Modeling tunnel boring machine performance by neuro-fuzzy methods

Abstract

This paper presents the results of a study into the application of neuro-fuzzy methods to model the performance of tunnel boring machines. A database consisting of over 640 TBM projects in rock has been used. It is shown that neuro-fuzzy methods give better results than other, more conventional, modeling approaches. Fuzzy set theory, fuzzy logic and neural networks techniques seem very well suited for typical geological engineering applications. In conjunction with statistics and conventional mathematical methods, hybrid models can be developed that may prove a step forward in the practice of ground engineering.