基于极限学习机的爆破参数综合优选  被引量:2

Comprehensive Optimization Selection of Blasting Parameters Based on Extreme Learning Machine

在线阅读下载全文

作  者:陈昌民 张钦礼[2] 姜志良[2] 

机构地区:[1]衡阳远景钨业有限责任公司 [2]中南大学资源与安全工程学院

出  处:《现代矿业》2015年第4期14-16,30,共4页Modern Mining

摘  要:为了合理选择川口钨矿变更采矿方法后采场的回采爆破参数,运用传统经验公式计算出爆破参数取值范围,根据极限学习机(ELM)理论,以矿岩容重、弹性模量、抗压强度等6个因素作为输入因子,以排距、孔底距、炸药单耗3个指标作为输出因子,并利用国内应用较成功的上向扇形中深孔崩矿的7个矿山情况为学习、训练样本,建立矿山回采爆破参数优化预测模型。综合经验公式和预测模型的结果,确定采区爆破参数:炮孔排距为1.3 m,孔底距为1.8 m,炸药单耗为0.5 kg/t。优选爆破参数适应本采区工程条件,爆破效果好,震动影响小。In order to select the blasting parameters of stope that the mining method has been changed of Chuankou Tungsten Mine reasonably, the traditional empirical formula is adopted to calculate the value range of the blasting parameters. Based on the theory of extreme learning machine (ELM), six factors such as ore-bearing rock density, elastic modulus and comprehensive strength and so on are taken as input factors, three factors of row spacing, hole bottom spacing and explosive unit consumption are used as output factors, the situations of seven mines that the upward fan-shaped medium-length hole blas- ting ore breaking method are applied successfully are taken as learning and training examples so as to es- tablish the optimal prediction model of the blasting parameters during stoping. According to the results of the traditional empirical formula and prediction model, the blasting parameters of mining area are ob- tained. The hole row spacing is 1, 3 m, distance of holes to the bottom is 1.8 m, the explosive unit con- sumption is O. 5 kg/t. The results show that, the blasting parameters by optimizing selection can adapt to the conditions of mining engineering and achieve the perfect blasting effect, besides that, the blasting vibration effect is small.

关 键 词:爆破参数 极限学习机 预测模型 

分 类 号:TD235[矿业工程—矿井建设]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象