Existing rock mass parameters, such as uniaxial compressive strength (UCS), rock quality designation (RQD), and distance between planes of weakness (DPW), are being widely used in the prediction of TBM performance in various hard rock conditions. In this paper, these factors are considered as input parameters to estimate the rate of penetration (ROP) based on 180 compiled data from two projects including the Queens water tunnel lot 3, Stage 2 in USA and KarajTehran water transfer tunnel in Iran. This study aims to evaluate the influence of rock mass parameters on TBM performance and develop a new empirical equation to estimate ROP using multivariate regression analysis and artificial intelligence algorithms. In this regard, by taking advantage of machine learning algorithms, two types of artificial intelligence techniques, including particle swarm optimization (PSO) and radial basis function network (RBF), have been employed to develop predictor networks to estimate TBM performance. To explain the relationships among rock mass parameters and ROP and to offer new empirical equations, regression analysis is also utilized. The proposed models have been validated based on the various machine learning loss functions including, MAD, RRSE, rRMSE, MSE, MAPE, and sensitivity analysis. The obtained results demonstrate that the calculated values are in good agreement with the actual data.