Inversion of Uniform Field Eddy Current Data Using Neural Networks

Mann, J. Matthew; Schmerr, Lester W.; Moulder, John C.; Kubovich, M. W.

doi:10.1007/978-1-4684-5772-8_85

Cited by 8 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[7][8][9] Extensive studies on inversion problems have been conducted also in other disciplines such as computer mechanics. [10][11][12][13][14] Attempts at the structural identification of a beam are made with measured eigenfrequencies and eigenmodes. This conversion utilizes a machine-learningrelated neural network.…”

Section: / /mentioning

confidence: 99%

Evaluation of optical constants in oxide thin films using machine learning

Saeki,

Makino

2023

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

This paper describes an inverse analysis method using neural networks on optical spectroscopy, and its application to the quantitative optical constant evaluation. The present method consists of three subprocesses. First, measurable UV–visible spectroscopic quantities were calculated as functions of the optical constants of the solid based on the Tomlin equations [J. Phys. D 1 1667 (1968)] by carefully eliminating the unpractical combinations of optical constants. Second, the backpropagation neural network is trained using the calculated relationships between the measurable quantities and the optical constants. Finally, the trained network is utilized to determine the optical constants from measured responses. The conventional (Newton–Raphson) method tends to require the judgment of a well-experienced analyst, while machine learning shows automatically human-free performance in data conversion.

show abstract

Section: / /mentioning

confidence: 99%

Evaluation of optical constants in oxide thin films using machine learning

Saeki,

Makino

2023

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

show abstract

“…Until now, various features have been proposed in many previous studies. Examples of such features include Fourier descriptors [7], amplitudes [8,9], phase angles [8], partial powers [9], statistical moments [10] and wavelet transform [11]. Once a certain set of features are extracted, a reduced set of features which contains the larger amount of information for the interpretation of ECT signals is selected by use of quantitative feature selection criteria [3].…”

Section: Introductionmentioning

confidence: 99%

Inversion of Eddy Current Test Signals Obtained from Steam Generator Tubes

Kim

Song

Hur³

et al. 2005

KEM

View full text Add to dashboard Cite

Eddy current testing (ECT) is widely used in in-service inspection as well as pre-service inspection of the steam generator (SG) tubes in nuclear power plant of pressurized water reactor type. The interpretation of ECT signals, however, is truly a difficult task so that the reliability enhancement of signal interpretation is strongly desired. An enhanced interpretation tools for ECT signals have been developed by the novel combination of neural networks and finite element modeling for quantitative flaw characterization SG tubes. A database was constructed using synthetic ECT signals generated by the finite element models and principal component analysis (PCA) was adopted in order to optimize the feature set of ECT signals. The improvement in the performances by the features with PCA and the excellent performance for the experimental ECT signals demonstrate the high potential of the developed inversion tools for reliable interpretation of eddy current signals. To explore the possibility of applying the developed approach in practical inspection, we developed an automated system (laboratory prototype) that can acquire experimental ECT signals from SG tubes and carry out the quantitative flaw characterization in a real time fashion by applying the approach developed in the present work.

show abstract

“…Until now, various features have been proposed in many previous studies. Examples of such features include Fourier descriptors [3], amplitudes [4,5], phase angles [4], partial powers [5], statistical moments [6] and wavelet transform [7]. Once a certain set of features are extracted, a reduced set of features which contains the larger amount of information for the interpretation of ECT signals is selected by use of quantitative feature selection criteria [2].…”

Section: Introductionmentioning

confidence: 99%

Principal Component Analysis of Eddy Current Signals Obtained from Steam Generator Tubes by Bobbin Probe

Kim

Song

Kim³

et al. 2004

KEM

View full text Add to dashboard Cite

The model-based interpretation tools for eddy current testing (ECT) signals have been developed by the novel combination of neural networks and finite element modeling for quantitative flaw characterization in steam generator tubes. The performance of inversion system strongly relies on the databases that had been used in the implementation of the specific system. It is also widely recognized that features play the most important role in the interpretation of ECT signals. In the present work, a database was constructed using synthetic ECT generated by the finite element models and principal component analysis (PCA) was adopted in order to optimize the feature set of eddy current signals. The features with PCA improved the performances of signal interpretations. The excellent performance obtained in the present work demonstrates the high potential of the developed inversion tools as a practical interpretation of eddy current signals.

show abstract

Inversion of Uniform Field Eddy Current Data Using Neural Networks

Cited by 8 publications

References 0 publications

Evaluation of optical constants in oxide thin films using machine learning

Evaluation of optical constants in oxide thin films using machine learning

Inversion of Eddy Current Test Signals Obtained from Steam Generator Tubes

Principal Component Analysis of Eddy Current Signals Obtained from Steam Generator Tubes by Bobbin Probe

Contact Info

Product

Resources

About