LAUSR

A reliable and accurate prediction of the tunnel boring machine (TBM) performance can assist in minimizing the relevant risks of high capital costs and in scheduling tunneling projects. This research aims to develop a novel hybrid intelligent system, i.e., adaptive neuro-fuzzy inference system (ANFIS)-polynomial neural network (PNN) optimized by the imperialism competitive algorithm (ICA), ANFIS-PNN-ICA for prediction of TBM performance. In fact, the role of ICA in this hybrid system is to optimize the membership functions obtained by ANFIS-PNN model for receiving a higher level of performance prediction. Based on previously published works, seven parameters including the rock quality designation, the rock mass rating, Brazilian tensile strength, rock mass weathering, the uniaxial compressive strength, revolution per minute and thrust force were set as inputs to predict TBM performance. Together with the ANFIS-PNN-ICA model, two single model of PNN and ANFIS were also constructed for comparison purposes. These models were designed conducting several parametric studies on their most important parameters and then, their performance capacities were assessed through the use of several performance indices, e.g., correlation coefficient (R). R values of (0.9642, 0.9654 and 1), (0.9482, 0.9671 and 0.9778) and (0.9652, 0.9642, 0.9898) were obtained for training, testing and all datasets of PNN, ANFIS and ANFIS-PNN-ICA models, respectively. These results revealed that the greater prediction capacity can be provided by the ANFIS-PNN-ICA predictive model compared to ANFIS and PNN models and this hybrid intelligent model can be introduced as an accurate, powerful and applicable technique in the field of TBM performance prediction.