Machine Learning-Based Flexural Capacity Prediction of Corroded RC Beams with an Efficient and User-Friendly Tool

Abstract

Steel corrosion poses a serious threat to the structural performance of reinforced concrete (RC) structures. Thus, this study evaluates the flexural capacity of RC beams through machine learning (ML)-based techniques with six parameters used as input features: beam width, beam effective depth, concrete compressive strength, reinforcement ratio, reinforcement yield strength, and corrosion level. Four single and ensemble ML models are evaluated; namely, decision tree, support vector machine, adaptive boosting, and gradient boosting. Hyperparameters of each model were optimized using grid search and K-fold cross-validation with root mean squared error used as the performance index. The predictive performance of each model was assessed using four statistical performance metrics. The analysis results demonstrated that the decision tree model exhibited overfitting and limited generalization ability. The adaptive boosting model also had a slight overfitting issue. In addition, the support vector machine reported comparable accuracy to that of adaptive boosting. Conversely, the proposed gradient boosting ensemble model achieved the best performance with strong generalization ability, as indicated by its lowest mean absolute error of 2.78 kN.m, mean absolute percent error of 13.40%, and root mean squared error of 3.56 kN.m, and the highest coefficient of determination of 97.30% on the test dataset. The optimized gradient boosting model has been deployed into a graphical user interface, allowing for practical implementation of the model and enabling fast, efficient, and intelligent prediction of the flexural capacity of corroded RC beams.

Machine Learning Techniques for Soil Characterization Using Cone Penetration Test Data

“…The performance of optimized ML models was evaluated using multiple statistical metrics such as root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), coefficient of determination R 2 , scatter index (SI), and performance index (PI) (see Table 2). Many researchers utilized these indices to evaluate the predictive performance of different ML models [53][54][55][56][57][58][59][60]. The RMSE measures the average magnitude of the errors between the predicted and actual values, indicating the model's predictive accuracy.…”

Effect of different material constitutive models in estimating the residual moment capacity of RC beams subjected to natural corrosion

“…, 2020; Jnaid and Aboutaha, 2016), neural network (Imam et al. , 2015), or machine learning-based techniques (Abushanab et al. , 2023; Alabduljabbar et al.…”

“…A wealth of references is available in the literature that provides reliable methods for estimating the flexural capacity of RC beams under chloride attack. Previous studies have employed finite element analysis (Castorena-Gonz alez et al, 2020;Jnaid and Aboutaha, 2016), neural network (Imam et al, 2015), or machine learning-based techniques (Abushanab et al, 2023;Alabduljabbar et al, 2020), which, despite their impressive predictive accuracy, are complicated and expensive. Perhaps, the simplest approach is to employ a single empirical factor (also called corrosion coefficient) that serves as a multiplier to the moment capacity to correct for the effect of corrosion.…”

The Flexural Strength Prediction of Carbon Fiber/Epoxy Composite Using Artificial Neural Network Approach

“…They found that using two hidden layers and 20 neurons provided the most accurate prediction value. In a recent study conducted by Abushanab A. et al (2023) [39], the flexural strength of reinforced concrete beams was evaluated using machine learning (ML) techniques. Various models, including SVM, DT, ADB, and GB, were employed for analysis.…”