研究论文

超细全尾砂絮凝沉降参数优化模型

  • 王新民 ,
  • 刘吉祥 ,
  • 陈秋松 ,
  • 肖崇春 ,
  • 万孝衡
展开
  • 中南大学资源与安全工程学院, 长沙 410083
王新民,教授,研究方向为采矿与充填技术,电子信箱:237755829@qq.com

收稿日期: 2014-03-05

  修回日期: 2014-04-15

  网络出版日期: 2014-06-20

基金资助

“十二五”国家科技支撑计划项目(2012BAC09B02)

Optimal Flocculating Sedimentation Parameters of Unclassified Tailings

  • WANG Xinmin ,
  • LIU Jixiang ,
  • CHEN Qiusong ,
  • XIAO Chongchun ,
  • WAN Xiaoheng
Expand
  • School of Resourcrs and Safety Engineering, Central South University, Changsha 410083, China

Received date: 2014-03-05

  Revised date: 2014-04-15

  Online published: 2014-06-20

摘要

为了得到最优的絮凝沉降参数,以絮凝沉降正交试验数据为训练样本和检验样本建立BP 神经网络预测模型。絮凝剂单耗、料浆浓度及絮凝剂浓度作为输入因子,沉降速度和极限浓度作为输出因子。对比隐含层节点数对模型训练过程及预测精度的影响,选取最佳预测模型节点数为9。将絮凝沉降参数细化输入到预测模型中,从而搜索出优选样本,优选参数絮凝剂单耗为4.5 g/t,絮凝剂浓度为0.11%,料浆浓度为15%。经实验对比,该模型对絮凝沉降参数预测结果的相对误差能控制在5%左右,精确度较高,可以作为絮凝沉降参数优选的一种新思路。

本文引用格式

王新民 , 刘吉祥 , 陈秋松 , 肖崇春 , 万孝衡 . 超细全尾砂絮凝沉降参数优化模型[J]. 科技导报, 2014 , 32(17) : 23 -28 . DOI: 10.3981/j.issn.1000-7857.2014.17.003

Abstract

Back-propagation neural network was used to optimize the flocculating sedimentation parameters. To get the best network mode, some learning and training samples were established by the numbered orthogonal blasting tests. In the process of establishing the network mode, the tailings concentration, flocculant consumption and flocculant concentration were used as the input data, the sedimentation speed and limiting concentration were confirmed to be the synthesized output data. Comparison of the influences of hidden layer nodes on model training process and prediction accuracy indicates that the optimal hidden layer node was 9. By entering the refined flocculating sedimentation parameters into the prediction model, optimal samples are searched and the optimal parameters show that the flocculating agent consumption is 4.5 g/t, flocculating concentration is 0.11% and tailings concentration is 15%. Compared with that of the experimental results, the relative error of the prediction results can be controlled at about 5%. The application indicates this mode has relatively high accuracy, providing a new method to optimize the flocculating sedimentation parameters.

参考文献

[1] 钱鸣高, 缪协兴, 许家林. 资源与环境协调(绿色)开采[J]. 煤炭学报, 2007, 32(1): 1-7. Qian Minggao, Miao Xiexing, Xu Jialin. Green mining of coal resources harmonizing with environment[J]. Journal of China Coal Society, 2007, 32 (1): 1-7.
[2] 王新民, 古德生, 张钦礼. 深井矿山充填理论与管道输送技术[M]. 长 沙: 中南大学出版社, 2010: 9-10. Wang Xinmin, Gu Desheng, Zhang Qinli. Theory and technology of deep mine backfilling[M]. Changsha: Central South University Press, 2010: 9-10.
[3] 孙光华, 李青山. 采空区充填技术研究[J]. 矿业研究与开发, 2011(5): 16-17, 65. Sun Guanghua, Li Qingshan. Study on the technology of fillinggoaf[J]. Mining Research and Development, 2011(5): 16-17, 65.
[4] 王洪江, 吴爱祥, 肖卫国, 等. 粗粒级膏体充填的技术进展及存在的问 题[J]. 金属矿山, 2009(11): 1-5. Wang Hongjiang, Wu Aixiang, Xiao Weiguo, et al. The progresses of coarse paste fill technology and its existing problem[J]. Metal Mine, 2009 (11): 1-5.
[5] 王勇, 王洪江, 吴爱祥, 等. 细粒全尾矿絮凝沉降特性研究[J]. 黄金, 2012, 33(1): 48-51. Wang Yong, Wang Hongjiang, Wu Aixiang, et al. Research on flocculation sedimentation characteristies of fine unclassified-tailings[J]. Gold, 2012, 33(1): 48-51.
[6] Rulyov N N, Laskowski J S, Concha F. The use of ultra-flocculation in optimization of the experimental flocculation procedures[J]. Physicochemical Problems of Mineral Processing, 2011, 47: 5-16.
[7] 焦华喆, 吴爱祥, 王洪江, 等. 全尾砂絮凝沉降特性实验研究[J]. 北京科 技大学学报, 2011, 33(12): 1437-1441. Jiao Huazhe, Wu Aixiang, Wang Hongjiang, et al. Experiment study on the flocculation settlement characteristic of unclassified tailings[J]. Journal of University of Science and Technology Beijing, 2011, 33(12): 1437-1441.
[8] 张钦礼, 谢盛青, 郑晶晶, 等. 充填料浆沉降规律研究及输送可行性分 析[J]. 重庆大学学报, 2011, 34(1): 105-107 Zhang Qinli, Xie Shengqing, Zheng Jingjing, et al. Sedimentation law research and transportation feasibility study of backfilling slurry[J]. Journal of Chongqing University, 2011, 34(1): 105-107
[9] 史秀志, 胡海燕, 杜向红, 等. 立式砂仓尾砂浆液絮凝沉降试验研究[J]. 矿冶工程, 2010(3): 1-3. Shi Xiuzhi, Hu Haiyan, Du Xianghong, et al. Experimental study on flocculating sedimentation of tailings slurry in a vertical sand tank[J]. Mining and Metallurgical Engineering, 2010(3): 1-3.
[10] 向平, 张蒙, 张智, 等. 基于BP神经网络的城市时用水量分时段预测 模型[J]. 中南大学学报: 自然科学版, 2012, 43(8): 3320-3323. Xiang Ping, Zhang Meng, Zhang Zhi, et al. Period-divided predictive model of urban hourly water consumption based on BP neural network[J]. Journal of Central South University: Science and Technology Edition, 2012, 43(8): 3320-3323.
[11] 蒋建平, 章杨松, 阎长虹, 等. BP神经网络在地基土压缩指数预测中 的应用[J]. 中南大学学报: 自然科学版, 2010, 41(2): 722-724. Jiang Jianping, Zhang Yangsong, Yan Changhong, et al. Application of BP neural network in prediction of compression index of soil[J]. Journal of Central South University: Science and Technology Edition, 2010, 41 (2): 722-724.
[12] 张钦礼, 李谢平, 杨伟. 基于BP网络的某矿山充填料浆配比优化[J]. 中南大学学报: 自然科学版, 2013, 44(7): 2867-2869. Zhang Qinli, Li Xieping, Yang Wei. Optimization of filling slurry ratio in a mine based on back-propagation neural network[J]. Journal of Central South University: Science and Technology Edition, 2013, 44(7): 2867-2869.
[13] Yuan Y, Chai L, Yang Z. Application of polymeric aluminum salts in remediation of soil contaminated by Pb, Cd, Cu, and Zn[J]. Journal of Central South University, 2013, 20(6): 1638-1640.
[14] Hu H, Zhang K, Zhang L, et al. Thermal decomposition behaviour of polyacrylamidomethyltrimethyl ammonium chloride in red mud separation process[J]. Journal of Central South University, 2008, 15(6): 808-810.
[15] 赵彬, 王新民, 史良贵, 等. 基于BP神经网络的爆破参数优选[J]. 矿冶 工程, 2009, 29(4): 24-27. Zhao Bin, Wang Xinmin, Shi Lianggui, et al. Optimizationof blasting parameters based on back-propagation neuralnetwork[J]. Mining and Metallurgical Engineering, 2009, 29(4):24-27.
[16] 张钦礼, 程健, 陈秋松, 等. GA-SVM和神经网络组合模型预测充填 钻孔寿命[J]. 科技导报, 2013, 31(34): 34-38. Zhang Qinli, Cheng Jian, Chen Qiusong, et al. Prediction of backfill drill-hole life based on combined model of GA-SVM and neural network[J]. Science & Technology Review, 2013, 31(34): 34-38.
[17] 刘凯, 黄德镛, 张明旭, 等. 大红山铜矿全尾砂絮凝沉降的试验研究[J]. 中国矿业, 2008(12): 60-63. Liu Kai, Huang Deyong, Zhang Mingxu, et al. Experimental study on all tailings flocculation settiling in Dahongshan cooper mine[J].China Mining Magazine, 2008(12): 60-63.
[18] 王星, 瞿圆媛, 胡伟伟, 等. 尾矿浆絮凝沉降影响因素的试验研究[J]. 金属矿山, 2008(5): 149-151 Wang Xing, Qu Yuanyuan, Hu Weiwei, et al. Experiment research on factors influencing tailing pulp flocculation settling[J]. Metal Mine, 2008 (5): 149-151
[19] Zhao Ru, Zhang Zheng, Shi Jiangbo. Characterization of stress corrosion crack growth of 304 stainless steel byelectrochemical noise and scanning Kelvin probe[J]. Journal of Central South University, 2008, 17 (1): 13-18.
[20] 喻寿益, 王吉林, 彭晓波. 基于神经网络的铜闪速熔炼过程工艺参数 预测模型[J]. 中南大学学报: 自然科学版, 2007, 8(3): 153-157. Yu Shouyi, Wang Jilin, Peng Xiaobo. Prediction model of craft parameters based on neural network during the process of copper flash smelting[J]. Journal of Central South University: Science and Technology Edition, 2007, 8(3): 153-157.
文章导航

/