently gives better crack profile reconstruction.

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Sign in / Sign up

Export Citation Format

Share Document