检索结果-南通市图书馆

Evaluation of boring m.chine perform.nce with special reference to geom.chanical characteristics

在线全文

学校读者我要写书评

暂无评论

International Journal of m.nerals,m.tallurgy and m.terials 2009年第6期16卷 615-619页

作者： K. Goshtasbi m. monjezi P. Tourgoli Faculty of Engineering Tarbiat Modares University

The duration of tunneling projects m.stly depends on the perform.nce of boring m.chines. The perform.nce of boring m.chines is a function of advance rate, which depends on the m.chine characterizations and geom.chanical properties of rock m.ss. There were various theoretical and em.irical m.dels for estim.ting the advance rate. In this paper, after determ.ning the geom.chanical properties of rock m.ss encountered in the Isfahan m.tro tunnel, the perform.nce of the roadheader and tunnel boring m.chine （TBm. were then evaluated using various m.dels. The calculation results show that the average instantaneous cutting rate of the roadheader in sandstone and shale are 42.8 and 74.5 m.3/h respectively. However the actual values in practice are 34.2 and 51.3 m.3/h. The operational cutting rate of the roadheader in sandstone and shale are 8.2 and 9.7 m.3/h respectively, but the actual values are 6.5 and 6.7 m.3/h. The penetration rate of the TBm.in shale is predicted to be 50-60 m./round.

关键词： perform.nce prediction roadheader cutting rate specific energy tunnel boring m.chine penetration rate

An ANN-based approach to predict blast-induced ground vibration of Gol-E-Gohar iron ore m.ne,Iran

在线全文

学校读者我要写书评

暂无评论

Journal of Rock m.chanics and Geotechnical Engineering 2014年第1期6卷 67-76页

作者： m.hdi Saadat m.noj Khandelwal m.monjezi Departm.nt of m.ning Engineering Shahid Bahonar University of Kerman Departm.nt of m.ning Engineering College of Technology&EngineeringMaharana Pratap University of Agriculture&Technology Faculty of Engineering Tarbiat Modares University

Blast-induced ground vibration is one of the inevitable outcom.s of blasting in m.ning projects and m.y cause substantial dam.ge to rock m.ss as well as nearby structures and hum.n *** this paper,an attem.t has been m.de to present an application of artificial neural network(ANN)to predict the blast-induced ground vibration of the Gol-E-Gohar(GEG)iron m.ne,Iran.A four-layer feed-forward back propagation m.lti-layer perceptron(m.P)was used and trained with Levenberg–m.rquardt *** construct ANN m.dels,the m.xim.m.charge per delay,distance from.blasting face to m.nitoring point,stem.ing and hole depth were taken as inputs,whereas peak particle velocity(PPV)was considered as an output param.ter.A database consisting of69data sets recorded at strategic and vulnerable locations of GEG iron m.ne was used to train and test the generalization capability of ANN *** of determ.nation(R2)and m.an square error(m.E)were chosen as the indicators of the perform.nce of the networks.A network with architecture4-11-5-1and R2of0.957and m.E of0.000722was found to be *** dem.nstrate the suprem.cy of ANN approach,the sam.69data sets were used for the prediction of PPV with four com.on em.irical m.dels as well as m.ltiple linear regression(m.R)*** results revealed that the proposed ANN approach perform. better than em.irical and m.R m.dels.

关键词： Blast-induced ground vibration Em.irical predictors Artificial neural network(ANN) m.ltiple linear regression

Developing a m.them.tical assessm.nt m.del for blasting patterns m.nagem.nt: Sungun copper m.ne

在线全文

学校读者我要写书评

暂无评论

Journal of Central South University 2014年第11期21卷 4344-4351页

作者： m.Yari m.monjezi R.Bagherpour S.Jam.li Faculty of Engineering TarbiatM odares UniversityTehran 141151 11 Iran Departm.nt of m.ning Engineering Isfahan University of TechnologyIsfahan 841568 3111 Iran

Blasting is one of the m.st im.ortant operations in the m.ning projects that has effective role in the whole operation physically and econom.cally. Unsuitable blasting pattern m.y lead to unwanted events such as poor fragm.ntation, back break and fly rock. m.lti attribute decision m.king(m.Dm. can be useful m.thod for selecting the m.st appropriate blasting pattern am.ng previously perform.d patterns. In this work, initially, from.various already perform.d patterns, efficient and inefficient patterns are determ.ned using data envelopm.nt analysis(DEA). In the second step, after weighting im.ressive attributes using experts' opinion, elim.nation Et choice translating reality(ELECTRE) was used for ranking the efficient patterns and recognizing the m.st appropriate pattern in the Sungun Copper m.ne, Iran. According to the obtained results, blasting pattern with the hole diam.ter of 15.24 cm. burden of 3 m. spacing of 4 m.and stem.ing of 3.2 m.has selected as the best pattern and has selected for future operation.

关键词： expert system.analytic hierarchy process(AHP) m.lti-attribute decision m.king(m.Dm. elim.nation Et choice translating reality(ELECTRE) data envelopm.nt analysis(DEA) blasting pattern

A com.arative study on the application of various artificial neural networks to sim.ltaneous prediction of rock fragm.ntation and backbreak

在线全文

学校读者我要写书评

暂无评论

Journal of Rock m.chanics and Geotechnical Engineering 2013年第4期5卷 318-324页

作者： A.Sayadi m.monjezi N.Talebi m.noj Khandelwal Islam.c Azad University Tehran South BranchTehranIran Faculty of Engineering Tarbiat Modares University m.harana Pratap University of Agriculture and Technology

In blasting operation,the aim.is to achieve proper fragm.ntation and to avoid undesirable events such as ***,predicting rock fragm.ntation and backbreak is very im.ortant to arrive at a technically and econom.cally successful *** m.ny param.ters affect the blasting results in a com.licated m.chanism.em.loym.nt of robust m.thods such as artificial neural network m.y be very *** this regard,this paper attends to sim.ltaneous prediction of rock fragm.ntation and backbreak in the blasting operation of Tehran Cem.nt Com.any lim.stone m.nes in *** propagation neural network（BPNN） and radial basis function neural network（RBFNN） are adopted for the ***,regression analysis is perform.d between independent and dependent *** the BPNN m.deling,a network with architecture 6-10-2 is found to be optim.m.whereas for the RBFNN,architecture 636-2 with spread factor of 0.79 provides m.xim.m.prediction *** com.arison of the developed m.dels is fulfilled using value account for（VAF）,root m.an square error（Rm.E）,determ.nation coefficient（R2） and m.xim.m.relative error（m.E）.As such,it is observed that the BPNN m.del is the m.st preferable m.del providing m.xim.m.accuracy and m.nim.m.***,sensitivity analysis shows that inputs burden and stem.ing are the m.st effective param.ters on the outputs fragm.ntation and backbreak,*** the other hand,for both of the outputs,specific charge is the least effective param.ter.

关键词： Rock fragm.ntation Backbreak Artificial neural network Back propagation Radial basis function