Use of Artificial Neural Network based Prediction of Optimum Case of Multistory Buildings by using Structural Response

Abstract

This research presents a hybrid civil engineering and computer science approach for the efficient structural analysis of multistory buildings subjected to seismic forces. A total of ten distinct building models labeled NS and BD1 to BD9 were developed using structural analysis software, incorporating Response Spectrum Analysis and varying concrete grades (M25 and M30). A grade change scenario was introduced in slab components at different floor levels, with resulting horizontal displacements extracted as key response parameters. These outputs served as critical input for two Python based Artificial Neural Network (ANN) models: one using a Feed Forward algorithm and the other using Back Propagation, both integrated with Artificial Intelligence (AI) and Machine Learning (ML). Preprocessing tasks such as data normalization, cleaning and missing value treatment were performed using Pandas and NumPy. Model training and validation were conducted using TensorFlow and scikit learn, employing 200 epoches for optimal learning. Performance evaluation using Mean Squared Error (MSE) and R² score revealed exceptional accuracy, from this the ANN model achieving an MSE of 0 and R² of 1. Among the building cases analyzed, the ANN approach successfully identified the most structurally efficient configuration with minimum displacements in both UX and UY directions. This methodology not only enhances computational speed and accuracy compared to conventional practices but also promotes data driven decision making for cost effective and optimized structural design. The research underscores the applicability of ANN embedded with AI &ML techniques in building engineering and opens pathways for broader multidisciplinary implementations.

Introduction

In the field of building engineering, Artificial Neural Networks (ANNs) are revolutionizing structural analysis and design by providing intelligent, data-driven predictions. ANNs effectively handle nonlinear, complex problems, enabling accurate predictions of structural behavior, seismic performance, and energy efficiency. Their capacity to improve with data makes them essential for smart, sustainable infrastructure.

Research Gap & Objectives

This project addresses gaps in integrating AI/ML with structural engineering by developing a Python-based ANN model to:

• Predict structural performance under seismic loads.

• Analyze multistory buildings with varying concrete grades at different floor levels.

• Provide an optimized structural solution and validate results against Indian Standard (IS) codes.

• Evaluate model performance using Mean Square Error (MSE) and R² score.

• Use Feed Forward and Back Propagation ANN for faster, intelligent building analysis.

Methodology

• Ten building cases (NS and BD1–BD9) are analyzed, each with a different floor level where the concrete grade changes from M25 to M35.

• Buildings are modeled in seismic zone III, incorporating SMRF and shear wall systems.

• Structural parameters include beam/column sizes, slab thickness, and steel grade (Fe 500).

• Python and Google Colab are used for AI model development, preprocessing, and simulation.

Results & Analysis

• Displacement values (in Ux and Uy directions) for all 10 cases were analyzed using ANN.

• Graphs illustrate the maximum displacements, highlighting the most efficient building configuration (with minimum displacement).

• Both Feed Forward and Back Propagation ANN models were applied to evaluate performance.

• ANN provided high accuracy as validated by MSE and R² scores.

• The system effectively predicted optimal configurations and recommended the best-case scenario using visual tools and regression validation.

Conclusion

The conclusion can be pointed out are as follows: 1) Multiple structural models were successfully created using building analysis software, incorporating with the Response Spectrum Analysis. Total 10 separate building cases created abbreviated as NS, BD1 to BD9 respectively using M25 and M30 concrete grade. 2) The grade change scenario has conducted in structural analysis software with grade change in slab component at different levels keeping the other floor levels at same grade. After analysis, the analysis tool yields horizontal displacement values as key output parameters. The results obtained will be required as critical input data for AIML ANN model programming. 3) Two different Python based machine learning ANN model has developed, the former one has a feed forward ANN ability and the later one has back propagation with AI based learning ability to predict the best possible case that incorporates essential pre processing steps such as data normalization with missing value treatment and data cleaning to ensure high quality and reliable input data. This has achieved using Pandas and NumPy. 4) Suitable validation techniques such as TensorFlow &sklearnhas used that train test split data and conduction of cross validation to ensure robust evaluation of model performance. An epoch 200 has followed that specifies the number of times the entire training dataset (X and Y) will be passed through the neural network. In current case, it will be done 200 times, it means more epochs can lead to better learning with risk overfitting. train test split was applied to the dataset, and the models were trained and validated using TensorFlow version &sklearn version correspondingly. 5) The AIML based Feed Forward Artificial Neural Network and Back Propagation Artificial Neural Network model established using meaningful relationships between the input result parameters and output responses (displacement), demonstrating strong predictive capability with exact linear regression. 6) Model performance was assessed using Mean Squared Error (MSE) and R² score. The results indicate that ANN trained over 200 epochs, produced an MSE of 0 and an R² of 1, thus indicating enhanced predictive performance and robustness. 7) By evaluating various building case with grade change in slab members, the ANN model accurately pinpointed the most efficient configuration with the lowest displacement for both UX and UY directions. This outcome underscores the practical applicability of ANN techniques in enhancing structural design through data driven analysis and structural variables. The primary objective of this dissertation has achieved with developed and implemented Feed Forward and Back Propagationbased Artificial Neural Network (ANN) integrated with AI and Machine Learning (ML) technique that enable rapid prediction and efficient structural analysis of buildings. This approach facilitates high speed evaluation of structural performance under various scenarios, significantly improving computational efficiency compared to conventional methods. Furthermore, this research adopts a multidisciplinary methodology that bridges civil engineering and computer science, leveraging the strengths of both fields. By applying intelligent predictive modeling, the research work has capable of recommending the most economical structural configuration across various grade change scenarios. The study also demonstrates the model\'s applicability in parallel domains, promoting a data driven &decision making framework for cost effective and optimized structural design.

References

[1] Pandelea, A. E. C., Budescu, M. Gh., Covatariu, G. M., & Gheorghe Asachi Technical University of Ia?i, Faculty of Civil Engineering and Building Services. (2014). Applications of artificial neural networks in civil engineering. In 2nd International Conference for PhD Students in Civil Engineering and Architecture. [2] Sasnauskas, R., SES Engineering, Chen, Y., Nvidia, Inc., Collingbourne, P., Google, Inc., Ketema, J., Embedded Systems Innovation by TNO, Lup, G., Microsoft, Inc., Taneja, J., University of Utah, Regehr, J., & University of Utah. (2018). A Synthesizing Superoptimizer. Conference Paper. [3] Shazeer, N. & Google. (2019). Fast Transformer Decoding: One Write Head is All You Need. Conference Paper. [4] Mark Chen et. al. Evaluating Large Language Models Trained on Code. (2021). In arXiv [Journal article]. https://arxiv.org/pdf/2107.03374 [5] Pearce, H., Tan, B., Ahmad, B., Karri, R., New York University, & University of Calgary. (2022). Examining Zero Shot Vulnerability Repair with Large Language Models [Journal article]. arXiv. https://arxiv.org/abs/2112.02125v3 [6] Andon, A., &Covatariu, G. (2022). A Study on Image Processing Using Artificial Neural Networks in Civil Engineering. BuletinulInstitutuluiPolitehnic “Gheorghe Asachi” Din Ia?i. Sec?iaConstruc?ii. Arhitectur?, 67(3), 85 94. https://doi.org/10.2478/bipca 2021 0027 [7] Majumdar, S., Jain, I., & Kukreja, K. (2016). AdaSort: Adaptive Sorting using Machine Learning. International Journal of Computer Applications, 145(12), 12 17. https://doi.org/10.5120/ijca2016910726 [8] Shaikh, A., Sawant, S., Patil, A., Bhandare, A., & International Research Journal of Modernization in Engineering, Technology and Science. (2024). RAISIN SORTING USING MACHINE LEARNING ALGORITHM. International Research Journal of Modernization in Engineering Technology and Science, 06. https://www.irjmets.com [9] Fuchsgruber, D., Po?stuvan, T., G ¨Unnemann, S., Geisler, S., Department of Computer Science & Munich Data Science Institute, TU Munich, & EPFL. (2024). GRAPH NEURAL NETWORKS FOR EDGE SIGNALS: ORIENTATION EQUIVARIANCE AND INVARIANCE. [10] Zhang, H., Liang, H., Ni, T., Huang, L., & Yang, J. (2021). Research on Multi Object Sorting System Based on Deep Learning. Sensors, 21(18), 6238. https://doi.org/10.3390/s21186238 [11] Purizaca, F. J. V., Barturen, D. a. C., Pérez, S. P. M., Tuesta Monteza, V. A., & Mejía Cabrera, H. I. (2020). Importance of artificial neural networks in civil engineering: a systematic review of the literature. ITECKNE Innovación E Investigación En Ingeniería, 18(1). https://doi.org/10.15332/iteckne.v18i1.2542 [12] Anjum, A., Hrairi, M., Shaikh, A. A., Yatim, N., & Ali, M. (2024). Integrating AI and statistical methods for enhancing civil structural practices: current trends, practical issues, and future direction. Frattura Ed IntegritàStrutturale, 19(71), 164 181. https://doi.org/10.3221/igf esis.71.12 [13] Li, X., Garzaran, M. J., & Padua, D. (2007). Optimizing Sorting with Machine Learning Algorithms. Conference Paper, 1 2, 1 6. https://doi.org/10.1109/ipdps.2007.370499 [14] Patil, P. U., Lande, S. B., Nagalkar, V. J., Nikam, S. B., & Wakchaure, G. (2021). Grading and sorting technique of dragon fruits using machine learning algorithms. Journal of Agriculture and Food Research, 4, 100118. https://doi.org/10.1016/j.jafr.2021.100118 [15] Xu Yang et. al. Research and applications of artificial neural network in pavement engineering: A state of the art review. (2021). In Journal of Traffic and Transportation Engineering (English Edition). [16] Daniel J. Mankowitz et. al.. Faster sorting algorithms discovered using deep reinforcement learning. (2023). Nature, 618, 257 258.

Copyright

Copyright © 2025 Tarun Athya, Dr. Raghvendra Singh. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.