img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2020, Vol. 28 ›› Issue (1): 82-89.doi: 10.11872/j.issn.1005-2518.2020.01.076

• 采选技术与矿山管理 • 上一篇    下一篇

基于粒子群算法优化BP神经网络的溶浸开采浸出率预测

卜斤革(),陈建宏()   

  1. 中南大学资源与安全工程学院,湖南 长沙 410083
  • 收稿日期:2019-06-11 修回日期:2019-09-30 出版日期:2020-02-29 发布日期:2020-02-26
  • 通讯作者: 陈建宏 E-mail:2934134271@qq.com;cjh@263.net
  • 作者简介:卜斤革(1994-),男,安徽芜湖人,硕士研究生,从事矿业经济和采矿系统工程研究工作。2934134271@qq.com
  • 基金资助:
    国家自然科学基金青年基金项目“基于人工智能的矿山技术经济指标动态优化 ”(51404305);国家自然科学基金项目“基于属性驱动的矿体动态建模及更新方法研究”(51504286);中国博士后科学基金面上项目“辰州矿业采掘计划可视化编制与优化研究”(2015M 572269);湖南省科技计划项目“辰州矿业采掘计划可视化编制与优化研究”(2015RS4060)

Based on Particle Swarm Algorithm to Optimize the BP Neural Network of Leaching Rate Prediction in Leaching Mining

Jinge BU(),Jianhong CHEN()   

  1. School of Resources and Safety Engineering,Central South University,Changsha 410083,Hunan,China
  • Received:2019-06-11 Revised:2019-09-30 Online:2020-02-29 Published:2020-02-26
  • Contact: Jianhong CHEN E-mail:2934134271@qq.com;cjh@263.net

摘要:

为了研究溶浸开采过程中浸出率的预测问题,以含锑硫化矿的浸出过程为例,采用经粒子群算法优化的BP神经网络模型预测浸出率。首先分析得出影响矿物浸出率的主要因素,并将已有样本数据进行变量训练,建立BP神经网络预测模型;其次利用粒子群算法优化该模型;最后分别利用BP神经网络模型和PSO-BP神经网络模型预测浸出率,并对比2种模型预测值与实际值的误差精度。研究结果表明:影响含锑硫化矿浸出率的主要因素有温度、时间、液固比、搅拌速度和HCl浓度,且这些因素相互影响,其与浸出率呈现高度非线性关系,采用粒子群算法优化的BP神经网络模型训练精度较高,对浸出率的预测更精确,相比BP神经网络,该模型得出的预测结果与实际值的相对误差以及方差都有明显下降。由此可见,该预测模型对当前矿区溶浸开采的浸出率优化有一定的参考价值。

关键词: 溶浸开采, 浸出率, 变量训练, BP神经网络, 粒子群优化, 误差分析

Abstract:

With the development of mining technology,the development of mineral resources in China is progressing steadily.Nowadays,the mining trend is green mining mode with environmental protection and high safety.However,many mining methods are faced with serious pollution and low recovery rate.Leaching mining is a kind of mining method which combines mining,sorting and hydrometallurgy.In order to explore how to improve the leaching rate during the leaching process,in this paper,the leaching process of antimonial sulfide ore was taken as an example to analysis the main factors that influence the leaching rate.The BP neural network prediction model was established and optimized by the particle swarm algorithm,so it can conduct the variable training with existing sample data.Finally, the BP neural network model, the PSO - BP neural network model were used to predict leaching rate, respectively,and compared to two kinds of model error precision of the predicted values and actual values.The research results show that the impact containing antimony sulfide ore leaching rate of interaction between these factors and nonlinear relationship and leaching rate is more by 40 groups will affect the relationship between parameters and the leaching rate of leaching rate of data through the neural network training model to predict the 8 groups of leaching rate data,compare the leaching rate of output value and the actual values can be found using the particle swarm algorithm to optimize BP neural network model training accuracy is higher,the more accurate predictions for leaching rate,the prediction data set of normalized linear curve slope is more close to 1.Through further error analysis,it can be seen that compared with BP neural network,the relative errors and variances of the predicted results of the model optimized by particle swarm optimization algorithm and the actual values are significantly reduced.Therefore,this prediction model has certain reference value for the optimization of leaching rate in the current leaching mining area.

Key words: leaching mining, leaching rate, variable training, BP neural network, particle swarm optimization, error analysis

中图分类号: 

  • TD87

图1

BP神经网络拓扑基本结构图"

图2

粒子群算法优化神经网络流程"

图3

以浸出率为输出变量的PSO-BP神经网络结构图"

表1

训练组样本数据"

编号温度/℃时间/h固液比/(mL·g-1搅拌速度/(r·min-1HCl浓度/(mol·L-1浸出率/%
185110300448.17
28558300484.73
385310500385.06
485410300383.75
585310300476.75
685110300346.25
785510300112.03
885110500358.32
985410900390.93
1085510300390.50
1185310300251.19
128556300476.00
1385310300110.75
1485210300464.25
1585412300491.08
1685110300236.75
1785210300110.24
1885112300459.07
198516300444.14
2085510900393.75
2185110900374.21
2285110300447.25
2385210900388.00
2485312300487.78
258528300463.65
2685510300493.06
2785512300493.58
2885410300486.25
2985110700363.53
308536300465.57
318556300476.00
3285410300111.01
3385410500389.96
3485510300493.06
3585210500372.67
3685210300466.20
3785510500393.24
3885210700374.61
3985410700391.48
4085510300266.25

表2

预测组样本数据"

编号温度/℃时间/h固液比/(mL·g-1搅拌速度/(r·min-1HCl浓度/(mol·L-1浸出率/%
18548300480.83
285510700393.55
385310300478.06
485210300466.02
585410300383.75
685310300376.75
785310300478.06
885310700385.26

图4

粒子群优化的神经网络浸出率预测组线性回归曲线"

图5

BP神经网络浸出率预测组的线性回归曲线"

表3

BP神经网络和PSO-BP神经网络模型预测结果统计"

序号实际值BP神经网络预测PSO-BP神经网络预测
预测值相对误差预测值相对误差
180.8379.45-0.017180.45-0.0047
293.5592.70-0.009393.21-0.0036
378.0678.210.001978.090.0038
466.0266.920.013666.130.0017
583.7583.05-0.008383.40-0.0042
676.7574.98-0.023175.91-0.0109
778.0678.870.010478.760.0089
885.2685.300.000485.290.0004

表4

BP神经网络、PSO-BP神经网络模型预测结果误差分析"

指标BP神经网络模型PSO-BP神经网络模型
最大相对误差0.02310.0109
最小相对误差0.00040.0004
平均相对误差0.01180.0057
样本方差0.96750.1985
1 田庆华,洪建邦,辛云涛,等.基于人工神经网络模型的含锑硫化矿氧化浸出行为预测[J].中国有色金属学,2018,28(10):2103-2111.
Tian Qinghua,Hong Jianbang,Xin Yuntao,et al.Prediction of oxidation leaching behavior of antimony-containing sulfide ore based on artificial neural network model[J].The Chinese Journal of Nonferrous metals,2018,28(10):2103-2111.
2 马胜利.溶浸采矿最优化问题分析与探讨[J].矿业研究与开发,1998,18(3):12-14.
Ma Shengli.Analysis and discussion on optimization of leaching mining [J].Mining Research and Development,1998,18(3):12-14.
3 马春华,黄治能.溶浸采矿技术研究应用现状综述[J].采矿技术,2013,13(3):42-45.
Ma Chunhua,Huang Zhineng.Review of research and application of leaching mining technology [J].Mining Technology,2013,13(3):42-45.
4 秦毅男,廖晓辉,赵庆治.一种基于粒子群优化算法的神经网络训练方法[J].河南师范大学学报(自然科学版),2007,35(3):167-171.
Qin Yinan,Liao Xiaohui,Zhao Qingzhi.A neural network training method based on particle swarm optimization [J].Journal of Henan Normal University(Nature Science Edition),2007,35(3):167-171.
5 王昌汉.溶浸采铀(矿)[M].北京:原子能出版社,1998:15-28.
Wang Changhan.Leaching Uranium(Ore)[M].Beijing:Atomic Energy Press,1998:15-28.
6 吴爱祥,王洪江,杨保华,等.溶浸采矿技术的进展与展望[J].采矿技术,2006,6(3):39-48.
Wu Aixiang,Wang Hongjiang,Yang Baohua,et al.Development and prospect of leaching mining technology[J]. Mining Technology,2006,6(3):39-48.
7 毛健,赵红东,姚婧婧.人工神经网络的发展及应用[J].电子设计工程,2011,19(24):62-65.
Mao Jian,Zhao Hongdong,Yao Jingjing.Application and prospect of artificial neural network[J].Electronic Design Engineering,2011,19(24):62-65.
8 韩立群.人工神经网络[M].北京:北京邮电大学出版社,2006.
Han Liqun.Artificial Neural Network[M].Beijing:Beijing University of Posts and Telecommunications Press,2006.
9 Ren C,An N,Wang J Z,et al.Optimal parameters selection for BP neural network based on particle swarm optimization:A case study of wind speed forecasting[J].Knowledge-Based Systems,2014,56(3):226-239.
10 彭时霖.基于人工神经网络的空调房间热环境参数的优化组合[D].长沙:湖南大学,2006.
Peng Shilin.Combination of Thermal Environment Parameters of Air-Conditioned Rooms Based on Artificial Neural Network [D].Changsha:Hunan University,2006.
11 焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社,1990.
Jiao Licheng.Neural Network System Theory[M].Xi’an:Xi’an University of Electronic Science and Technology Press,1990.
12 刘浪,陈建宏,杨珊,等.基于灰色关联分析的PSO-BP算法预测矿震危险性[J].中南大学学报(自然科学版),2011,42(8):2400-2405.
Liu Lang,Chen Jianhong,Yang Shan,et al.Prediction of PSO-BP algorithm in risk prediction of mine earthquake based on grey correlation analysis[J].Journal of Central South University(Science and Technology),2011,42 (8):2400-2405.
13 陈建宏,周汉凌,于凤玲.基于改进的QPSO-BP算法的铀价格预测模型及应用[J].计算机工程与应用,2013,49(21):235-239.
Chen Jianhong,Zhou Hanling,Yu Fengling.Uranium price forecasting model based on BP improved by QPSO and its application[J].Computer Engineering and Application,2013,49(21):235-239.
14 朱晴,王晶晶.基于粒子群优化BP神经网络的高校科研管理评估研究[J].现代电子技术,2019,42(7):87-94.
Zhu Qing,Wang Jingjing.Research on university scientific research management evaluation based on particle swarm optimization algorithm and BP neural network[J].Modern Electronics Technique,2019,42(7):87-94.
15 张磊.基于粒子群神经网络的软岩巷道变形预测[J].内蒙古煤炭经济,2014(8):182-184.
Zhang Lei.Prediction of soft rock roadway deformation based on particle swarm optimization neural network [J].Inner Mongolia Coal Economy,2014(8):182-184.
16 许敏.基于PSO算法的BP神经网络在边坡稳定性评价中的应用[J].温州职业技术学院学报,2009,9(2):45-51.
Xu Min.Application of BP neural network in slope stability evaluation on the basis of PSO algorithm[J].Journal of Wenzhou Vocational and Technical College,2009,9(2):45-51.
17 赵振江.基于PSO-BP神经网络的网络流量预测与研究[J].计算机应用与软件,2009,26(1):218-221.
Zhao Zhenjiang.Prediction and research on network traffic based on PSO-BP neural network[J].Computer Applications and Software,2009,26(1):218-221.
18 袁子清.矿震地震活动响应规律及其危险性预测研究[D].长沙:中南大学,2007.
Yuan Ziqing.Research on Seismic Aactivity Response Law and Hazard Prediction of Mine Earthquakes[D].Changsha:Central South University,2007.
19 Kim H J,Jang B S,Park C K,et al.Fatigue analysis of floating wind turbine support structure applying modified stress transfer function by artificial neural network[J].Ocean Engineering,2018,149:113-126.
20 王维,李洪儒.BP神经网络在状态监测数据趋势预测中的应用[J].微计算机信息,2005(21):141-143.
Wang Wei,Li Hongru.Application of BP ANN in predicting condition monitoring data[J].Microcomputer Information,2005(21):141-143.
21 闻新.MATLAB 神经网络应用设计[M].北京:科学出版社,2001:278-283.
Wen Xin.Neural Network Simulation and Application Based on MATLAB[M].Beijing:Science Press,2003:278-283.
[1] 李任豪,顾合龙,李夕兵,侯奎奎,朱明德,王玺. 基于PSO-RBF神经网络模型的岩爆倾向性预测[J]. 黄金科学技术, 2020, 28(1): 134-141.
[2] 梁昌金, 马传净. 碘—氨浸出体系用于废旧印刷线路板中金的浸取[J]. 黄金科学技术, 2019, 27(5): 784-790.
[3] 肖文丰,陈建宏,陈毅,王喜梅. 基于神经网络与遗传算法的多目标充填料浆配比优化[J]. 黄金科学技术, 2019, 27(4): 581-588.
[4] 随晓丹,罗周全,秦亚光,王玉乐,彭东. 基于小波分解的尾矿坝浸润线预测方法研究[J]. 黄金科学技术, 2019, 27(1): 137-143.
[5] 杨玮,王刚,曹欢,张凯. 含铜金精矿焙烧—酸浸对金、银浸出率的影响[J]. 黄金科学技术, 2017, 25(5): 122-126.
[6] 王硕. 甘肃某金矿浸金工艺试验研究[J]. 黄金科学技术, 2017, 25(4): 122-127.
[7] 邓高,杨珊. 基于组合预测与变精度粗糙模糊集的采空区稳定性评价[J]. 黄金科学技术, 2017, 25(3): 98-107.
[8] 毕林,赵辉,杨新锋 . DIMINE填挖方量计算原理与方法研究[J]. 黄金科学技术, 2017, 25(3): 108-115.
[9] 杨俊彦,国洪柱,陈萍,徐忠敏. 常压富氧浸出在黄金氰化生产中的应用[J]. 黄金科学技术, 2016, 24(4): 160-163.
[10] 史秀志,范玉乾,尚雪义. 基于PCA-BP神经网络模型的充填体强度预测[J]. 黄金科学技术, 2016, 24(3): 64-69.
[11] 过江,张碧肖. 基于PCA与BP神经网络的充填管道失效风险评估[J]. 黄金科学技术, 2015, 23(5): 66-71.
[12] 陈建宏,朱鼎耀,陈轶俊,叶阿明,邱文. 基于PCA-BP神经网络的尾矿库坝体稳定性分析[J]. 黄金科学技术, 2015, 23(5): 47-52.
[13] 张玲玲,李国清*,姜光成,李威,胡乃联. 基于BP神经网络的地质缺失数据处理方法[J]. 黄金科学技术, 2015, 23(5): 53-59.
[14] 王帅,李超,李宏煦. 难浸金矿预处理技术及其研究进展[J]. 黄金科学技术, 2014, 22(4): 129-134.
[15] 高伟伟,刘金强,李蕊蕊,张仁高,邓洪瑞,王善健,林鑫. 气力搅拌浸出槽在黄金选厂的应用[J]. 黄金科学技术, 2014, 22(3): 86-89.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 李洪杰, 戚静洁, 马树江. 胶西北地区金矿床构造控矿规律[J]. J4, 2010, 18(4): 41 -46 .
[2] 杨晓鸿. 贡果亚陇地区金锑矿成矿前景及其找矿意义[J]. J4, 2010, 18(6): 38 -41 .
[3] 于清军, 于清源, 路仁江, 孙建, 黄山, 刘吉兴. 浅孔留矿与中深孔爆破联合回采复杂矿体技术研究[J]. J4, 2011, 19(1): 49 -50 .
[4] 张渊, 张洪喜. 山东黄埠岭金矿7号脉地质特征及控矿机理研究[J]. J4, 2010, 18(4): 12 -16 .
[5] 梁超, 祝延修. 安徽省南部金、多金属成矿地质特征及找矿方向[J]. J4, 2011, 19(1): 21 -27 .
[6] 张志国,胡军海 ,刘涛. 大兴安岭中段旁开门金银矿地质特征及找矿标志[J]. J4, 2008, 16(1): 43 -47 .
[7] 胡琴霞, 李建忠, 喻光明, 谢艳芳, 张圣潇. 白龙江成矿带金矿点初探[J]. J4, 2010, 18(3): 51 -53 .
[8] 刘洪君, 刘喜友. 额尔古纳——呼伦深断裂带的形成发展及其对矿产的控制作用[J]. J4, 2007, 15(1): 10 -13 .
[9] 张印飞. 陕西双王金矿床八号矿体矿化规律探讨[J]. J4, 2008, 16(1): 35 -38 .
[10] 刘洪君, 刘喜友. 李家峪矿区侵入体的生成时代及与成矿关系问题的探讨[J]. J4, 2007, 15(1): 31 -34 .