Naslov
Machine learning intelligence to assess the shear capacity of corroded reinforced concrete beams

Autori
Kumar, Aman ; Arora, Harish Chandra ; Kapoor, Nishant Raj ; Kumar, Krishna ; Hadzima-Nyarko, Marijana ; Radu, Dorin

Kolaboracija
Academy of Scientific and Innovative Research (AcSIR), Ghaziabad, India ; Structural Engineering Department, CSIR-Central Building Research Institute Roorkee, Roorkee, India ; Department of Architecture and Planning, CSIR-Central Building Research Institute Roorkee, Roorkee, India ; Department of Hydro and Renewable Energy, Indian Institute of Technology Roorkee, Roorkee, India ; Faculty of Civil Engineering, Transilvania University of Braşov, Braşov, Romania

Izvornik
Scientific reports (2045-2322) 13 (2023); 2857, 26

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
machine learning (ML) techniques ; shear strength ; corroded reinforced concrete beams (CRCBs) ; artifcial neural networks (ANN) ; adaptive-neuro fuzzy inference systems (ANFIS), decision tree (DT) ; extreme gradient boosting (XGBoost)

Sažetak
The ability of machine learning (ML) techniques to forecast the shear strength of corroded reinforced concrete beams (CRCBs) is examined in the present study. These ML techniques include artificial neural networks (ANN), adaptive-neuro fuzzy inference systems (ANFIS), decision tree (DT) and extreme gradient boosting (XGBoost). A thorough databank with 140 data points about the shear capacity of CRCBs with various degrees of corrosion was compiled after a review of the literature. The inputs parameters of the implemented models are the width of the beam, the effective depth of the beam, concrete compressive strength (CS), yield strength of reinforcement, percentage of longitudinal reinforcement, percentage of transversal reinforcement (stirrups), yield strength of stirrups, stirrups spacing, shear span-to-depth ratio (a/d), corrosion degree of main reinforcement, and corrosion degree of stirrups. The coefficient of determination of the ANN, ANFIS, DT, and XGBoost models are 0.9811, 0.9866, 0.9799, and 0.9998, respectively. The MAPE of the XGBoost model is 99.39%, 99.16%, and 99.28% lower than ANN, ANFIS, and DT models. According to the results of the sensitivity examination, the shear strength of the CRCBs is most affected by the depth of the beam, stirrups spacing, and the a/d. The graphical displays of the Taylor graph, violin plot, and multi-histogram plot additionally support the XGBoost model's dependability and precision. In addition, this model demonstrated good experimental data fit when compared to other analytical and ML models. Accurate prediction of shear strength using the XGBoost approach confirmed that this approach is capable of handling a wide range of data and can be used as a model to predict shear strength with higher accuracy. The effectiveness of the developed XGBoost model is higher than the existing models in terms of precision, economic considerations, and safety, as indicated by the comparative study.

Izvorni jezik
Engleski

Znanstvena područja
Građevinarstvo

POVEZANOST RADA