Shear strength prediction of reinforced concrete beams by baseline, ensemble, and hybrid machine learning models

Chou, Jui‐Sheng; Pham, Thi-Phuong-Trang; Nguyen, Thi-Kha; Pham, Anh-Duc; Ngo, Ngoc-Tri

doi:10.1007/s00500-019-04103-2

Cited by 44 publications

(17 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 8 and Figure 12 present the values of performance metrics for MOES and the compared models. Based on an earlier study, 12 ACI 318‐08 and CSA methods yielded values of shear strength with MAPE values of 46.368% and 42.276%, which are much higher than those of the other models. Those methods may not capture the underlying nonlinear function of the shear strength of RC beams with FRP reinforcement.…”

Section: Case Data and Experimental Resultsmentioning

confidence: 90%

“…In the last few decades, FRP has been used to retard the deterioration of RC structures by the corrosion of steel reinforcement, which has become a serious and costly problem. The data set that was used herein includes shear strength results for 209 RC beams with FRP reinforcement, was taken from the work of Zhang et al 48 and used in Chou et al 12 Table 5 and Figure 10 presents the statistical attributes and feature correlations of the two data sets: Case 2 (shear strength of RC deep beam) and Case 3 (shear strength of RC beams with FRP reinforcement).…”

Section: Case Data and Experimental Resultsmentioning

confidence: 99%

“…Their simulating results demonstrated that the proposed models performed remarkably well with high accuracy and outperformed other competitive methods. Chou et al proposed a hybrid model that coordinated LSSVR and smart firefly algorithm to predict shear strength of RC beams 12 . The numerical results revealed that the proposed hybrid model is more effective than empirical formulas (i.e., CSA A23.3‐04, ACI 318‐08, EN 1992‐1‐1, AS 3600‐2009, and EN 2004‐1‐1).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Metaheuristics‐optimized ensemble system for predicting mechanical strength of reinforced concrete materials

Chou

Nguyen

2021

Struct Control Health Monit

View full text Add to dashboard Cite

Summary This paper develops a novel artificial intelligence (AI)‐based approach, called the metaheuristics‐optimized ensemble system (MOES), to assist civil engineers significantly in achieving accurate estimations of the mechanical strength of reinforced concrete (RC) materials. MOES integrates the advantages of hybrid and ensemble models by combining a metaheuristic optimization algorithm and efficient AI models. The metaheuristic algorithm finds the optimal hyperparameters of individual AI techniques and simultaneously adjusts their weights to yield the best optimized‐weight‐ensemble model. Particularly, the developed MOES was established by integrating the forensic‐based investigation optimization algorithm, the radial basis function neural network, and the least squares support vector regression. Four case studies of predicting structural mechanics of RC beams were performed to evaluate the performance of MOES and compare it to those of other single AI models, conventional ensemble models, hybrid models, and empirical methods. The analytical results of cross‐validation reveal that MOES was the most reliable approach, achieving the best values of all performance evaluation indexes. The automated predictive analytics revealed the robustness, efficiency, and stability of MOES. Thus, the proposed approach is a highly promising tool for predicting the structural mechanics of RC beams. The success of MOES in estimating the mechanical strength of RC beams has redefined the way of optimizing an ensemble AI model, which is the primary contribution of this research to the relevant body of knowledge.

show abstract

Section: Case Data and Experimental Resultsmentioning

confidence: 90%

Section: Case Data and Experimental Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Metaheuristics‐optimized ensemble system for predicting mechanical strength of reinforced concrete materials

Chou

Nguyen

2021

Struct Control Health Monit

View full text Add to dashboard Cite

show abstract

“…e integration of SVR model with firefly algorithm for the sake of prediction accuracy of SFRCB shear strength [28]. e hybrid least squares support vector regression-smart firefly algorithm (LSSVR-SFA) model was established for shear strength prediction of RC beams [29]. A new novel AI model based on the hybridization of ANN model with atom search optimization (ASO) algorithm for SFRCB shear strength [30].…”

Section: Introductionmentioning

confidence: 99%

Random Forest versus Support Vector Machine Models’ Applicability for Predicting Beam Shear Strength

Mohammed

Ismail

2021

Complexity

View full text Add to dashboard Cite

The shear and bending are the actions that are experienced in the beam owing to the fact that the beam is a flexural member due to the load in the transverse direction to their longitudinal axis. The shear strength (Vs) computation of reinforced concrete (RC) beams has been a major topic in the field of structural engineering. There have been several methodologies introduced for the Vs prediction; however, the modeling accuracy is relatively low owing to the complex characteristic of the resistance mechanism involving dowel effect of longitudinal reinforcement, concrete in the compression zone, contribution of the stirrups if existed, and the aggregate interlock. Hence, the current research proposed a new soft computing model called random forest (RF) to predict Vs. Experimental datasets were collected from the open-source literature including the related geometric properties and concrete characteristics of beam specimens. Nine input combinations were constructed based on the statistical correlation to be supplied for the proposed predictive model. The prediction accuracy of the RF model was validated against the Support Vector Machine (SVM), and several other empirical formulations have been adopted in the literature. The proposed RF model revealed better prediction accuracy in addition the model structure emphasis in the incorporation of seven predictors by excluding (beam flange thickness and coefficient). In the quantitative term, the minimal root mean square error value was attained (RMSE = 89.68 kN).

show abstract

“…In Guo et al (2020a) ensemble learning is used to address class-imbalance problems, while Guo et al (2020b) and Yousefnezhad et al (2021) employed ensemble learning to increase prediction accuracy and robustness in classification problems. Chou et al (2020) proposed an ensemble learning framework to predict shear strength of reinforced concrete beams. Obtained results illustrated the ability of the proposed frameworks to outperformed other machine learning frameworks potentially serving as a better alternative to help in the design of such structures.…”

Section: Introductionmentioning

confidence: 99%

Ensemble of Hybrid Neural Networks to Compensate for Epistemic Uncertainties: A Case Study in System Prognosis

Dourado

Viana

2021

Preprint

View full text Add to dashboard Cite

In this contribution, a case study considering an unexpected corrosion-fatigue crack propagation issue in an aircraft fleet is used to discuss how to compensate for incomplete knowledge in time dependent responses integration and extrapolation. For the considered application, degradation resulting from mechanical fatigue is well understood and accounted in the damage models. However, the unexpected corrosion effects are not accounted in damage integration, yielding a large discrepancy between predicted and observed crack lengths. To address this epistemic uncertainty in the fleet damage accumulation model, hybrid neural networks cells are formulated; where physics-informed layers address well-understood aspects of the degradation, and data-driven layers are trained to act as correction terms. The considered case study encompasses highly imbalanced data sets with uncertainties acting asynchronously. To improve overall accuracy, ensemble learning techniques are adapted to merge the resulting hybrid neural network cells predictions. Lastly, a heuristic based on optimal ensemble weights is presented to help in the decision-making task of defining safe operation of the fleet. Results show that our proposed approach was capable of compensating for the epistemic uncertainties, and that the proposed heuristic can be used to rank aircraft damage severity, allowing to prioritize aircraft for inspection and/or route reassignment.

show abstract

Shear strength prediction of reinforced concrete beams by baseline, ensemble, and hybrid machine learning models

Cited by 44 publications

References 52 publications

Metaheuristics‐optimized ensemble system for predicting mechanical strength of reinforced concrete materials

Metaheuristics‐optimized ensemble system for predicting mechanical strength of reinforced concrete materials

Random Forest versus Support Vector Machine Models’ Applicability for Predicting Beam Shear Strength

Ensemble of Hybrid Neural Networks to Compensate for Epistemic Uncertainties: A Case Study in System Prognosis

Contact Info

Product

Resources

About