img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2022, Vol. 30 ›› Issue (6): 958-967.doi: 10.11872/j.issn.1005-2518.2022.06.081

• 采选技术与矿山管理 • 上一篇    

基于PCA-RBF网络模型的硫化矿自燃安全性研究

杨珊(),李文文(),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:2022-06-21 修回日期:2022-09-04 出版日期:2022-12-31 发布日期:2023-01-06
  • 通讯作者: 李文文 E-mail:yangshan@csu.edu.cn;liwen_study@163.com
  • 作者简介:杨珊(1983-),男,湖北监利人,副教授,从事矿业经济与采矿系统工程研究工作。yangshan@csu.edu.cn
  • 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)

Study on Spontaneous Combustion Safety of Sulfide Ore Based on PCA-RBF Network Model

Shan YANG(),Wenwen LI(),Jianhong CHEN   

  1. School of Resources and Safety Engineering,Central South University,Changsha 410083,Hunan,China
  • Received:2022-06-21 Revised:2022-09-04 Online:2022-12-31 Published:2023-01-06
  • Contact: Wenwen LI E-mail:yangshan@csu.edu.cn;liwen_study@163.com

摘要:

为了更加准确地预测硫化矿自燃安全性,综合考虑硫化矿自燃倾向性及火灾后果严重性,将硫化矿自燃安全性划分为9个等级,并选取矿山含硫量、矿山含碳量、矿石温度、矿石堆放时间、采场人员数量、氧气浓度和采场矿层厚度作为评价因素集。利用主成分分析法(Principal Component Analysis,PCA)对94个采场样本数据进行降维处理,得到包含70%以上原始信息的3个主成分。将降维后的84组数据作为基于径向基函数神经网络(Radial Basis Function Neural Network,RBF)预测模型的训练样本,10组数据作为检验样本进行硫化矿自燃安全性预测。最后分别利用十折交叉验证法和留一法对94组检验样本的自燃安全性预测结果进行检验,得到硫化矿自燃安全性预测准确率分别为92.55%和91.49%。研究结果表明:PCA-RBF网络模型对硫化矿自燃安全性的预测性能良好,且优于未经主成分分析的结果。

关键词: 硫化矿, 自燃倾向性, 火灾后果, 主成分分析, RBF神经网络, 等级预测

Abstract:

Spontaneous combustion of sulfide ore will cause a series of environmental,safety,and property hazards.It is of great practical significance to predict the tendency of spontaneous combustion of sulfide ore and the severity of fire consequences more accurately for the realization of more safe and efficient mining of sulfide ore.In this paper,seven factors affecting the spontaneous combustion tendency of sulfide ore were compre-hensively considered as the evaluation index factors,including mine sulfur content,mine carbon content,ore temperature,ore stacking time,the number of stope personnel,oxygen concentration,and stope ore layer thickness.The spontaneous combustion safety of sulfide ore was divided into nine grades,representing different spontaneous combustion tendencies and severity of fire consequences.94 sets of actual stope data were collected,and the principal component analysis (PCA) was used to reduce the dimension of the 94 sets of stope data.Three principal components containing more than 70% of the original information were obtained.84 sets of data after dimension reduction were used as training samples of the radial basis function neural network (RBF) prediction model,and 10 groups of test samples were used to establish the PCA-RBF self-ignition prediction model of sulfide ore.The 10-fold cross-validation method and leave one-out method were used to verify the prediction results of the PCA-RBF model with the actual results.The prediction accuracy of the PCA-RBF model is 92.55%,and the correlation coefficient is 0.94.The prediction accuracy of the PCA-RBF model is 91.49%,and the correlation coefficient is 0.97.Both of the two verification methods show that the PCA-RBF model has good applicability to the prediction of spontaneous combustion safety of sulfide ores.The results of a small amount of prediction deviation are also less different from the actual results,and the overall prediction accuracy is higher than that of the RBF model.The results show that the radial basis function neural network based on principal component analysis has good prediction performance for the spontaneous combustion safety of sulfide ore.The prediction accuracy of the sample is above 90%,and the correlation coefficient is greater than 0.9,which is better than the results without principal component analysis.PCA-RBF model can be used to pre-dict the grade of spontaneous combustion safety of sulfide ore,which can guide the safety production of mine.

Key words: sulfide ore, spontaneous combustion tendency, fire result, principal component analysis, radial basis function neural network(RBF), grade prediction

中图分类号: 

  • X936

图1

硫化矿自燃安全性评价指标"

表1

硫化矿自燃倾向性指标分级"

评价指标硫化矿自燃倾向性分级
自燃严重氧化轻微氧化
矿山含硫量/%[32.36,42.31][22.42,32.36)[12.47,22.42)
矿山含碳量/%[12.06,15.63][8.49,12.06)[4.92,8.49)
矿堆温度/℃[25.4,37.4][13.4,24.4)[1.4,13.4)
矿石堆放时间/d[45,57][34,45)[22,34)

表2

火灾后果严重性指标分级"

评价指标火灾后果严重性分级
严重一般严重不严重
采场人员数量/人[10,15][5,10)[0,5)
氧气浓度/%[20,21][19,20)[18,19)
矿层厚度/m[7,9][5,7)[3,5)

图2

RBF神经网络模型"

图 3

硫化矿自燃安全性预测模型流程"

表3

采场内矿石自燃安全性统计结果"

采场编号

矿山含硫量

/%

矿山含碳量

/%

矿石温度

/℃

矿石堆放时间/h采场人员数量/人

矿层厚度

/m

氧气浓度

/%

自燃倾向性火灾严重性
141.213.328.56273.419.2自燃一般严重
231.97.725.282146.118.6自燃一般严重
322.412.828.857113.120.1自燃严重
422.43.822.84747.618.9轻微氧化不严重
523.32.327.93946.520.9严重氧化不严重
643.411.927.25594.519.7自燃一般严重
735.14.422.85978.119.3严重氧化不严重
831.46.126.56486.818.8自燃一般严重
928.24.323.72738.918.3轻微氧化不严重
1022.711.927.361134.720.5自燃严重
1122.47.822.847116.618.3轻微氧化一般严重
1234.67.922.267123.719.5轻微氧化严重
1332.412.321.83764.219.2严重氧化一般严重
1421.94.722.43947.318.5轻微氧化不严重
1535.74.921.55887.419.1严重氧化不严重
1638.55.726.87965.918.2自燃一般严重
1731.38.723.663143.919.8轻微氧化严重
1828.84.128.24335.220.3严重氧化不严重
1928.89.123.43395.218.4严重氧化一般严重
2022.412.327.266124.320.7自燃严重
2137.38.324.557125.818.4自燃一般严重
2228.33.327.64255.120.1严重氧化不严重
2337.113.422.57963.719.5自燃一般严重
2434.39.226.69276.118.1自燃一般严重
2533.93.822.26998.619.8严重氧化不严重
??????????
5746.011.128.77174.919.5自燃一般严重
5821.33.122.85657.818.1轻微氧化不严重
5937.24.723.56668.719.6严重氧化不严重
6032.86.223.761114.919.7轻微氧化严重
??????????
9031.98.019.54953.718.7严重氧化一般严重
9132.76.524.72833.119.3严重氧化不严重
9228.45.136.94464.518.5严重氧化一般严重
9339.113.435.25184.719.6自燃一般严重
9439.114.735.25375.319.3自燃严重

表4

主成分方差贡献率及其特征值"

主成分特征值贡献率/%累计贡献率/%
pc12.41934.55334.553
pc21.42020.28154.834
pc31.12120.01174.845

表5

主成分提取后输入因子数据"

采场编号pc1pc2pc3自燃安全性采场编号pc1pc2pc3自燃安全性
181.354340.862622.527721955.550519.553213.45155
281.897157.97519.630322075.760339.07446.05221
372.781831.17108.166512171.888941.136215.85172
449.796626.950910.563992254.818722.071215.39046
549.028317.758812.757662384.080854.169016.75032
677.833938.144422.439822485.404463.087015.50652
763.401441.437615.978562567.712649.334412.84586
868.514542.059414.46712?????
942.215714.388816.989695785.019749.699224.81842
1073.467336.12606.116215853.037734.04158.93449
1157.818029.18516.953185967.333146.705317.63236
1275.874147.200411.887476070.042641.572212.19397
1360.438322.411216.46095?????
1446.480121.109010.868899060.718532.059214.81955
1564.075541.682515.403869151.760113.392419.67406
1677.948154.734719.448729262.025220.103719.28685
1774.900343.04239.388979378.131929.647924.01322
1855.326121.854517.049669479.022931.044124.72501

表6

PCA-RBF与RBF模型预测结果对比"

采场编号期望自燃安全性PCA-RBFRBF
3112*
6222
1187*8
16223*
22666
46444
58997*
72222
84555
91666

表7

交叉验证结果对比"

验证方法模型误判样本总数/个平均准确率/%
十折交叉验证PCA-RBF模型792.55
RBF模型1089.36
留一法验证PCA-RBF模型891.49
RBF模型1287.23

图4

十折验证法结果对比"

图5

留一法验证结果对比"

Cai Yilun, Yang Fuqiang, Liu Xiaoxia,2019.Early warning of spontaneous combustion of sulfide ore and its application based on RBF neural network[J].Nonferrous Metals Engineering,9(7):72-78.
Gao Feng, Xiao Ronglan,2016.Fuzzy evaluation on spontaneous combustion tendency of sulfide ores based on comprehensive weights[J].Mining Research and Development,36(11):28-31.
Gu H, Song B F,2009.Study on effectiveness evaluation of weapon systems based on grey relational analysis and TOPSIS[J].Journal of Systems Engineering and Electronics,20(1):106-111.
Han Chaoqun, Chen Jianhong, Zhou Zhiyong,et al,2019.Research on prediction of rock mass blastability classification based on PCA-SVM Model[J].Gold Science and Technology,27(6):879-887.
Han Ziqing, Li Zijun, Xu Yuanyuan,2022.Evaluation of spontaneous combustion tendency of sulfide ore based on partial ordered set[J].Gold Science and Technology,30(1):105-112.
Huang Yuejun,2000.Study on the spontaneous combustion of high temperature sulphride ores and its control technology[J].Non-Ferrous Mining and Metallurgy,(1):13-15.
Li Yameng, Ding Junhang, Sun Baonan,et al,2022.Comparison of short-term prediction effects of the sea surface temperature and salinity based on BP and RBF neural network[J].Advances in Marine Science,40(2):220-232.
Li Zijun,2007.Investigation on the Mechanism of Spontaneous Combustion of Culphide Ores and the Key Technologies for Preventing Fire[D].Changsha:Central South University.
Li Zijun, Gu Desheng, Wu Chao,2004.Dangerousness assessment of ore spontaneous combustion in high temperature high sulfur deposits[J].Metal Mine,33(5):57-59,64.
Li Zijun, Wang Fasong, Ma Shubao,2009.Safety assessment of the spontaneous combustion tendency of sulfide ores based on AHP and SPA[J].Science & Technology Review,27(19):69-73.
Luo Kai, Wu Chao, Yang Fuqiang,et al,2014a.Bayes discriminant analysis of spontaneous combustion tendency classification of sulfide minerals in metal mines[J].Journal of Central South University (Science and Technology),45(7):2244-2249.
Luo Kai, Wu Chao, Yang Fuqiang,2014b.Management res-ponse system to ores spontaneous combustion based on dominance—Based rough sets and grey target[J].Journal of Central South University (Science and Technology),45(1):223-230.
Mao Dan, Chen Yuanjiang,2008.Characteristic overview and analysis of spontaneous combustion of sulfide ores[J].Industrial Minerals and Processing,(1):34-38.
Navarra A, Graham J T, Somot S,et al,2010.Mössbauer quantification of pyrrhotite in relation to self-heating[J].Minerals Engineering,23:652-658.
Pan W, Wu C, Li Z J,et al,2017.Evaluation of spontaneous combustion tendency of sulfide ore heap based on nonlinear parameters[J].Journal of Central South University,24(10):2431-2437.
Shao Liangshan, Ma Han, Wen Tingxin,2014.Coal spontaneous combustion prediction model of support vector machine combined with factor analysis[J].Journal of Liaoning Technical University (Natural Science),33(4):433-436.
Wang Jianbo, Peng Longbiao, Li Na,et al,2017.Fire risk evaluation of subway station based on PCA-RBF neural network[J].Industrial Safety and Environmental Protection,43(9):67-70.
Xie Zhengwen, Wu Chao, Li Zijun,et al,2012.Evaluation on spontaneous combustion tendency of sulfide ores based on entropy and set pair analysis theory[J].Journal of Central South University (Science and Technology),43(5):1858-1863.
Xu Chunming, Wu Chao, Chen Yuanjiang,2008.Grey system approach in application to the prediction of spontaneous combustion of sulfide ore residue[J].Journal of Safety and Environment,(4):125-127.
Yang Fuqiang,2011.Study on the Mechanism and Forecasting Technologies for Spontaneous Combustion of Sulfide Minerals in Metal Mines[D].Changsha:Central South University.
Yang Fuqiang, Chen Bohui,2012.Application of attribute interval recognition model to comprehensive assessment of spontaneous combustion tendency of sulfide ores[J].China Safety Science Journal,22(1):70-75.
Yang Fuqiang, Liu Guangning, Guo Lele,2015.GA-BP neural network model and its application to spontaneous combustion tendency classification of sulfide ores[J].Journal of Natural Disasters,24(4):227-232.
Yang Shan, Yuan Mingke, Su Kaijun,et al,2022.Analysis of internal-caused fire in the stopes based on chain variable precision rough fuzzy set[J].Gold Science and Technology,30(1):93-104.
Zhang Lining, Fan Liangqiong, An Jing,et al,2021.Fire safety assessment of college dormitory based on PCA-RBF[J].Journal of Safety and Environment,21(3):921-926.
Zhang Yue, Liu Jie, Fu Yu,et al,2021.Research on prediction of spontaneous combustion tendency of sulfide ores based on game theory and set pair analysis[J].Nonferrous Metals(Mining Section),73(3):141-146.
蔡逸伦,阳富强,刘晓霞,2019.硫化矿石自燃灾害预警的RBF神经网络模型及应用[J].有色金属工程,9(7):72-78.
高峰,肖蓉兰,2016.基于综合权重的硫化矿石自燃倾向性评价研究[J].矿业研究与开发,36(11):28-31.
韩超群,陈建宏,周智勇,等,2019.基于主成分分析—支持向量机模型的矿岩可爆性等级预测研究[J].黄金科学技术,27(6):879-887.
韩梓晴,李孜军,徐圆圆,2022.基于偏序集的硫化矿石自燃倾向性评价[J].黄金科学技术,30(1):105-112.
黄跃军,2000.高温高硫矿床矿石自燃性及防治技术研究[J].有色矿冶,(1):13-15.
李亚蒙,丁军航,孙宝楠,等,2022.BP和RBF神经网络应用于海表温盐短期预测效果对比[J].海洋科学进展,40(2):220-232.
李孜军,2007.硫化矿石自燃机理及其预防关键技术研究[D].长沙:中南大学.
李孜军,古德生,吴超,2004.高温高硫矿床矿石自燃危险性的评价[J].金属矿山,33(5):57-59,64.
李孜军,汪发松,马树宝,2009.基于层次分析法和集对理论的硫化矿自燃倾向性评定[J].科技导报,27(19):69-73.
罗凯,吴超,阳富强,等,2014a.矿山硫化矿自燃倾向性分级的Bayes判别法及应用[J].中南大学学报(自然科学版),45(7):2244-2249.
罗凯,吴超,阳富强,2014b.基于优势关系粗糙集与灰靶决策的矿石自燃管理应对体系[J].中南大学学报(自然科学版),45(1):223-230.
毛丹,陈沅江,2008.硫化矿石堆氧化自燃全过程特征综述与分析[J].化工矿物与加工,(1):34-38.
邵良杉,马寒,温廷新,2014.因子分析与支持向量机相结合的煤炭自燃预测[J].辽宁工程技术大学学报(自然科学版),33(4):433-436.
王建波,彭龙镖,李娜,等,2017.基于PCA-RBF神经网络的地铁车站火灾风险评估[J].工业安全与环保,43(9):67-70.
谢正文,吴超,李孜军,等,2012.基于信息熵和集对分析理论的硫化矿石自燃倾向性判定[J].中南大学学报(自然科学版),43(5):1858-1863.
许春明,吴超,陈沅江,2008.硫化矿石堆自燃的灰色预测研究[J].安全与环境学报,(4):125-127.
阳富强,2011.金属矿山硫化矿自然发火机理及其预测预报技术研究[D].长沙:中南大学.
阳富强,陈伯辉,2012.硫化矿石自燃倾向性评价的属性区间识别模型[J].中国安全科学学报,22(1):70-75.
阳富强,刘广宁,郭乐乐,2015.硫化矿石自燃倾向性等级划分的GA-BP神经网络模型及应用[J].自然灾害学报,24(4):227-232.
杨珊,袁鸣珂,苏凯俊,等,2022.基于链式变精度粗糙模糊集采场内因火灾分析[J].黄金科学技术,30(1):93-104.
张立宁,范良琼,安晶,等,2021.基于PCA-RBF的高校学生宿舍火灾安全评价及应用[J].安全与环境学报,21(3):921-926.
张悦,刘杰,傅钰,等,2021.基于博弈论集对分析的硫化矿石自燃倾向预测方法研究[J].有色金属(矿山部分),73(3):141-146.
[1] 温廷新,苏焕博. 基于MICE_RF的组合赋权—极限随机树岩爆预测模型[J]. 黄金科学技术, 2022, 30(3): 392-403.
[2] 谢饶青, 陈建宏, 肖文丰. 基于NPCA-GA-BP神经网络的采场稳定性预测方法[J]. 黄金科学技术, 2022, 30(2): 272-281.
[3] 韩梓晴,李孜军,徐圆圆. 基于偏序集的硫化矿石自燃倾向性评价[J]. 黄金科学技术, 2022, 30(1): 105-112.
[4] 高峰,吴晓东,周科平. 基于主成分分析和PSO-ELM算法的排土场稳定性预测模型[J]. 黄金科学技术, 2021, 29(5): 658-668.
[5] 骆正山,黄仁惠,申国臣. 基于KPCA-IPSO-LSSVM的充填管道磨损风险预测[J]. 黄金科学技术, 2021, 29(2): 245-255.
[6] 宋翔宇,张振,王君玉,李荣改. 含金硫化矿碱性氧化提金研究现状与展望[J]. 黄金科学技术, 2020, 28(6): 940-954.
[7] 许瑞, 侯奎奎, 王玺, 刘兴全, 李夕兵. 基于核主成分分析与SVM的岩爆烈度组合预测模型[J]. 黄金科学技术, 2020, 28(4): 575-584.
[8] 傅开彬,王维清,赵涛涛,龙美樵,侯普尧,杜明霞. 缅甸实皆省某金矿工艺矿物学研究[J]. 黄金科学技术, 2020, 28(2): 278-284.
[9] 陈超民,冷成彪,司国辉. 基于GIS与层次分析法的综合成矿预测——以新疆库米什地区为例[J]. 黄金科学技术, 2020, 28(2): 213-227.
[10] 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.
[11] 韩超群,陈建宏,周智勇,杨珊. 基于主成分分析—支持向量机模型的矿岩可爆性等级预测研究[J]. 黄金科学技术, 2019, 27(6): 879-887.
[12] 周贺鹏, 胡洁, 段朝阳, 邓攀, 钟志刚, 张永兵. 甘肃洛坝铅锌矿选矿流程考察与优化[J]. 黄金科学技术, 2019, 27(5): 696-703.
[13] 李科明,刘志祥,兰明. 滨海金矿涌水危险评价及涌水量混沌预测研究[J]. 黄金科学技术, 2019, 27(4): 539-547.
[14] 崔宇,李夕兵,董陇军,白吕. 玲珑金矿微震监测台网布设优化[J]. 黄金科学技术, 2019, 27(3): 417-424.
[15] 段学良,马凤山,赵海军,郭捷,顾鸿宇,刘帅奇. 滨海矿山矿坑涌水源识别与混合比研究[J]. 黄金科学技术, 2019, 27(3): 406-416.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!