Neural network based defect detection and depth estimation in TNDE

Darabi, A.; Maldague, Xavier

doi:10.1016/s0963-8695(01)00041-x

Cited by 71 publications

(29 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This academic specimen was flashed heated for 15 ms (with two flashes of 6.4 KJ of electrical energy per flash) and 200 thermograms were recorded (from t = 0.1 to t = 20 s). The experimental apparatus is described elsewhere [8]. and the dotted curves ∆T [i,j] (t).…”

Section: Plexiglasmentioning

confidence: 99%

New Absolute Contrast for pulsed thermography

Klein¹,

Maldague²,

Pilla³

et al. 2002

Proceedings of the 2002 International Conference on Quantitative InfraRed Thermography

101

View full text Add to dashboard Cite

In this paper, a new absolute thermal contrast method is proposed for pulsed infrared thermography. It is based on the computations of reconstructed defect-free images so that no a priori knowledge of a sound area on the sample is necessary. Moreover, a correction is applied to take into account possible delays in the acquisition time. Results are presented both on Plexiglas TM and graphite-epoxy specimens. Comparisons with Pulsed Phase Thermography phase images are also presented along with a discussion on the advantages of the proposed method.

show abstract

Section: Plexiglasmentioning

confidence: 99%

New Absolute Contrast for pulsed thermography

Klein¹,

Maldague²,

Pilla³

et al. 2002

Proceedings of the 2002 International Conference on Quantitative InfraRed Thermography

101

View full text Add to dashboard Cite

show abstract

“…The purpose of this section is not to provide a detailed description of NN, which is for instance available elsewhere [5]. Here, we provide some insights on the subject as a result of several studies carried out in our laboratory.…”

Section: Neural Network (Nn)mentioning

confidence: 99%

“…using phase data for detection and amplitude data for characterization). Simulated data is privileged to experimental data during the training phase to avoid the use of redundant and non-representative information during training and to study noise effects on NN [5]. Figure 5 shows some results obtained with a PNN for a sample simulating corrosion on aluminum for: (a) temperature data, (b) amplitude data, and (c) phase data [11].…”

Section: Neural Network (Nn)mentioning

confidence: 99%

See 1 more Smart Citation

Thermographic nondestructive evaluation: overview of recent progress

et al. 2003

Self Cite

View full text Add to dashboard Cite

This paper presents a summary of recent research activities carried out at our laboratory in the field of Infrared Thermography for Nondestructive Evaluation (TNDE). First, we explore the latest developments in signal improvement. We describe three approaches: multiple pulse stimulation [1]; the use of Synthetic Data for de-noising of the signal [2]; and a new approach derived from the Fourier diffusion equation called the Differentiated Absolute Contrast method (DAC) [3]. Secondly, we examine the advances carried out in inverse solutions. We describe the use of the Wavelet Transform [4] to manage pulsed thermographic data, and we present a summary on Neural Networks for TNDE [5]. Finally, we look at the problem of complex geometry inspection. In this case, due to surface shape, heat variations might be incorrectly identified as flaws. We describe the Shape-from-Heating approach [6] and we propose some potential research avenues to deal with this problem.

show abstract

“…[17,18], artificial neural networks (ANNs) are used for the classification of a defect in different materials. The neural networks are powerful and strong mathematical models for the classification and pattern-recognition problems.…”

Section: Introductionmentioning

confidence: 99%

Predictive Maintenance of Power Substation Equipment by Infrared Thermography Using a Machine-Learning Approach

et al. 2017

View full text Add to dashboard Cite

A variety of reasons, specifically contact issues, irregular loads, cracks in insulation, defective relays, terminal junctions and other similar issues, increase the internal temperature of electrical instruments. This results in unexpected disturbances and potential damage to power equipment. Therefore, the initial prevention measures of thermal anomalies in electrical tools are essential to prevent power-equipment failure. In this article, we address this initial prevention mechanism for power substations using a computer-vision approach by taking advantage of infrared thermal images. The thermal images are taken through infrared cameras without disturbing the working operations of power substations. Thus, this article augments the non-destructive approach to defect analysis in electrical power equipment using computer vision and machine learning. We use a total of 150 thermal pictures of different electrical equipment in 10 different substations in operating conditions, using 300 different hotspots. Our approach uses multi-layered perceptron (MLP) to classify the thermal conditions of components of power substations into "defect" and "non-defect" classes. A total of eleven features, which are first-order and second-order statistical features, are calculated from the thermal sample images. The performance of MLP shows initial accuracy of 79.78%. We further augment the MLP with graph cut to increase accuracy to 84%. We argue that with the successful development and deployment of this new system, the Technology Department of Chongqing can arrange the recommended actions and thus save cost in repair and outages. This can play an important role in the quick and reliable inspection to potentially prevent power substation equipment from failure, which will save the whole system from breakdown. The increased 84% accuracy with the integration of the graph cut shows the efficacy of the proposed defect analysis approach.

show abstract

Neural network based defect detection and depth estimation in TNDE

Cited by 71 publications

References 8 publications

New Absolute Contrast for pulsed thermography

New Absolute Contrast for pulsed thermography

Thermographic nondestructive evaluation: overview of recent progress

Predictive Maintenance of Power Substation Equipment by Infrared Thermography Using a Machine-Learning Approach

Contact Info

Product

Resources

About