Artificial intelligence approach for detecting material deterioration in hybrid building constructions

Andrei V. Chesnokov1, Vitalii V. Mikhailov1, Ivan V. Dolmatov1

1The Faculty of Civil Engineering, Lipetsk State Technical University, Moskovskaya street 30, 398600 Lipetsk, Russian Federation.



Hybrid constructions include heterogeneous materials with different behaviors under load. The aim is to achieve a so-called synergistic effect when the advantages of particular structural elements complement each other in a unified system.
The building constructions considered in the research include high-strength steel cables, fiberglass rods, and flexible polymer membranes. The membrane is attached to the rods which have been elastically bent from the initially straight shape into an arch-like form.
Structural materials inevitably deteriorate during a long operational period. The present study focuses on detecting material deterioration using Artificial Neural Networks (ANNs), which belong to the scope of intelligent techniques for data analysis.
Appropriate ANN structures and required features are proposed. A semi-supervised learning strategy is used. The approach allows the training of the networks with normal data only derived from the construction without defects. Material degradationis detected by the level of reconstruction error produced by the network given the input data.
The work contributes to the field of structural health monitoring of hybrid building constructions. It provides the opportunity to detect material deterioration given the forces in particular structural elements.

Cite as:

Chesnokov, A. V., Mikhailov, V. V., & Dolmatov, I. V. (2021). Artificial intelligence approach for detecting material deterioration in hybrid building constructions. Computer Methods in Materials Science, 21(2), 83-94.

Article (PDF):

Key words:

Hybrid constructions, Material deterioration, Artificial neural network, Semi-supervised machine learning


Bridgens, B.N., Gosling, P.D., & Birchall, M.J.S. (2004). Tensile fabric structures: concepts, practice and developments. The Structural Engineer, 82(14), 21–27.

Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: a survey. ACM Computing Surveys, 41(3), article 15, 1–58.

Chesnokov, A.V., Mikhailov, V.V., & Dolmatov, I.V. (2017). Bending-active dome-shaped structure. In K. Bletzinger, E. Oñate, & B. Kröplin (Eds.). VIII International Conference on Textile Composites and Inflatable Structures. Structural membranes 9–11 october 2017, Munich, Germany (pp. 427–435).

Chesnokov, A.V., Mikhailov, V.V., & Dolmatov, I.V. (2019). Bending-active frame: analysis and estimation of structural parameters. In A. Zanelli, C. Monticelli, M. Mollaert, B. Stimpfle (Eds.). Proceedings of the TensiNet Symposium. Softening the habitats. Sustainable innovation in minimal mass structures and lightweight architectures (pp. 111–122).

Colasante, G., & Gosling, P.D. (2016). Including shear in a neural network constitutive model for architectural textiles. In J. Chilton, P. Gosling, M. Mollaert, & B. Stimpfle (Eds.). TENSINET – COST TU1303 International Symposium 2016
“Novel structural skins – Improving sustainability and efficiency through new structural textile materials and designs”
(pp. 103–112). “Procedia Engineering”, vol. 155.

Gipperich, K., Canobbio, R., Lombardi, S., & Malinowsky, M. (2004). Fabrication, installation and maintenance. In B. Forster, & M. Mollaert (Eds.). European Design Guide for Tensile Surface Structures (pp. 243–254). TensiNet.

Hansen, L.K., & Salamon, P. (1990). Neural network ensembles. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(10), 993–1001.

Hodge, V.J., & Austin, J. (2004). A survey of outlier detection methodologies. Artificial Intelligence Review, 22(2),

Horr, A.M., Asadsajadi, S.R., & Safi, M. (2003). Design of large space structures with imperfection using ANN-based simulator. International Journal of Space Structures, 18(4), 235–255.
Kaveh, A., & Dehkordi, M.R. (2003). Neural networks for the analysis and design of domes, International Journal of Space Structures, 18(3), 181–193.

Lienhard, J., Alpermann, H., Gengnagel, C., & Knippers, J. (2013). Active bending, a review on structures where bending is used as a self-formation process, International Journal of Space Structures, 28(3–4), 187–196.

Luo, T., & Nagarajan, S.G. (2018). Distributed anomaly detection using autoencoder neural networks in WSN for IoT. In 2018 IEEE International Conference on Communications (ICC) (pp. 1–6).

Osovskiy, S. (2002). Neyronnyye seti dlya obrabotki informatsii. Finansy i statistika [Осовский, С. (2002). Нейронные сети для обработки информации. Финансы и статистика].

Pozo, F., Tibaduiza, D.A., Anaya, M., & Vitola, J. (2017). A machine learning methodology for structural damage classification in structural health monitoring. In A. Guemes, A. Benjeddou, J. Rodellar, & J. Leng (Eds.). 8th ECCOMAS Thematic Conference ,on Smart Structures and Materials. SMART 2017 (pp. 698–708).

Sommerville, J. (2007). Defects and rework in new build: an analysis of the phenomenon and drivers. Structural Survey, 25(5), 391–407.

Thimm, G., & Fiesler, E. (1995). Neural network initialization. In J. Mira, F. Sandoval (Eds.). From Natural to Artificial Neural Computation (pp. 533–542), IWANN.

Van Mele, T., De Laet, L., Veenendaal, D., Mollaert, M., & Block, P. (2013). Shaping tension structures with actively bent linear elements, International Journal of Space Structures, 28(3–4), 127–135.

Wang, C., Abdul-Rahman, H., Wood, L.C., Mohd-Rahim, F.A., Zainon, N., & Saputri, E. (2015). Defects of tensioned membrane ,structures (TMS) in the Tropics. Journal of Performance of Constructed Facilities, 29(2).