Modeling Concrete Strength with Augment-Neuron Networks

Abstract

In this paper, a novel neural network architecture, augment-neuron network, is proposed and examined for its efficiency and accuracy in modeling concrete strength with seven factors (water/cement ratio, water, cement, fine aggregate, coarse aggregate, maximum grain size, and age of testing). The architecture of the augment-neuron network is that of a standard back-propagation neural network, but augment neurons, i.e., logarithm neurons and exponent neurons, are added to the input layer and the output layer of the network. Two hundred examples were collected from actual experimental data from 15 sources. The system was trained based on 100 training examples chosen randomly from the example set, and then tested using the remaining 100 examples. The results showed that the logarithm neurons and exponent neurons in the network provide an enhanced network architecture to improve performance of these networks for modeling concrete strength significantly. A neural network–based concrete mix optimization methodology is proposed and is verified to be a promising tool for mix optimization.