Prediction of the penetration rate of tbm using adaptive neuro fuzzy inference system (ANFIS)

Abstract

Rate of penetration of Tunnel Boring Machines (TBM) has a significant role in the planning, measurement of productivity and performance of any tunneling project. In this paper, the application of Adaptive Neuro Fuzzy Inference System (ANFIS) in prediction of TBM penetration rate is evaluated. For this purpose, a database including Rock Quality Designation (RQD), Uni-axial Compressive Strength (UCS) of the rock, the Distance between Planes of Weakness (DPW) in the rock mass, and empirical data regarding rate of penetration of TBM from several tunneling projects are collected. The Rate of Penetration is then estimated by using ANFIS. These results are then compared with measured TBM penetration rates (actual data). It is concluded that ANFIS can be applied successfully for such purpose and result in high accuracy for prediction for the rate of penetration of TBM. The method provided in this paper can assist the mining engineer to estimate the performance of tunneling accurately.