Source: Applications of Artificial Intelligence in Structural Engineering: A Review · Zenodo Authors: G. A. Suryawanshi Licence: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0/

International Journal of Inventive Engineering and Sciences (IJIES) ISSN: 2319-9598 (Online), Volume-12 Issue-9, September 2025

Applications of Artificial Intelligence in Structural Engineering: A Review

G. A. Suryawanshi, L. S. Mahajan, S. R. Bhagat

Abstract: Artificial intelligence (AI) is a computational approach that aims to mimic human-like thinking/cognitive

abilities to tackle complicated engineering issues. AI is appropriate for engineering contexts with a large set of inputs. AI

is a feasible alternative to traditional modelling and statistical techniques. Experimentation is a herculean task in the domain of

structural engineering, so AI-based techniques are viable alternatives for the prediction of various engineering design

parameters, such as structural response, compressive strength, etc. The goal of this research is to outline numerous applications

of artificial intelligence in structural engineering that have emerged in recent years. Initially, a broad introduction to AI is

provided, followed by a discussion of the relevance of AI in the field of structural engineering. Thereafter, a review of recent applications of AI techniques such as deep learning (DL), pattern

recognition (PR), and machine learning (ML) in structural engineering is presented, and the ability of such techniques to

meet the constraints of conventional models is explored. Furthermore, the benefits of adopting such algorithmic approaches are thoroughly addressed. Finally, future research

areas and latest innovations by using deep learning, pattern recognition, and machine learning are given, along with their

shortcomings. Keywords: Structural Engineering, Artificial Intelligence, Machine Learning, Deep Learning. Abbreviations: ISI: Indian Standards Institute BIS: Bureau of Indian Standards AI: Artificial Intelligence DL: Deep Learning ML: Machine Learning PR: Pattern Recognition ASTM: American Society for Testing and Materials SHM: Structural Health Monitoring ASCE: American Society of Civil Engineers BPNN: Back Propagation Neural Networks FFANN: Feed Forward Artificial Neural Network IO: Immediate Occupancy LS: Life Safety CP: Collapse Prevention RC: Reinforced Concrete MDPI: Multidisciplinary Digital Publishing Institute

FRP: Fibre Reinforced Polymer MLP: Multilayer Perceptron BRB: Buckling-Restrained Braced RSM: Response Surface Model PSDM: Probabilistic Seismic Demand Model LR: Logistic Regression PGA: Peak Ground Acceleration DSHA: Deterministic Seismic Hazard Analysis PSHA: Probabilistic Seismic Hazard Analysis CNN: Convolutional Neural Network SVM: Support Vector Machine AHP: Analytical Hierarchy Process R2: R-squared (Coefficient of determination) R: Correlation Coefficient MAE: Mean Absolute Error RMSE: Root Mean Square Error MAPE: Mean Absolute Percentage Error VEcv: Variance Explained by Cross-Validation

I. INTRODUCTION

Engineers frequently develop experiments to investigate

practical difficulties. However, such investigations are constrained in terms of the number of test/cube samples and variables used, as well as the research facilities available. To verify that tests are comparable, testing standards/guidelines, such as those developed by the Bureau of Indian Standards (BIS), the Indian Standards Institute (ISI), the American Society for Testing and Materials (ASTM), and the International Organisation for Standardisation, have been established. For many experimental trials and situations, these guidelines include a specific statement regarding the testing process, technology, and technical requirements. In the Structural Engineering domain, research facilities are primarily available for the elemental response of different structural members. Engineers can utilise modern numerical methods, such as finite element analysis, instead of relying on experimentation. Machine learning (ML) is another promising new tool for addressing various practical difficulties in the structural engineering domain [1].

||Manuscript received on||01|August 2025||| First Revised| |---|---|---|---|---|---|---| ||Manuscript received on 15||August|2025 |||Second Revised| ||Manuscript received on 02 September 2025. Correspondence Author(s)||Accepted on 15 September 2025 | Manuscript published on 30|September||2025 | Manuscript| |G. A.|Suryawanshi|,|Assistant||Professor, Dr. Babasaheb|Ambedkar| ||Technological 20100860@dbatu.ac.in|University,|Lonere,|Raigad,|India.|Email ID:| |L.|S. Mahajan,|Research Technological University, Lonere, Raigad, India.|Scholar,|Dr.|Babasaheb|Ambedkar| |S.|R. Bhagat, CC-BY-NC-ND license|Professor Technological University, Lonere, Raigad, India. Sciences Publication (BEIESP). This is an|& © The Authors. Published by Blue Eyes Intelligence Engineering and|HoD, Dr. open-access http://creativecommons.org/licenses/by-nc-nd/4.0/|Babasaheb|Ambedkar article under the|

Artificial intelligence (AI) is a branch of computer science whose goal is to enable computers to do tasks that are similar to those performed by humans [2]. In contrast to statistical techniques, AI does not start with making assumptions about a phenomenon. AI, on the other hand, is a specially built computational technique aimed at replicating human-like thinking/cognitive ability to tackle complicated technical challenges. AI is well-suited to engineering scenarios involving a high number of inputs (random variables) and a non-linear relationship between random variables and output. In many instances, AI utilises evolutionary algorithms that attempt to learn patterns

Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) © Copyright: All rights reserved.

Retrieval Number: 100.1/ijies.B35380111222 DOI: 10.35940/ijies.B3538.12090925 Journal Website: www.ijies.org

Applications of Artificial Intelligence in Structural Engineering: A Review

applications

layers that can create linear and non-linear models. On the other hand, the hidden layers are linked to the output layer,

Table I: Summary of Some of the AI Models Developed by Different Researchers in the Domain of Structural Engineering in Recent Years, from 2018 to 2021

structural engineering”, “AI in structural engineering”, “ANN in structural engineering”, “Machine Learning/Deep learning/Pattern Recognition Applications Structural engineering”, “Prediction of compressive strength of concrete by AI techniques” from prominent and well-accepted academic databases as Scopus, Web of Science, American Society of Civil Engineers (ASCE) Library, Wiley Online Library, Sage, Science Direct, Multidisciplinary digital publishing institute (MDPI), Taylor & Francis Online and Emerald. The articles/Journal Papers/conference proceedings selected for review are from recent years, from 2018 to 2021. Randomly, 30 articles related to applications of AI in the structural engineering domain were selected for this study.

A. Applications of AI in Structural Engineering

With advancements in technology, AI plays a vital role in the sub-domains of Structural Engineering. Some of the most critical applications are as follows: Structural Health Monitoring (SHM) is the process of implementing a damage detection and characterisation strategy for engineering structures. It involves monitoring of existing structures such as bridges, heritage buildings, etc., with the help of sensors from remote locations. As of today, one cannot monitor the health of structures from remote locations without sensors. Current practices to monitor/evaluate the performance of existing structures are the Visual Inspection Method and the Non-destructive method. As these practices have some limitations, such as being time-consuming and costly, working only in accessible regions of the structures, needing a high degree of expertise, etc [Y. Hooda, et al. [19]. It is challenging to detect damage to existing infrastructure by conventional vibration-based methods of SHM. Therefore, there is a need for alternative novel techniques. Various AI techniques provide advanced mathematical frameworks and algorithms that can help to discover and model the performance of a structure through deep mining of monitoring data collected from sensors [20].

M. Mishra et al. [21] carried out a systematic review to assess the health condition of heritage buildings using different emerging AI techniques, including ML, and also discussed the future scope and challenges of AI techniques related to heritage buildings. P. Singh et.al [22] carried out a literature review of various machine learning methods for monitoring of existing structures and also discussed current methods of SHM, such as vibration-based methods, Visual inspection, etc., and how to implement them with different machine learning techniques. O. Avci et.al. [24] reviewed vibration-based damage detection of civil infrastructures by using conventional methods as well as AI techniques such as ML and DL. As the structure becomes more complicated, the dependence on system physics for interpreting the observed sensor data becomes less (See Fig. No. 1), and a predominantly data-driven approach is adopted. For complex real-world structures, the preferred method must be data-driven, with system-physics/domain knowledge integrated in some way [14].

Fig.1: Structural Health Monitoring (SHM) [14]

Seismic hazard analysis involves the quantitative estimation of ground shaking hazards at a particular area. Seismic hazards can be analysed in two ways: deterministically and probabilistically. When a specific earthquake scenario is assumed, deterministic seismic hazard analysis (DSHA) is carried out. When uncertainties such as earthquake size, location, and time of occurrence are explicitly considered, probabilistic seismic hazard analysis (PSHA) is carried out. A critical part of seismic hazard analysis is the determination of Peak Ground Acceleration (PGA) and response acceleration (spectral acceleration) for an area/site [25]. A schematic figure shows (See Fig.2) training an ANN to predict the PGA of ground motions using strong motion databases [14]. Kirti Jadhav et.al [14] developed a smartphone application for seismic hazard safety assessment of RC Buildings by using ML, and also developed an ML-based framework for the seismic hazard safety of RC Buildings and studied damage classification techniques, the efficacy of the Machine Learning (ML) method in damage prediction via a Support Vector Machine (SVM) model. R. Jena et.al [26] developed a convolutional neural network (CNN) model for earthquake probability assessment in NE India and conducted vulnerability assessments using the analytical hierarchy process (AHP), Venn's intersection theory for hazard, and an integrated model for risk mapping and also developed a CNN model for earthquake probability estimation & to identify the earthquake-prone areas at Palu, Indonesia.

[Fig.2: Structural Hazard Analysis (SHA) [14]]

Seismic fragility can be defined as the proneness of a structural component or a system to fail to perform satisfactorily under a predefined limit state when subjected to an extensive range of seismic action. In accordance with the above definition, seismic fragility analysis can be regarded as a probabilistic measure for seismic performance assessment of structural components or systems.

Applications of Artificial Intelligence in Structural Engineering: A Review

There are two different end products of seismic fragility analysis: a damage probability matrix and a fragility curve [16]. R. Segura Padgett et. al [16] developed metamodels by using different machine learning techniques to find the approximate seismic response of concrete gravity dams, and practical design guidelines were devised from analysis of metamodels. Sun et al. [15] established machine learning-based algorithms for seismic fragility analysis of steel buckling-restrained braced (BRB) frames. Following the figure number. 3 shows that the development of a multi- predictor probabilistic seismic demand model (PSDM) and a multidimensional fragility model through response surface model (RSM) and logistic regression (LR) [14].

[Fig.3: Seismic Fragility Analysis [14]]

Structural optimisation is crucial for improving the efficiency, cost-effectiveness, and environmental sustainability of built structures. Over the last few decades, structural optimisation has proved itself as an essential tool in the design process. The goal of the optimisation can be to minimise the stresses, amount of steel, overall cost, etc., for a given amount of material and boundary conditions. Structural Designs based on an optimal material distribution for the structural system are not only efficient and lightweight but are also often aesthetically pleasant from an architectural point of view [27]. L. Mei et al. [27] carried out a critical literature review on structural optimisation in the civil engineering domain. C. Long et. al [17] studied a novel approach for structural optimisation of 2D & 3D truss structures by using deep learning. Hao Zheng et.al [28] proposed a novel method by using machine learning techniques for topological design compression-only shell structures with planar faces, considering both structural performance & construction constraints. J. Melchiorre et al. [18] developed machine learning algorithms for the structural optimisation of circular arches with different cross-sections. The strength of concrete is an important parameter to determine the performance of the material during service conditions. For the mix design of concrete, the strength is essential. Generally, concrete has high compressive strength and low tensile strength. Conventionally, statistical analyses such as linear & Non-Linear regression are critical tools to find the strength of concrete mixes. However, results obtained through statistical analyses are often inferior in most cases. In recent years, machine learning algorithms have drawn more and more attention because of their capability to deal with multivariable analysis [13]. G. Du et. al [13] developed a genetic algorithm to predict compressive strength of self-compacting concrete by using back propagation neural networks (BPNN). P.F.S. Silva et al. [29] developed three models, including Random Forest, ANN & SVM, for predicting the compressive strength of concrete. S. D. Latif [30] developed a prediction model for compressive strength using datasets obtained from a deep

learning method, long short-term memory (LSTM), and a Support vector machine (SVM). Bhagat S.R. et. al [23] reviewed different AI techniques for forecasting pollution.

III. CONCLUSION AND FUTURE SCOPE

This research looked at how artificial intelligence (AI) can be used in the field of structural engineering. There are five critical areas, such as structural health monitoring (SHM), seismic hazard analysis, seismic fragility analysis, optimisation of structural systems/members & prediction of strength of concrete, in which one can apply various AI techniques. A summary of multiple AI techniques in the structural engineering field, as employed by researchers over the past three years, from 2018 to 2021, is presented in tabular form. The review demonstrates that various AI approaches like machine learning, pattern recognition, and deep learning have the capacity to understand nonlinear relationships among the contributing factors, allowing them to tackle a wide range of issues that are difficult or impossible to address using conventional approaches. The review further shows that various AI techniques have been applied to the computational structural analysis domain, such as in finite element analysis, to improve computational time. Numerous challenges must be addressed to apply various AI techniques in the structural engineering domain. The first challenge is obtaining sufficient, diverse, and high-quality data. The second difficulty is the black box character of some AI approaches. It is fair to advise structural engineers who are completely unaware of the AI algorithms not to utilise various AI approaches. The third issue, which seems to be a side effect of AI's massive popularity, is that it is sometimes extolled like a panacea for all challenges in different sectors. The fourth issue concentrates on assessing whether various AI algorithms are appropriate for specific problems in the structural engineering domain. The fourth issue focuses on evaluating whether various AI algorithms are suitable for particular problems in the structural engineering domain. In summary, the authors believe that there are several potential domains where AI algorithms might give substantial benefits to practising structural engineers.

ACKNOWLEDGEMENT

I want to thank Prof. Dr. S.R. Bhagat, sir & Mr. L.S. Mahajan for encouraging me to write a review paper on 'Applications of Artificial Intelligence in Structural Engineering.'

DECLARATION STATEMENT

After aggregating input from all authors, I must verify the accuracy of the following information as the article's author.

• Conflicts of Interest/ Competing Interests: Based on my understanding, this article has no conflicts of interest.

• Funding Support: This article has not been funded by any organizations or agencies. This independence ensures that the research is conducted with objectivity and without any external influence.

• Ethical Approval and Consent to Participate: The content of this article does not necessitate ethical approval or consent to participate with supporting documentation.

• Data Access Statement and Material Availability: The adequate resources of this article are publicly accessible.

• Author’s Contributions: Each author has individually contributed to the article. Mr. G. A. Suryawanshi: Conceptualisation, Methodology, Writing-review & editing, Mr. L. S. Mahajan & Dr. S. R. Bhagat: Conceptualisation, Supervision, Investigation.

REFERENCES

1. M. Z. Naser, V. Kodur, H. Thai, R. Hawileh, J. Abdalla, V. V. Degtyarev “Benchmarking databases and machine learning algorithms in structural and fire engineering domains”, Journal of Building Engineering, Volume 44 (2021) 102977. https://doi.org/10.1016/j.jobe.2021.102977

2. Y. An, H. Li, T. Su & Y. Wang, “Determining Uncertainties in AI Applications in AEC Sector and their Corresponding Mitigation Strategies”, Automation in Construction, Volume 131 (2021) 103883. https://doi.org/10.1016/j.autcon.2021.103883

3. M. Z. Naser, “AI–based cognitive framework for evaluating response of concrete structures in extreme conditions”, Engineering Applications of Artificial Intelligence, Volume 81 (2019), Pages 437-

4. https://doi.org/10.1016/j.engappai.2019.03.004

5. P. Geyer & S. Singaravel, "Component-based machine learning for performance prediction in building design," Applied Energy Elsevier, vol. 228 (2018), pages 1439-1453. https://doi.org/10.1016/j.apenergy.2018.07.011

6. A. Pham, N. Ngo, and T. Nguyen, “Machine learning for predicting long-term deflections in reinforced concrete flexural structures”, Journal of Computational Design and Engineering, (2020) vol. 7(1) pages 95–106. http://dx.doi.org/10.1093/jcde/qwaa010

7. D. Thaler, M. Stoffel, B. Markert, F. Bamer, “Machine-learning- enhanced tail end prediction of structural response statistics in earthquake engineering”, Wiley Earthquake Engg. & Structural Dynamics (2021) pages 1–17. https://doi.org/10.1002/eqe.3432

8. M. K. Almustafa and M. L. Nehdi, “Machine learning model for predicting structural response of RC slabs exposed to blast loading”, Elsevier Engineering Structures, 221 (2020) 111109. https://doi.org/10.1016/j.engstruct.2020.111109

9. J. Won and J. Shin, “Machine Learning-Based Approach for Seismic Damage Prediction Method of Building Structures Considering Soil-Structure Interaction”, Sustainability Multidisciplinary Digital Publishing Institute (MDPI), (2021) vol. 13 4334. https://doi.org/10.3390/su13084334

10. M. K. Almustafa and M.L. Nehdi, “Machine learning prediction of structural response for FRP retrofitted RC slabs subjected to blast loading”, Elsevier Engineering Structures, 244 (2020) 112752. https://doi.org/10.1016/j.engstruct.2021.112752

11. D. Birky, J. Ladd, I. Guardiola and A. Young, “Predicting the dynamic response of a structure using an artificial neural network”, Journal of Low Frequency Noise, Vibration and Active Control (2021), Vol. 0(0) pages 1–14. http://dx.doi.org/10.1177/14613484211038408

12. D. Feng et.al, “Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach”, Construction and Building Materials, (2020) Volume 230 117000. https://doi.org/10.1016/j.conbuildmat.2019.117000

13. C. J. Lin and N. J. Wu, “An ANN Model for Predicting the Compressive Strength of Concrete”, Applied Sciences (2021), vol. 11,

14. https://doi.org/10.3390/app11093798

15. G. Du, Bu L, Hou Q, Zhou J, Lu B, “Prediction of the compressive strength of high-performance self-compacting concrete by an ultrasonic-rebound method based on a GA-BP neural network”, PLoS ONE 16(5): e0250795. https://doi.org/10.1371/journal.pone.0250795

16. K. Jadhav, E. Harirchian, V. Kumari & T. Lahmer, “ML-EHSAPP: A prototype for machine learning-based earthquake hazard safety assessment of structures by using a smartphone app”, European Journal of Environmental and Civil Engineering, (2021). http://dx.doi.org/10.1080/19648189.2021.1892829

17. B. Sun, Y. Zhang and C. Huang, “Machine Learning-Based Seismic Fragility Analysis of Large-Scale Steel Buckling Restrained Brace Frames”, Computer Modelling in Engineering & Sciences Tech Sci.

18. Press, (2020) vol.125. R. Segura, J. E. Padgett, and P. Paultre, “Metamodel https://doi.org/10.32604/cmes.2020.09632 -Based Seismic Fragility Analysis of Concrete Gravity Dams”, J. Struct. Engg. (ASCE) 2020, 146(7): 04020121. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002629

19. C. Long & Nguyen-Xuan H. (2020). “Deep learning for computational structural optimisation.” ISA Transactions, 103. https://doi.org/10.1016/j.isatra.2020.03.033

20. Melchiorre J., Bertetto A. and Carlo Marano G. (2021), “Application of a Machine Learning Algorithm for the Structural Optimisation of Circular Arches with Different Cross-Sections”, Journal of Applied Mathematics and Physics, 9, 1159-1170. http://dx.doi.org/10.4236/jamp.2021.95079

21. Y. Hooda, P. Kuhar, K. Sharma and N. K. Verma, “Emerging Applications of Artificial Intelligence in Structural Engineering and Construction Industry”, IOP Publishing, Journal of Physics: Conference Series, 1950 (2021) 012062. https://doi.org/10.1088/1742- 6596/1950/1/012062

22. Y. Bao, Li H., “Machine learning paradigm for structural health monitoring. Structural Health Monitoring”, (2021) SAGE Publications, 20(4):1353-1372. https://doi.org/10.1177/1475921720972416

23. M. Mishra, “Machine learning techniques for structural health monitoring of heritage buildings: A state-of-the-art review and case studies”, Journal of Cultural Heritage (2021) Volume 47 Pages 227-

24. https://doi.org/10.1016/j.culher.2020.09.005

25. P. Singh, U. F. Ahmad, and S. Yadav, “Structural Health Monitoring and Damage Detection through Machine Learning approaches, E3S Web of Conferences (2020), 220, 01096. http://dx.doi.org/10.1051/e3sconf/202022001096

26. S.R. Bhagat, G.A. Suryawanshi, Monali Mahajan and Lomesh S. Mahajan, “Artificial neural network techniques for evaluation of pollution”, IOP Conf. Ser..: Earth Environ. Sci. 796 012052. https://iopscience.iop.org/article/10.1088/1755- 1315/796/1/012052/pdf

27. O. Avci, O. Abdeljaber, S. Kiranyaz, M. Hussein, M. Gabbouj and D. J. Inman, “A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications”, Elsevier Mechanical Systems and Signal Processing (2021), Volume 147,107077. https://doi.org/10.1016/j.ymssp.2020.107077

28. Y. Xie, M. E. Sichani, J. E. Padgett and Des Roches R., “The promise of implementing machine learning in earthquake engineering: A state-of-the-art review”, Earthquake Spectra (2020);36(4):1769-1801. http://dx.doi.org/10.1177/8755293020919419

29. R. Jena, B. Pradhan, S. P. Naik and A. M. Alamri, “Earthquake risk assessment in NE India using deep learning and geospatial analysis”, Geoscience Frontiers (2021) Volume 12, Issue 3, May, 101110. https://doi.org/10.1016/j.gsf.2020.11.007

30. L. Mei and Wang Q., “Structural Optimisation in Civil Engineering: A Literature Review”, Buildings MDPI (2021), 11, 66. https://doi.org/10.3390/buildings11020066

31. H. Zheng, V. Moosavi and M. Akbarzadeh, “Machine learning assisted evaluations in structural design and construction”, Automation in Construction, (2020) Volume 119, 103346. https://doi.org/10.1016/j.autcon.2020.103346

32. P. F. S. Silva, G. Moita and V. Arruda, “Machine learning techniques to predict the compressive strength of concrete”, Rev. int. métodos numér. cálc. diseño ing. (2020). Vol. 36, (4), 48. http://dx.doi.org/10.23967/j.rimni.2020.09.008

33. S. D. Latif, “Concrete compressive strength prediction modelling utilising deep learning long short-term memory algorithm for a sustainable environment”, Environ Sci Pollution Res 28, 30294– 30302 (2021). https://doi.org/10.1007/s11356-021-12877-y Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of the Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP)/ journal and/or the editor(s). The Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP) and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions, or products referred to in the content.