A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing

Junaid Khan; Shalini Paka; Wisam Bukaita

doi:doi:10.11648/j.ajce.20251306.13

Research Article |

| Peer-Reviewed

A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing

Junaid Khan, Shalini Paka, Wisam Bukaita^*

Published in American Journal of Civil Engineering (Volume 13, Issue 6)

Received: 28 October 2025 Accepted: 7 November 2025 Published: 9 December 2025

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

This study presents a machine learning framework for the automated design of reinforced concrete (RC) beams in compliance with ACI 318-19 code provisions. Traditional RC beam design requires iterative calculations to satisfy strength and serviceability criteria across a wide range of geometric, material, and loading parameters. To enhance efficiency and consistency, a dataset comprising 10,000 synthetically generated beam configurations was developed by varying span length, concrete compressive strength, steel yield stress, and applied loading. Each configuration was generated using ACI 318-19 design equations to ensure code compliance and structural validity. A deep neural network (DNN) regression model was trained to learn the nonlinear mapping between input parameters and corresponding design outputs, including required tensile reinforcement, bar diameters, stirrup spacing, and ultimate moment capacity. Model performance was evaluated using a quantitative error matrix reporting mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R²) for each output variable. The model achieved MAE values ranging from 0.35 to 10 units, RMSE values from 0.45 to 12 units, and R² values between 0.95 and 0.99, demonstrating high predictive accuracy and strong agreement with ACI-based reference designs. These results confirm that the framework can automatically generate code-compliant RC beam designs with high fidelity to ACI 318-19 specifications. By providing consistent, rapid, and interpretable predictions, this approach establishes a foundation for AI-assisted structural engineering tools that reduce computational time, improve design accuracy, and support data-driven automation in structural design workflows.

Published in	American Journal of Civil Engineering (Volume 13, Issue 6)
DOI	10.11648/j.ajce.20251306.13
Page(s)	350-361
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2025. Published by Science Publishing Group

Keywords

Deep Learning Framework, Reinforced Concrete Beam Design, ACI 318-19 Code Compliance, Structural Design Automation, Explainable Artificial Intelligence (XAI), Code-Constrained Neural Networks

References

[1]	Yehia, Saad A., Sabry Fayed, and Mohamed H. Zakaria. 2024. “Prediction of RC T-Beams Shear Strength Based on Machine Learning.” International Journal of Concrete Structures & Materials 18: 52. https://doi.org/10.1186/s40069-024-00690-z
[2]	Yang, Yuanzhang, and Gaoyang Liu. 2023. “Data-Driven Shear Strength Prediction of FRP-Reinforced Concrete Beams without Stirrups Based on Machine Learning Methods.” Buildings 13(2): 313. https://doi.org/10.3390/buildings13020313
[3]	Pham, Anh-Duc, Nguyen Thi-Kha, and Ngo Ngoc-Tri. 2020. “Machine Learning for Predicting Long-Term Deflections in Reinforced Concrete Flexural Structures.” Journal of Computational Design and Engineering 7(1): 95-106. https://doi.org/10.1093/jcde/qwaa010
[4]	Bedriñana, Luis Alberto, Julio Sucasaca, Jhon Tovar, and Henry Burton. 2023. “Design-Oriented Machine-Learning Models for Predicting the Shear Strength of Prestressed Concrete Beams.” Journal of Bridge Engineering 4: BEENG-6013. https://doi.org/10.1061/jbenf2.beeng-6013
[5]	Gasser, Moamen, Omar Mahmoud, and Taha Elsayed. 2023. “Reliable Machine Learning for the Shear Strength of Beams Strengthened Using Externally Bonded FRP Jackets.” Frontiers in Materials 10: 1153421. https://doi.org/10.3389/fmats.2023.1153421
[6]	Hoang et al. 2022: “Shear Strength Estimation of Reinforced Concrete Deep Beams: A Hybrid Soft Computing Approach” (Sustainability 2022, 14(9): 5238). https://doi.org/10.3390/su14095238
[7]	Abushanab, Abdelrahman, Tadesse Gemeda Wakjira, and Wael Alnahhal. 2023. “Machine Learning-Based Flexural Capacity Prediction of Corroded RC Beams with an Efficient and User-Friendly Tool.” Sustainability 15: 4824. https://doi.org/10.3390/su15064824
[8]	Ma, Cailong, Sixuan Wang, Jianping Zhao, Xufeng Xiao, Chenxi Xie, and Xinlong Feng. 2023. “Prediction of Shear Strength of RC Deep Beams Based on Interpretable Machine Learning.” Construction and Building Materials 131640. https://doi.org/10.1016/j.conbuildmat.2023.131640
[9]	Hosseinzadeh, Alireza, and Mehdi Dehestani. 2025. “Intelligent Low-Carbon Reinforced Concrete Beam Design Optimization via Deep Reinforcement Learning.” Scientific Reports 15: 33143. https://doi.org/10.1038/s41598-025-18543-4
[10]	Jeong, Jong Hyun, and Hongki Jo. 2021. “Deep Reinforcement Learning for Automated Design of Reinforced Concrete Structures.” Computer-Aided Civil and Infrastructure Engineering 36(12): 1508-1529. https://doi.org/10.1111/mice.12773
[11]	Yang, Jian, Yan Hao, Dang Peng, Jun Shi, and Yi Zhang. 2025. “Machine Learning-Based Methods for Predicting the Structural Damage and Failure Mode of RC Slabs Under Blast Loading.” Buildings 15(8): 1221. https://doi.org/10.3390/buildings15081221
[12]	Zhang, Chao, Xuhong Zhou, Chengran Xu, Zhou Wu, Jiepeng Liu, and Hongtuo Qi. 2025. “Automatic Generation of Precast Concrete Component Fabrication Drawings Based on BIM and Multi-Agent Reinforcement Learning.” Buildings 15(2): 284. https://doi.org/10.3390/buildings15020284
[13]	Mahmoodian, Mojtaba, and Shasha Wang. 2025. “Advancing Smart Construction through BIM-Enabled Automation in Reinforced Concrete Slab Design.” Buildings 15(3): 343. https://doi.org/10.3390/buildings15030343
[14]	Zhang, Guangnan, Zainab Hasan Ali, Mohammed Suleman Aldlemy, et al. (2020). “Reinforced concrete deep beam shear strength capacity modelling using an integrative bio-inspired algorithm with an artificial intelligence model.” Engineering with Computers 38(S1): 15-28. https://doi.org/10.1007/s00366-020-01137-1
[15]	Mahmoodian, Amir, and Lei Wang. 2025. “Advancing Smart Construction through BIM-Enabled Automation in Reinforced Concrete Slab Design.” Buildings 15(3): 343. https://doi.org/10.3390/buildings15030343
[16]	Laissy, Mohamed, Besher Belbol, Osama Boshi, and Abdalla Eldeiasti. 2024. “AI Analysis of the Thermal Effects on Reinforced Concrete Buildings with Floating Columns.” Engineering, Technology & Applied Science Research 14(5): 16154-16159. https://doi.org/10.48084/etasr.8160
[17]	Bai, Jing, and Wei Zhang. 2025. “Research on Concrete Beam Damage Detection Using Convolutional Neural Networks and Vibrations from ABAQUS Models and Computer Vision.” Buildings 15 (2): 220. https://doi.org/10.3390/buildings15020220
[18]	Tahaei Yaghoubi, Seyed Morteza, Mehrdad Vafaei, Ali Kheyroddin, and Farzad Hejazi. 2023. “Machine Learning-Based Predictive Models for Equivalent Damping Ratio of RC Shear Walls.” Bulletin of Earthquake Engineering 21(1): 1–25. https://doi.org/10.1007/s10518-022-01533-6
[19]	Alruwais, Nasser, and Mohammed Zakariah. 2023. “Student-Engagement Detection in Classroom Using Machine Learning Algorithm.” Electronics 12(3): 731. https://doi.org/10.3390/electronics12030731

Cite This Article

Plain Text BibTeX RIS

APA Style

Khan, J., Paka, S., Bukaita, W. (2025). A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing. American Journal of Civil Engineering, 13(6), 350-361. https://doi.org/10.11648/j.ajce.20251306.13

Copy | Download

ACS Style

Khan, J.; Paka, S.; Bukaita, W. A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing. Am. J. Civ. Eng. 2025, 13(6), 350-361. doi: 10.11648/j.ajce.20251306.13

Copy | Download

AMA Style

Khan J, Paka S, Bukaita W. A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing. Am J Civ Eng. 2025;13(6):350-361. doi: 10.11648/j.ajce.20251306.13

Copy | Download

@article{10.11648/j.ajce.20251306.13,
  author = {Junaid Khan and Shalini Paka and Wisam Bukaita},
  title = {A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing},
  journal = {American Journal of Civil Engineering},
  volume = {13},
  number = {6},
  pages = {350-361},
  doi = {10.11648/j.ajce.20251306.13},
  url = {https://doi.org/10.11648/j.ajce.20251306.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajce.20251306.13},
  abstract = {This study presents a machine learning framework for the automated design of reinforced concrete (RC) beams in compliance with ACI 318-19 code provisions. Traditional RC beam design requires iterative calculations to satisfy strength and serviceability criteria across a wide range of geometric, material, and loading parameters. To enhance efficiency and consistency, a dataset comprising 10,000 synthetically generated beam configurations was developed by varying span length, concrete compressive strength, steel yield stress, and applied loading. Each configuration was generated using ACI 318-19 design equations to ensure code compliance and structural validity. A deep neural network (DNN) regression model was trained to learn the nonlinear mapping between input parameters and corresponding design outputs, including required tensile reinforcement, bar diameters, stirrup spacing, and ultimate moment capacity. Model performance was evaluated using a quantitative error matrix reporting mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R2) for each output variable. The model achieved MAE values ranging from 0.35 to 10 units, RMSE values from 0.45 to 12 units, and R2 values between 0.95 and 0.99, demonstrating high predictive accuracy and strong agreement with ACI-based reference designs. These results confirm that the framework can automatically generate code-compliant RC beam designs with high fidelity to ACI 318-19 specifications. By providing consistent, rapid, and interpretable predictions, this approach establishes a foundation for AI-assisted structural engineering tools that reduce computational time, improve design accuracy, and support data-driven automation in structural design workflows.},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing
AU  - Junaid Khan
AU  - Shalini Paka
AU  - Wisam Bukaita
Y1  - 2025/12/09
PY  - 2025
N1  - https://doi.org/10.11648/j.ajce.20251306.13
DO  - 10.11648/j.ajce.20251306.13
T2  - American Journal of Civil Engineering
JF  - American Journal of Civil Engineering
JO  - American Journal of Civil Engineering
SP  - 350
EP  - 361
PB  - Science Publishing Group
SN  - 2330-8737
UR  - https://doi.org/10.11648/j.ajce.20251306.13
AB  - This study presents a machine learning framework for the automated design of reinforced concrete (RC) beams in compliance with ACI 318-19 code provisions. Traditional RC beam design requires iterative calculations to satisfy strength and serviceability criteria across a wide range of geometric, material, and loading parameters. To enhance efficiency and consistency, a dataset comprising 10,000 synthetically generated beam configurations was developed by varying span length, concrete compressive strength, steel yield stress, and applied loading. Each configuration was generated using ACI 318-19 design equations to ensure code compliance and structural validity. A deep neural network (DNN) regression model was trained to learn the nonlinear mapping between input parameters and corresponding design outputs, including required tensile reinforcement, bar diameters, stirrup spacing, and ultimate moment capacity. Model performance was evaluated using a quantitative error matrix reporting mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R2) for each output variable. The model achieved MAE values ranging from 0.35 to 10 units, RMSE values from 0.45 to 12 units, and R2 values between 0.95 and 0.99, demonstrating high predictive accuracy and strong agreement with ACI-based reference designs. These results confirm that the framework can automatically generate code-compliant RC beam designs with high fidelity to ACI 318-19 specifications. By providing consistent, rapid, and interpretable predictions, this approach establishes a foundation for AI-assisted structural engineering tools that reduce computational time, improve design accuracy, and support data-driven automation in structural design workflows.
VL  - 13
IS  - 6
ER  -

Copy | Download

Author Information

Junaid Khan

Math and Computer Science, Lawrence Technological University, Southfield, USA

Contact Email
Shalini Paka

Math and Computer Science, Lawrence Technological University, Southfield, USA

Contact Email
Wisam Bukaita

Math and Computer Science, Lawrence Technological University, Southfield, USA

Contact Email

http://orcid.org/0000-0001-6255-3848

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Khan, J., Paka, S., Bukaita, W. (2025). A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing. American Journal of Civil Engineering, 13(6), 350-361. https://doi.org/10.11648/j.ajce.20251306.13

Copy | Download

ACS Style

Khan, J.; Paka, S.; Bukaita, W. A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing. Am. J. Civ. Eng. 2025, 13(6), 350-361. doi: 10.11648/j.ajce.20251306.13

Copy | Download

AMA Style

Khan J, Paka S, Bukaita W. A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing. Am J Civ Eng. 2025;13(6):350-361. doi: 10.11648/j.ajce.20251306.13

Copy | Download

@article{10.11648/j.ajce.20251306.13,
  author = {Junaid Khan and Shalini Paka and Wisam Bukaita},
  title = {A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing},
  journal = {American Journal of Civil Engineering},
  volume = {13},
  number = {6},
  pages = {350-361},
  doi = {10.11648/j.ajce.20251306.13},
  url = {https://doi.org/10.11648/j.ajce.20251306.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajce.20251306.13},
  abstract = {This study presents a machine learning framework for the automated design of reinforced concrete (RC) beams in compliance with ACI 318-19 code provisions. Traditional RC beam design requires iterative calculations to satisfy strength and serviceability criteria across a wide range of geometric, material, and loading parameters. To enhance efficiency and consistency, a dataset comprising 10,000 synthetically generated beam configurations was developed by varying span length, concrete compressive strength, steel yield stress, and applied loading. Each configuration was generated using ACI 318-19 design equations to ensure code compliance and structural validity. A deep neural network (DNN) regression model was trained to learn the nonlinear mapping between input parameters and corresponding design outputs, including required tensile reinforcement, bar diameters, stirrup spacing, and ultimate moment capacity. Model performance was evaluated using a quantitative error matrix reporting mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R2) for each output variable. The model achieved MAE values ranging from 0.35 to 10 units, RMSE values from 0.45 to 12 units, and R2 values between 0.95 and 0.99, demonstrating high predictive accuracy and strong agreement with ACI-based reference designs. These results confirm that the framework can automatically generate code-compliant RC beam designs with high fidelity to ACI 318-19 specifications. By providing consistent, rapid, and interpretable predictions, this approach establishes a foundation for AI-assisted structural engineering tools that reduce computational time, improve design accuracy, and support data-driven automation in structural design workflows.},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - A Multi-Output Deep Learning Framework for Automated Reinforced Concrete (RC) Beam Design and Detailing
AU  - Junaid Khan
AU  - Shalini Paka
AU  - Wisam Bukaita
Y1  - 2025/12/09
PY  - 2025
N1  - https://doi.org/10.11648/j.ajce.20251306.13
DO  - 10.11648/j.ajce.20251306.13
T2  - American Journal of Civil Engineering
JF  - American Journal of Civil Engineering
JO  - American Journal of Civil Engineering
SP  - 350
EP  - 361
PB  - Science Publishing Group
SN  - 2330-8737
UR  - https://doi.org/10.11648/j.ajce.20251306.13
AB  - This study presents a machine learning framework for the automated design of reinforced concrete (RC) beams in compliance with ACI 318-19 code provisions. Traditional RC beam design requires iterative calculations to satisfy strength and serviceability criteria across a wide range of geometric, material, and loading parameters. To enhance efficiency and consistency, a dataset comprising 10,000 synthetically generated beam configurations was developed by varying span length, concrete compressive strength, steel yield stress, and applied loading. Each configuration was generated using ACI 318-19 design equations to ensure code compliance and structural validity. A deep neural network (DNN) regression model was trained to learn the nonlinear mapping between input parameters and corresponding design outputs, including required tensile reinforcement, bar diameters, stirrup spacing, and ultimate moment capacity. Model performance was evaluated using a quantitative error matrix reporting mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R2) for each output variable. The model achieved MAE values ranging from 0.35 to 10 units, RMSE values from 0.45 to 12 units, and R2 values between 0.95 and 0.99, demonstrating high predictive accuracy and strong agreement with ACI-based reference designs. These results confirm that the framework can automatically generate code-compliant RC beam designs with high fidelity to ACI 318-19 specifications. By providing consistent, rapid, and interpretable predictions, this approach establishes a foundation for AI-assisted structural engineering tools that reduce computational time, improve design accuracy, and support data-driven automation in structural design workflows.
VL  - 13
IS  - 6
ER  -

Copy | Download