[1]龚尚福,李岩松.基于数据融合的井下瓦斯浓度状态预测[J].西安科技大学学报,2018,(03):506-514.[doi:10.13800/j.cnki.xakjdxxb.2018.0323]
 GONG Shang-fu,LI Yan-song.Prediction of underground gas concentration state based on data fusion[J].Journal of Xi'an University of Science and Technology,2018,(03):506-514.[doi:10.13800/j.cnki.xakjdxxb.2018.0323]
点击复制

基于数据融合的井下瓦斯浓度状态预测(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2018年03期
页码:
506-514
栏目:
出版日期:
2018-05-15

文章信息/Info

Title:
Prediction of underground gas concentration state based on data fusion
文章编号:
1672-9315(2018)03-0506-09
作者:
龚尚福李岩松
西安科技大学 计算机科学与技术学院,陕西 西安 710054
Author(s):
GONG Shang-fuLI Yan-song
(College of Computer Science and Engineering,Xi'an University of Science and Technology,Xi'an 710054,China)
关键词:
瓦斯预测 神经网络 数据融合 DS证据理论
Keywords:
gas prediction neural network data fusion DS evidence theory
分类号:
TD 76
DOI:
10.13800/j.cnki.xakjdxxb.2018.0323
文献标志码:
A
摘要:
针对现有方法中单独使用神经网络进行瓦斯预测时正确性得不到保障的问题,引入了数据融合的方法进行修正,期望在决策层达到提高正确率的目的。首先,将原始数据降噪,通过状态划分以明确模型中DS证据理论所需要的识别框架; 然后,在保持数据拓扑意义不变的情况下,将数据重构为多维向量作为样本数据,利用该样本训练BP神经网络和径向基函数神经网络得到独立的2个预测模块,再选取样本训练得到分类器; 最后,结合统计误差从证据折扣的观点来构造DS证据理论中的基本概率分配函数,使得数据在融合的过程中减少冲突。结果表明,提出的“预测-分类-融合”模型对瓦斯浓度区间判断的正确率比单独使用神经网络预测时的高。利用状态划分和数据融合可以对瓦斯数据进行有效的映射; 在构造分类器时可以结合相关性分析,以得到更多的证据体,有利于挖掘出潜在的信息,指导安全生产。
Abstract:
Aimed at the problem that the correctness could not be guaranteed when the neural network was used alone to predict the gas in the existing method,the data fusion method was introduced to correct the problem and the expectation was to achieve the goal of improving the accuracy at the decision-making level.Firstly,the original data was denoised,and the state identification was used to identify the identification framework needed by DS evidence theory in the model.Then,the data was reconstructed into multidimensional vectors as the sample data while maintaining the topological meaning of the data,and then the sample was used to train BP neural network and radial basis function neural network to get two independent prediction modules,and then choose the sample training to get the classifier.Finally,we combined the statistical error to construct the basic probability distribution function in DS evidence theory from the viewpoint of evidence discount for reducing conflicts in the process of convergence.The experimental results show that the proposed “prediction-classification-fusion” model has higher correctness of judging interval of gas concentration than when using neural network alone.The use of state partitioning and data fusion can effectively map the gas data.In the construction of the classifier,it can be combined with the correlation analysis in order to get more body of evidence,be conducive to mining potential information and guide safe production.

参考文献/References:

[1] 刘永茜.钻屑法测定瓦斯含量存在问题分析及改进[J].煤炭科学技术,2014,42(6):136-139. LIU Yong-xi.Analysis and improvement of the problem of gas content determination by cuttings method[J].Coal Science and Technology,2014,42(6):136-139.
[2] 张子敏.瓦斯地质学[M].徐州:中国矿业大学出版社,2009. ZHANG Zi-min.Gas geology[M].Xuzhou:China University of Mining and Technology Press,2009.
[3]Trifu C I.Urbancic T I.用采矿诱发微震法判别岩体性态特性[J].世界采矿快报,1998,14(2):34-36. Trifu C.Urbancic T I.Using mining-induced microseismic method to discriminate the characteristics of rock behavior[J].World Mining Express,1998,14(2):34-36.
[4]杨金海,秦天健.天然氡气法测岩石孔隙度方法研究[J].西南石油学院学报,2000,22(3):19-20. YANG Jin-hai,QIN Tian-jian.Study on the method of measuring the porosity of rock by natural radon Gas method[J].Journal of Southwest Petroleum Institute,2000,22(3):19-20.
[5] 王忠奎.工作面瓦斯涌出量预测及瓦斯来源分析[J].矿业安全与环保,2008,35(3):54-56. WANG Zhong-kui.Prediction of gas emission in working face and analysis of gas source[J].Mining Safety and Environmental Protection,2008,35(3):54-56.
[6]杨志法,尚彦军,刘 英.关于岩土工程类比法的研究[J].工程地质学报,1997,5(4):300-305. YANG Zhi-fa,SHANG Yan-jun,LIU Ying.Study on analogy method of geotechnical engineering[J].Engineering Geology Journal,1997,5(4):300-305.
[7] 杨 耀.地震视负速度法在隧道超前地质预报中的应用[J].工程地球物理学报,2009,6(6):754-758. YANG Yao.Application of seismic apparent negative velocity method in tunnel advance geological prediction[J].Journal of Engineering Geophysics,2009,6(6):754-758.
[8]高晓旭,董丁稳.BP神经网络在煤矿本质安全评价模型中的应用[J].西安科技大学学报,2011,31(6):781-784. GAO Xiao-xu.DONG Ding-wen.Application of BP neural network in evaluation model of intrinsic safety of coal mine[J].Journal of Xi'an University of Science and Technology,2011,31(6):781-784.
[9]韩 兵,付 华.基于BP神经网络数据融合的瓦斯监测系统[J].工矿自动化,2008(4):10-13. HAN Bing,FU Hua.Gas monitoring system based on BP neural network data fusion[J].Industrial Automation,2008(4):10-13.
[10]李 洋,石必明.基于贝叶斯正则化BP人工神经网络的煤与瓦斯突出预测的研究[J].工矿自动化,2009(2):2-3. LI Yang,SHI Bi-ming.Study on prediction of coal and gas outburst based on Bayesian BP artificial neural network[J].Industrial Automation,2009(2):2-3.
[11]徐雪战,孟祥瑞,邹云龙.基于瓦斯浓度变化的煤与瓦斯突出预警技术[J].工矿自动化,2016,42(9):18-21. XU Xue-zhan,MENG Xiang-rui,ZOU Yun-long.Early warning technology of coal and gas outburst based on the change of gas concentration[J].Industrial Automation,2016,42(9):18-21.
[12]董丁稳,常心坦.瓦斯浓度区间预测的灰色聚类与高斯过程模型[J].中国安全科学学报,2011,21(5):41-45. DONG Ding-wen,CHANG Xin-tan.Grey clustering and Gaussian process model for interval prediction of gas concentration[J].Chinese Journal of Safety Sciences,2011,21(5):41-45.
[13]王立政.BP神经网络在城市轨道交通客流短时预测中的应用研究[D].苏州:苏州科技大学,2017. WANG Li-zheng.Application of BP neural network in short time forecast of urban rail transit passenger flow[D]. Suzhou:Suzhou University of Science and Technology,2014.
[14]何立志.基于改进BPNN和DS证据理论的列车走行部故障诊断研究[D].成都:西南交通大学,2014. HE Li-zhi.Research on train running fault diagnosis based on improved BPNN and DS evidence theory[D].Chengdu:Southwest Jiaotong University,2014.
[15]Wang Tang,Jin Tang.An improved mean filter algorithm for impulse noise elimination[J].Advanced Materials Research,2014,3187(936):2279-2283.
[16]丁星星,杨林峰,张 莹,等.煤矿瓦斯爆炸浓度参数的确定[J].中原工学院学报,2010,21(6):9-11. DING Xing-xing,YANG Lin-feng,ZHANG Ying,et al.Determination of gas explosion concentration parameters in coal mine[J].Journal of Zhongyuan Institute of Technology,2010,21(6):9-11.
[17]修春波,刘向东,张宇河.相空间重构延迟时间与嵌入维数的选择[J].北京理工大学学报,2003,23(2):219-224. XU Chun-bo,LIU Xiang-dong,ZHANG Yu-he.The selection of delay time and embedding dimension of phase space reconstruction[J].Transactions of Beijing Institute of Technology,2003,23(2):219-224.
[18]孙海云,曹庆杰.相空间重构延迟时间的确定[J].山东工业大学学报,2000,30(2):107-110. SUN Hai-yun,CAO Qing-jie.Determination of delay time of phase space reconstruction[J].Journal of Shandong University of Technology,2000,30(2):107-110.
[19]胡 瑜,陈 涛.基于C-C算法的混沌吸引子的相空间重构技术[J].电子测量与仪器学报,2012,26(5):425-430. HU Yu,CHEN Tao.Phase space reconstruction technique of chaotic attractor based on C algorithm[J].Journal of Electronic Measurement and Instrumentation,2012,26(5):425-430.
[20]Jakub Nedbalek.RBF neural networks for function approximation in dynamic modelling[J].Journal of Konbin,2008,8(1):37-39.
[21]PAN Guang,WU Lin-li.Information fusion based on improved D-S evidence theory[J].Applied Mechanics and Materials,2013,2700(411):51-53.

相似文献/References:

[1]丁 华,王 剑,王 彬.基于灰关联分析和神经网络的煤与瓦斯突出预测[J].西安科技大学学报,2009,(02):136.
 DING Hua,WANG Jian,WANG Bin.Coal and gas outburst forecast based on ANN and grey correlation[J].Journal of Xi'an University of Science and Technology,2009,(03):136.
[2]高 宁,高彩云,吴良才.GPS高程迭加拟合模型的研究[J].西安科技大学学报,2009,(03):339.
 GAO Ning,GAO Cai-yun,WU Liang-cai.Research of combined model for GPS height[J].Journal of Xi'an University of Science and Technology,2009,(03):339.
[3]李伟山,王 琳,卫 晨.LSTM在煤矿瓦斯预测预警系统中的应用与设计[J].西安科技大学学报,2018,(06):1027.[doi:10.13800/j.cnki.xakjdxxb.2018.0621]
 LI Wei-shan,WANG Lin,WEI Chen.Application and design of LSTM in coal mine gas prediction and warning system[J].Journal of Xi'an University of Science and Technology,2018,(03):1027.[doi:10.13800/j.cnki.xakjdxxb.2018.0621]
[4]赵忠杰,田 梅.数据融合技术在公路隧道火灾探测中的应用[J].西安科技大学学报,2007,(03):435.
 ZHAO Zhong-jie,TIAN Mei.Application of data fusion technology to highway tunnels fire detection[J].Journal of Xi'an University of Science and Technology,2007,(03):435.

备注/Memo

备注/Memo:
收稿日期:2017-09-11 责任编辑:刘 洁
基金项目:国家自然科学基金(U1251114); 陕西省自然科学基础研究计划(2012JM8029); 西安市科学计划(CX1519(3))
通信作者:龚尚福(1954-),男,宁夏平罗人,教授,E-mail:gongsf@xust.edu.cn
更新日期/Last Update: 2018-06-30