Fuzzy model for the prediction of unconfined compressive strength of rock samples

A data driven approach to the modeling of unconfined compressive strength o f rock samples is presented. Fuzzy logic approach is used to represent a no nlinear relationship as a smooth concatenation of local linear submodels. T he partitioning of the input space into fuzzy regions, represented by the i ndividual rules, is obtained through fuzzy clustering. The numerical result s are compared with a conventional statistical (multi-linear) model. It is shown that the fuzzy model is not only more accurate but as opposed to othe r black-box approaches (such as neural networks), it also provides some ins ight into the nonlinear relationship represented by the model. (C) 1999 Els evier Science Ltd. All rights reserved.