THE APPLICATION OF NEURAL NETWORKS TO ROCK ENGINEERING SYSTEMS (RES)

Authors
Citation
Y. Yang et Q. Zhang, THE APPLICATION OF NEURAL NETWORKS TO ROCK ENGINEERING SYSTEMS (RES), International journal of rock mechanics and mining sciences & geomechanics abstracts, 35(6), 1998, pp. 727-745
Citations number
19
Categorie Soggetti
Geochemitry & Geophysics","Mining & Mineral Processing
Volume
35
Issue
6
Year of publication
1998
Pages
727 - 745
Database
ISI
SICI code
Abstract
This paper proposes a new approach for applying neural networks in Roc k Engineering Systems (RES) based on the learning abilities of neural networks. By considering the analysis of the coding method's for the i nteraction matrix in RES and the learning processes of neural networks such as the Back Propagation (BP) method neural networks can provide a useful mapping from om system inputs to system outputs for rock engi neering, so that the influence of inputs on outputs can be obtained. T hen the results of the neural network analysis can be presented in a s imilar way to the global interaction matrix used in RES to present the fully-coupled system results. The neural network procedures are expla ined first, with illustrative demonstrations for simultaneous equation s. Then, the link with the RES type of analysis is explained, together with some demonstration examples for rock engineering data sets. The specific analysis procedure is presented and then wider rock engineeri ng examples are given relating to the characteristics of rock masses a nd engineering parameters. The main presentation tools used in this ne ural network approach are the Relative Strength Effect (RSE) and the G lobal Relative Strength Effect (GRSE) matrix. There is discussion of t he value of this approach and an indication of the likely areas of fut ure development. (C) 1998 Elsevier Science Ltd.