Eddy current modelling using multi-layer perceptron neural networks for detecting surface cracks (original) (raw)
Related papers
Periodica Polytechnica Civil Engineering
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...
2016
In this work, we suggest an approach of signal inversion from sensors used in eddy current (EC) nondestructive testing (NDT). The aim is to characterize surface cracks from the EC signal. A methodology that combines 3D finite element (FEM) simulation and a data inversion by neural networks (NN) is proposed. We show that the use of a set of numerical measurements representing the EC signature of surface crack enables to remedy of the unicity problem. The obtained results show that the developed approach leads to the quantification of the crack.
Natural crack recognition using inverse neural model and multi-frequency eddy current method
IEEE Transactions on Magnetics, 2001
In this paper a Multi-Frequency Excitation and Spectrogram Eddy Current System and an inverse neural model were used to detect and identify natural flaws in steam generator tubes. It is shown that the applied dynamic neural model of the ECT sensor offers very high speed of operation and guarantees reliability of the recognition results.
Crack Shape Reconstruction in Eddy Current Testing Using Machine Learning Systems for Regression
IEEE Transactions on Instrumentation and Measurement, 2000
Nondestructive testing techniques for the diagnosis of defects in solid materials can follow three steps, i.e., detection, location, and characterization. The solutions currently on the market allow for good detection and location of defects, but their characterization in terms of the exact determination of defect shape and dimensions is still an open question. This paper proposes a method for the reliable estimation of crack shape and dimensions in conductive materials using a suitable nondestructive instrument based on the eddy current principle and machine learning system postprocessing. After the design and tuning stages, a performance comparison between the two machine learning systems [artificial neural network (ANN) and support vector machine (SVM)] was carried out. An experimental validation carried out on a number of specimens with different known cracks confirmed the suitability of the proposed approach for defect characterization.
Identification of crack depths from eddy current testing signal
IEEE Transactions on Magnetics, 1998
This paper demonstrates the identification of crack depths using signals obtained from eddy current testing (ECT). The identification method is based on finite elements with the pre-computed unflawed database approach and a meshless crack representation technique, and parameter estimation in non-linear problems. Four different cracks are estimated by using laboratory data. Index Terms-Eddy current testing, steam generator tubes, inverse problems, finite element methods, reduced magnetic vector potentials, pre-computed unflawed database approach, meshless crack representation technique, trust region method.
2012 IEEE I2MTC - International Instrumentation and Measurement Technology Conference, Proceedings, 2012
Feature extraction and defect parameters estimation from eddy current testing data has received special attention in the last years. Principal component analysis, wavelet decomposition and Fourier descriptors are some of the tools used for feature extraction. Particular interest is devoted to using artificial neural networks to perform parameters estimation and profile reconstruction of defects. This work reports the use of non-linear regressions for feature extraction based on the modeling of the measured response by a set of additive Gaussians and artificial neural networks to estimate the width and depth of defects.
Russian Journal of Nondestructive Testing, 2020
The study of 3D eddy current non destructive testing system for cracks characterization using finite element method requires a great amount of computing time and memory space. In this article, we have validated the developed model and then determined directly the crack length by analyzing the complete signal. Afterwards, we have extracted from the complete sensor sweep signal the maximal amplitude that we have exploited to estimate the crack depth.
Measurement Science Review, 2022
The growing complexity of industrial processes and manufactured parts, the growing need for safety in service and the desire to optimize the life of parts, require the implementation of increasingly complex quality assessments. Among the various anomalies to consider, sub-millimeter surface defects must be the subject of particular care. These defects are extremely dangerous as they are often the starting point for larger defects such as fatigue cracks, which can lead to the destruction of the parts. Penetrant testing is now widely used for this type of defect, due to its good performance. Nevertheless, it should be abandoned eventually due to environmental standards. Among the possible alternatives, the use of eddy currents (EC) for conductive materials is a reliable, fast, and inexpensive alternative. The study concerns the design and modeling of eddy current probe structures comprising micro-sensors for non-destructive testing. The moving band finite element method is implemented...
A Study of the Automated Eddy Current Detection of Cracks in Steel Plates
Journal of Nondestructive Evaluation, 2019
Applying life estimation approaches to determine in-service life of structures and plan the inspection schedules accordingly are becoming acceptable safety design procedures in aerospace. However, these design systems shall be fed with reliable parameters related to material properties, loading conditions and defect characteristics. In this context, the role of non-destructive (NDT) testing reliability is of high importance in detecting and sizing defects. Eddy current test (ECT) is an electromagnetic NDT method frequently used to inspect tiny surface fatigue cracks in sensitive industries. Owing to the new advances in robotic technologies, there is a trend to integrate the ECT into automated systems to perform NDT inspections more efficiently. In fact, ECT can be effectively automated as to increase the coverage, repeatability and scanning speed. The reliability of ECT scanning, however, should be thoroughly investigated and compared to conventional modes of applications to obtain ...