Experimental study on shear mechanical characteristics and its size effect of concrete joints based on BP neural network method

• Published in: Construction & building materials Vol. 442; p. 137583
• Main Authors: Zhang, Zhezhe, Guo, Baohua, Zhu, Chuangwei, Zhong, Pengbo, Rong, Tenglong
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 06.09.2024
• Subjects: BP neural network; Pre-peak shear stiffness; Rock mechanics; Shearing strength; Size effect; Shearing strength; BP neural network; Rock mechanics; Size effect; Pre-peak shear stiffness
• ISSN: 0950-0618
• DOI: 10.1016/j.conbuildmat.2024.137583

In order to study the shear mechanical characteristics and its size effect on concrete joints, this paper uses the RDS-200 shear test system developed by GCTS company to carry out the indoor direct shear tests on concrete joint specimens with five kinds of JRC and five grades of joint surface size under five normal stress conditions. The results show that the pre-peak shear stiffness of concrete joints is not significantly affected by JRC and normal stress, but is significantly affected by the joint surface size. The pre-peak shear stiffness decreases with the increase of joint surface size, when the joint surface size increases from 35 mm to 95 mm, the pre-peak shear stiffness of specimens with JRC being 0 ∼ 2, 4 ∼ 6, 8 ∼ 10, 12 ∼ 14 and 16 ∼ 18 decreased by 66.96 %, 63.87 %, 71.67 %, 64.57 % and 66.32 %, respectively, with an average of 66.68 %. Moreover, with the increase of joint surface size, the decrease rate of pre-peak shear stiffness decreases gradually, which is basically exponential, that is because the pre-peak shear stiffness has negative size effect. In addition, the peak shear strength of concrete joints increases with the increase of normal stress and JRC, and the relationship between peak shear strength and normal stress conforms to the Mohr-Coulomb criterion. Furthermore, there is no obvious size effect on the peak shear strength of concrete joints in the range of 35–95 mm. An intelligent prediction method for predicting the peak shear strength and pre-peak shear stiffness of concrete joints considering JRC, joint surface size and normal stress was established. The prediction results show that the BP Neural Network optimized by genetic algorithm can effectively predict the peak shear strength and pre-peak shear stiffness of concrete joints, the average error of peak shear strength is about 4.91 %, and the average error of pre-peak shear stiffness is 9.37 %. The conclusions can provide some reference for the evaluation of shear instability of rock joints in surface and underground rock engineering. •With the help of 3D printing technology, concrete joint specimens were fabricated.•The significance test of indoor direct shear test results was carried out, and the influencing factors with higher significance were obtained.•The influence law between the influencing factors and the results is summarized.•Based on BP neural network, an intelligent prediction method for predicting peak shear strength and pre-peak shear stiffness is established.