Defect characterization in infrared non-destructive testing with learning machines

Benítez, Hernán D.; Loaiza, Humberto; Caicedo, Eduardo; Ibarra-Castanedo, Clemente; Bendada, A.; Maldague, Xavier

doi:10.1016/j.ndteint.2009.05.004

Cited by 34 publications

(19 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…˗ Good statistical agreement between the network output and the real depth values, for the testing data, is confirmed by the results of the regression analysis -cf. Figs 11,14,17. For all three examined datasets, it was noticed that a high value of the correlation coefficient R occurred between the neural network output depth values and the values of depth applied in the training process -cf.…”

Section: Discussionmentioning

confidence: 82%

See 1 more Smart Citation

Characterization of Material Defects Using Active Thermography and an Artificial Neural Network

Dudzik¹

2013

Metrology and Measurement Systems

View full text Add to dashboard Cite

In the paper a method using active thermography and a neural algorithm for material defect characterization is presented. Experimental investigations are conducted with the stepped heating method, so-called time-resolved infrared radiometry, for the test specimen made of a material with low thermal diffusivity. The results of the experimental investigations were used in simulations of artificial neural networks. Simulations are performed for three datasets representing three stages of the heating process occurring in the investigated sample. In this work, the simulation research aimed to determine the accuracy of defect depth estimation with the use of the mentioned algorithm is descibed.

show abstract

Section: Discussionmentioning

confidence: 82%

“…Defect depth estimation can be considered as a classification [12,17] or regression [18] problem. In this work, the regressive neural network was applied.…”

Section: Neural Algorithm For Defect Depth Estimationmentioning

confidence: 99%

Characterization of Material Defects Using Active Thermography and an Artificial Neural Network

Dudzik¹

2013

Metrology and Measurement Systems

View full text Add to dashboard Cite

show abstract

“…More effective approaches, based on advanced signal processing and artificial intelligence paradigms, have been proposed in the last decade (Benitez et al, 2009) (Wang et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

Automatic Inspection of Aircraft Components Using Thermographic and Ultrasonic Techniques

Leo¹

2012

Recent Advances in Aircraft Technology

View full text Add to dashboard Cite

“…When external heat sources are used, these usually consist in high power optical lamps able to deposit a very intense and short heat impulse on the component surface [2]. Several applications have been proposed based on the evaluation of thermal contrast between a defected and a sound area [2][3][4][5][6]. A common drawback of these techniques is the opportune choice of a reference sound area when, as usually happens, a non uniform heat deposition is present.…”

Section: Introductionmentioning

confidence: 99%

“…The recent Source Distribution Image (SDI) proposes a criterion for choosing the sound area on zones which have received the same amount of heat [4]. The TSR [5] and DAC [6] techniques both are based on synthetic data reconstruction based on the expected, rather than measured, features of the sound area thermal decay. All methods still require a careful control of the heating pulse intensity and duration.…”

Section: Introductionmentioning

confidence: 99%

Thermal NDE of thick GRP panels by means of a Pulse Modulated Lock-In Thermography technique

Pitarresi

2010

EPJ Web of Conferences

View full text Add to dashboard Cite

Abstract. This work describes the development and implementation of an infrared thermal NDE procedure for the evaluation of subsurface defects. The approach is called Pulse-Modulated Lock-In Thermography (PMLT) and is based on the analysis of the frequency response of the measured temperature and comparison with the carrier frequencies launched by the external heat delivering source. The heat deposited on the object is in particular modulated as a train of square waves. This is easily achieved by periodically shuttering the heat source. The temperature is then sampled throughout the deposition of a few square waves. A lock-in algorithm is then implemented able to selectively filter out components at the main carrier frequencies of the heating signal and evaluate the phase information. Defected areas at different depths can be marked based on phase contrast, by using data from a single experiment as in Pulsed-Phase Thermography. An artificially defected thick GRP panel typical of naval monolithic hull structures, is investigated to validate the proposed technique. Experimental data have confirmed the potentials of PMLT as a flexible IR NDT approach, and its ability to be implemented by means of low cost heating and IR equipments.

show abstract

Defect characterization in infrared non-destructive testing with learning machines

Cited by 34 publications

References 23 publications

Characterization of Material Defects Using Active Thermography and an Artificial Neural Network

Characterization of Material Defects Using Active Thermography and an Artificial Neural Network

Automatic Inspection of Aircraft Components Using Thermographic and Ultrasonic Techniques

Thermal NDE of thick GRP panels by means of a Pulse Modulated Lock-In Thermography technique

Contact Info

Product

Resources

About