One of the key problems in tunneling is to define realitcic parameters for rock mass propreties as a basis for succesful numerical modelling. The main goal of this problem is how to extrapolate the parameter from the zone of testing to the whole area (volume) that is of interest for interaction analyses of the system rock mass-structure. So it is necessary to find an appropriate way to find intelegent tools to combine data from empirical classification rock mass methods having in mind that there are a lot of variations in statistic values.First step in the procedure is to divide the tunnel length in quasi-homogenous zones, while the second is to define adequate geotechnical and numerical models as a basis for interaction of rock – structures system and stress-strain behaviour of rock massif. Artificial neural networks (ANN) have been found to be powerful and versatile computational tools for many different problems in civil engineering over the past 2 decades. They have proved useful for solving certain types of problems, which are too complex, or too resource-intensive nonlinear problems to tackle using more traditional computational methods, such as the finite element method. ANN-s are intelligent tools, which have gained strong popularity in a large array of engineering applications such as pattern recognition, function approximation, optimization, forecasting, data retrieval, automatic control or classification, where conventional analytical methods are difficult to pursue, or show inferior performance.A review of some problems in tunnelling that were successfully solved by using neural networks is presented in this paper. A general introduction to neural networks (NN), their basic features and learning methods is given. After that, it is possible to use neural networks to solve necessary problems in tunnelling.

tunnelling; rock complexes; classification; extrapolation; neural networks