Adaptive Neuro-Fuzzy Inference System Model Based on the Width and Depth of the Defect in an Eddy Current Signal

Abstract

Non-destructive evaluation (NDE) plays an important role in many industrial fields, such as detecting cracking in steam generator tubing in nuclear power plants and aircraft. This paper investigates on the effect of the depth of the defect, width of the defect, and the type of the material on the eddy current signal which is modeled by an adaptive neuro-fuzzy inference system (ANFIS). A total of 60 samples of artificial defects are located 20 mm parallel to the length of the block in each of the three types of material. A weld probe was used to inspect the block. The ANFIS model has three neurons in the input layer and one neuron in the output layer as the eddy current signal. The used design of experiments (DOE) software indicates that the model equations, which contain only linear and two-factor interaction terms, were developed to predict the percentage signal. This signal was validated through the use of the unseen data. The predicted results on the depth and width of defect significantly influenced the percentage of the signal (p < 0.0001) at the 95% confidence level. The ANFIS model proves that the deviation of the eddy current testing measurement was influenced by the width and depth of the defect less than the conductivity of the materials.

Challenges in improving the performance of eddy current testing: Review

“…78 However, the high frequency applied for the inspection of small discontinuities occured in the near-surface. 79,80…”

Investigate the effect of lift-off on eddy current signal for carbon steel plate

“…The Design expert @ version 7.0.0 was used to designing the experiment, drawing RSM plots and analysis of data statistically. The central composite design (CCD) is applied to examine the lift-off and depth defect effect factors on the eddy current testing and investigate the interactive effect of the factors [14]. The eddy current signal was selected as the response variable, while the lift-off (X1) and depth defect (X2) as two independent variables as shown in Table 1.…”

Hybrid GMR/IR probe to reduce the effects of lift-off

“…Eddy current testing (ECT) techniques are widely used in many industrial sectors to examine and estimate the integrity of conductive materials due to their high sensitivity and robustness. 1 ECT techniques are utilized in applications such as in detection of defects on a conductive sample, measurement of sample thickness, estimating coating thickness on pipelines, and measuring properties of materials like electrical conductivity and permeability. The most recent research presents the magneto-resistive sensors in ECT techniques due to their linear response which makes them suitable for detecting low-amplitude electromagnetic field when a low frequency is applied.…”