Bituminous mix characterisation: evolving intelligent systems

Abstract

This paper describes a novel implementation of evolving connectionist systems (Ecos) based predictive modelling of the dynamic modulus (|E*|) of hot-mix asphalt, a construction material used in preparing the surface layer of roads. Ecos are open-architecture artificial neural networks with a dynamically evolving structure that is automatically adjusted by the training algorithm thereby overcoming the limitations associated with conventional and constructive artificial neural networks. Two Ecos methods are investigated – the dynamic evolving neuro-fuzzy inference system (Denfis) and the evolving fuzzy neural network (EFuNN). Preliminary investigations show that Ecos-based hot-mix asphalt |E*| predictive modelling is a promising alternative to regression-based methods, although not as powerful as traditional multi-layered perceptron back-propagation artificial neural networks.