Condition Monitoring of Ground Anchorages using an Artificial Neural Network and Wavelet techniques

Abstract

Ground anchorage systems in form of rock bolts are used extensively throughout the world as supporting devices for civil engineering constructions as varied as bridges, tunnels and dams. The condition monitoring of rock bolts is a new area of research, with the objective being a wholly automated or semi-automated condition monitoring system capable of repeatable and accurate diagnosis of faults and rockbolt post-tension levels. The automated system will comprise of a preprocessing phase incorporating wavelet techniques and an analysis phase comprising of a trained multi-layer perceptron neural network.