Afrasiabian Bijan, Aghajani-Bazzazi Abbas, Hosseini Navid
5th Iranian Rock Mechanics Conference (IRMC5), Tehran, Iran
Publication year: 2014

In recent years the use of Tunnel Boring Machines has become increasingly important due to their wide applications and developments in the tunneling industry. In this way, determination and evaluation of effective parameters on the performance of these machines, are important due to the cost of drilling and economical issues. The estimation of the penetration rate is considered as one of the most important parameter to assess the TBMs performance which is linked to the operational expenses. The effective parameters on the TBMs penetration rate could be categorized in terms of the dependence on the ground and machine conditions. In this study the penetration rate has been predicted by means of the Artificial Neural Network and Multivariate Linear Regression Analysis. In this study, the Tehran-Karaj water conveyance tunnel located in the province of Alborz has been chosen to be investigated. Initially data were collected and then effective parameters on the penetration rate were determined. Finally by choosing the most proper neural network, sensitivity analysis on the parameters was carried out. Furthermore, considering the Coefficient of determination, mean square error, and root mean square error as the main criteria, a comparison between the two mentioned methods has been done. Results show the used model of artificial neural network with six input parameters and two hidden layers with eight and sixteen neurons, has remarkedly higher Coefficient of determination with lower values of errors with respect to the linear regression. In this way, corresponding values of the neural network and multivariate regression methods are 0.991 and 0.861, respectively. Therefore the predicted results via neural network show better agreements with actual values.