Optimum Design of High-Strength Concrete Mix Proportion for Crack Resistance Using Artificial Neural Networks and Genetic Algorithm

Abstract

The fact that high-strength concrete is easily to crack has a significant negative impact on its durability and strength. This paper gives an optimum design method of high-strength concrete for improving crack resistance based on orthogonal test artificial neural networks (ANN) and genetic algorithm. First, orthogonal test is operated to determine the influence of the concrete mix proportion to the slump, compressive strength, tensile strength, and elastic modulus, followed by calculating and predicting the concrete performance using ANN. Based on results from orthogonal test and ANN, a functional relationship among slump, compressive strength, tensile strength, elastic modulus, and mix proportion has been built. On this basis, using the widely used shrinkage and creep models, the functional relationship between the concrete cracking risk coefficient and the mix proportion is derived, and finally genetic algorithm is used to optimize the concrete mix proportion to improve its crack resistance. The research results showed that, compared with the control concrete, the cracking risk coefficient of the optimized concrete was reduced by 25%, and its crack resistance was significantly improved.

Using Multivariate Regression and ANN Models to Predict Properties of Concrete Cured under Hot Weather

“…In comparison to other studies, Yue et al [97] developed an ANN model to predict fc, ft, elastic modulus, and concrete slump. The resulting R 2 values obtained for these properties were above 0.94.…”

“…Table7shows the results of the combined ANN model for predicting the properties of concrete. The R 2 values of fc, ft, and PV obtained through this model are above 0.9, reflecting higher prediction accuracy.In comparison to other studies, Yue et al[97] developed an ANN model to predict fc, ft, elastic modulus, and concrete slump. The resulting R 2 values obtained for these properties were above 0.94.…”

Early Cracking Risk Prediction Model of Concrete under the Action of Multifield Coupling

“…where σ t (t) is the deformation tensile stress (cracking driving force) of concrete at the early age t, MPa; f t (t) is the tensile strength of concrete at the early age t, MPa; E (t) is the elastic modulus of the concrete at the early age t, MPa; ε sh−e (t) is the effective shrinkage strain of the concrete at the early age t. Among them, when η < 0.7, the concrete does not crack; when 0.7 ≤ η ≤ 1.0, the concrete may crack; when η > 1.0, the concrete cracks. Gao et al's [22,23] research showed that the effective shrinkage strain ε sh−e (t) was the result of the interaction of the shrinkage strain and the creep strain (strain of concrete due to creep) of the concrete, as shown in…”

“…where t and t 0 are the age of concrete and the age of concrete under loading, respectively, d; ε sh (t) is the shrinkage strain of the concrete at the age t; ε creep (t, t 0 ) is the shrinkage strain of the concrete due to creep in the early age (t, t 0 ). Bentz et al's [9,23] study showed that the relationship between creep strain and effective shrinkage strain can be expressed by creep coefficient φ, as shown in…”

The Need of Statistical Approach for Optimising Mixture Design of Controlled Low-Strength Materials

“…Analytical methods help obtain the optimal concrete mixes based on in-depth and extensive experimental knowledge of certain heavy components and the fundamental formulae obtained from past experiments [30][31][32][33]. For example, artificial neural networks, genetic algorithms, and mathematical programming are tools for evaluating semi-experimental (analytic) methods based on a combination of experimental databases or predictive models developed for trial [34][35][36][37][38][39].…”