دوره 16، شماره 4 - ( 7-1405 )                   جلد 16 شماره 4 صفحات 546-515 | برگشت به فهرست نسخه ها


XML English Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Shahbazi M, Bolbolvand M, Tavakkoli S M. MACHINE LEARNING-BASED PREDICTION AND MULTI-OBJECTIVE OPTIMIZATION OF TENSILE STRENGTH IN ULTRA-HIGH-PERFORMANCE CONCRETE (UHPC). , IJOCE. 2026; 16 (4) :515-546
URL: http://ijoce.iust.ac.ir/article-1-692-fa.html
MACHINE LEARNING-BASED PREDICTION AND MULTI-OBJECTIVE OPTIMIZATION OF TENSILE STRENGTH IN ULTRA-HIGH-PERFORMANCE CONCRETE (UHPC). , عنوان نشریه. 1405; 16 (4) :515-546

URL: http://ijoce.iust.ac.ir/article-1-692-fa.html


چکیده:   (16 مشاهده)
This study is conducted to estimate the tensile strength (TS) of ultra-high-performance concrete (UHPC) using machine learning techniques and considering various influencing parameters, including different types of steel fibres. To predict TS, nine machine learning algorithms are employed, including categorical gradient boosting (CatBoost), gradient boosting machine (GBM), artificial neural networks (ANN), random forest (RF), light gradient boosting machine (LightGBM), k-nearest neighbors (KNN), extreme gradient boosting (XGBoost), support vector machine (SVM), and decision tree (DT). The results are interpreted using the Shapley additive explanations (SHAP) method to improve the transparency and interpretability of the model. A total of 247 experimental data points is collected, with 80% used for training and 20% for testing the models. Among the evaluated algorithms, the CatBoost model achieved the highest predictive performance with a coefficient of determination R2  = 0.939. Additionally, to examine the interaction between economic efficiency and TS in UHPC design, three mixing design scenarios (economic, balanced, and TS-focused) are developed within the framework of multi-objective optimization based on machine learning using the Whale Optimization Algorithm (WOA). To facilitate practical implementation, a graphical user interface (GUI) is developed. All data, source codes, and the GUI are publicly available at the following address: https://github.com/MiladBolbolvand/UHPC_Tensile_Strength.git.
متن کامل [PDF 2399 kb]   (23 دریافت)    
نوع مطالعه: پژوهشي | موضوع مقاله: Machine Learning
دریافت: 1405/5/26 | پذیرش: 1405/7/28 | انتشار: 1405/8/1

ارسال نظر درباره این مقاله : نام کاربری یا پست الکترونیک شما:
CAPTCHA

بازنشر اطلاعات
Creative Commons License این مقاله تحت شرایط Creative Commons Attribution-NonCommercial 4.0 International License قابل بازنشر است.

کلیه حقوق این وب سایت متعلق به دانشگاه علم و صنعت ایران می باشد.

طراحی و برنامه نویسی : یکتاوب افزار شرق

© 2026 CC BY-NC 4.0 | Iran University of Science & Technology

Designed & Developed by : Yektaweb