Optimum Design of Flexural Strength and Stiffness for Reinforced Concrete Beams Using Machine Learning

Abstract

In this paper, an optimization approach was presented for the flexural strength and stiffness design of reinforced concrete beams. Surrogate modeling based on machine learning was applied to predict the responses of the structural system in three-point flexure tests. Three design input variables, the area of steel bars in the compression zone, the area of steel bars in the tension zone, and the area of steel bars in the shear zone, were adopted for the dataset and arranged by the Box-Behnken design method. The dataset was composed of thirteen specimens of reinforced concrete beams. The specimens were tested under three-points flexure loading at the age of 28 days and both the failure load and the maximum deflection values were recorded. Compression and tension tests were conducted to obtain the concrete data for the analysis and numerical modeling. Afterward, finite element modeling was performed for all the specimens using the ATENA program to verify the experimental tests. Subsequently, the surrogate models for the flexural strength and the stiffness were constructed. Finally, optimization was conducted, supporting the factorial method for the predicted responses. The adopted approach proved to be an excellent tool to optimize the design of reinforced concrete beams for flexure and stiffness. In addition, experimental and numerical results were in very good agreement in terms of both the failure type and the cracking pattern.

Experimental Investigation of Shear Behavior in High-Strength Concrete Beams Reinforced with Hooked-End Steel Fibers and High-Strength Steel Rebars

“…The simulation of fiber-reinforced concrete (FRC) beam behavior was carried out us ing ATENA [39] in conjunction with the GID [40] pre-processor software. This softwar has been previously used in numerous research to simulate the behavior of normal con crete [41][42][43][44][45] and FRCs [7][8][9][10]. As there is currently no standardized method for modeling FRC, an inverse analysis based on the software developers' guidelines [39] was employed to derive the post-cracking tensile stress versus fracture strain relationship for FRCs.…”

Performance Prediction and Optimization of Single-Piston Free Piston Expander-Linear Generator Based on Machine Learning and Genetic Algorithm

“…For the hidden layer, there is no widely recognized method for selecting its number of layers. Researchers need to determine different network structures for specific research problems [49,50]. Based on the preliminary trial calculations and comprehensive consideration of prediction accuracy and training time, two hidden layers were selected in this study.…”

Transformative role of machine learning in design optimization of reinforced concrete frames

“…Gaussian processes or neural networks are ML approaches. [111], may be used to create surrogate models that simulate intricate and costly computer structural evaluations [67]. The computing complexity of the optimization process is greatly reduced by these surrogate models, which enable quick assessments of the objective function and constraints.…”