Prediction of representative deformation modulus of longwall panel roof rock strata using Mamdani fuzzy system  

作　　者：Mohammad Rezaei Mostafa Asadizadeh Abbas Majdi Mohammad Farouq Hossaini 

机构地区：[1]School of Mining Engineering, College of Engineering, University of Tehran

出　　处：《International Journal of Mining Science and Technology》2015年第1期23-30,共8页矿业科学技术学报（英文版）

摘　　要：Deformation modulus is the important parameter in stability analysis of tunnels, dams and mining struc- tures. In this paper, two predictive models including Mamdani fuzzy system （MFS） and multivariable regression analysis （MVRA） were developed to predict deformation modulus based on data obtained from dilatometer tests carried out in Bakhtiary dam site and additional data collected from longwall coal mines. Models inputs were considered to be rock quality designation, overburden height, weathering, unconfined compressive strength, bedding inclination to core axis, joint roughness coefficient and fill thickness. To control the models performance, calculating indices such as root mean square error （RMSE）, variance account for （VAF） and determination coefficient （R^2） were used. The MFS results show the significant prediction accuracy along with high performance compared to MVRA results. Finally, the sensitivity analysis of MFS results shows that the most and the least effective parameters on deformation modulus are weatherin~ and overburden height, respectively.Deformation modulus is the important parameter in stability analysis of tunnels, dams and mining structures. In this paper, two predictive models including Mamdani fuzzy system(MFS) and multivariable regression analysis(MVRA) were developed to predict deformation modulus based on data obtained from dilatometer tests carried out in Bakhtiary dam site and additional data collected from longwall coal mines. Models inputs were considered to be rock quality designation, overburden height, weathering,unconfined compressive strength, bedding inclination to core axis, joint roughness coefficient and fill thickness. To control the models performance, calculating indices such as root mean square error(RMSE),variance account for(VAF) and determination coefficient(R2) were used. The MFS results show the significant prediction accuracy along with high performance compared to MVRA results. Finally, the sensitivity analysis of MFS results shows that the most and the least effective parameters on deformation modulus are weathering and overburden height, respectively.

关 键 词：Deformation modulusDilatometer testMamdani fuzzy systemMultivariable regression analysis 

分 类 号：TD325[矿业工程—矿井建设]