The prediction analysis of properties of recycled aggregate permeable concrete based on back-propagation neural network

Abstract

The further study on recycled aggregates can promote the standardization and scale of the comprehensive recycling industry of the construction waste and meet the requirements of sustainable development. Therefore, this paper studies the relationship between the material and property and the relationship between properties of recycled aggregate permeable concrete. The test data sets of compressive strength, splitting strength, porosity and permeability coefficient of recycled aggregate permeable concrete are obtained. The results show: after statistical analysis, these four properties approximately follow the normal distribution law, and clearly there is an opposition feature between the strength and permeability. The average relative errors of the unilateral relationship prediction model (between materials and key properties) and the bilateral relationship model (between key properties) based on the Back-Propagation neural network method are both within 7%. The results of this study can provide reference for researchers to evaluate or predict the properties of recycled aggregate permeable concrete as well as reduce the loss of manpower and financial resources during the test.