基于PSO改进的BP网络在爆破大块率优化中的应用
发布时间：2019-03-02 17:26
【摘要】：为解决地下矿山爆破开采采场大块率较高的问题,将PSO算法应用于BP网络中,生成PSO-BP模型对影响大块产生的主要参数进行优化。以参数孔底距、排距、一次炸药单耗、起爆位置为输入因子,大块率为输出因子建立PSO-BP模型,采用现场实测数据初步训练模型,通过控制变量法对模型参数的选取分别进行敏感性分析,得出最佳的大块率PSO-BP评价模型。增加模型各输入因子水平数,按L16(34)正交表组成优选样本,经评价模型的计算预测,搜索出最优的大块率影响参数值。研究结果表明:以东际金矿为例,采用孔底起爆方式,得出最佳大块率预测值9.98%,最优参数值是排距为1.6 m,孔底距为1.8 m,一次炸药单耗为0.350 kg/m~3。
[Abstract]:In order to solve the problem of high ratio of large blocks in blasting mining of underground mines, the PSO algorithm is applied to BP network to generate PSO-BP model to optimize the main parameters affecting the production of large blocks. Based on the parameters of hole bottom distance, row distance, primary explosive unit consumption, initiation position as input factor and bulk ratio as output factor, the PSO-BP model is established, and the preliminary training model of field measured data is adopted. Based on the sensitivity analysis of the parameters of the model by the control variable method, the best PSO-BP evaluation model of bulk ratio is obtained. According to the orthogonal table of L16 (34), the optimal sample is formed by increasing the number of input factors of the model. Through the calculation and prediction of the evaluation model, the optimal parameter value of the influence of block ratio is found. The results show that: taking Dongji Gold Mine as an example, the optimum mass ratio is 9.98%, the optimum parameter is 1.6m, the hole bottom distance is 1.8m, and the unit consumption of primary explosive is 0.350 kg/m~3. by the way of hole bottom initiation. The results show that the optimum mass ratio is 9.98%, the optimum parameter is 1.6m, 1.8m and 0.350 min respectively.
【作者单位】： 中南大学资源与安全工程学院;
【基金】：国家自然科学基金项目(51374244)
【分类号】：TD235
本文编号：2433286
[Abstract]:In order to solve the problem of high ratio of large blocks in blasting mining of underground mines, the PSO algorithm is applied to BP network to generate PSO-BP model to optimize the main parameters affecting the production of large blocks. Based on the parameters of hole bottom distance, row distance, primary explosive unit consumption, initiation position as input factor and bulk ratio as output factor, the PSO-BP model is established, and the preliminary training model of field measured data is adopted. Based on the sensitivity analysis of the parameters of the model by the control variable method, the best PSO-BP evaluation model of bulk ratio is obtained. According to the orthogonal table of L16 (34), the optimal sample is formed by increasing the number of input factors of the model. Through the calculation and prediction of the evaluation model, the optimal parameter value of the influence of block ratio is found. The results show that: taking Dongji Gold Mine as an example, the optimum mass ratio is 9.98%, the optimum parameter is 1.6m, the hole bottom distance is 1.8m, and the unit consumption of primary explosive is 0.350 kg/m~3. by the way of hole bottom initiation. The results show that the optimum mass ratio is 9.98%, the optimum parameter is 1.6m, 1.8m and 0.350 min respectively.
【作者单位】： 中南大学资源与安全工程学院;
【基金】：国家自然科学基金项目(51374244)
【分类号】：TD235
【相似文献】
相关期刊论文 前5条
1 张晓铭;张爱绒;郭勇义;;基于PSO算法优化的自组织竞争神经网络在煤与瓦斯突出预测中的应用研究[J];中国煤炭;2013年01期
2 黄启富;陈建宏;;基于多轮PSO算法的中长期动态优化配矿研究[J];计算机应用研究;2010年10期
3 谢国民;康海潮;付华;何武林;;协同进化PSO算法在瓦斯含量预测中的应用研究[J];压电与声光;2011年05期
4 孙杰;韩艳;段勇;崔宝侠;;基于改进的PSO算法的球磨机PID神经网络控制系统[J];工矿自动化;2011年05期
5 ;[J];;年期
相关硕士学位论文 前1条
1 张晓铭;基于PSO算法优化的自组织竞争神经网络在煤与瓦斯突出预测中的应用研究[D];太原理工大学;2013年
，本文编号：2433286
本文链接：https://www.wllwen.com/guanlilunwen/gongchengguanli/2433286.html
