Journals / Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi / 2026 / Cilt: 17 Sayı: 2

ML-Based Design of Gravity Retaining Walls

Ağırlık İstinat Duvarlarının Makine Öğrenmesi Tabanlı Tasarımı

Kevser Küley(KAHRAMANMARAŞ SÜTÇÜ İMAM ÜNİVERSİTESİ)0009-0007-8609-355X
Alirıza İlker Akgönen(KAHRAMANMARAŞ SÜTÇÜ İMAM ÜNİVERSİTESİ)0000-0001-7384-8764
Yavuz Canbay(KAHRAMANMARAŞ SÜTÇÜ İMAM ÜNİVERSİTESİ)0000-0003-2316-7893
Pages
—
Publication Date
2026-07-28
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The findings indicate that machine learning methods can serve as effective and reliable alternatives to conventional engineering approaches in the design process of gravity retaining walls.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Gravity retaining walls are important geotechnical structures that resist lateral loads arising from earth pressure, hydrostatic pressure, and granular backfill materials primarily through their self-weight.
📊
Key Findings & Data:In order to achieve a safe design, multiple failure modes—such as overturning, sliding, and bearing capacity failure—must be evaluated in an integrated manner.
💡
Conclusion & Impact:The findings indicate that machine learning methods can serve as effective and reliable alternatives to conventional engineering approaches in the design process of gravity retaining walls.
🔬Design:Modeling & Simulation
📍Scope:2018 Verileri
⚙️Variables:Ağırlık istinat duvarı · makine öğrenmesi · regresyon

Abstract

Gravity retaining walls are important geotechnical structures that resist lateral loads arising from earth pressure, hydrostatic pressure, and granular backfill materials primarily through their self-weight. In order to achieve a safe design, multiple failure modes—such as overturning, sliding, and bearing capacity failure—must be evaluated in an integrated manner. In this study, the fundamental parameters affecting the design of gravity retaining walls were systematically investigated. A total of 620 retaining wall designs were generated using the Sta4CAD software by considering varying geometric properties, soil conditions, and seismic effects. All analyses were conducted in accordance with the provisions of the Turkish Building Earthquake Code (TBDY-2018). The resulting comprehensive dataset was analyzed using the Python programming language to evaluate the applicability of data-driven approaches in engineering problems. Within this scope, various machine learning algorithms were implemented on the dataset, the performance of the developed models was compared, and their success in predicting critical design parameters of retaining walls was assessed. The findings indicate that machine learning methods can serve as effective and reliable alternatives to conventional engineering approaches in the design process of gravity retaining walls.

Özet

Ağırlık istinat duvarları, yanal toprak basıncı, hidrostatik basınç ve granüler dolgu malzemelerinden kaynaklanan yatay yükleri kendi ağırlıkları aracılığıyla dengeleyen önemli geoteknik yapı elemanlarıdır. Bu yapıların güvenli bir biçimde tasarlanabilmesi için devrilme, kayma ve temel taşıma gücü göçmesi gibi farklı göçme modlarının birlikte değerlendirilmesi gerekmektedir. Bu çalışmada, ağırlık istinat duvarlarının tasarımını etkileyen temel parametreler sistematik bir yaklaşımla ele alınmış; farklı geometrik özellikler, zemin koşulları ve deprem etkileri dikkate alınarak Sta4CAD programı aracılığıyla toplam 620 adet istinat duvarı tasarımı gerçekleştirilmiştir. Söz konusu analizler, Türkiye Bina Deprem Yönetmeliği (TBDY-2018) esaslarına uygun olarak yürütülmüştür. Elde edilen kapsamlı veri seti, mühendislik problemlerinde veri odaklı yaklaşımların uygulanabilirliğini incelemek amacıyla Python programlama dili kullanılarak analiz edilmiştir. Bu kapsamda, veri seti üzerinde çeşitli makine öğrenmesi algoritmaları uygulanmış, geliştirilen modellerin performansları karşılaştırılmış ve istinat duvarı tasarımına ilişkin kritik parametrelerin tahmin edilmesindeki başarı düzeyleri değerlendirilmiştir. Elde edilen bulgular, geleneksel mühendislik yaklaşımlarına alternatif olarak makine öğrenmesi yöntemlerinin istinat duvarı tasarım süreçlerinde etkin ve güvenilir bir şekilde kullanılabileceğini göstermektedir.

🔖

Cite This Article

Küley, K., Akgönen, A. İ., Canbay, Y. (2026). ML-Based Design of Gravity Retaining Walls. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, Cilt: 17 Sayı: 2. https://doi.org/10.24012/dumf.1940125

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (27)

  1. S. Talatahari and R. Sheikholeslami, "Optimum design of gravity and reinforced retaining walls using enhanced charged system search algorithm," KSCE Journal of Civil Engineering, vol. 18, no. 5, pp. 1464-1469, 2014.
  2. S. Talatahari, R. Sheikholeslami, M. Shadfaran, and M. Pourbaba, "Optimum design of gravity retaining walls using charged system search algorithm," Mathematical Problems in Engineering, vol. 2012, no. 1, p. 301628, 2012.
  3. J. J. Pons, V. Penadés-Plà, V. Yepes, and J. V. Martí, "Life cycle assessment of earth-retaining walls: An environmental comparison," Journal of Cleaner Production, vol. 192, pp. 411-420, 2018.
  4. B. Kaymak and U. Dağdeviren, "SİMETRİK AĞIRLIK İSTİNAT DUVARLARININ OPTİMUM TASARIMI," Journal of Science and Technology of Dumlupınar University, no. 040, pp. 45-57, 2018.
  5. X. Li, L. Su, Y. Wu, and S. He, "Seismic stability of gravity retaining walls under combined horizontal and vertical accelerations," Geotechnical and Geological Engineering, vol. 33, pp. 161-166, 2015.
  6. Z. Kurt, M. Kurt, and M. F. Yentimur, "A Case Study for Retaining Wall Design," (in en), Sciennovation, vol. 2, no. 1, pp. 21-28, September 2020. [Online]. Available: https://dergipark.org.tr/tr/pub/sciennovation/issue/56784/792029.
  7. R. Alsirawan and A. Alnmr, "Dynamic behavior of gravity segmental retaining walls," Pollack Periodica, vol. 18, 11/07 2022, doi: 10.1556/606.2022.00722.
  8. Y. Zhou, S. Shi, Q. Cai, and J. Liang, "Deformation State Analysis and Design Method of Bottom-Confined Gravity Retaining Walls," Sustainability, vol. 15, no. 5, p. 4405, 2023. [Online]. Available: https://www.mdpi.com/2071-1050/15/5/4405.
  9. D. Shah, "Stability Analysis of Gravity Retaining Wall by DEM Simulation," pp. 1-5, 10/04 2024, doi: 10.56472/25839233/IJAST-V2I4P101.
  10. R. Mustafa, P. Samui, and S. Kumari, "Seismic Performance of Gravity Retaining Walls Under Quasi-static Approach Using Probabilistic Analysis," Transportation Infrastructure Geotechnology, vol. 11, no. 2, pp. 612-649, 2024/04/01 2024, doi: 10.1007/s40515-023-00298-y.
  11. H. Chen, P. G. Asteris, D. Jahed Armaghani, B. Gordan, and B. T. Pham, "Assessing Dynamic Conditions of the Retaining Wall: Developing Two Hybrid Intelligent Models," Applied Sciences, vol. 9, no. 6, p. 1042, 2019. [Online]. Available: https://www.mdpi.com/2076-3417/9/6/1042.
  12. R. Mustafa, P. Samui, and S. Kumari, "Reliability Analysis of Gravity Retaining Wall Using Hybrid ANFIS," Infrastructures, vol. 7, no. 9, p. 121, 2022. [Online]. Available: https://www.mdpi.com/2412-3811/7/9/121.
  13. R. Mustafa, P. Samui, S. Kumari, E. T. Mohamad, and R. M. Bhatawdekar, "Probabilistic analysis of gravity retaining wall against bearing failure," Asian Journal of Civil Engineering, vol. 24, no. 8, pp. 3099-3119, 2023/12/01 2023, doi: 10.1007/s42107-023-00697-z.
  14. A. Kumar and A. Burman, "Reliability analysis of gravity retaining wall under seismic conditions using a novel hybrid paradigm of ELM and improved grey wolf optimizer," Modeling Earth Systems and Environment, vol. 11, no. 3, p. 214, 2025/04/12 2025, doi: 10.1007/s40808-025-02390-3.
  15. SAP. "Makine Öğrenmesi Nedir?,." https://www.sap.com/turkey/products/artificial-intelligence/what-is-machine-learning.html (accessed.
  16. M. Atalay and E. Çelik, Mehmet Akif Ersoy University Journal of Social Sciences Institute, vol. 9, no. 22, pp. 155-172, December 2017, doi: 10.20875/makusobed.309727.
  17. D. Kılınç, E. Borandağ, F. Yücalar, V. Tunalı, M. Şimşek, and A. Özçift, "KNN algoritması ve r dili ile metin madenciliği kullanılarak bilimsel makale tasnifi," Marmara Fen Bilimleri Dergisi, vol. 28, no. 3, pp. 89-94, 2016.
  18. S. W. Jarantow, E. D. Pisors, and M. L. Chiu, "Introduction to the use of linear and nonlinear regression analysis in quantitative biological assays," Current Protocols, vol. 3, no. 6, p. e801, 2023.
  19. Z. D. Akşehir and E. Kılıç, "Makine öğrenmesi teknikleri ile banka hisse senetlerinin fiyat tahmini," Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, vol. 12, no. 2, pp. 30-39, 2019.
  20. A. Liaw and M. Wiener, "Classification and regression by randomForest," R news, vol. 2, no. 3, pp. 18-22, 2002.
  21. A. Natekin and A. Knoll, "Gradient boosting machines, a tutorial," Frontiers in neurorobotics, vol. 7, p. 63623, 2013.
  22. S. Bhanu Koduri, L. Gunisetti, C. Raja Ramesh, K. Mutyalu, and D. Ganesh, "Prediction of crop production using adaboost regression method," in Journal of physics: conference series, 2019, vol. 1228, no. 1: IOP Publishing, p. 012005.
  23. G. L. E. Ekibi. "Makine Öğrenmesinde Destek Vektör Regresyonu." https://www.mygreatlearning.com/blog/support-vector-regression/ (accessed.
  24. R. M. Durao, M. T. Mendes, and M. J. Pereira, "Forecasting O3 levels in industrial area surroundings up to 24 h in advance, combining classification trees and MLP models," Atmospheric Pollution Research, vol. 7, no. 6, pp. 961-970, 2016.
  25. Mustafa Erdogan. "Makine Öğrenmesi Regresyon Modellerindeki Hata Metriklerine Güncel Bakış: MAE, MSE, RMSE, R-Kare (R2)." https://medium.com/academy-team/makine-öğrenmesi-regresyon-modellerindeki-hata-metriklerine-güncel-bakış-mae-mse-rmse-r-kare-d1ab758c5759 (accessed 2025).
  26. D. Chicco, M. J. Warrens, and G. Jurman, "The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation," Peerj computer science, vol. 7, p. e623, 2021.
  27. M. Almsallti, A. B. Alzubi, and O. R. Adegboye, "Hybrid metaheuristic optimized extreme learning machine for sustainability focused co2 emission prediction using globalization-driven indicators," Sustainability, vol. 17, no. 15, p. 6783, 2025.