Journal of Yangtze River Scientific Research Institute ›› 2023, Vol. 40 ›› Issue (3): 166-173.DOI: 10.11988/ckyyb.20220648

• HYDRAULIC STRUCTURE AND MATERIAL • Previous Articles     Next Articles

Influence of Stone Powder Parameters on Mechanical Properties of Concrete

ZHANG Yan, LIU Jia-hao, LÜ Yuan, LI Zhi-hao, ZHANG Yan-nan, LI Sheng, CHEN Zhuan-wen   

  1. School of Architecture and Civil Engineering, Xi'an University of Science and Technology, Xi'an 710054, China
  • Received:2022-06-10 Revised:2022-09-21 Online:2023-03-01 Published:2023-03-28

Abstract: The aim of the study is to investigate the influences of different stone powder parameters on the mechanical propertices of concrete. Compressive strength and flexural strength tests of stone powder concrete were carried out by orthogonal test method. The microstructure of concrete under the influence of stone powder was tested and analyzed by SEM and MIP test. Based on BP neural network, the 28 d compressive strength of concrete was predicted and further analyzed with variable parameters. Results show that the strength of concrete is most affected by the content of stone powder,less by the lithology,and least by the fineness. The strength of concrete first increases and then decreases with the increase of stone powder content.When the content of stone powder is 10%,the compressive strength of concrete increases by 18.21% and the flexural strength increases by 17.91% compared with the reference group.The strength of tuff powder concrete is larger than that of limestone powder concrete and red sandstone powder concrete in sequence.With the increase of the fineness of stone powder,the strength of concrete gradually increases.The average relative error of the model established based on the BP neural network is 2.33%.According to the extended analysis of variable parameters, the change rule of predicted values is consistent with experimental result.

Key words: concrete, mechanical properties, stone powder parameters, orthogonal test method, SEM, MIP test, BP neural network

CLC Number: