Pulsed eddy current detection of cracks in F/A-18 inner wing spar without wing skin removal using Modified Principal Component Analysis

Horan, Peter; Underhill, P. R.; Krause, Thomas W.

doi:10.1016/j.ndteint.2013.01.004

Cited by 60 publications

(45 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MPCA used for this work differs from conventional PCA in that it retains the signal mean, producing a least squares interpretation instead of variance minimization [6]. This technique allows for incremental reproduction of signals through linear combinations of principal components and their scores, significantly reducing dimensionality, while retaining most information originally contained in the data [5].…”

Section: Theorymentioning

confidence: 99%

“…PEC signal response can be viewed as consisting of a spectrum of discrete frequencies, far greater in number than what is normally captured by multi-frequency eddy current testing, but with an associated complexity in signal response. In order to address the subtle variations and extract dominant features in the measured PEC signal, a modified principal components analysis (MPCA) has been applied [5][6][7]. MPCA is based on a minimization of sum square residuals interpretation of results instead of a variance minimization interpretation as used in conventional PCA for feature extraction [6].…”

Section: Introductionmentioning

confidence: 99%

“…In order to address the subtle variations and extract dominant features in the measured PEC signal, a modified principal components analysis (MPCA) has been applied [5][6][7]. MPCA is based on a minimization of sum square residuals interpretation of results instead of a variance minimization interpretation as used in conventional PCA for feature extraction [6]. Multiple linear regression models have been investigated for extracting support structure hole inner diameter (ID) and two dimensional tube position MPCA results [8,9].…”

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: Theorymentioning

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

“…The base of the guide is covered in a thin clear sheet with a center hole cut to the same size as the fastener heads. This hole is used to align the probe concentrically over the fastener head [5]. A previous study [4] has shown that slight off-centering of the probe over the ferrous fastener can change the amplitude and shape of the resulting signal.…”

Section: Probe Design and Alignmentmentioning

confidence: 99%

“…PEC signals were analyzed using Modified Principal Components Analysis (MPCA) [5,6]. Prior to applying the MPCA, the signal was gated to include only the short time response where the notch information is contained.…”

Section: Modified Principal Components Analysis Of Signal Responsementioning

confidence: 99%

Enhancing pulsed eddy current for inspection of P-3 Orion lap-joint structures

Butt¹,

Underhill²,

Krause³

2016

AIP Conference Proceedings

View full text Add to dashboard Cite

Pulsed Eddy Current Non-destructive Testing and Evaluation: A Review

Sophian

Tian

Fan

2017

Chin. J. Mech. Eng.

215

View full text Add to dashboard Cite

Pulsed eddy current (PEC) non-destructive testing and evaluation (NDT&E) has been around for some time and it is still attracting extensive attention from researchers around the globe, which can be witnessed through the reports reviewed in this paper. Thanks to its richness of spectral components, various applications of this technique have been proposed and reported in the literature covering both structural integrity inspection and material characterization in various industrial sectors. To support its development and for better understanding of the phenomena around the transient induced eddy currents, attempts for its modelling both analytically and numerically have been made by researchers around the world. This review is an attempt to capture the state-of-the-art development and applications of PEC, especially in the last 15 years and it is not intended to be exhaustive. Future challenges and opportunities for PEC NDT&E are also presented.

show abstract

Pulsed eddy current detection of cracks in F/A-18 inner wing spar without wing skin removal using Modified Principal Component Analysis

Cited by 60 publications

References 10 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

Enhancing pulsed eddy current for inspection of P-3 Orion lap-joint structures

Pulsed Eddy Current Non-destructive Testing and Evaluation: A Review

Contact Info

Product

Resources

About