Sage Journals: Discover world-class research

Abstract

An empirical method for the design of spans in underground entry-type excavations has been developed by applying neural network analysis to an extensive casehistory database. The Braincel program was chosen for the analysis and data were compiled for 292 case histories from six Canadian mines, covering a wide range of rock-mass ratings (RMR) and spans. Rock classification and opening geometry information were input to the program and opening stability was the result. The neural network ‘expert’ created by training on the database was used to make predictions on 342 grid points of RMR against span. The span design graph derived from the analysis is shown to be an improvement on existing empirical methods of assessing the stability of underground entry-type excavations and the database used to train the neural network is appended.

Get full access to this article

View all access options for this article.

References

Braincel for Excel 4.0, 5.0 and 7.0, version 3. Promised Land Technologies, Inc. New Haven, CT, U.S.A., 1993.

Merritt

A. H.

Geologic prediction for underground excavations. In Proc. First North American rapid excavation and tunneling conf. (New York: AIME, 1972), 115–32.

Barton

, Lien

and Lunde

Engineering classification of rock masses for the design of tunnel support. Rock Mechanics, 6, no.4, 1974, 189–236.

Barton

Rock mass classification and tunnel reinforcement selection using Q-system. Rock classification systems for engineering purposes, American Society for Testing and Materials, A.S.T.M. 984, 1988, 59–88.

Bieniawski

Z. T.

Rock mechanics design in mining and tunnelling (Rotterdam: Balkema, 1984), 272 p.

Lang

Span design for entry-type excavations. M.Sc. Thesis, University of British Columbia, 1994.

Pakalnis

and Vongpaisal

Mine design—an empirical approach. In International congress on mine design, Queen's University, Kingston, Ontario, 1993 (Rotterdam: Balkema, 1993), 455–67.

Mah

Development of empirical design techniques in burstprone ground at the A. W. White mine, CANMET Project no. 1-9180, Canmet DSS file no. 02SQ.23440-1-9180, 1995.

Pakalnis

and McNamara

Development of sill pillar mining techniques in burst-prone ground, CANMET, DSS contract no. 23440-5-1293/001/SQ, 1997, 170.

10.

Wang

Empirical entry-type underground excavation span design. M.Eng. thesis, University of British Columbia, 1999.

11.

Wang

. Empirical underground entry-type excavation span design modification. In Proc. 53rd Annual conf. Canadian Geotechnical Society (Canada: Groupe Géotechnique de Montréal, 2000), 285–90.

12.

Bieniawski

Z. T.

Rock mass classification in rock engineering. In Proc. Symp. exploration for rock engineering, Johannesburg, vol. 1 (Cape Town: Balkema, 1976), 97–106.

13.

Mawdesley

, Trueman

and Whiten

W. J.

Extending the Mathews stability graph for open-stope design. Trans. Instn Min. Metall. (Sect. A: Min. technol.), 110, 2001, A27–39.

Application of a neural network in the empirical design of underground excavation spans

Abstract

Get full access to this article

References