Application of neural networks for classification of eddy current NDT data

Upda, L.; Upda, S.S.

doi:10.1016/0963-8695(92)90069-s

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, the magnetic field induced by eddy currents has been applied in a variety of technologies, mainly in the non-destructive evaluation of materials (NDE). In 1879, D. E. Hughes demonstrated that the induced magnetic field has some information on the chemical, physical, and electrical characteristics of the conducting material [11]. Indeed, the induced magnetic field is influenced by path variations in the superficial eddy currents caused by the presence of surface imperfections in the studied structure.…”

Section: Introductionmentioning

confidence: 99%

“…Although several review articles have been published that compile advances and research in eddy-current-based technologies [11,29,37,38], they are only focused on specific applications. After an exhaustive search, we found a review article that covers a wide spectrum of applications that depend on eddy currents; unfortunately, its publication dates back more than three decades [39].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Past, Present, and Future of New Applications in Utilization of Eddy Currents

Romero-Arismendi,

Olivares-Galvan,

Hernandez-Avila

et al. 2024

Technologies

View full text Add to dashboard Cite

Eddy currents are an electromagnetic phenomenon that represent an inexhaustible source of inspiration for technological innovations in the 21st century. Throughout history, these currents have been a subject of research and technological development in multiple fields. This article delves into the fascinating world of eddy currents, revealing their physical foundations and highlighting their impact on a wide range of applications, ranging from non-destructive evaluation of materials to levitation phenomena, as well as their influence on fields as diverse as medicine, the automotive industry, and aerospace. The nature of eddy currents has stimulated the imaginations of scientists and engineers, driving the creation of revolutionary technologies that are transforming our society. As we progress through this article, we will cover the main aspects of eddy currents, their practical applications, and challenges for future works.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Past, Present, and Future of New Applications in Utilization of Eddy Currents

Romero-Arismendi,

Olivares-Galvan,

Hernandez-Avila

et al. 2024

Technologies

View full text Add to dashboard Cite

show abstract

“…A classifier in NDE is a decision system which classifies a measured signal into one of two possible categories, namely defect or non-defect. Till date, numerous rule-based and pattern recognition based algorithms have been implemented for detection and classification of defects in various NDE inspections such as Fisher Linear Discriminant method for classifying flaws in eddy current signals [1], neural networks [2] [3] for classifying signals from ultrasonic weld inspection, Support Vector Machines [4] for non-stationary image processing of eddy current NDE images and K-means clustering for differential probe signals [5]. Such algortihms have provided good classification results in different NDE applications, yet they focus primarily on minimizing misclassifcation error without throwing much light on the reliability of data anaysis.…”

Section: Introductionmentioning

confidence: 99%

Ensemble of classifiers for confidence-rated classification of NDE signal

Banerjee

Safdarnejad

Удпа³

et al. 2016

AIP Conference Proceedings

View full text Add to dashboard Cite

Abstract. Ensemble of classifiers in general, aims to improve classification accuracy by combining results from multiple weak hypotheses into a single strong classifier through weighted majority voting. Improved versions of ensemble of classifiers generate self-rated confidence scores which estimate the reliability of each of its prediction and boost the classifier using these confidence-rated predictions. However, such a confidence metric is based only on the rate of correct classification. In existing works, although ensemble of classifiers has been widely used in computational intelligence, the effect of all factors of unreliability on the confidence of classification is highly overlooked. With relevance to NDE, classification results are affected by inherent ambiguity of classifica-tion, non-discriminative features, inadequate training samples and noise due to measurement. In this paper, we extend the existing ensemble classification by maximizing confidence of every classification decision in addition to minimizing the classification error. Initial results of the approach on data from eddy current inspection show improvement in classification performance of defect and non-defect indications.

show abstract

Application of neural networks for classification of eddy current NDT data

Cited by 2 publications

References 0 publications

Past, Present, and Future of New Applications in Utilization of Eddy Currents

Past, Present, and Future of New Applications in Utilization of Eddy Currents

Ensemble of classifiers for confidence-rated classification of NDE signal

Contact Info

Product

Resources

About