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

Materials ◽  
2020 ◽  
Vol 13 (20) ◽  
pp. 4552
Author(s):  
Yong Yu ◽  
Xinyu Zhao ◽  
Jinjun Xu ◽  
Cheng Chen ◽  
Simret Deresa ◽  
...  

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.

2016 ◽  
Vol 23 (1) ◽  
pp. 76-84 ◽  
Author(s):  
Hyun-Do YUN ◽  
Won-Chang CHOI

As the demand for sustainable construction materials has risen over recent years, researchers have conducted several studies to expand the practical application of recycled construction materials, such as recycled aggregate. The author’s previous research shows the potential application of recycled aggregate over a broad range of structural mem­ber types. This paper continues the earlier work and investigates the shear behaviour of reinforced recycled aggregate concrete beams without shear reinforcement using findings from the author’s previous research. The variables in the test program are replacement rate (0%, 30%, 60%, and 100%) of recycled aggregate and shear span-to-depth ratio (2.0, 2.5, 3.0, 4.0, and 5.0). This work compares the experimental results with results obtained using current code equations found in American Concrete Institute (ACI) 318 (2014) and equations proposed in the literature. This research has found that the current code equations can adequately predict the shear strength of recycled coarse aggregate concrete beams and possibly can be applied for the use of recycled aggregate in structural elements.


2021 ◽  
Author(s):  
Roya Shoghi Haghdoost

A theoretical study is conducted to investigate the shear behaviour of recycled aggregate concrete (RAC) beams with and without shear reinforcements along with the performance evaluation various Code based/other existing equations in predicting shear strength. In addition, three artificial neural network (ANN) models for shear strength prediction of RAC beams with and without shear reinforcements are developed and their performance validated by using 108 beams from available research studies. Most of the Codes and existing methods underestimate the shear capacity of RAC beams with/without shear reinforcement. However, over estimation of shear strength by Codes/existing methods for about 10% RAC beams needs to be addressed when using such Codes/existing methods for shear strength prediction. All three ANN models are found to predict shear strength of RAC beams. Developed ANN models are able to simulate the effect of shear reinforcement on the shear strength of RAC beams.


Buildings ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 402
Author(s):  
Monthian Setkit ◽  
Satjapan Leelatanon ◽  
Thanongsak Imjai ◽  
Reyes Garcia ◽  
Suchart Limkatanyu

For decades, recycled coarse aggregate (RCA) has been used to make recycled aggregate concrete (RAC). Numerous studies have compared the mechanical properties and durability of recycled aggregate concrete (RAC) to those of natural aggregate concrete (NAC). However, test results on the shear strength of reinforced recycled aggregate concrete beams are still limited and sometimes contradictory. Shear failure is generally brittle and must be prevented. This article studies experimentally and analytically the shear strength of reinforced RAC beams without stirrups. Eight RAC beams and two controlled NAC beams were tested under the four-point flexural test with the shear span-to-effective depth ratio (a/d) of 3.10. The main parameters investigated were the replacement percentage of RCA (0%, 25%, 50%, 75%, and 100%) and longitudinal reinforcement ratio (ρw) of 1.16% and 1.81%. It was found that the normalized shear stresses of RAC beams with ρw = 1.81% at all levels of replacement percentage were quite similar to those of the NAC counterparts. Moreover, the normalized shear stress of the beam with 100% RCA and ρw = 1.16% was only 6% lower than that of the NAC beam. A database of 128 RAC beams without shear reinforcement from literature was analyzed to evaluate the accuracy of the ACI 318-19 shear provisions in predicting the shear strength of the beams. For an RCA replacement ratio of between 50% and 100%, it was proposed to apply a reduction factor of 0.75 to the current ACI code equation to account for the physical variations of RCA, such as replacement percentage, RCA source and quality, density, amount of residual mortar, and physical irregularity.


2021 ◽  
Vol 18 (3) ◽  
pp. 184-193
Author(s):  
A.U. Adebanjo ◽  
B.I.O. Dahunsi ◽  
J.O. Labiran

In this study, locally produced Metakaolin (MK) was used as an admixture in recycled aggregate concrete of grades M 25 and M 30. The content of MK varied from 0-15% at 5% intervals. The physical and mechanical properties (bulk density, specific gravity, water absorption, aggregate crushing value and aggregate impact value) of aggregates were determined, the chemical composition as well as reactivity of MK was evaluated using X-Ray Fluorescence (XRF) technique and modified Chappelle test. The workability  (slump) and strength (compressive and split tensile) properties of fresh and hardened RAC were examined relative to that of conventional concrete. The results of the experiments revealed that the specific gravity (SG), water absorption and aggregate impact value of recycled aggregates (RA) were 2.23, 5.35% and 32%, respectively. The MK used had an optimum reactivity of 2060.8 mg of Ca(OH)2 fixed at a temperature of 660 oC. The slump values for M 25 and M 30 control specimens were 72 mm and 65 mm, respectively while the slump values of MK modified RAC decreased from 67-45 mm for M 25 and 55-35 mm for M 30 as MK increased from 0-15%. The 56th-day compressive strength of the control samples was 21.73 N/mm2 for M 25 and 26.8 N/mm2 for M 30, respectively, while RAC samples ranged from 14.96 - 17.04 N/mm2 for M 25 and 20.55 - 22.67 N/mm2 for M 30 whereas the split tensile strength for the control samples was 2.71 N/mm2 and 3.06 N/mm2 for the two grades in that sequence, while those of RAC ranged from 2.26-2.49 N/mm2 for M 25 and 2.62 – 2.84 N/mm2 for M 30. Despite the fact that metakaolin modified RAC had lower strength properties than conventional concrete, the use of 10% metakaolin as a RA modifier in concrete production will provide a sustainable alternative to conventional aggregates in concrete mix design.


2021 ◽  
Author(s):  
Roya Shoghi Haghdoost

A theoretical study is conducted to investigate the shear behaviour of recycled aggregate concrete (RAC) beams with and without shear reinforcements along with the performance evaluation various Code based/other existing equations in predicting shear strength. In addition, three artificial neural network (ANN) models for shear strength prediction of RAC beams with and without shear reinforcements are developed and their performance validated by using 108 beams from available research studies. Most of the Codes and existing methods underestimate the shear capacity of RAC beams with/without shear reinforcement. However, over estimation of shear strength by Codes/existing methods for about 10% RAC beams needs to be addressed when using such Codes/existing methods for shear strength prediction. All three ANN models are found to predict shear strength of RAC beams. Developed ANN models are able to simulate the effect of shear reinforcement on the shear strength of RAC beams.


Sign in / Sign up

Export Citation Format

Share Document