Two-stage neural algorithm for defect detection and characterization uses an active thermography

Dudzik, Sebastian

doi:10.1016/j.infrared.2015.03.003

Cited by 39 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results were obtained using a test sample made of material with a low thermal diffusivity (0.12 × 10 −6 m 2 •s −1 ), which is even lower than that of concrete. The largest value of the relative mean error of the defect depth estimation for the testing data was equal to 4.6% [62].…”

Section: Defect Detectability and Quantificationmentioning

confidence: 93%

See 1 more Smart Citation

Review of Active IR Thermography for Detection and Characterization of Defects in Reinforced Concrete

2016

View full text Add to dashboard Cite

Active thermography methods enable structural investigations of reinforced concrete elements taking into account many different testing problems. The goal of this review is to provide an overview on the state-of-the-art regarding the use of active infrared thermography (IRT) for detection and characterization of defects in reinforced concrete. The paper will provide the physical background, equipment being used, as well as post-processing methods that are used to analyse sequences of thermograms. This work also presents the fields of applicability of IRT with a focus on the aspects related to reinforced concrete structures, as well as the advantages, limitations and potential sources of errors of IRT employment. Additionally previous non-destructive testing (NDT) studies that employed thermography techniques with natural excitation are briefly presented. A review of the future trends of thermal imaging are also included in this work. It can be concluded that while IRT is a useful tool for the characterisation of defects in the building sector, there is great prospect for the development of more advanced, effective and accurate approaches that will employ a combination of thermography approaches.

show abstract

Section: Defect Detectability and Quantificationmentioning

confidence: 93%

“…Dudzik [62] presented a two-stage neural algorithm for defect detection and characterization. In order to estimate the defect depth, two neural networks trained on data obtained using an active IRT were employed.…”

Section: Defect Detectability and Quantificationmentioning

confidence: 99%

Review of Active IR Thermography for Detection and Characterization of Defects in Reinforced Concrete

2016

View full text Add to dashboard Cite

show abstract

“…ATs working principle is that defects and other types of discontinuities in materials tructure can alter a specimen’s diffusivity and cause heat flow alterations [ 2 ]. In this work, we focus on AT and the detection of internal defects [ 3 ], as well as their dimensional analysis [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

Predictive Models for the Characterization of Internal Defects in Additive Materials from Active Thermography Sequences Supported by Machine Learning Methods

Rodríguez‐Martín

Fueyo

Aguilera

et al. 2020

Sensors

View full text Add to dashboard Cite

The present article addresses a generation of predictive models that assesses the thickness and length of internal defects in additive manufacturing materials. These modes use data from the application of active transient thermography numerical simulation. In this manner, the raised procedure is an ad-hoc hybrid method that integrates finite element simulation and machine learning models using different predictive feature sets and characteristics (i.e., regression, Gaussian regression, support vector machines, multilayer perceptron, and random forest). The performance results for each model were statistically analyzed, evaluated, and compared in terms of predictive performance, processing time, and outlier sensibility to facilitate the choice of a predictive method to obtain the thickness and length of an internal defect from thermographic monitoring. The best model to predictdefect thickness with six thermal features was interaction linear regression. To make predictive models for defect length and thickness, the best model was Gaussian process regression. However, models such as support vector machines also had significative advantages in terms of processing time and adequate performance for certain feature sets. In this way, the results showed that the predictive capability of some types of algorithms could allow for the detection and measurement of internal defects in materials produced by additive manufacturing using active thermography as a non-destructive test.

show abstract

“…At present, it has been widely used in mechanical manufacturing, electric power, construction, chemical and other fields. At present, has been widely used in mechanical manufacturing, electric power, construction, chemical and other fields [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Experimental research on YSZ TBC structure debonding defect detection using long-pulsed excitation of infrared thermal wave non-destructive testing

et al. 2019

View full text Add to dashboard Cite

Thermal barrier coating structure components are prone to coating cracking, debonding and peeling defects in the service process, which affects the work safety and reliability of the hot end parts, even result to catastrophic consequences. Experimental research on Yttria-stabilized zirconia thermal barrier coating structure debonding defect detection has been conducted using long-pulsed excitation of infrared wave non-destructive testing technology. Differences between surface temperature signals of sound and defective regions, detection effect comparison of heating and cooling process, detection effect comparison of different defect preparation methods, and impact of inspection parameters on detection effect were studied and discussed. The research conclusions will provide technical guidance to Yttria-stabilized zirconia thermal barrier coating structure debonding defects using long-pulsed excitation of infrared wave non-destructive testing technology.

show abstract

Two-stage neural algorithm for defect detection and characterization uses an active thermography

Cited by 39 publications

References 20 publications

Review of Active IR Thermography for Detection and Characterization of Defects in Reinforced Concrete

Review of Active IR Thermography for Detection and Characterization of Defects in Reinforced Concrete

Predictive Models for the Characterization of Internal Defects in Additive Materials from Active Thermography Sequences Supported by Machine Learning Methods

Experimental research on YSZ TBC structure debonding defect detection using long-pulsed excitation of infrared thermal wave non-destructive testing

Contact Info

Product

Resources

About