scholarly journals Predicting the Shear Strength of Fiber Reinforced Concrete Corbels Via Support Vector Machines

2018 ◽  
Vol 39 (2) ◽  
pp. 496-514
Author(s):  
Ahmet Emin KURTOĞLU
2006 ◽  
Vol 33 (6) ◽  
pp. 726-734 ◽  
Author(s):  
Fariborz Majdzadeh ◽  
Sayed Mohamad Soleimani ◽  
Nemkumar Banthia

The purpose of this study was to investigate the influence of fiber reinforcement on the shear capacity of reinforced concrete (RC) beams. Both steel and synthetic fibers at variable volume fractions were investigated. Two series of tests were performed: structural tests, where RC beams were tested to failure under an applied four-point load; and materials tests, where companion fiber-reinforced concrete (FRC) prisms were tested under direct shear to obtain material properties such as shear strength and shear toughness. FRC test results indicated an almost linear increase in the shear strength of concrete with an increase in the fiber volume fraction. Fiber reinforcement enhanced the shear load capacity and shear deformation capacity of RC beams, but 1% fiber volume fraction was seen as optimal; no benefits were noted when the fiber volume fraction was increased beyond 1%. Finally, an equation is proposed to predict the shear capacity of RC beams.Key words: shear strength, fiber-reinforced concrete, RC beam, stirrups, energy absorption capacity, steel fiber, synthetic fiber.


2014 ◽  
Vol 578-579 ◽  
pp. 1556-1561 ◽  
Author(s):  
Shuai Yang ◽  
Cong Qi Fang ◽  
Zhi Jie Yuan

The mechanical properties of corroded reinforced concrete under repeated load are investigated. The maximum crack width, mid-span deflection and reduction factor are predicted by using support vector machines. The maximum crack width and deflection are predicted by the black-box modeling based on support vector machines with the radial basis function kernel function. The reduction factor is predicted by using piecewise regression formula, whole regression formula and black-box modeling, respectively. The proposed prediction method is verified by comparing all prediction results with the experimental values. It is shown that the proposed method has high prediction accuracy, extensive applicable range and many predictive strategies.


Sign in / Sign up

Export Citation Format

Share Document