Concrete Subsurface Crack Detection Using Thermal Imaging in a Deep Neural Network

Mabrouka Abuhmida(1*), Daniel Milner(2), Jiping Bai(3)

(1) University of South Wales
(2) University of South Wales
(3) University of South Wales
(*) Corresponding Author


Impact actions, such as a zone directly affected by conflict and warfare, can negatively impact the structural integrity of concrete structures. Even indirect impact actions can make structures unsafe, creating subsurface defects in concrete. However, the result of indirect impact actions is often undetected because of the time required and expert knowledge needed to assess the structure. Yet, there are no techniques currently available to assess the usability and the safety of a concrete structure rapidly and with no expert knowledge.. This paper presents a combination of thermal imaging and artificial intelligence (AI) to enable a novel, contactless, autonomous, and fast technique for detecting hidden defects in concrete structures. In this paper, a ResNet50 model was trained on simulated data of subsurface defected and defect-free concrete blocks to test if it is possible to classify between the two. The model developed achieved a validation accuracy of 99.93%. Because of the success of this model, a laboratory experiment was conducted by compressing concrete blocks and recording the process using a thermal camera to create a dataset of concrete blocks with and without subsurface cracks. This dataset was used to train a new model with the same architecture and hyper-parameters as the initial model and achieved a validation accuracy of 100%. This investigation proves it is possible for AI to detect subsurface cracks and hidden defects by classifying the thermal images of concrete surfaces.


Deep learning; thermal imaging; concrete defects; artificial intelligence

Full Text:



[1] J. C. Agunwamba and T. Adagba, 'A COMPARATIVE ANALYSIS OF THE REBOUND HAMMER AND ULTRASONIC PULSE VELOCITY IN TESTING CONCRETE', Niger. J. Technol., vol. 31, no. 1, p. 9, 2012.

[2] INTERNATIONAL ATOMIC ENERGY AGENCY, 'Guidebook on non-destructive testing of concrete structures'. 2002.

[3] R. L. Wankhade and A. B. Landage, 'Non-destructive Testing of Concrete Structures in Karad Region', Procedia Eng., vol. 51, pp. 8–18, 2013, doi: 10.1016/j.proeng.2013.01.005.

[4] J. Hoła, J. Bień, Ł. Sadowski, and K. Schabowicz, 'Non-destructive and semi-destructive diagnostics of concrete structures in assessment of their durability', Bull. Pol. Acad. Sci. Tech. Sci., vol. 63, no. 1, pp. 87–96, Mar. 2015, doi: 10.1515/bpasts-2015-0010.

[5] G. Thiagarajan, A. V. Kadambi, S. Robert, and C. F. Johnson, 'Experimental and finite element analysis of doubly reinforced concrete slabs subjected to blast loads', Int. J. Impact Eng., vol. 75, pp. 162–173, Jan. 2015, doi: 10.1016/j.ijimpeng.2014.07.018.

[6] M. Valinejadshoubi, A. Bagchi, and O. Moselhi, 'Structural health monitoring of buildings and infrastructure', Struct. Health Monit., vol. 1, p. 50371, 2016.

[7] R. Jankowski, 'Impact force spectrum for damage assessment of earthquake-induced structural pounding', in Key Engineering Materials, 2005, vol. 293, pp. 711–718.

[8] C. S. Scutarasu, D. Diaconu-Şotropa, and M. Barbuta, 'Case Study on Modeling Fire Action Complexity in Fire Safety Engineering of Structures', in Advanced Engineering Forum, 2017, vol. 21, pp. 102–107.

[9] B. Kim, S.-W. Choi, G. Hu, D.-E. Lee, and R. O. Serfa Juan, 'Multivariate Analysis of Concrete Image Using Thermography and Edge Detection', Sensors, vol. 21, no. 21, p. 7396, Nov. 2021, doi: 10.3390/s21217396.

[10] G. F. Sirca Jr. and H. Adeli, 'INFRARED THERMOGRAPHY FOR DETECTING DEFECTS IN CONCRETE STRUCTURES', J. Civ. Eng. Manag., vol. 24, no. 7, pp. 508–515, Nov. 2018, doi: 10.3846/jcem.2018.6186.

[11] J. McKinney and F. Ali, 'Artificial Neural Networks for the Spalling Classification & Failure Prediction Times of High Strength Concrete Columns', J. Struct. Fire Eng., vol. 5, no. 3, pp. 203–214, Sep. 2014, doi: 10.1260/2040-2317.5.3.203.

[12] S. Gupta, 'Using Artificial Neural Network to Predict the Compressive Strength of Concrete containing Nano-silica', Civ. Eng. Archit., vol. 1, no. 3, pp. 96–102, Oct. 2013, doi: 10.13189/cea.2013.010306.

[13] G. Trtnik, F. Kavčič, and G. Turk, 'Prediction of concrete strength using ultrasonic pulse velocity and artificial neural networks', Ultrasonics, vol. 49, no. 1, pp. 53–60, Jan. 2009, doi: 10.1016/j.ultras.2008.05.001.

[14] H. N. Muliauwan, D. Prayogo, G. Gaby, and K. Harsono, 'Prediction of Concrete Compressive Strength Using Artificial Intelligence Methods', J. Phys. Conf. Ser., vol. 1625, no. 1, p. 012018, Sep. 2020, doi: 10.1088/1742-6596/1625/1/012018.

[15] I. Ignatov, O. Mosin, and C. Stoyanov, 'Fields in electromagnetic spectrum emitted from human body. applications in medicine', J. Health Med. Nurs., vol. 7, no. 1–22, 2014.

[16] J. M. Lloyd, Thermal imaging systems. Springer Science & Business Media, 2013.

[17] H. Choi, B. F. Soeriawidjaja, S. H. Lee, and M. Kwak, 'A convenient platform for real-time non-contact thermal measurement and processing', Bull. Korean Chem. Soc., 2022.

[18] M. Atkins and M. Boer, 'Application of Thermo-Fluidic Measurement Techniques'. Butterworth-Heinemann, 2016.

[19] T. Sakagami and S. Kubo, 'Development of a new non-destructive testing technique for quantitative evaluations of delamination defects in concrete structures based on phase delay measurement using lock-in thermography', Infrared Phys. Technol., vol. 43, no. 3–5, pp. 311–316, 2002.

[20] C. Maierhofer, A. Brink, M. Röllig, and H. Wiggenhauser, 'Quantitative impulse-thermography as non-destructive testing method in civil engineering–Experimental results and numerical simulations', Constr. Build. Mater., vol. 19, no. 10, pp. 731–737, 2005.

[21] H. Wiggenhauser, 'Active IR-applications in civil engineering', Infrared Phys. Technol., vol. 43, no. 3–5, pp. 233–238, 2002.

[22] K. Tomita and M. Y. L. Chew, 'A Review of infrared thermography for delamination detection on infrastructures and buildings', Sensors, vol. 22, no. 2, p. 423, 2022.

[23] Y. Cho, N. Bianchi-Berthouze, N. Marquardt, and S. J. Julier, 'Deep Thermal Imaging: Proximate Material Type Recognition in the Wild through Deep Learning of Spatial Surface Temperature Patterns', in Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, Montreal QC Canada, Apr. 2018, pp. 1–13. doi: 10.1145/3173574.3173576.

[24] R. Khallaf and M. Khallaf, 'Classification and analysis of deep learning applications in construction: A systematic literature review', Autom. Constr., vol. 129, p. 103760, Sep. 2021, doi: 10.1016/j.autcon.2021.103760.

[25] T. Drzymała, W. Jackiewicz-Rek, M. Tomaszewski, A. Kuś, J. Gałaj, and R. Šukys, ‘Effects of High Temperature on the Properties of High Performance Concrete (HPC)’, Procedia Eng., vol. 172, pp. 256–263, 2017, doi: 10.1016/j.proeng.2017.02.108.

[26] D. Andrushia A, A. N, E. Lubloy, and P. A. G, 'Deep learning based thermal crack detection on structural concrete exposed to elevated temperature', Adv. Struct. Eng., vol. 24, no. 9, pp. 1896–1909, Jul. 2021, doi: 10.1177/1369433220986637.

[27] D. G. Aggelis, E. Z. Kordatos, M. Strantza, D. V. Soulioti, and T. E. Matikas, 'NDT approach for characterisation of subsurface cracks in concrete', Constr. Build. Mater., vol. 25, no. 7, pp. 3089–3097, Jul. 2011, doi: 10.1016/j.conbuildmat.2010.12.045.

[28] M. Abuhmida, D. Milne, J. Bai, and M. Sahal, 'ABAQUS-concrete hidden defects thermal simulation'. Mendeley Data, 2022. doi: 10.17632/65nbxg9pr3.1.

[29] G. G. Celano, 'A ResNet-50-based Convolutional Neural Network Model for Language ID Identification from Speech Recordings', in Proceedings of the Third Workshop on Computational Typology and Multilingual NLP, 2021, pp. 136–144.

[30] Y. Fang, L. Dong, H. Bao, X. Wang, and F. Wei, 'Corrupted image modeling for self-supervised visual pre-training', ArXiv Prepr. ArXiv220203382, 2022.

[31] S. Mascarenhas and M. Agarwal, 'A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification', in 2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON), 2021, vol. 1, pp. 96–99.

[32] K. He, X. Zhang, S. Ren, and J. Sun, 'Deep Residual Learning for Image Recognition'.

[33] T. Ridnik, H. Lawen, A. Noy, E. Ben Baruch, G. Sharir, and I. Friedman, 'Tresnet: High performance gpu-dedicated architecture', in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 1400–1409.

[34] J. Peng et al., 'Residual convolutional neural network for predicting response of transarterial chemoembolisation in hepatocellular carcinoma from CT imaging', Eur. Radiol., vol. 30, no. 1, pp. 413–424, 2020.

[35] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, 'Rethinking the inception architecture for computer vision', presented at the Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 2818–2826.

[36] M.-H. Guo et al., 'Attention mechanisms in computer vision: A survey', Comput. Vis. Media, vol. 8, no. 3, pp. 331–368, 2022.

[37] D. Hu, J. Chen, and S. Li, 'Reconstructing unseen spaces in collapsed structures for search and rescue via deep learning based radargram inversion', Autom. Constr., vol. 140, p. 104380, 2022.

[38] M. Abuhmida, D. Milne, J. Bai, and M. Sahal, 'Concrete pressure test- thermal images'. Mendeley Data, 2022. doi: 10.17632/kbvssyjhcj.1.


Article Metrics

Abstract views : 323 | views : 233


  • There are currently no refbacks.

Copyright (c) 2023 IJCCS (Indonesian Journal of Computing and Cybernetics Systems)

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Copyright of :
IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
ISSN 1978-1520 (print); ISSN 2460-7258 (online)
is a scientific journal the results of Computing
and Cybernetics Systems
A publication of IndoCEISS.
Gedung S1 Ruang 416 FMIPA UGM, Sekip Utara, Yogyakarta 55281
Fax: +62274 555133 |

View My Stats1
View My Stats2