---

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.

---

Stochastic nature of earthquake has raised a challenge for engineers to choose which record for their analyses. Clustering is offered as a solution for such a data mining problem to automatically distinguish between ground motion records based on similarities in the corresponding seismic attributes. The present work formulates an optimization problem to seek for the best clustering measures. In order to solve this problem, the well-known K-means algorithm and colliding bodies optimization are employed. The latter acts like a parameter-less meta-heuristic while the former provides strong intensification. Consequently, a hybrid algorithm is proposed by combining features of both the algorithms to enhance the search and avoid premature convergence. Numerical simulations show competative performance of the proposed method in the treated example of optimal ground motion clustering; regarding global optimization and quality of final solutions.

---

Opposition-based learning was first introduced as a solution for machine learning; however, it is being extended to other artificial intelligence and soft computing fields including meta-heuristic optimization. It not only utilizes an estimate of a solution but also enters its counter-part information into the search process. The present work applies such an approach to Colliding Bodies Optimization as a powerful meta-heuristic with several engineering applications. Special combination of static and dynamic opposition-based operators are hybridized with CBO so that its performance is enhanced. The proposed OCBO is validated in a variety of benchmark test functions in addition to structural optimization and optimal clustering. According to the results, the proposed method of opposition-based learning has been quite effective in performance enhancement of parameter-less colliding bodies optimization.