A novel feature extraction for eddy current testing of steam generator tubes

Jo, Nam-Hoon; Lee, Hyang-Beom

doi:10.1016/j.ndteint.2009.05.006

Cited by 18 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANNs have been examined for solving inverse ECT problems for SG tubes [13,14]. Examples include reconstruction of crack profiles from ECT data using binary regression outputs [14], and deterministic length and depth outputs after pre-processing [15,16]. Numerically simulated data has been used to train ANNs to identify impedance plane features for SG tubes [15], or processed with PCA to extract relevant signal features and compress ECT data [11,13,14,16,17].…”

Section: Introductionmentioning

confidence: 99%

“…Examples include reconstruction of crack profiles from ECT data using binary regression outputs [14], and deterministic length and depth outputs after pre-processing [15,16]. Numerically simulated data has been used to train ANNs to identify impedance plane features for SG tubes [15], or processed with PCA to extract relevant signal features and compress ECT data [11,13,14,16,17]. ANN, in combination with PCA, has been implemented for flaw classification for ECT of riveted lap-joints, demonstrating high quality results with high compression capability [18].…”

Section: Introductionmentioning

confidence: 99%

“…PCA combined with ANN has also been applied to simulated PEC responses of stress corrosion cracking [19]. Noise added to finite element method modeling results, in order to simulate real inspection conditions, has been used to train and test ANNs [13][14][15]19,20]. It has been demonstrated that while ANNs can successfully interpolate results for bounded input data, they do not extrapolate well when data falls outside training bounds [16].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of machine learning tools for inspection of steam generator tube structures using pulsed eddy current

Buck

Underhill

Morelli

et al. 2017

AIP Conference Proceedings

View full text Add to dashboard Cite

Abstract. Degradation of nuclear steam generator (SG) tubes and support structures can result in a loss of reactor efficiency. Regular in-service inspection, by conventional eddy current testing (ECT), permits detection of cracks, measurement of wall loss, and identification of other SG tube degradation modes. However, ECT is challenged by overlapping degradation modes such as might occur for SG tube fretting accompanied by tube off-set within a corroding ferromagnetic support structure. Pulsed eddy current (PEC) is an emerging technology examined here for inspection of Alloy-800 SG tubes and associated carbon steel drilled support structures. Support structure hole size was varied to simulate uniform corrosion, while SG tube was off-set relative to hole axis. PEC measurements were performed using a single driver with an 8 pick-up coil configuration in the presence of flat-bottom rectangular frets as an overlapping degradation mode. A modified principal component analysis (MPCA) was performed on the time-voltage data in order to reduce data dimensionality. The MPCA scores were then used to train a support vector machine (SVM) that simultaneously targeted four independent parameters associated with; support structure hole size, tube off-centering in two dimensions and fret depth. The support vector machine was trained, tested, and validated on experimental data. Results were compared with a previously developed artificial neural network (ANN) trained on the same data. Estimates of tube position showed comparable results between the two machine learning tools. However, the ANN produced better estimates of hole inner diameter and fret depth. The better results from ANN analysis was attributed to challenges associated with the SVM when non-constant variance is present in the data.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of machine learning tools for inspection of steam generator tube structures using pulsed eddy current

Buck

Underhill

Morelli

et al. 2017

AIP Conference Proceedings

View full text Add to dashboard Cite

show abstract

“…Due to its diagnostic advantages, the eddy current testing (ECT) method has been extensively used for the periodic testing of steam generator (SG) tubes to ensure the safe operation of nuclear power plants [1]- [7]. ECT is one of popular non-destructive testing methods.…”

Section: Introductionmentioning

confidence: 99%

“…Among those techniques, an artificial neural network (ANN) is recognized as one of the most popular techniques. The methods to classify the defect type have been studied based on the ECT signals by means of a probabilistic neural network [6] and multi-layer perceptron (MLP) neural networks [7]. In [7], a conjugate gradient back-propagation (CGBP) algorithm has been used for training a MLP network to classify the defect type.…”

Section: Introductionmentioning

confidence: 99%

Classification of the Types of Defects in Steam Generator Tubes using the Quasi-Newton Method

Lee¹,

Jo²,

Roh³

2010

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

-Multi-layer perceptron neural networks have been constructed to classify four types of defects in steam generator tubes. Three features are extracted from the signals of the eddy current testing method. These include maximum impedance, phase angle at the point of maximum impedance, and an angle between the point of maximum impedance and the point of half the maximum impedance. Two hundred sets of these features are used for training and assessing the networks. Two approaches are involved to train the networks and to classify the defect type. One is the conjugate gradient method and the other is the Broydon-Fletcher-Goldfarb-Shanno method which is recognized as the most popular algorithm of quasi-Newton methods. It is found from the computation results that the training time of the Broydon-Fletcher-Goldfarb-Shanno method is much faster than that of the conjugate gradient method in most cases. On the other hand, no significant difference of the classification performance between the two methods is observed.

show abstract

PWR heat exchanger tube defects: Trends, signatures and diagnostic techniques

Ayodeji

Liu

2019

Progress in Nuclear Energy

View full text Add to dashboard Cite

A novel feature extraction for eddy current testing of steam generator tubes

Cited by 18 publications

References 8 publications

Evaluation of machine learning tools for inspection of steam generator tube structures using pulsed eddy current

Evaluation of machine learning tools for inspection of steam generator tube structures using pulsed eddy current

Classification of the Types of Defects in Steam Generator Tubes using the Quasi-Newton Method

PWR heat exchanger tube defects: Trends, signatures and diagnostic techniques

Contact Info

Product

Resources

About