A new method of modelling the rock microfracturing process in double-torsion experiments using neural networks

Microfracturing of rock is a complicated damage evolution process. Inaccura te prediction of micro-fracturing behaviours suggests a need for the develo pment of a better modelling method. Analysis of acoustic emission (AE) meas urements in double-torsion tests indicates that micro-fracturing behaviours during the loading stage have fractal time structures. This fractal behavi our can be described by C(t) proportional to t(D), where D is the correlati on exponent, t is the time and C(t) is the correlation integral. Furthermor e, by utilizing measured AE data, a new method has been developed to model the AE behaviours of micro-fracturing in rock, in air, and following soakin g in water and in a chemical solution of DTAB. The neutral models NN(10,21, 2) and NN(10,20,2) were found to describe reasonably well the AE behaviours of micro-fracturing in rock under air and DTAB conditions, and water condi tions, respectively. The cumulative AE events and the cumulative AE counts predicted by the neural models agreed well with those measured in experimen ts. Copyright (C) 1999 John Wiley & Sons, Ltd.