img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2024, Vol. 32 ›› Issue (1): 75-81.doi: 10.11872/j.issn.1005-2518.2024.01.108

• 采选技术与矿山管理 • 上一篇    下一篇

基于曲线拟合和神经网络的独头巷道CO浓度预测研究

周昌微(),谢贤平(),都喜东   

  1. 昆明理工大学国土资源工程学院,云南 昆明 650000
  • 收稿日期:2023-07-31 修回日期:2023-11-07 出版日期:2024-02-29 发布日期:2024-03-22
  • 通讯作者: 谢贤平 E-mail:1655460339@qq.com;xxping@kmust.edu.cn
  • 作者简介:周昌微(1997-),男,陕西安康人,硕士研究生,从事矿井通风和安全工程研究工作。1655460339@qq.com
  • 基金资助:
    云南省基础研究计划项目“堆浸体系中氧化铜矿散体孔裂隙双重介质演化及渗流响应机制研究”(202101BE070001-039);云南省教育厅科学研究基金项目“深部含水页岩储层CO2地质封存机制及其吸附特性响应规律研究”(2022J0055)

Research on the Prediction of CO Concentration in Single-head Roadway Based on Curve Fitting and Neural Network

Changwei ZHOU(),Xianping XIE(),Xidong DU   

  1. Faculty of Land Resources Engineering,Kunming University of Science and Technology,Kunming 650000,Yunnan,China
  • Received:2023-07-31 Revised:2023-11-07 Online:2024-02-29 Published:2024-03-22
  • Contact: Xianping XIE E-mail:1655460339@qq.com;xxping@kmust.edu.cn

摘要:

为了准确预测矿山独头巷道CO浓度,基于云南老厂锡矿1800运输巷甩车场独头巷道掘进工作面CO浓度监测数据,运用MATLAB曲线拟合工具箱对该独头巷道中CO浓度随时间的变化情况进行曲线拟合,建立了该矿山独头巷道中CO浓度随时间变化的数学模型。通过该模型得到该独头巷道中CO浓度值达到安全规程要求所需的时间。然后,运用卷积神经网络时间序列预测模型(CNN模型)和BP神经网络时间序列预测模型(BP模型)对独头巷道CO浓度进行预测,并比较评价指标R2RMSE。结果表明:BP神经网络时间序列预测模型对该独头巷道CO浓度的预测效果更好,为该矿山独头巷道CO浓度值的监测和控制提供了准确可靠的理论依据。

关键词: 独头巷道, MATLAB, 曲线拟合, 卷积神经网络, BP神经网络, 时间序列预测

Abstract:

In order to realize the prediction of CO concentration in the single-head roadway of the mine,based on the monitoring data of CO concentration in the heading face of the single-head roadway in the 1800 transport lane of Laochang tin mine in Yunnan Province.Firstly,the MATLAB curve fitting toolbox was used to fit the curve of the change of CO concentration with time in the single-head roadway,and the mathematical model of the change of CO concentration with time in the single-head roadway of the mine was established.Through the model,the time required for the CO concentration value in the single-head roadway of the mine to reach the CO concentration value required by the safety regulations was obtained.Then,the convolutional neural network time series prediction model(CNN model) and the BP neural network time series prediction model(BP model) were used to predict the CO concentration,and the two evaluation indexes of R2 and RMSE were compared.The results show that the BP neural network time series prediction model has the better prediction effect on the CO concentration of the single-head roadway,which provides an accurate and reliable theoretical basis for the monitoring and control of the CO concentration value of the single-head roadway in the mine.

Key words: single-head roadway, MATLAB, curve fitting, convolutional neural network, BP neural network, time series prediction

中图分类号: 

  • TD711.41

图1

独头巷道内某监测点CO浓度时间序列图"

表1

某监测点的CO浓度随时间的变化"

时间/sCO浓度/(×10-6时间/sCO浓度/(×10-6时间/sCO浓度/(×10-6时间/sCO浓度/(×10-6时间/sCO浓度/(×10-6
09047401921 4801352 220922 96039
208867601951 5001352 240902 98037
408777802031 5201352 260923 00039
608848002051 5401352 280913 02039
808888202111 5601352 300903 04038
1007438401931 5801332 320903 06040
1207418601971 6001272 340923 08037
1407308801951 6201262 360863 10038
1607399001961 6401262 380833 12038
1807439201961 6601262 400843 14040
2007209401961 6801262 420843 16040
2205359601841 7001252 440823 18039
2405169801801 7201212 460843 20039
2605011 0001791 7401202 480783 22041
2804891 0201781 7601192 500763 24043
3004711 0401791 7801202 520753 26042
3204621 0601781 8001182 540763 28043
3402831 0801791 8201182 560753 30042
3602791 1001631 8401182 580753 32043
3802631 1201631 8601142 600753 34045
4002691 1401641 8801142 620683 36048
4202701 1601641 9001132 640683 38047
4402741 1801641 9201122 660673 40046
4601881 2001641 9401122 680693 42048
4801771 2201511 9601112 700683 44049
5001941 2401511 9801062 720673 46049
5202001 2601512 0001072 740563 48051
5402151 2801512 0201062 760533 50052
5602231 3001522 0401062 780523 52053
5802331 3201522 0601072 800563 54052
6001741 3401432 0801072 820503 56051
6201871 3601432 1001052 840483 58053
6401911 3801432 1201042 860423 60038
6602041 4001432 1401022 88038
6802101 4201432 1601012 90036
7002201 4401432 1801012 92037
7201841 4601372 2001002 94038

图2

神经网络原理示意图"

图3

BP神经网络结构"

图4

CNN神经网络模型预测结果"

图5

BP神经网络模型预测结果"

表2

各预测模型的R2和RMSE"

模型类型R2RMSE
CNN神经网络模型0.90564.4643
BP神经网络模型0.95792.9821
Adedipupo O O, Ayodele A A, Abideen L T,et al,2022.Detection of appropriate model for nigeria population growth using Root Mean Square Error (RMSE)[J].International Journal of Systems Science and Applied Mathematics,7(3):46-51.
Cao Y, Ji H, Zhang Y,et al,2018.Study on distribution of CO and concentration prediction in blind gallery after blasting operation[J].Archives of Mining Sciences,63(2):283-300.
Chen Chao, Nie Hexiang, Li Qiong,et al,2022.Prediction model of CO pollutant concentration distribution characteristics in urban underground roads based on traffic wind conditions[J].China Journal of Highway,35 (5):161-169.
Gao Qiuying, Wang Lili, Wang Rongzhong,2021.Research on least squares curve fitting and optimization algorithm[J].Industrial Control Computer,34 (11):100-101.
Ji Hongguang, Cao Yang, Zhang Ge,et al,2014.Prediction of smoke exhaust time during excavation of single-head roadway[J].Metal Mine,43(5):142-145.
Gong Xiaoyan, Sun Yuheng, Liu Zhuangzhuang,et al,2023.Study on airflow intelligent control model of fully mechanized heading face based on BP neuralnet work[J].Safety and Environmental Engineering,30(30):138-145.
Jiang Feng, Han Xingyu, Wang Hui,2023.Prediction of PM2.5 concentration in Yangtze River Economic Belt based on graph neural network[J].Environmental Science and Te-chnology,46(11):90-101.
Li Peng, Duan Shuqing, Wang Kun,et al,2014.Grey model and curve fitting settlement prediction and correlation analysis[J].Journal of Underground Space and Engineering,10 (1):109-115.
Yanhong Lü, Wang Qin,2013.Research on tunnel CO concentration prediction based on neural network information fusion[J].Information Technology,37 (9):128-131.
Piepho H P,2019.An adjusted coefficient of determination (R2) for generalized linear mixed models in one go[J].Biometrical Journal,61(4):860-872.
Shi Xiuzhi, Fan Yuqian, Shang Xueyi,2016.Filling strength prediction based on PCA-BP neural network model[J].Gold Science and Technology,24(3):64-69.
Wang Shibin, Chen Rihui, Liu Shitao,et al,2014.Analysis and prediction of CO concentration change after blasting in heading face [J].Science and Technology and Engineering,14 (6):101-103,107.
Wu F, Shi S, Lu Y,et al,2023.Analysis of CO source and prediction model of gushing concentration at the return air corner of working face in shallow coal seam mine[J].Combustion Science and Technology:1-16.
Wu Min, Pan Chunrong,2023.Application of one-dimensional convolutional neural network in magnetite separation[J / OL].Nonferrous Metals(Mineral Processing Section): 1-6[2023-07-28 ].
Wu Y, Zhang Y, Zhou C,et al,2021.Study of CO sources and early-warning concentration of spontaneous combustion at air return corner in fully mechanized mining faces[J].Combustion Science and Technology,193(9):1587-1604.
Xie Raoqing, Chen Jianhong, Xiao Wenfeng,2022.Prediction method of stope stability based on NPCA-GA-BP neural network[J].Gold Science and Technology,30(2):272-281.
Yang Tingting, Gao Qian, Li Haoqian,et al,2022.Fault warning of coal mill based on convolutional neural network-long short-term memory neural network[J].Thermal Power Generation,51(10):122-129.
Zeng Junhui, Li Xibing,2019.Prediction of mine subsidence area based on chaotic time series analysis method [J].Gold Science and Technology,27 (2):249-256.
Zhai Xiaowei, Ma Lingjun, Deng Jun,2011.Research and application of CO concentration prediction model in upper corner of working face[J].Coal Science and Technology,39 (11):59-62.
Zhang Ge, Cao Yang, Ji Hongguang,et al,2014.Model test study on the emission law and concentration prediction of gun smoke in single-head roadway[J].Modern Tunnel Te-chnology,51(4):150-154.
Zhang Zhigang, Xu Ying, Zhang Jinqiu,et al,2022.Prediction model of CO gas concentration in highway tunnel based on random forest[J].Science and Technology and Engineering,22 (26):11729-11735.
Zhou Kaihong, Ran Hongmei, Jiang Qinggu,et al,2023.Nonlinear error compensation of digital dial gauge based on improved BP neural network[J].Modern Manufacturing Engineering,(7 ):117-122.
陈超,聂鹤翔,李琼,等,2022.基于交通风条件多点进出城市地下道路CO污染物浓度分布特性预测模型[J].中国公路学报,35(5):161-169.
高秋英,王丽丽,王荣忠,2021.最小二乘法曲线拟合及优化算法研究[J].工业控制计算机,34(11):100-101.
纪洪广,曹杨,张舸,等,2014.独头巷道掘进过程中排烟时间预测[J].金属矿山,43(5):142-145.
龚晓燕,孙育恒,刘壮壮,等,2023.基于BP神经网络的煤矿综掘面风流智能调控模型研究 [J].安全与环境工程,30(30):138-145.
蒋锋,韩兴钰,王辉,2023.基于图神经网络的长江流域经济带PM2.5浓度预测[J].环境科学与技术,46(11):90-101.
李篷,段淑清,王堃,等,2014.灰色模型与曲线拟合沉降预测及相关性分析[J].地下空间与工程学报,10(1):109-115.
吕燕红,王芹,2013.基于神经网络信息融合隧道CO浓度预测研究[J].信息技术,37(9):128-131.
史秀志,范玉乾,尚雪义,2016.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,24(3):64-69.
王时彬,陈日辉,刘世涛,等,2014.独头掘进面爆破后CO浓度变化分析及预测[J].科学技术与工程,14(6):101-103,107.
吴敏,潘春荣,2023.一维卷积神经网络在磁铁矿分选中的应用[J/OL].有色金属(选矿部分):1-6[2023-07-28].
谢饶青,陈建宏,肖文丰,2022.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,30(2):272-281.
杨婷婷,高乾,李浩千,等,2022.基于卷积神经网络—长短时记忆神经网络的磨煤机故障预警[J].热力发电,51(10):122-129.
曾俊晖,李夕兵,2019.基于混沌时间序列分析方法的矿山塌陷区范围预测[J].黄金科学技术,27(2):249-256.
翟小伟,马灵军,邓军,2011.工作面上隅角CO浓度预测模型的研究与应用[J].煤炭科学技术,39(11):59-62.
张舸,曹杨,纪洪广,等,2014.独头巷道中炮烟散发规律及浓度预测模型试验研究[J].现代隧道技术,51(4):150-154.
张志刚,徐莹,张锦秋,等,2022.基于随机森林的公路隧道CO气体浓度预测模型[J].科学技术与工程,22(26):11729-11735.
周凯红,冉红梅,蒋青谷,等,2023.基于改进BP神经网络的数显千分表非线性误差补偿[J].现代制造工程,(7):117-122.
[1] 张帅,赵鑫,彭祥玉,王宇斌,桂婉婷,田家怡. 基于双隐含层BP神经网络的某金矿回收率预测研究[J]. 黄金科学技术, 2024, 32(1): 170-178.
[2] 方博扬,赵国彦,马举,陈立强,简筝. Adaboost集成学习优化的巷道围岩松动圈预测研究[J]. 黄金科学技术, 2023, 31(3): 497-506.
[3] 谢学斌, 刘涛, 张欢. 基于改进CEEMDAN-DCNN的声发射源识别分类方法[J]. 黄金科学技术, 2022, 30(2): 209-221.
[4] 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.
[5] 李泽佑, 黄锐, 赵淑琪, 沈学, 吴娥. 高海拔矿山独头巷道通风降尘方法优选[J]. 黄金科学技术, 2020, 28(5): 743-752.
[6] 卜斤革,陈建宏. 基于粒子群算法优化BP神经网络的溶浸开采浸出率预测[J]. 黄金科学技术, 2020, 28(1): 82-89.
[7] 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.
[8] 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.
[9] 毕林,谢伟,崔君. 基于卷积神经网络的矿工安全帽佩戴识别研究[J]. 黄金科学技术, 2017, 25(4): 73-80.
[10] 刘晓明,赵君杰,彭平安,毕林,代碧波. 有效微震信号自动识别技术研究[J]. 黄金科学技术, 2017, 25(3): 84-91.
[11] 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.
[12] 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.
[13] 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.
[14] 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.
[15] 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.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!