基于神经网络的煤矿安全综合评价模型研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
本文首先分析了我国煤矿安全现状,论述了开展煤矿安全综合评价的必要性,然后在事故致因理论的基础上,结合煤矿生产系统复杂多样的特点,用事故树分析法、人-机-环境分析法和层次分析法三种常用方法构建煤矿安全指标分析模型,以此作为分析煤矿安全综合评价指标的工具。
     通过煤矿安全指标分析模型得到煤矿安全评价综合指标体系,将其纵向分为目标层、中间层和因素层三个层次,横向则划分为人员素质因素、生产装备因素、生产环境因素和安全管理因素四个方面总共34个指标。
     介绍了神经网络的结构、算法等内容,对BP神经网络的学习算法所存在的局部最小问题,采用附加动量法进行了改进,利用改进后的BP神经网络建立煤矿安全综合评价模型,确定了模型为三层(34-14-5)结构,采用MATLAB中的神经网络工具箱进行编程,在计算机中实现了煤矿安全综合评价神经网络模型的建立。采用国内比较具有代表性的20个实例样本对神经网络进行训练,对训练过程中误差函数存在收敛慢的问题,在附加动量法的基础上采用自适应调整步长的方法进行改进,最后通过该模型对义马煤业集团公司下属耿村、常村等矿进行评价,其结果与实际情况相符,说明该模型成功建立起影响因素和煤矿安全状况之间复杂的非线性映射关系,具有一定的实用价值。
     随着样本库的逐渐充实,该模型的评价结果会越来越精确,其应用价值也会越来越高。
Firstly, this paper analyzes the status quo of Chinese coal mine safety, and it is necessary to carry out a comprehensive evaluation for coal mine. Based on safety accident causation theory and the complexity of coal mine system, three methods which commonly used in safety analysis, fault tree analysis, Human-Machine-Environment analysis and analytic hierarchy process, are synthesized to build the indicators analysis model of coal mine safety, by which we could get the factors that affect safety status of coal mine.
     Through the analysis model, indicators system is built, which is vertically divided into the target layer, middle layer and indicators layer. And in the indicators layer, there are 34 indicators horizontally ranging in four areas, the personnel quality part, equipment part, environmental factors and safety management part.
     Then make an introduction of the neural networks' structure, algorithms and so on, for the existence of local minimum of the BP neural network learning algorithm, this paper adopt an additional momentum method to improve it's efficiency. Then use the improved BP neural network model to build comprehensive evaluation model of coal mine safety with three layers of 34-14-5 structure, and program the model in the computer by the neural network toolbox of MATLAB. After that, train the neural network with 20 representative samples, we find out that it is slowly the training error function curve converges, then the method of self-adaptively adjusting steps is obtained in the paper.
     Finally, five instances of Yima Coal Industry Group are used for simulation, and the result shows that the model has successfully established the complex nonlinear mapping relationship between safety indicators and the actual safety situation of the mines.
     With the abundance of the sample library in future, this model will get more accurate evaluation results, and its application value will be enhanced.
引文
[1]范维唐,卢鉴章,申宝宏等.煤矿灾害防治的技术与对策[M].徐州:中国矿业大学出版社,2007.
    [2]陈红.中国煤矿重大事故中的不安全行为研究[M].北京:科学出版社,2006.
    [3]国家安全生产监督管理总局政策法规司.中国安全生产年鉴2005-2007[M].北京:煤炭工业出版社,2006-2008.
    [4]李树刚,常心坦,林海飞.西北地区安全生产存在问题及对策研究[J].采煤与安全工程学报,2006,23(1):52-55.
    [5]《中国安全生产形势报告》编委会.转折与发展—中国安全生产形势报告(2006)[R].北京:中国劳动社会保障出版社,2007.
    [6]罗云,黄毅.中国安全生产发展战略—论安全生产保障五要素[M].北京:化学工业出版社安全科学与工程出版中心,2005.
    [7]卢鉴章,申宝宏.煤矿灾害防治技术基础知识[M].徐州:中国矿业大学出版社,2008.
    [8]刘铁民,张兴凯,刘功智.安全评价方法应用指南[M].北京:化学工业出版社,2005.71-78,458-472.
    [9]王起全,徐德蜀.安全评价操作实务[M].北京:气象出版社,2009.5-14,123-130,184-188.
    [10]来存良.煤矿信息化技术[M].北京:煤炭工业出版社,2007.260-262.
    [11]Li Yancang, Suo Juanjuan. Safety assessment of platform loadout procedures based on unascertained measures[J]. Chinese Journal of Oceanology and Limnology,2007,25(4):354-358.
    [12]何际泽,张瑞明.安全生产技术[M].北京:化学工业出版社,2008.233-264.
    [13]张希久,于宗立.煤矿安全技术培训教案精选[M].徐州:中国矿业大学出版社,2009.
    [14]慕庆国.煤矿事故预防管理[M].北京:中国劳动社会保障出版社,2006.
    [15]华道友.煤矿重大事故处理与救灾技术[M].成都:西南交通大学出版社,2006.10-19.
    [16]施式亮,何利文.矿井安全非线性动力学评价及过程可视化[J].煤炭学报,2005,30(6)
    [17]吴穹,许开立.安全管理学[M].北京:煤炭工业出版社,2002.29-31.
    [18]Zhao Xiaohu, Wang Qingqing, Zhao Keke. Research of Coal Mine Safety Assessment Based on Multi-agent about Evidence Theory[C]. International Conference on Information Technology and Computer Science,2009.
    [19]Alessandro Tugnoli, Faisal Khan, Paul Amyotte, Valerio Cozzani. Safety Assessment In Plant Layout Design Using Indexing Approach:Implementing Inherent Safety Perspective Part 2-domino Hazard Index And Case Study[J]. Journal of Hazardous Materials,2008,160(1).
    [20]Michael O'Toole. The relationship between employees' perceptions of safety and organizational culture[J]. Journal of Safety Research,2002,33:241-243.
    [21]Liu Hui, Sun Shimei, Zhang Zhichao, Wen Xin. Study and Application on Safety Comprehensive Assessment of Man-Machine-Environment System for Highway Tunnel Construction[C]. The 2008 International Symposium on Safety Science and Technology,2008.
    [22]边馥萍,侯文华,梁冯珍.数学模型方法与算法[M].北京:高等教育出版社,2005.163-168.
    [23]Peter Montague. Reducing the harms associated with risk assessments[J]. Environmental Impact Assessment Review,2004,24(7-8):733-748.
    [24]冯定.神经网络专家系统[M].北京:科学出版社,2006.29-32.
    [25]张德丰.MATLAB模糊系统设计[M].北京:国防工业出版社,2009.
    [26](美)Martin T. Hagan, Howard B. Demuth, Mark H. Beale著.戴葵等译.神经网络设计[M].北京:机械工业出版社,2002(9).
    [27](美)Sandhya Samarasinge著.史晓霞,陈一民,李军治等译.神经网络在应用科学和工程中的应用——从基本原理到复杂的模式识别[M].北京:机械工业出版社,2009(7).
    [28]张良均,曹晶,蒋世忠.神经网络实用教程[M].北京:机械工业出版社,2008.
    [29]张德丰.MATLAB神经网络应用设计[M].北京:机械工业出版社,2009.
    [30]施式亮,王海桥.矿井安全非线性动力学评价[M].北京:煤炭工业出版社,2001.
    [31]李勇,孙艳萍,孙海波,宋景东.用于故障预测的BP网络模型及改进[J].东北电力学院学报,1999,19(1):27-32.
    [32]刘婧,刘弘.人工神经网络模型的对比分析及应用研究[J].信息技术与信息化,2007,2:75-78.
    [33]Liu Yajing, Mao Shanjun, Li Mei, Yao Jiming. Study of a Comprehensive Assessment Method for Coal Mine Safety Based on a Hierarchical Grey Analysis [J]. Journal of China University of Mining & Technology,2007,17(1):6-10.
    [34]黄辉宇,李从东.基于人工神经网络的煤矿安全评估模型研究[J].工业工程,2007,10(1):112-115.
    [35]Kazumi Saito, Ryohei Nakano. Extracting regression rules from neural networks[J]. Neural Networks,2002,15:1279-1288.
    [36]Fan Yongjian, Mai Jianying, Shen Yanguang. Study of the Safety Assessment Model of Coal Mine Based on BP Neural Network[C]. International Conference on Intelligent Computation Technology and Automation,2009.
    [37]高大启.有教师的线性基本函数前向三层神经网络结构研究[J].计算机学报,1998,21(1):80-86.
    [38]N.Okada, et al.. Intergrated Research on Methodological Development of Urban Diagnosis for Disaster Risk and its Applications[M]. Annuals of Disas, Prev. Res. Inst., No.47C,2004:1-8.
    [39]Yahya H. Zweiri, Lakmal D. Seneviratne, Kaspar Althoefer. Stability analysis of a three-term backpropagation algorithm[J]. Science Direct,2005,18:1341-1347.
    [40]Guoqiang Zhang, Michael Y. Hu, B. Eddy Patuwo, Daniel C. Indro. Artificial neural networks in bankruptcy prediction:General framework and cross-validation analysis[J]. European Journal of Operational Research,1999,116:16-32.
    [41]L. D. Arya, L. S. Titare, D. P. Kothari. Determination of probabilistic risk of voltage collapse using radial basis function (RBF) network[J]. Electric Power Systems Research,2006,76:426-434.
    [42]Tung-Chueng Chang and Ru-Jen Chao. Application of back-propagation networks in debris flow prediction[J]. Engineering Geology,2006,85:270-280.
    [43]John Grznar, Sameer Prasad, Jasmine Tata. Neural networks and organizational systems:Modeling non-linear relationships[J]. European Journal of Operational Research,2007,181:939-955.
    [44]W.M. Jenkins. Neural network weight training by mutation[J]. Computers & Structures,2006,84: 2107-2112.
    [45]王伟.人工神经网络原理—入门与应用[M].北京:北京航空航天大学出版社,1995.53-61.
    [46]张立明.人工神经网络的模型及其应用[M].上海:复旦大学出版社,1993.43-47.
    [47]赵广兴,高新春,张建国,王国际.事故树分析法在煤矿专项安全评价中的应用[J].中国煤炭,2005,31(7):63-65.
    [48]梁建国.事故树分析法在斜巷运输事故中的应用[J].煤炭技术,2009,28(1):93-95.
    [49]练友红,汪长明.用事故树分析法确定煤矿瓦斯突出的主导因素探讨[J].矿业安全与环保,2006,33(z1):95-97.
    [50]邓明.矿井采煤面瓦斯爆炸事故树分析[J].工业安全与环保,2002,28(11):45-46.
    [51]张飞,周连春,王文才,李风梅,张世明.煤矿火灾的事故树分析[J].煤炭工程,2009,(6):69-71.
    [52]刘世民.煤矿机电设备的安全评价研究[D].北京工业大学,2007.
    [53]张凡,赵仕华,王丽娜,郑衡,宋宜诺.煤矿矿井火灾事故树评价分析[J].科技风,2009,(12):139-141.
    [54]康钦容,唐建新,张卫中,韦小娟.事故树分析法在白皎煤矿煤与瓦斯突出安全评价中的应用[J].矿业安全与环保,2006,33(3):83-85.
    [55]周少统,张振华,刘宏江.煤矿片帮冒顶危险性分析[J].煤矿现代化,2006,(3):32.
    [56]吴祥,程远平,刘静,王海峰,王亮.煤矿重特大瓦斯事故关键链控制研究[C].中国(淮南)煤矿瓦斯治理技术国际会议论文集,2007:420-426.
    [57]张跃华.事故树分析法在煤矿中的应用[J].山东煤炭科技,2003,(3):65-67.
    [58]王长申,孙亚军,杭远.基于事故树分析的煤矿潜在突水危险评价研究[J].岩石力学与工程学报,2009,28(2):298-305.
    [59]贾智伟,景国勋,张强,段振伟.基于三角模糊数的矿井火灾事故树分析[J].安全与环境学报,2004,4(6):62-65.
    [60]张超,张云鹏,杨莉娜,朱令起.中小煤矿煤尘爆炸事故的事故树分析[J].煤炭技术,2006, 25(2):60-62.
    [61]孔宪复.煤矿井下采掘工作面爆破事故产生原因分析[J].科技资讯,2008,(29):76.
    [62]王森林,王洪德.用事故树法分析矿井内因火灾引起CO中毒事故[J].煤炭开采,2001,(3):68-70.
    [63]张振菊.煤矿大巷轨道运输的安全性分析[J].矿业安全与环保,2005,32(3):38-40.
    [64]冯海明.矿井机车伤亡事故的勘察与预防[J].中国煤炭,2005,31(6):46-47.
    [65]耿俊艳,高文乐,高秋野,李振.拆除爆破伤亡的事故树分析[J].煤矿安全,2008,39(2):85-87.
    [66]林友,黄德镛,叶加冕,彭芬兰.矿山竖井提升伤亡事故的事故树分析[J].云南冶金,2006,35(3):7-9,48
    [67]黄相岩,程文东.基于事故树理论的矿山人员触电事故致因分析[J].中国西部科技,2008,7(17):48-49.
    [68]吴立云,杨玉中,石琴谱.胶带输送事故的事故树分析[J].矿业安全与环保,1999,(6):38-41.
    [69]陶明,任少峰,王玉杰,陶令.一起爆破飞石事故的事故树分析[J].爆破,2007,24(3):114-116.
    [70]蒋绍军.基于事故树分析法的锚杆支护煤巷顶板安全评价[J].矿业安全与环保,2009,36(z1):220-222.
    [71]翁平.地下矿山顶板事故分析与预防对策研究[J].现代矿业,2009,(11):87-89.
    [72]杨军伟,林大能,张鹏,彭斌.基于事故树理论的爆破事故致因分析[J].采矿技术,2007,7(3):49-50.
    [73]王育军,夏建波,林友.掘进工作面炮烟中毒事故的事故树分析[J].昆明冶金高等专科学校学报,2009,25(1):5-8.
    [74]冯兴隆,陈日辉.矿井坠井伤亡事故的事故树分析[J].山东煤炭科技,2005,(1):64-65.
    [75]李广涛,黄德镛,丁军明.FTA在斜井跑车事故分析中的应用[J].矿业工程,2006,4(6):61-63.
    [76]景国勋,段振伟,贾智伟.胶带输送机运输事故树可靠性的计算机模拟[J].中国安全科学学报,2003,13(7):71-73.
    [78]赵清华.地下矿山斜井跑车事故原因分析与预防[J].中国矿业,2007,16(4):53-60.
    [79]冯治斌.基于事故树分析法的矿井水灾安全评价[J].中州煤炭,2003,(4):43-44.
    [80]沈斐敏.回采工作面冒顶伤害事故的事故树分析[C].煤矿系统工程学术交流会论文集.1988.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700