---

The  tunnel  boring  machine  (TBM)  penetration  rate  estimation  is  one  of  the  crucial  and complex  tasks  encountered  frequently  to  excavate  the  mechanical  tunnels.  Estimating  the machine  penetration  rate  may  reduce  the  risks  related  to  high  capital  costs  typical  for excavation  operation.  Thus  establishing  a  relationship  between  rock  properties  and  TBM penetration  rate  can  be  very  helpful  in  estimation  of  this  vital  parameter.  However, establishing relationship between rock properties and TBM penetration rate is not a simple task and cannot be done using a simple linear or nonlinear method. Adaptive neuro fuzzy inference system based on fuzzy c–means clustering algorithm (ANFIS–FCM) is one of the 
robust  artificial  intelligence  algorithms  proved  to  be  very  successful  in  recognition  of relationships  between  input  and  output  parameters.  The  aim  of  this  paper  is  to  show  the application of ANFIS–FCM in estimation of TBM performance. The model was applied to available data given in open source literatures. The results obtained show that the ANFIS–FCM model can be used successfully for estimation of the TBM performance.

---

During project planning, the prediction of TBM performance is a key factor for selection of tunneling methods and preparation of project schedules. During the construction, TBM performance need to be evaluated based on the encountered rock mass conditions. In this paper, the model based on a relevance vector regression (RVR) optimized by dolphin echolocation algorithm (DEA) for prediction of specific rock mass boreability index (SRMBI) is proposed. The DEA is combined with the RVR for determining the optimal value of its user-defined parameters. The optimized RVR by DEA was employed to available data given in the open source literature. In this model, rock mass uniaxial compressive strength, brittleness index (B_i), volumetric joint account (J_v), and joint orientation (J_o) were used as the input, while the SRMBI was the output parameter. The performances of the suggested predictive model were tested according to two performance indices, i.e., mean square error and determination coefficient. The results show that the RVR- DEA model can be successfully utilized for estimation of the SRMBI in mechanical tunneling.