基于小波分形特征与模式识别的矿山微震波形识别研究
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
在前人研究的基础之上,探讨、验证了矿山微震信号的分形特征,并根据微震信号的特征确立了相关的无标度区间及分形盒维数算法。利用矿山爆破振动、岩石破裂及电磁干扰3类信号频谱分布不同这一特征,结合小波分析与分形理论,通过MATLAB编制相应程序,对3类信号进行了5层小波包分解,求取了指定特征频带上重构信号的分形盒维数。以该盒维数为信号特征,建立23维特征向量,通过SVM支持向量机对300组矿山现场微震信号进行了训练和分类识别。研究结果表明:特征频带上的分形盒维数与信号的整体盒维数接近,表明特征频带上的分形盒维数表征了整体的分形特征;3类信号具有明显分形特征,电磁干扰信号最为明显;SVM识别网络识别微震信号,识别正确率高,但运算速度及识别效率仍有待提高。
High-precision location is the focus of hot research about microseismic technology,and classification of microseismic events is the basis for the location.Based on the previous studies,the fractal characteristics of microseismic signals are studied,and the range and scale-free fractal box dimensions of the algorithm are established.Using the spectral differences about mine blasting vibration,rock fracture and electromagnetic interference signals,and based on the wavelet analysis and the fractal theory,the microseismic signals are decomposed into 5 layers to gain specified frequency bands using MATLAB software.Then the box fractal dimensions about those specified frequency band reconstructed signals can be calculated.The 23-dimensional values of pattern recognition feature vector can be established.Finally,the support vector machine SVM is adopted to train,classify and recognize 300 sets of data.The results show that three types of signals have obvious fractal characteristics in the specified frequency bands,especially the electromagnetic interference signals.The fractal dimension box of specified frequency bands is close to the whole signal dimension box.The SVM network model with 23 fractal dimension vectors can be well used to recognize microseismic events,and the correct identification rate is 94%,with can meet the needs of the project site,but the efficiency of identification still needs further improvement.
引文
[1]MOLCHAN G,KRONROD T.Seismic interevent time:aspatial scaling and multifractality[J].Pure and AppliedGeophysics,2007,164(1):75–96.
    [2]钟明寿,龙源,谢全民,等.基于分形盒维数和多重分形的爆破地震波信号分析[J].振动与冲击,2010,29(1):7–11.(ZHONG Ming-shou,LONG Yuan,XIE Quan-min,et al.Signal analysis for blasting seismic wave based on fractalbox-dimension and multi-fractal[J].Journal of Vibration andShock,2010,29(1):7–11.(in Chinese))
    [3]WANG C,WU A,LIU X,et al.Study on fractal characteristicsof b value with microseismic activity in deep mining[J].Procedia Earth and Planetary Science.2009,1(1):592–597.
    [4]唐礼忠,XIA K W,李夕兵.矿山地震活动多重分形特性与地震活动性预测[J].岩石力学与工程学报,2010(9):1818-1824.(TANG Li-zhong,XIA K W,LI Xi-bing.Seismicmulti-fractal characteristics in mines and seismicityprediction[J].Chinese Journal of Rock Mechanics andEngineering,2010,29(9):1818–1824.(in Chinese))
    [5]李信富,李小凡,武晔.分形理论在地震学中的应用研究[J].地球物理学进展,2007,22(2):411–417.(LI Xin-fu,LI Xiao-fan,WU Ye.Application of fractal theory inseismology[J].Progress in Geophysics,2007,22(2):411–417.(in Chinese))
    [6]曾锦光,舒雅琴,钟勇.地震波的分形与混沌性质[J].石油地球物理勘探,1995,30(6):743–748.(ZENG Jin-guang,SHU Ya-qin,ZHONG Yong.Fractal and chaoticcharacteristics of seismic data[J].Oil GeophysicalProspecting,1995,30(6):743–748.(in Chinese))
    [7]赵春艳,谷峻松.地震波的分形特性[J].辽宁工程技术大学学报(自然科学版),2001,20(4):423–425.(ZHAOChun-yan,GU Jun-song.The fractal characteristics ofseismic waves[J].Journal of Liaoning TechnicalUniversity(Natural Science),2001,20(4):423–425.(inChinese))
    [8]田丰,王晋国,王明祥.基于分形理论的地震数据分析[J].长安大学学报(自然科学版),2008,28(2):108–110.(TIAN Feng,WANG Jin-guo,WANG Ming-xiang.Treatment of seismic datum based on fractal theory[J].Journal of Chang’an University(Natural Science Edition),2008,28(2):108–110.(in Chinese))
    [9]张济忠.分形[M].北京:清华大学出版社,1995.(ZHANGJi-zhong.Fractal[M].Beijing:Tsinghua University Press,1995.(in Chinese))
    [10]CAO A,DOU L,YAN R,et al.Classification ofmicroseismic events in high stress zone[J].Mining Scienceand Technology(China),2009,19(6):718–723.
    [11]解文荣,张莉.地震波形的分形判别与特征提取[J].华北地震科学,2004,22(4):22–24.(XIE Wen-rong,ZHANGLi.The fractal identification of seismic wave and theextraction for its characteristics[J].North China EarthquakeSciences,2004,22(4):22–24.(in Chinese))
    [12]曹茂森,任青文,王怀洪.基于小波与分形理论的地震异常检测[J].地球物理学报,2005,48(3):672–679.(CAOMao-sen,REN Qing-wen,WANG Huai-hong.A method ofdetecting seismic seismic singularities using combinedwavelet with fractal[J].Chinese Journal of Geophysics,2005,48(3):672–679.(in Chinese))
    [13]詹毅,钟本善.利用小波变换提高地震波初至拾取的精确度[J].成都理工大学学报(自然科学版),2004(6):703–707.(ZHAN Yi,ZHONG Ben-shan.Improved accuracy ofpicking first arrival with wavelet transform in seismicsurvey[J].Journal of Chengdu University of Technology(Science&Technology Edition),2004(6):703–707.(inChinese))
    [14]李舜酩,李香莲.振动信号的现代分析技术与应用[M].北京:国防工业出版社,2008.(LI Shun-ming,LI Xiang-lian.Modern analysis techniques and application of vibrationsignals[M].Beijing:National Defense Industry Press,2008.(in Chinese))
    [15]谢全民,龙源,钟明寿,等.小波包与分形组合技术在爆破振动信号分析中的应用研究[J].振动与冲击,2011,30(1):11–15.(XIE Quan-min,LONG Yuan,ZHONGMing-shou,et al.Application of wavelet packet and fractalcombination technology in blasting vibration signalanalysis[J].Journal of Vibration and Shock,2011,30(1):11–15.(in Chinese))

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心