摘要
为了优化某矿山采场的爆破参数,提出了水平凿岩方式代替上向倾斜凿岩方式的改进方案。根据改进方案,在采场中进行了L_9(3~3)的爆破参数正交试验,获取了9组试验结果。利用RBF神经网络模型对试验结果进行预测,以最小抵抗线、孔间距、周边孔距作为输入因子,炸药单耗、大块率作为输出因子,当隐含层个数为9时,预测效果最优;在综合考虑爆破成本和爆破效果的前提下,提出了爆破综合期望指数公式来最终优选爆破参数,获取了48个爆破综合期望指数,最大值1.134。综合分析,最终推荐矿山最优爆破参数为:排距1 m,孔间距1.4 m,周边孔距1 m,炸药单耗0.185 kg·t^(-1)。实际应用证明,选择的孔网参数合理,大块率降低至7%以下,极大的降低了爆破成本。
In order to optimize blasting parameters in an underground mine,an improvement program is put forward on the level blast hole drilling method instead of the tilt and upward drilling approach. According to the improved scheme,the L9（3^3） blasting orthogonal test is carried out,and 9 groups of data are obtained from the tests. By using RBF neural network prediction model to forecast the results of the blasting orthogonal test,the minimum burden,hole space and contour hole space are used as input factors,and explosives specific charge and boulder yield are used as output factors. When the number of the hidden layer is 9,the prediction effect is optimal. In the premise of considering the blasting cost and blasting effect,the comprehensive blasting exponential formula to determine the optimal blasting parameters is proposed,and 48 blasting comprehensive expectations parameters are obtained,of which the maximum value is 1. 134. The optimal recommend blasting parameters are given as row space 1 m,hole space1. 4 m,the contour hole space 1 m and explosives specific charge 0. 185 kg t-1. The reasonable blasting parameters can decrease large rock rate to 7% and reduce the cost.
出处
《爆破》
CSCD
北大核心
2017年第1期1-6,共6页
Blasting
基金
国家科技支撑计划项目(2013BAB02B05)
关键词
地下开采
回采工艺改进
正交试验
RBF神经网络
爆破综合期望指数
underground mining
mining technology improvement
orthogonal test
RBF neural network
blasting comprehensive expectation formula
