Application of artificial neural networks to the prediction of tunnel boring machine penetration rate

Rate of penetration of a Tunnel Boring Machine (TBM) in a rock environment is generally a key parameter for the successful accomplishment of a tunneling project. This paper presents the results of a study into the application of an Artificial Neural Network (ANN) technique for modeling the penetration rate of tunnel boring machines. A database, including actual, measured TBM penetration rates, uniaxial compressive strengths of the rock, the distance between planes of weakness in the rock mass and rock quality designation was established. Data collected from three different TBM projects (the Queens Water Tunnel, USA, the Karaj-Tehran water transfer tunnel, Iran, and the Gilgel Gibe II hydroelectric project, Ethiopia). A five-layer ANN was found to be optimum, with an architecture of three neurons in the input layer, 9, 7 and 3 neurons in the first, second and third hidden layers, respectively, and one neuron in the output layer. The correlation coefficient determined for penetration rate predicted by the ANN was 0.94.