NEURAL-NETWORK DYNAMIC MODELING OF ROCK MICROFRACTURING SEQUENCES UNDER TRIAXIAL COMPRESSIVE STRESS CONDITIONS

Rock fracturing processes are very complicated nonlinear dynamic syste ms. Distributions of acoustic emission (AE) events in the time dimensi on during microfracturing processes of rock under triaxial compressive stress conditions have fractal structures that proceed as C(t) propor tional to t(D), where the fractal dimension D is 0.43 less than or equ al to D less than or equal to 1.0. As the fracturing process progresse s, the system's state initially changes from ordered to disordered (fr actal dimension D decreases from about 1 to about 0.48) and then chang es back to ordered (fractal dimension increases from 0.48 to about 0.9 1). Corresponding to each evolutionary process of the system's states, AE event patterns such as the AE event rate, AE count rate, and ampli tude in rock fracturing processes were recognized using neural network techniques. AE event patterns at 8-10 succeeding time points were pre dicted using the corresponding models. AE event patterns in rock micro fracturing processes are effectively described by the neural dynamic m odel NN(n, h, 1). The models so obtained are applicable for extrapolat ed recognition of AE event patterns with adequate accuracy. An improve d learning algorithm is proposed to train the networks with generally improved performance of the models. (C) 1998 Elsevier Science B.V. All rights reserved.