›› 2017, Vol. 38 ›› Issue (S2): 89-98.doi: 10.16285/j.rsm.2017.S2.012

• 基础理论与实验研究 • 上一篇    下一篇

基于声发射信号聚类分析和神经网络识别的岩爆预警方法实验研究

张艳博1,2,杨 震1,2,姚旭龙1,2,梁 鹏1,2,田宝柱1,2,孙 林1,2   

  1. 1. 华北理工大学 矿业工程学院,河北 唐山 063009;2. 华北理工大学 河北省矿业开发与安全技术重点实验室,河北 唐山 063009
  • 收稿日期:2017-06-26 出版日期:2017-11-23 发布日期:2018-06-05
  • 通讯作者: 杨震,男,1992年生,硕士研究生,从事矿山岩石力学及声发射信号处理等方面的研究工作。E-mail:yangzhen_ncst@163.com E-mail:fzdn44444@163.com
  • 作者简介:张艳博,男,1973年生,博士,教授,从事矿山岩石力学与工程研究工作。
  • 基金资助:

    国家自然科学基金(No. 51374088, No. 51574102);河北省高等学校科学技术研究项目(No. QN2016124, No. QN2016125);华北理工大学研究生创新项目(No. 2017S07)。

Experimental study of rockburst early warning method based on acoustic emission cluster analysis and neural network identification

ZHANG Yan-bo1,2, YANG Zhen1,2, YAO Xu-long1,2, LIANG Peng1,2, TIAN Bao-zhu1,2, SUN Lin1,2   

  1. 1. College of Mining Engineering, North China University of Science and Technology, Tangshan, Hebei 063009, China; 2. Mining Development and Technology Safety Key Laboratory of Hebei Province, North China University of Science and Technology, Tangshan, Hebei 063009, China
  • Received:2017-06-26 Online:2017-11-23 Published:2018-06-05
  • Supported by:

    This work was supported by the National Natural Science Foundation of China (51374088, 51574102), Science and Technology Research Projects of University in Hebei(QN2016124, QN2016125), and Supported by the Graduate Student Innovation Fund of North China University of Science and Technology (2017S07).

摘要: 开展巷道岩爆室内模拟声发射监测实验,对岩爆过程中的声发射信号进行聚类分析,得到3种类型声发射信号,优选具有岩爆前兆演化异常、能量大、数量小等特征的信号类型作为岩爆前兆特征信号。岩爆发生前,岩爆前兆特征信号开始密集出现,明显的前兆异常。运用时间窗函数对岩爆前兆特征信号的时间密集性进行量化分析,提出衡量信号时序演化特征的量化指标即时间密集度 。岩爆发生前,前兆信号密集出现,出现了 ≥3值,可将首次 ≥3作为岩爆前兆信息,可将岩爆预警阈值a划定为3。基于岩爆前兆特征信号优选和预警阈值提取,借助BP神经网络,智能识取岩爆前兆特征信号,利用时间窗函数计算岩爆前兆特征信号 值,当岩爆前兆特征信号 值开始达到岩爆预警阈值( ≥a)时则进行岩爆灾害预警,建立了基于巷道岩爆模拟实验声发射数据的岩爆实时预警方法,为工程现场岩爆预警方法的建立提供了新思路。

关键词: 声发射(AE), 聚类分析, 神经网络, 岩爆预警

Abstract: Three types of AE signals are obtained by carrying out the tunnel rock burst simulation experiment and clustering rock explosion signal. The acoustic emission signals which have the characteristics of the precursory anomaly, large energy and small quantity, are preferred as precursor characteristic signals of rockburst. Before the rockburst, the precursor characteristic signal of rockburst appeared densely; it is shown obvious precursory anomaly. The window functionis used to carry out the quantitative analysis of temporal density of precursor signal and put forward the quantitative index——time intensity which can measure timing evolution characteristics of signal. Before the rockburst, the precursory signal appeared densely, is greater than or equal to 3. This situation firstly appears can be as the precursor information of rockburst; therefore the early warning threshold a can be set to 3. Based on optimization of rockburst precursor signal and early warning threshold extraction, with the help of BP neural network, intelligently identify rockburst precursor signal. The time window function is used to calculate value of precursor signal. When value of precursor signal start to achieve rockburst warning threshold ( ≥a), it starts to warn rockburst. Therefore, a real-time warning method of rockburst based on AE data of tunnel rockburst simulation experiment is established so as to provides a new idea for the construction of early warning method of rockburst.

Key words: acoustic emission(AE), cluster analysis, neural network, rockburst warning

中图分类号: 

  • TU 452

[1] 王创业, 常新科, 刘沂琳, 郭文彬, . 单轴压缩条件下大理岩破裂过程声发射频谱 演化特征实验研究[J]. 岩土力学, 2020, 41(S1): 51-62.
[2] 房昱纬, 吴振君, 盛谦, 汤华, 梁栋才, . 基于超前钻探测试的隧道地层智能识别方法[J]. 岩土力学, 2020, 41(7): 2494-2503.
[3] 旷杜敏, 龙志林, 周益春, 闫超萍, 陈佳敏, . 基于BP神经网络的岩土胶结材料速率敏感 效应预测研究[J]. 岩土力学, 2019, 40(S1): 390-399.
[4] 赵久彬, 刘元雪, 刘娜, 胡明, . 海量监测数据下分布式BP神经网络区域 滑坡空间预测方法[J]. 岩土力学, 2019, 40(7): 2866-2872.
[5] 钟国强, 王 浩, 李 莉, 王成汤, 谢壁婷, . 基于SFLA-GRNN模型的基坑地表最大沉降预测[J]. 岩土力学, 2019, 40(2): 792-798.
[6] 梁天成,刘云志,付海峰,严玉忠,修乃岭,王 臻. 多级循环泵注水力压裂模拟实验研究[J]. , 2018, 39(S1): 355-361.
[7] 秦雨樵,汤 华,冯振洋,尹小涛,王东英, . 基于聚类分析的边坡稳定性研究[J]. , 2018, 39(8): 2977-2983.
[8] 王庆武,巨能攀,杜玲丽,黄 健,胡 勇,. 拉林铁路桑日至加查段三维地应力场反演分析[J]. , 2018, 39(4): 1450-1462.
[9] 马春驰,李天斌,张 航,王剑锋, . 基于EMS微震参数的岩爆预警方法及探讨[J]. , 2018, 39(2): 765-774.
[10] 姜德义,谢凯楠,王静怡,陈 结,郭 威,明 镜,肖 鹏,蒋 翔,. 砂岩临界状态的声发射能量与等候时间差统计分布规律[J]. , 2017, 38(S2): 223-228.
[11] 陈世万,杨春和,王贵宾,李二兵,陈 亮,. 北山坑探设施开挖损伤区现场声发射监测试验研究[J]. , 2017, 38(S2): 349-358.
[12] 张社荣,胡安奎,王 超,彭振辉, . 基于SLR-ANN的地应力场三维智能反演方法研究[J]. , 2017, 38(9): 2737-2745.
[13] 杨 啸 ,杨志强 ,高 谦 ,陈得信,. 混合充填骨料胶结充填强度试验与最优配比决策研究[J]. , 2016, 37(S2): 635-641.
[14] 王佳信,周宗红,赵 婷,余洋先,龙 刚,李春阳. 基于Alpha稳定分布概率神经网络的围岩稳定性分类研究[J]. , 2016, 37(S2): 649-657.
[15] 胡 军,董建华 ,王凯凯 ,黄贵臣,. 边坡稳定性的CPSO-BP模型研究[J]. , 2016, 37(S1): 577-582.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!