Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Mining & Safety Engineering》 2008-01
Add to Favorite Get Latest Update

Rockburst Prediction Method Based on Case Reasoning Pattern Recognition

SU Guo-shao1,2,ZHANG Xiao-fei1,YAN Liu-bin1 (1.College of Civil and Architecture Engineering,Guangxi University,Nanning,Guangxi 530004,China;2.Key Laboratory of Rock and Soil Mechanics,Chinese Academy of Sciences,Wuhan,Hubei 430071,China)  
Because of poor understanding about the mechanism of rockbust and about the effect factors,it is very difficult to give an accurate prediction using conventional methods.Aiming at this problem,we proposed a new method based on K-Nearest Neighbor case reasoning technology,which is one of the simplest and most effective tools in the field of machine learning.First,the effect factors of rockbust and instance histories were collected and input to the data base.Then,instance histories whose effect factors similar to new instance were selected through scanning the data based on the neighbor similarity function.Finally,rockburst risk of the new instance could be recognized by votes of instance histories selected.The results of prediction for mining induced rockburst at great depth in South African show that this method is feasible and reliable for rockburst prediction with high precision.The method will be attractive for a wide range of application in deep mining engineering.
【Fund】: 中国科学院岩土力学重点实验室开放研究基金项目(Z110601);; 广西大学科研基金项目(X017019)
【CateGory Index】: TD31;TP18
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved