基于PSO改進的BP網(wǎng)絡在爆破大塊率優(yōu)化中的應用
發(fā)布時間：2019-03-02 17:26
【摘要】：為解決地下礦山爆破開采采場大塊率較高的問題,將PSO算法應用于BP網(wǎng)絡中,生成PSO-BP模型對影響大塊產(chǎn)生的主要參數(shù)進行優(yōu)化。以參數(shù)孔底距、排距、一次炸藥單耗、起爆位置為輸入因子,大塊率為輸出因子建立PSO-BP模型,采用現(xiàn)場實測數(shù)據(jù)初步訓練模型,通過控制變量法對模型參數(shù)的選取分別進行敏感性分析,得出最佳的大塊率PSO-BP評價模型。增加模型各輸入因子水平數(shù),按L16(34)正交表組成優(yōu)選樣本,經(jīng)評價模型的計算預測,搜索出最優(yōu)的大塊率影響參數(shù)值。研究結(jié)果表明:以東際金礦為例,采用孔底起爆方式,得出最佳大塊率預測值9.98%,最優(yōu)參數(shù)值是排距為1.6 m,孔底距為1.8 m,一次炸藥單耗為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.
【作者單位】： 中南大學資源與安全工程學院;
【基金】：國家自然科學基金項目(51374244)
【分類號】：TD235
本文編號：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.
【作者單位】： 中南大學資源與安全工程學院;
【基金】：國家自然科學基金項目(51374244)
【分類號】：TD235
【相似文獻】
相關(guān)期刊論文 前5條
1 張曉銘;張愛絨;郭勇義;;基于PSO算法優(yōu)化的自組織競爭神經(jīng)網(wǎng)絡在煤與瓦斯突出預測中的應用研究[J];中國煤炭;2013年01期
2 黃啟富;陳建宏;;基于多輪PSO算法的中長期動態(tài)優(yōu)化配礦研究[J];計算機應用研究;2010年10期
3 謝國民;康海潮;付華;何武林;;協(xié)同進化PSO算法在瓦斯含量預測中的應用研究[J];壓電與聲光;2011年05期
4 孫杰;韓艷;段勇;崔寶俠;;基于改進的PSO算法的球磨機PID神經(jīng)網(wǎng)絡控制系統(tǒng)[J];工礦自動化;2011年05期
5 ;[J];;年期
相關(guān)碩士學位論文 前1條
1 張曉銘;基于PSO算法優(yōu)化的自組織競爭神經(jīng)網(wǎng)絡在煤與瓦斯突出預測中的應用研究[D];太原理工大學;2013年
，本文編號：2433286
本文鏈接：http://sikaile.net/guanlilunwen/gongchengguanli/2433286.html
最近更新
教材專著
