METHODOLOGY FOR INTEGRATING ARTIFICIAL INTELLIGENCE AND INFORMATION MODELING TECHNOLOGIES IN DESIGNING WOODEN MEMORIAL COMPLEXES
DOI:
https://doi.org/10.36773/1818-1112-2026-139-1-50-58Keywords:
Building Information Model, generative design, diffusion models, parametric design, wooden structures, digital design technologies, ArchiCAD, Stable Diffusion, neural network visualization, small architectural formsAbstract
The current stage of construction industry development is characterized by active implementation of digital technologies that create prerequisites for transformation of traditional design processes. This study is devoted to the development of an integrated methodology for designing small architectural memorial forms made of wood, based on sequential application of generative neural network models, parametric information modeling, and automated visualization algorithms.
Experimental validation was performed on the design of a memorial complex including an arched-frame gazebo with a diameter of 9,5 m and a five-beam truss structure. Application of Stable Diffusion and Midjourney diffusion models enabled generation of 40 conceptual variants in 3,5 hours, which is 17–23 times faster than traditional sketching. Systematic analysis revealed optimal text prompt volume in the range of 150–200 words, ensuring concept compliance at the level of 8,9 out of 10 with quality improvement of 43,5 % compared to brief descriptions.
Information model of LOD 350 detail level includes 247 elements of the arched system and 184 elements of the truss structure.
Neural network visualization using diffusion models and ControlNet module reduced time costs by 3,6–4,6 times while maintaining quality at 8,4 versus 8,7 for traditional rendering. Optimal generation parameters were established: denoising strength in range of 0,60–0,70 and guidance scale in range of 9–11 units.
Developed methodology provides reduction of total labor costs by 80–85 % with economic effect of 6,66–13,28 million rubles annually for an organization with project portfolio of 15–20 objects. Payback period of investments is 0,8–1,6 months. Results confirm feasibility of integrating artificial intelligence technologies and information modeling for creating efficient adaptive design process.
References
Azhar, S. Building Information Modeling (BIM): Trends, Benefits, Risks, and Challenges for the AEC Industry / S. Azhar // Leadership and Management in Engineering. – 2011. – Vol. 11, № 3. – P. 241–252. – DOI: 10.1061/(ASCE)LM.1943-5630.0000127.
BIM Handbook: A Guide to Building Information Modeling for Owners, Managers, Designers, Engineers and Contractors / C. Eastman, P. Teicholz, R. Sacks, K. Liston. – 2nd ed. – Hoboken : John Wiley & Sons, 2011. – 648 p. – DOI: 10.1002/9780470261309.
Caetano, I. Computational design in architecture: Defining parametric, generative, and algorithmic design / I. Caetano, L. Santos, A. Leitão // Frontiers of Architectural Research. – 2020. – Vol. 9, № 2. – P. 287–300. – DOI: 10.1016/j.foar.2019.12.008.
The wood from the trees: The use of timber in construction / M. H. Ramage, H. Burridge, M. Busse-Wicher [et al.] // Renewable and Sustainable Energy Reviews. – 2017. – Vol. 68. – P. 333–359. – DOI: 10.1016/j.rser.2016.09.107.
Dallasega, P. Industry 4.0 as an Enabler of Proximity for Construction Supply Chains: A Systematic Literature Review / P. Dallasega, E. Rauch, C. Linder // Computers in Industry. – 2018. – Vol. 99. – P. 205–225. – DOI: 10.1016/j.compind.2018.03.039.
Bryde, D. The project benefits of Building Information Modelling (BIM) / D. Bryde, M. Broquetas, J. M. Volm // International Journal of Project Management. – 2013. – Vol. 31, № 7. – P. 971–980. – DOI: 10.1016/j.ijproman.2012.12.001.
Artificial Intelligence and Architectural Design: An Introduction / J. Muntañola, M. Saura, A. Cocho-Bermejo, J. Beltran Borràs. – Barcelona : Polytechnic University of Catalonia, 2022. – DOI: 10.5821/ebook-9788419184498.
High-Resolution Image Synthesis with Latent Diffusion Models / R. Rombach, A. Blattmann, D. Lorenz [et al.] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). – New Orleans, 2022. – P. 10684–10695. – DOI: 10.1109/CVPR52688.2022.01042.
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding / C. Saharia, W. Chan, S. Saxena [et al.] // Advances in Neural Information Processing Systems (NeurIPS). – 2022. – Vol. 35. – P. 36479–36494. – DOI: 10.48550/arXiv.2205.11487.
Amanzadegan, M. A Systematic Review of the BIM in Construction: From Smart Building Management to Interoperability of BIM & AI / M. Amanzadegan, A. Heidari, Y. Peyvastehgar // Architectural Science Review. – 2023. – Vol. 66, № 5. – P. 1–20. – DOI: 10.1080/00038628.2023.2263721.
Integrating Building Information Modelling and Artificial Intelligence in Construction Projects: A Review of Challenges and Mitigation Strategies / A. A. Khan, A. O. Bello, M. Arqam [et al.] // Technologies. – 2024. – Vol. 12, № 10. – Art. 185. – DOI: 10.3390/technologies12100185.
Integrated applications of building information modeling and artificial intelligence techniques in the AEC/FM industry / F. Zhang, A. P. C. Chan, A. Darko [et al.] // Automation in Construction. – 2022. – Vol. 139. – Art. 104289. – DOI: 10.1016/j.autcon.2022.104289.
Nguyen Van, T. Research Trends on Machine Learning in Construction Management: A Scientometric Analysis / T. Nguyen Van, T. Nguyen Quoc // Journal of Applied Science and Technology Trends. – 2021. – Vol. 2, № 2. – P. 124–132. – DOI: 10.38094/jastt203105.
Alnajjar, O. A Systematic Review of Lean Construction, BIM and Emerging Technologies Integration: Identifying Key Tools / O. Alnajjar, E. Atencio, J. Turmo // Buildings. – 2025. – Vol. 15, № 16. – Art. 2884. – DOI: 10.3390/buildings15162884.
Towards 4D BIM: A Systematic Literature Review on Challenges, Strategies and Tools in Leveraging AI with BIM / M. Awe, A. Malhi, M. Budka [et al.] // Buildings. – 2025. – Vol. 15, № 7. – Art. 1072. – DOI: 10.3390/buildings15071072.
Generative AI for Architectural Design: A Literature Review / C. Li, T. Zhang, X. Du [et al.] // arXiv. – 2024. – arXiv:2404.01335. – URL: https://arxiv.org/abs/2404.01335 (date of access: 24.10.2025).
Lobos-Calquin, D. Implementation of BIM Technologies in Wood Construction: Multidisciplinary Review / D. Lobos-Calquin, R. Mata, C. Correa [et al.] // Buildings. – 2024. – Vol. 14, № 3. – P. 677. – DOI: 10.3390/buildings14030677.
BIMForum. Level of Development (LOD) Specification, Part I & Commentary. – Washington D.C. : BIMForum, 2023. – 238 p. – URL: https://bimforum.org/lod (дата обращения: 24.10.2025).
Zhang, L. Adding Conditional Control to Text-to-Image Diffusion Models / L. Zhang, A. Rao, M. Agrawala // Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). – Paris, 2023. – P. 3836–3847. – DOI: 10.1109/ICCV51070.2023.00355.
As, I. Artificial Intelligence in Architecture: Generating Conceptual Design via Deep Learning / I. As, P. Basu // International Journal of Architectural Computing. – 2018. – Vol. 16, № 4. – P. 306–327. – DOI: 10.1177/1478077118800982.
Artificial Intelligence in the Construction Industry: A Review of Present Status, Opportunities and Future Challenges / S. O. Abioye, L. O. Oyedele, L. Akanbi [et al.] // Journal of Building Engineering. – 2021. – Vol. 44. – P. 103299. – DOI: 10.1016/j.jobe.2021.103299.
Ho, J. Denoising Diffusion Probabilistic Models / J. Ho, A. Jain, P. Abbeel // Advances in Neural Information Processing Systems (NeurIPS). – 2020. – Vol. 33. – P. 6840–6851. – DOI: 10.48550/arXiv.2006.11239.
Regenwetter, L. Deep Generative Models in Engineering Design: A Review / L. Regenwetter, A. H. Nobari, F. Ahmed // Journal of Mechanical Design. – 2022. – Vol. 144, № 7. – P. 071703. – DOI: 10.1115/1.4053859.
Исаев, Ш. М. Современные подходы к проектированию архитектурного освещения с помощью искусственного интеллекта / Ш. М. Исаев, А. И. Зацепина // Неделя науки Инженерно-строительного института – 2025: материалы секции «Цифровое строительство зданий и сооружений». – СПб. : Изд-во СПбПУ, 2025. – С. 263–265.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The work is provided under the terms of Creative Commons public license Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). This license allows an unlimited number of persons to reproduce and share the Licensed Material in all media and formats. Any use of the Licensed Material shall contain an identification of its Creator(s) and must be for non-commercial purposes only. Users may not prevent other individuals from taking any actions allowed by the license.
