Pattern Deep Region Learning for Crack Detection in Thermography Diagnosis System

Hu, Jue; Xu, Weiping; Gao, Bin; Tian, Gui Yun; Wang, Yizhe; Wu, Yong Bo; Yin, Ying; Chen, Juan

doi:10.3390/met8080612

Cited by 34 publications

(18 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jang et al, use data from vision and laser IR thermography along with deep convolutional neural networks (CNN) to improve concrete crack detectability [23]. In [24], the authors use principal component analysis (PCA) along with Faster-Region CNN to improve the crack detection rate in stainless steel and steel specimens from eddy current pulsed thermography data.…”

Section: Thermography Non-destructive Testingmentioning

confidence: 99%

Transient Thermography for Flaw Detection in Friction Stir Welding: A Machine Learning Approach

Atwya

Panoutsos

2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

A systematic computational method to simulate and detect sub-surface flaws, through non-destructive transient thermography, in aluminium sheets and friction stir welded sheets is proposed. The proposed method relies on feature extraction methods and a data-driven machine learning modelling structure. In this work, we propose the use of a multi-layer perceptron feed-forward neural-network with feature extraction methods to improve the flaw-probing depth of transient thermography inspection. Furthermore, for the first time, we propose Thermographic Signal Linear Modelling (TSLM), a hyper-parameterfree feature extraction technique for transient thermography. The new feature extraction and modelling framework was tested with out-of-sample experimental transient thermography data and results show effectiveness in sub-surface flaw detection of up to 2.3 mm deep in aluminium sheets (99.8 % true positive rate, 92.1 % true negative rate) and up to 2.2 mm deep in friction stir welds (97.2 % true positive rate, 87.8 % true negative rate).

show abstract

Section: Thermography Non-destructive Testingmentioning

confidence: 99%

Transient Thermography for Flaw Detection in Friction Stir Welding: A Machine Learning Approach

Atwya

Panoutsos

2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…Finally, Hu et al [6] proposed an end-to-end pattern deep region learning structure to achieve precise crack detection and localization with the eddy current pulsed thermography technique. The proposed approach was tested with experimental tests on artificial and natural cracks derived from industry.…”

Section: Contributionsmentioning

confidence: 99%

Thermal Methods for Damage Evaluation of Metallic Materials

Galietti

Palumbo

2019

Metals

View full text Add to dashboard Cite

show abstract

“…For the defect identification and detection, several state-of-the-art defect detection algorithms have been proposed in previous literature. These included Faster-Region based Convolutional Neural Networks (Faster-RCNN) [4], YOLO-V3 [5], Autoencoders structured neural network [6], and conditional monitoring (CM)-based feature learning methods [7,8]. Faster-RCNN and YOLO-V3 detectors were used to automatically localize flaws in a thermography diagnosis system.…”

Section: Introductionmentioning

confidence: 99%

Automatic Defects Segmentation and Identification by Deep Learning Algorithm with Pulsed Thermography: Synthetic and Experimental Data

Fang

Ibarra-Castanedo

Maldague

2021

BDCC

View full text Add to dashboard Cite

In quality evaluation (QE) of the industrial production field, infrared thermography (IRT) is one of the most crucial techniques used for evaluating composite materials due to the properties of low cost, fast inspection of large surfaces, and safety. The application of deep neural networks tends to be a prominent direction in IRT Non-Destructive Testing (NDT). During the training of the neural network, the Achilles heel is the necessity of a large database. The collection of huge amounts of training data is the high expense task. In NDT with deep learning, synthetic data contributing to training in infrared thermography remains relatively unexplored. In this paper, synthetic data from the standard Finite Element Models are combined with experimental data to build repositories with Mask Region based Convolutional Neural Networks (Mask-RCNN) to strengthen the neural network, learning the essential features of objects of interest and achieving defect segmentation automatically. These results indicate the possibility of adapting inexpensive synthetic data merging with a certain amount of the experimental database for training the neural networks in order to achieve the compelling performance from a limited collection of the annotated experimental data of a real-world practical thermography experiment.

show abstract

Pattern Deep Region Learning for Crack Detection in Thermography Diagnosis System

Cited by 34 publications

References 33 publications

Transient Thermography for Flaw Detection in Friction Stir Welding: A Machine Learning Approach

Transient Thermography for Flaw Detection in Friction Stir Welding: A Machine Learning Approach

Thermal Methods for Damage Evaluation of Metallic Materials

Automatic Defects Segmentation and Identification by Deep Learning Algorithm with Pulsed Thermography: Synthetic and Experimental Data

Contact Info

Product

Resources

About