Towards end-to-end pulsed eddy current classification and regression with CNN

Fu, Xin; Zhang, Chengkai; Peng, Xiang; Jian, Lihua; Liu, Zheng

doi:10.1109/i2mtc.2019.8826858

Cited by 10 publications

(4 citation statements)

References 24 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The trained CNN achieved a mean absolute error of 0.198 between the predicted profiles and ground truth. In terms of pulsed ECT, a multi-task CNN was developed in [25], which installed a softmax layer and a fully connection layer as two outputs in order to simultaneously classify the type and predict the depth of flaw, respectively. The total loss was an addition of the classification loss and regression loss.…”

Section: Introductionmentioning

confidence: 99%

Depth Evaluation for Metal Surface Defects by Eddy Current Testing Using Deep Residual Convolutional Neural Networks

Tian

Tao²,

Chen

et al. 2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Eddy current testing (ECT) is an effective technique for evaluating depth of metal surface defects. However, in practice, evaluation primarily relies on the experience of an operator and is often carried out by manual inspection. In this paper, we address the challenges of automatic depth evaluation of metal surface defects by virtual of state-of-the-art deep learning (DL) techniques. The main contributions are three-fold. Firstly, a highly-integrated portable ECT device is developed, taking the advantage of an advanced field programmable gate array (Zynq-7020 system on chip) and provides fast data acquisition and in-phase/quadrature demodulation. Secondly, a dataset, termed as MDDECT, is constructed using the ECT device by human operators and made openly available. It contains 48,000 scans from 18 defects of different depths and lift-offs. Thirdly, the depth evaluation problem is formulated as a time series classification problem, and various state-of-the-art 1-d residual convolutional neural networks are trained and evaluated on the MDDECT dataset. A 38-layer 1-d ResNeXt achieves an accuracy of 93.58% in discriminating the surface defects in a stainless steel sheet with depths from 0.3 mm to 2.0 mm in the resolution of 0.1 mm. In addition, results show that the trained ResNeXt1D-38 model is immune to lift-off signals.

show abstract

Section: Introductionmentioning

confidence: 99%

Depth Evaluation for Metal Surface Defects by Eddy Current Testing Using Deep Residual Convolutional Neural Networks

Tian

Tao²,

Chen

et al. 2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…It has been demonstrated that deep CNNs have outstandingly succeeded in image classification and processing [31,35]. Moreover, deep CNNs that extract features hidden in data have potential for regression analysis [36][37][38][39]. CNN regression allows multiple outputs, relying on convolutional operations to train the corresponding weights.…”

Section: Introductionmentioning

confidence: 99%

Elastography mapped by deep convolutional neural networks

Liu

Kruggel

Sun

2021

Sci. China Technol. Sci.

View full text Add to dashboard Cite

Elastography emerges as a medical modality to map stiffness distribution of tissues and is expected to help identify malignant tumors. To this end, tissues are externally stimulated with dynamic waves, and thereafter mechanical responses are internally measured. However, internal measurements limit the resolution and accuracy due to wave scattering and frequency-dependence. Although models have been reported only with need for acquiring transmitted responses, the computational processes are timeconsuming in the inverse analysis. Here we develop an architecture of deep learning-based convolutional neural networks (CNNs) to image elastography based on sound transmission. The proposed CNNs contain three branches, one of which considers the contribution of original features in input data. By comparison, the developed architecture not only maps elastography accurately, but also is more efficient than traditional CNNs in sequence.

show abstract

“…Training samples were procured from a forward model with inputs and outputs exchanged. In terms of pulsed ECT, a multi-task CNN was developed in [13], which installed a softmax layer and a fully connection layer as two outputs in order to simultaneously classify the type and predict the depth of flaw, respectively. In [14], a plain CNN was used to estimate the crack depth for a heat transfer tube of the steam generator of a pressurised water reactor, which, compared to conventional numerical models, was less computationally expensive at inference time.…”

Section: Introductionmentioning

confidence: 99%

Depth Evaluation for Metal Surface Defects by Eddy Current Testing using Deep Residual Convolutional Neural Networks

Tian¹,

Tao²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Eddy current testing (ECT) is an effective technique in the evaluation of the depth of metal surface defects. However, in practice, the evaluation primarily relies on the experience of an operator and is often carried out by manual inspection. In this paper, we address the challenges of automatic depth evaluation of metal surface defects by virtual of state-of-the-art deep learning (DL) techniques. The main contributions are three-fold. Firstly, a highlyintegrated portable ECT device is developed, which takes advantage of an advanced field programmable gate array (Zynq-7020 system on chip) and provides fast data acquisition and in-phase/quadrature demodulation. Secondly, a dataset, termed as MDDECT, is constructed using the ECT device by human operators and made openly available. It contains 48,000 scans from 18 defects of different depths and lift-offs. Thirdly, the depth evaluation problem is formulated as a time series classification problem, and various state-of-the-art 1-d residual convolutional neural networks are trained and evaluated on the MDDECT dataset. A 38layer 1-d ResNeXt achieves an accuracy of 93.58% in discriminating the surface defects in a stainless steel sheet. The depths of the defects vary from 0.3 mm to 2.0 mm in a resolution of 0.1 mm. In addition, results show that the trained ResNeXt1D-38 model is immune to lift-off signals.

show abstract

Towards end-to-end pulsed eddy current classification and regression with CNN

Cited by 10 publications

References 24 publications

Depth Evaluation for Metal Surface Defects by Eddy Current Testing Using Deep Residual Convolutional Neural Networks

Depth Evaluation for Metal Surface Defects by Eddy Current Testing Using Deep Residual Convolutional Neural Networks

Elastography mapped by deep convolutional neural networks

Depth Evaluation for Metal Surface Defects by Eddy Current Testing using Deep Residual Convolutional Neural Networks

Contact Info

Product

Resources

About