A Fuzzy Adaptive Resonance Theory‐Based Model for Mix Proportion Estimation of High‐Performance Concrete

Abstract

A new approach that adopts the use of fuzzy adaptive resonance theory (ART) neural network in estimating high-performance concrete (HPC) mix proportion from experimental data is devised. The proposed model receives a set of desired concrete performances, searches for a set of mix proportions that is near to the desired concrete performances, classifies the mix proportions into clusters, measures the similarity between performances of deduced clusters with desired performances, and deduces a mix proportion. The proposed model was used to estimate the mix proportions of five batches of concrete based on the performance criteria of 7th and 28th day compressive strengths. The generated mix proportions were used in an experimental work and the errors were within 13% for 7th compressive strength; and 7% for the 28th day compressive strength, signifying the reliability of the fuzzy ART-based model in estimating the mix proportion of HPC. This article contributes to an alternative method of mix proportion estimation of HPC by avoiding the use of complicated function approximation techniques. NOTATIONSThe following symbols are used in this article: FDesired concrete performances ε Tolerance range q m

Deep neural network with high‐order neuron for the prediction of foamed concrete strength

“…Therefore, these predictions are generally extrapolative in practice (Nehdi, Djebbar, & Khan, ). Moreover, such semi‐analytical models require the determination of empirical constants that are not easy to obtain to describe such complex relationships between mixture proportions and the compressive strength (Chiew, Ng, Chai, & Tay, ). Therefore, there is a significant need for the development of an advanced prediction tool.…”

Effect of Carbon Pricing on Optimal Mix Design of Sustainable High-Strength Concrete

“…Yadollahi et al [18] estimated the strength and slump of radiation shielding concrete using neural works and found the optimal mixtures based on parameter analysis of neural networks. Chiew et al [19] predicted the properties of concrete using fuzzy adaptive resonance theory neural network and found the optimal mixtures based on similarity measurement. However, we should note that the methods in references [15][16][17][18][19] have some weak points.…”

“…Chiew et al [19] predicted the properties of concrete using fuzzy adaptive resonance theory neural network and found the optimal mixtures based on similarity measurement. However, we should note that the methods in references [15][16][17][18][19] have some weak points. Previous studies mainly focused on the material cost of mixtures and ignored the carbon pricing [15][16][17][18][19].…”

“…Previous studies mainly focused on the material cost of mixtures and ignored the carbon pricing [15][16][17][18][19]. Moreover, the effect of increasing the carbon pricing on mix design is not highlighted [15][16][17][18][19]. On the other hand, neural networks are a local search optimization method and are likely to fall into local extremum [15][16][17][18][19].…”

“…Moreover, the effect of increasing the carbon pricing on mix design is not highlighted [15][16][17][18][19]. On the other hand, neural networks are a local search optimization method and are likely to fall into local extremum [15][16][17][18][19]. The physical meaning of weight matrix and bias vector in neural networks is not clear.…”