Sizing of natural crack using multi-output support vector regression method from multi-frequency eddy current testing signals

2020 ◽  
Vol 64 (1-4) ◽  
pp. 721-728
Author(s):  
Li Wang ◽  
Zhenmao Chen
Keyword(s):  
Support Vector Regression ◽  
Quantitative Evaluation ◽  
Eddy Current ◽  
Crack Depth ◽  
Eddy Current Testing ◽  
Support Vector ◽  
Efficient Operation ◽  
Current Testing ◽  
Multiple Parameters ◽  
Equipment Sizing

In the nondestructive evaluation for components of key equipment, sizing of natural crack is important in order to guarantee both the safety and efficient operation for large mechanical systems. Natural cracks have complex boundary and there may be electric current flowing through crack faces. If a simple model of artificial notch is used to simulate it, errors often occur in crack depth reconstruction from eddy current testing (ECT) signals. However, if a complex crack conductivity model is used, quantitative evaluation of natural crack will be transformed into a multivariable nonlinear optimization problem and the solution is difficult. In this paper, based on the relationship between crack parameters and features of multi-frequency ECT signals, a multi-output support vector regression algorithm using domain decomposition for parameters was proposed. The algorithm realized the quantitative evaluation of multiple parameters of crack in turn. Numerical examples with simulated and measured ECT signals were presented to verify the efficiency of the proposed strategy.

Investigation of Rotating Eddy Current Testing Simulation Using Simplified Model

2021 ◽  
Author(s):  
Chenkai Yang ◽  
Jiuhao Ge ◽  
Baowang Hu
Keyword(s):  
Simulation Model ◽  
Eddy Current ◽  
Crack Depth ◽  
Eddy Current Testing ◽  
Simplified Model ◽  
Current Testing ◽  
Application Condition ◽  
Exciting Frequency ◽  
Text Signal ◽  
Peak Value

To reduce the time of simulation for rotating Eddy current testing (RECT) technique, a simplified model without modeling probe was proposed previously. However, the applicability of the simplified simulation model was unknown. In this paper, the applicability of the simplified model for the RECT technique was investigated. The application condition of the simplified model was provided by comparing it with the results of the traditional simulation model. The simplified model was suitable for the study of cracks shorter than 70% size of the uniform Eddy current induced by the probe in a traditional model or experiment. The experiment was conducted to validate the simplified model. Moreover, using the simplified model, the effects of crack depth, orientation, and exciting frequency were studied. The deeper the crack depth was, the greater peak value of [Formula: see text] signal was. The crack angle was linear with the phase of signal. The exciting frequency affected the amplitude and phase of the signal at the same time.

Crack Sizing of Deep Cracks in Eddy Current Testing Using 3D Electromagnetic Field Analysis

2004 ◽  
Author(s):  
Toshiyuki Takagi ◽  
Tetsuya Uchimoto ◽  
Hisashi Endo
Keyword(s):  
Eddy Current ◽  
Crack Depth ◽  
High Accuracy ◽  
Eddy Current Testing ◽  
Field Analysis ◽  
Current Field ◽  
Metal Structures ◽  
Current Testing ◽  
Crack Sizing ◽  
Exhaustive Study

A computer-aided approach of the eddy current testing (ECT) is described to detect and to size up deep cracks in thick metal structures. A 3D eddy current field analysis based on the finite elements performs designing ECT probes and evaluating the size of crack depth quantitatively. An exhaustive study on the ECT probe specification gives the optimal design of coil elements and their combination. The experimental verification shows that the developed ECT probe employing double exciting coils is capable of detecting crack depth over 10mm from the inspection surfaces. The depth of cracks is quantitatively evaluated from the measured ECT signals with the help of numerical calculation. The results of evaluation profile the crack shapes with fairly high accuracy, supporting our approach.

The combination of adaptive database SDM and multi-output SVM for eddy current testing

2015 ◽  
Vol 34 (6) ◽  
pp. 1731-1739 ◽  
Author(s):  
M. Chelabi ◽  
T. Hacib ◽  
Z. Belli ◽  
M. R. Mekideche ◽  
Y. Le Bihan
Keyword(s):  
Eddy Current ◽  
Eddy Current Testing ◽  
Learning Performance ◽  
Support Vector ◽  
Inversion Method ◽  
Defect Characterization ◽  
Content Type ◽  
Current Testing ◽  
Svm Model ◽  
Schema Design

Purpose – Eddy current testing (ECT) is a nondestructive testing method for the detection of flaws that uses electromagnetic induction to find defects in conductive materials. In this method, eddy currents are generated in a conductive material by a changing magnetic field. A defect is detected when there is a disruption in the flow of the eddy current. The purpose of this paper is to develop a new noniterative inversion methodology for detecting degradation (defect characterization) such as cracking, corrosion and erosion from the measurement of the impedance variations. Design/methodology/approach – The methodology is based on multi-output support vector machines (SVM) combined with the adaptive database schema design method (SDM). The forward problem was solved numerically using finite element method (FEM), with its accuracy experimentally verified. The multi-output SVM is a statistical learning method that has good generalization capability and learning performance. FEM is used to create the adaptive database required to train the multi-output SVM and the genetic algorithm is used to tune the parameters of multi-output SVM model. Findings – The results show the applicability of multi-output SVM to solve eddy current inverse problems instead of using traditional iterative inversion methods which can be very time-consuming. With the experimental results the authors demonstrate the accuracy which can be provided by the multi-output SVM technique. Practical implications – The work allows extending the capability of the experimentation ECT defect characterization system developed at LGEP. Originality/value – A new inversion method is developed and applied to ECT defect characterization. This new concept introduces multi-output SVM in the context of ECT. The real data together with estimated one obtained by multi-output SVM model are compared in order to evaluate the effectiveness of the developed technique.

Novel austenitic steel ageing classification method using eddy current testing and a support vector machine

Measurement ◽  
2018 ◽  
Vol 127 ◽  
pp. 98-103 ◽  
Author(s):  
Mónica P. Arenas ◽  
Tiago J. Rocha ◽  
Chandra S. Angani ◽  
Artur L. Ribeiro ◽  
Helena G. Ramos ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Austenitic Steel ◽  
Eddy Current ◽  
Eddy Current Testing ◽  
Classification Method ◽  
Support Vector ◽  
Current Testing

Quantitative evaluation of surface crack in ferromagnetic materials based on Bayesian network in eddy current testing

2020 ◽  
Vol 64 (1-4) ◽  
pp. 1073-1079
Author(s):  
Jing Song ◽  
Yanzhen Zhao
Keyword(s):  
Bayesian Network ◽  
Quantitative Evaluation ◽  
Eddy Current ◽  
Crack Size ◽  
Ferromagnetic Materials ◽  
Eddy Current Testing ◽  
Surface Cracks ◽  
Induced Voltage ◽  
Current Testing ◽  
Small Cracks

Quantitative evaluation of surface cracks using detection signal is of great significance for accurate prediction of cracks in eddy current testing. It is very difficult to evaluate both the width and depth of small cracks. A quantitative evaluation method based on Bayesian network is proposed for estimating the width and depth of surface cracks in the ferromagnetic materials. First, the simulation model of eddy current testing (ECT) is established and verified by the experimental results. Then, the variation of induced voltage with crack size is studied. Four feature points of real and imaginary part of induced voltage of the receiver coil are selected to characterize the crack size. Finally, a Bayesian network is applied to evaluate the crack size based on numerical simulation results. The evaluation results show that Bayesian network can accurately estimate the width and depth of small cracks.

Sign in / Sign up

Export Citation Format

Share Document