Artificial Neural Networks for Inverse Problems in Damage Detection using Computational and Experimental Eddy Current
Abstract
A new method for computing fracture mechanics parameters applicable for measuring tests relying on Eddy currents is proposed. This method is based on inversing Eddy current with simultaneous use of Artificial Neural Networks (ANN) for the localization and the shape classification of defects. It allows the reconstruction of cracks and damage in the plate profile of an inspected specimen to assess its material properties. The procedure consists on inverting all the Eddy current probe impedance measurements which are recorded according to the position of the probe, the excitation frequency or both. In the non-destructive evaluation by Eddy currents or in the case of an inverse problem which is difficult to solve, results from a lot of variety of concepts such as physics and complex mathematics are needed. The corresponding solution has a significant impact on the characterization of cracks in materials. On the other side, a simulation by a numerical approach based on the finite element method is employed to detect cracks in materials and eventually, study their propagation. It is shown here that this method has emerged as one of the most efficient techniques for prospecting cracks and enables the study of an increase in size of cracks and its propagation in aluminum material. Besides, it can easily predict future defects in different mechanical parts of a given material and be useful in the treatment of materials than the process of changing parts. It has been proven that it gives good results and high performance for different materials.
Keywords:
crack, eddy current, artificial neural network, femPublished Online
How to Cite
Issue
Section
License
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see The Effect of Open Access). As soon as the paper is accepted, finally submitted and edited, the paper will appear in the "OnlineFirst" page of the journal, thus from this point no other internet-based publication is necessary.

