Convolutional Neural Network-Based Regression for Predicting the Chloride Ion Diffusion Coefficient of Concrete

The durability performance of reinforced concrete(RC)building structures is significantly affected by the corrosion of the steel reinforcement due to chloride penetration,thus,the chloride ion diffusion coefficient should be investigated through experiments or theoretical equations to assess the durability of an RC structure.This study aims to predict the chloride ion diffusion coefficient of concrete,a heterogeneous material.A convolutional neural network(CNN)-based regression model that learns the condition of the concrete surface through deep learning,is developed to efficiently obtain the chloride ion diffusion coefficient.For the model implementation to determine the chloride ion diffusion coefficient,concrete mixes with w/c ratios of 0.33,0.40,0.46,0.50,0.62,and 0.68,are cured for 28 days;subsequently,the surface image data of the specimens are collected.Finally,the proposed model predicts the chloride ion diffusion coefficient using the concrete surface image data and exhibits an error of approximately 1.5E−12 m^(2)/s.The results suggest the applicability of proposed model to the field of facility maintenance for estimating the chloride ion diffusion coefficient of concrete using images.

Durability of sea-sand containing concrete:Effects of chloride ion penetration

This paper describes an orthogonal experiment on the effect of water/cement ratio,water consumption per cubic meter,curing time,and type of sand on the response＂resistance to chloride ion penetration＂.A sea-sand containing concrete was used for the trials.An analysis of chloride ion diffusion coefficients at different factor levels was performed.A predictive model of chloride ion diffusion in concrete is developed through regression analysis.The experimental results show that when the water/cement ratio varies from 0.45 to 0.60,and the water consumption per cubic meter varies from 185 to 215 kg,and the curing time varies from 30 to 180 d then the size of the effects fall in the order（most significant first）： curing time,type of sand,water consumption per cubic meter,and water/cement ratio.Chloride ion penetration is reduced,and better durability of the concrete is observed,with longer curing times,less water consumption per cubic meter,and a smaller water/cement ratio.

Corrosion life of artificial reef under natural seawater conditions

Corrosion of steel bars with chloride salt erosion is one of the main reasons for the deterioration of the performance of reinforced concrete structures.The key to the service life of concrete members is the transport rate of chloride ions and the time for rusting of steel bars.In this paper,the artificial reef concrete member is taken as the research object,and the diffusion coefficient of seawater chloride ion in C30,C35 and steel slag composite artificial reef concrete is analyzed.The critical chloride ion concentration of steel corrosion in concrete is used as the boundary condition for life prediction.The chloride ion diffusion model predicts the corrosion life of C30,C35 and steel slag composite artificial reefs in seawater.The results show that the diffusion law of chloride ions in concrete artificial reefs basically meets Fick's second law.The corrosion life of C30,C35 and steel slag composite concrete reefs was calculated by the model to be 51.6,54.8 and 56.8 years,respectively.