摘要：Rolling Dynamic Compaction(RDC),which is a ground improvement technique involving non-circular modules drawn behind a tractor,has provided the construction industry with an improved ground compaction capability,especially with respect to a greater influence depth and a higher speed of compaction,resulting in increased productivity. However,to date,there is no reliable method to predict the effectiveness of RDC in a range of ground conditions. This paper presents a new and unique predictive tool developed by means of artificial neural networks(ANNs) that permits a priori prediction of density improvement resulting from a range of ground improvement projects that employed 4-sided RDC modules;commercially known as"impact rollers". The strong coefficient of correlation(i.e. R >0.86) and the parametric behavior achieved in this study indicate that the model is successful in providing reliable predictions of the effectiveness of RDC in various ground conditions.

关键词：soil mechanics rolling dynamic compaction 

单位：School; of; Civil; Environmental; and; Mining; Engineering; University; of; Adelaide; Adelaide; 5005; Australia