采礦外文翻譯---采礦工業(yè)中實(shí)用的神經(jīng)網(wǎng)絡(luò)應(yīng)用程序

1、英文原文 英文原文Practical Neural Network Applications in the Mining IndustryL. Miller-Tait, R. PakalnisDepartment of Mining and Mineral Process Engineering,University of British Columbia,Vancouver, B.C., CanadaABSTRACTThe minin

2、g industry relies heavily upon empirical analysis for design and prediction. Neural networks are computer programs that use parallel processing, similar to the human brain, to analyze data for trends and correlation. Two

3、 practical neural network applications in the mining industry would be rockburst prediction and stope dilution estimates. This paper summarizes neural network data analysis results for a 1995 Goldcorp/Canmet study on roc

4、kbursting and a 1986 UBC/Canmet study on open stope dilution at the Ruttan Mine.1. INTRODUCTIONMany aspects of mine design are based upon empirical data. Neural Networks analyze data and predictions based on previous res

5、ults. Neural networks have advantages over conventional empirical design approaches. These advantages include:? Neural networks can easily use multiple inputs to analyze data.? By using multiple hidden layers and nodes n

6、eural networks investigate the combined influence of inputs.? Neural networks can be easily retrained as new data becomes available making them a more dynamic and flexible empirical estimation approach.? Neural network s

7、oftware is inexpensive and easy to use.? Neural networks have demonstrated a more accurate empirical estimate over conventional methods.The advantages of using neural networks are illustrated in a rockburst prediction ex

8、ample and an open stope dilution example.2. ROCKBURST PREDICTIONThe first example of a potential situation where neural networks could be useful in the mining industry is the prediction of rockbursts through physical inp

9、uts. To quote directly from the Ontario Ministry of Labor “...we do not have the ability to predict when and where rockbursts will occur, and the experts in the field agree that we are not close to make such predictions”

10、 [1]. Between 1984 and 1993 eight underground miners were killed in Ontario due to rockbursts. This accounted for ? Jw - joint water reduction factor? SRF - stress reduction factor.The actual Q formula is Q= RQD/Jn ×

11、; Jr/Ja × Jw/SRF.The Jw/SRF factor was assumed to be 1.0 for this study because dry conditions are assumed. Stress is factored through modelling and strain measurements. The Q factor ranges on a logarithmic scale ra

12、nging from 0.001 to 1,000 where 0.001 is extremely poor rock and 1,000 is virtually perfect rock.Span [5] - the meaning of span refers to the width of an underground opening in plan view. Span can be determined through t

13、he largest diameter of a circle within an underground excavation.SRF’ [2] - refers to the adjusting of RMR values relative to stress ratios and previous history of ground conditions. It does not refer directly to SRF use

14、d in the calculation of Q. Stress criteria is based upon the ratio of induced stress over unconfined compressive strength (UCS) of the rock.2.2. Output FactorsBurst refers to a stope in which a rockburst has occurred. A

15、rockburst is an instantaneous rock failure in or about an excavated area characterized/accompanied by a shock or tremor in the surrounding rock.PUN-RF refers to potentially unstable ground with respect to a roof fall. A

16、stope is considered potentially unstable if any of the following conditions occur [2]:? The opening may exhibit strong discontinuities having orientations that form potential wedges in the back.? Extra ground support may

17、 have been installed to prevent a potential fall of ground.? Instrumentation installed in the stope has recorded continuing movement of the stope back.? There may be an increased frequency of ground working or scaling.PU

18、N-GW refers to a stope considered potentially unstable due to the likelihood of a ground wedge failure. This is a subset of PUN-RF collected separately to identify areas where jointing may result in wedge failures.Cave r

19、efers to when uncontrolled ground failures result in caving.3. NEURAL NETWORK ANALYSISThe above inputs and outputs were run on a neural network to see if a neural network could predict results from the input data and als

20、o to see which inputs had the greatest effect on output prediction. A two layer network consisting of 13 nodes was run for 10105 cycles reaching a 1.69 percent error. Seventy three observations were used to train the net