Machine Learning-Based Evaluation of Shear Capacity of Recycled Aggregate Concrete Beams

Abstract

Recycled aggregate concrete (RAC) is a promising solution to address the challenges raised by concrete production. However, the current lack of pertinent design rules has led to a hesitance to accept structural members made with RAC. It would entail even more difficulties when facing application scenarios where brittle failure is possible (e.g., beam in shear). In this paper, existing major shear design formulae established primarily for conventional concrete beams were assessed for RAC beams. Results showed that when applied to the shear test database compiled for RAC beams, those formulae provided only inaccurate estimations with surprisingly large scatter. To cope with this bias, machine learning (ML) techniques deemed as potential alternative predictors were resorted to. First, a Grey Relational Analysis (GRA) was carried out to rank the importance of the parameters that would affect the shear capacity of RAC beams. Then, two contemporary ML approaches, namely, the artificial neural network (ANN) and the random forest (RF), were leveraged to simulate the beams’ shear strength. It was found that both models produced even better predictions than the evaluated formulae. With this superiority, a parametric study was undertaken to observe the trends of how the parameters played roles in influencing the shear resistance of RAC beams. The findings indicated that, though less influential than the structural parameters such as shear span ratio, the effect of the replacement ratio of recycled aggregate (RA) was still significant. Nevertheless, the value of vc/(fc)1/2 (i.e., the shear contribution from RAC normalized with respect to the square root of its strength) predicted by the ML-based approaches appeared to be insignificantly affected by the replacement level. Given the existing inevitable large experimental scatter, more shear tests are certainly needed and, for safe application of RAC, using partial factors calibrated to consider the uncertainty is feasible when designing the shear strength of RAC beams. Some suggestions for future works are also given at the end of this paper.

Evaluation of Shear Capacity of Steel Fiber Reinforced Concrete Beams without Stirrups Using Artificial Intelligence Models

“…Thus, ξ i , which represents the gray relational coefficient, is determined by: where 0 ≤ ρ ≤ 1, and it frequently adopts a value of 0.50 [ 31 ].…”

“…It is noteworthy that the closer λ is to unity, the closer the correlations, and vice versa. In general, when λ is larger than 0.7, there is a strong correlation; when λ is smaller than 0.5, the correlation can be treated as negligible [ 31 ].…”

“…BPANN is an AI model that tries to simulate the structural or functional aspects of biological neural networks [ 31 ]. While BPANN cannot exactly replicate the remarkable abilities of human brains, it is well suited for simulating complex processes with the proper selection of inputs and careful construction of network structures.…”

“…As a result, they have been gradually accepted by the civil engineering community for predicting different properties of materials and structures [ 29 ]. AI models often outperform mechanics-based models, as the former can exploit hidden patterns between seemingly unrelated parameters to draw useful solution(s) [ 30 , 31 ].…”

The Simple Mix Design Method and Confined Behavior Analysis for Recycled Aggregate Concrete

“…Since the late 20th century, a growing number of studies have focused on the new environmental concrete [3,4]. Over the past two decades, many researches have studied some salient issues for the practical application of RAC: The production process and the compressive strength prediction are studied in the early stage [5][6][7]; the comprehensive mechanical properties and durability properties are studied over the past decades [8][9][10]; from the components and micro-properties of RAC to the macro-performance of RAC, the properties are studied in recent years [11][12][13][14][15][16][17]. Against the common concrete with natural aggregate, the RAC with a similar mix proportion has a weakened mechanical property and a great dispersion of properties, due to the weakened and uncertainty properties of recycled aggregate [18][19][20].…”