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

Eddy current testing (ECT) is one of the most popular Nondestructive Testing (NDT) techniques, especially for conductive materials. Reconstructing the crack profile from measured EC signals is one of the main goals of ECT. This task is highly challenging, as the EC signals are nonlinear responses resulted from the presence of cracks, and reconstructing the crack profile requires establishing the forward model of the nonlinear electromagnetic dynamics and solving its inverse problem, which is an ill-posed numerical optimization problem. Instead of solving the inverse problem numerically, we propose to directly learn the inverse mapping from EC signals to crack profiles with a deep encoder-decoder convolutional neural network named EddyNet. EddyNet is trained on a set of randomly generated crack profiles and the corresponding simulated EC responses generated from a realistic forward model. On the held-out test data, EddyNet achieved a mean absolute error of 0.207 between predicted profiles and ground truth ones. Qualitatively, the geometries of predicted profiles are visually similar to the ground truth profiles. Our method greatly reduces the usual reliance on domain experts, and the reconstruction is extremely fast both on GPUs and on CPUs. The source code of EddyNet is released on https://github.com/askerlee/EddyNet.

[1]  C. Reboud,et al.  Efficient Modeling of ECT Signals for Realistic Cracks in Layered Half-Space , 2013, IEEE Transactions on Magnetics.

[2]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[3]  Javier García-Martín,et al.  Non-Destructive Techniques Based on Eddy Current Testing , 2011, Sensors.

[4]  J. R. Bowler.  Inversion of open cracks using eddy-current probe impedance measurements , 2000 .

[5]  Harold A. Sabbagh,et al.  A theoretical and computational model of eddy-current probes incorporating volume integral and conjugate gradient methods , 1990 .

[6]  Aggelos K. Katsaggelos,et al.  Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods , 2018, IEEE Signal Processing Magazine.

[7]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[8]  Rushil Anirudh,et al.  An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks , 2018, ArXiv.

[9]  Michael Unser,et al.  Convolutional Neural Networks for Inverse Problems in Imaging: A Review , 2017, IEEE Signal Processing Magazine.

[10]  Harold A. Sabbagh,et al.  A model of eddy-current probes with ferrite cores , 1989 .

[11]  Carola-Bibiane Schönlieb,et al.  Adversarial Regularizers in Inverse Problems , 2018, NeurIPS.

[12]  Robert Hughes.  High-sensitivity eddy-current testing technology for defect detection in aerospace superalloys , 2015 .

[13]  Dominique Lesselier,et al.  Eddy‐Current Modeling of Ferrite‐Cored Probes , 2005 .