基于WPD-SVD的矿山微震信号特征提取及分类方法
|
摘要
为减少人工识别矿山微震事件的工作量,提出了基于小波包分解(WPD)和奇异值分解(SVD)提取微震信号特征的方法。首先对爆破震动、岩体破裂、机械干扰和电干扰等4种信号进行4层小波包分解,再利用奇异值分解计算第4层节点上小波包系数构成矩阵得到奇异值。以奇异值为特征值,建立16维特征向量,利用支持向量机(SVM)对400组矿山现场微震信号进行了训练和分类。研究结果表明:与爆破震动、岩体破裂和电干扰信号相比,机械干扰信号的奇异值的差异性最大;SVM的分类正确率达到94.5%,取得了理想的分类效果。
In order to reduce the work load of artificial recognition of mine microseismic events,a method for feature extraction was proposed based on the wavelet packet decomposition( WPD) and singular value decomposition( SVD). Firstly,blasting vibration,rock fracture,mechanical interference and electrical interference signals were decomposed into 4 layers based on WPD,then the singular value was obtained by calculating the wavelet packet coefficients on the fourth layer through the use of SVD.With the singular value as the eigenvalue,a 16-dimensional eigenvector was established.The support vector machine( SVM) was adopted to train and classify the microseismic signals in 400 sets of mines. The results showed that compared with blasting vibration,rock fracture and electrical interference,the singular value of mechanical interference signal was the most significant.The classification accuracy of SVM reached 94.5%,which achieved the ideal classification effect.
In order to reduce the work load of artificial recognition of mine microseismic events,a method for feature extraction was proposed based on the wavelet packet decomposition( WPD) and singular value decomposition( SVD). Firstly,blasting vibration,rock fracture,mechanical interference and electrical interference signals were decomposed into 4 layers based on WPD,then the singular value was obtained by calculating the wavelet packet coefficients on the fourth layer through the use of SVD.With the singular value as the eigenvalue,a 16-dimensional eigenvector was established.The support vector machine( SVM) was adopted to train and classify the microseismic signals in 400 sets of mines. The results showed that compared with blasting vibration,rock fracture and electrical interference,the singular value of mechanical interference signal was the most significant.The classification accuracy of SVM reached 94.5%,which achieved the ideal classification effect.
引文
[1]董陇军,李夕兵,唐礼忠,等.无需预先测速的微震震源定位的数学形式及震源参数确定[J].岩石力学与工程学报,2011,30(10):2057-2067.
[2]赵国彦,邓青林,马举.基于FSWT时频分析的矿山微震信号分析与识别[J].岩土工程学报,2015,37(2):306-312.
[3]唐守锋,童敏明,潘玉祥,等.煤岩破裂微震信号的小波特征能谱系数分析法[J].仪器仪表学报,2011,32(7):1521-1527.
[4]徐飞.基于小波变换的爆破振动信号分析方法及应用[J].淮南:安徽理工大学,2011.
[5]朱权洁,姜福兴,尹永明,等.基于小波分形特征与模式识别的矿山微震波形识别研究[J].岩土工程学报,2012,34(11):2036-2042.
[6]MA J,ZHAO G Y,DONG L J,et al.A comparison of mineseismic discriminators based on features of source parametersto waveform characteristics[J].Shock and Vibration,2015(1):1-10.
[7]MALOVICHKO D.Discrimination of blasts in mine seismology[C]//Proceedings of the Deep Mining 2012.Perth:Australian Centre for Geomechanics,2012:1-8.
[8]尚雪义,李夕兵,彭康,等.基于EMD-SVD的矿山微震与爆破信号特征提取及分类方法[J].岩土工程学报,2016,38(10):1849-1858.
[9]ALLMANN B P,SHEARER P M,HAUKSSON E.Spectral discrimination between quarry blasts and earthquakes in Southern California[J].Bulletin of the Seismological Society of America,2008,98(4):2073-2079.
[10]董陇军,孙道元,李夕兵,等.微震与爆破事件统计识别方法及工程应用[J].岩石力学与工程学报,2016,35(7):1423-1433.
[11]许大为,潘一山,李国臻,等.基于小波变换的矿山微震信号滤波方法研究[J].矿业工程,2007,5(2):66-68.
[12]徐锋,刘云飞.基于EMD-SVD的声发射信号特征提取及分类方法[J].应用基础与工程科学学报,2014,22(6):1238-1247.
[13]徐锋,刘云飞,宋军.基于中值滤波-SVD和EMD的声发射信号特征提取[J].仪器仪表学报,2011,32(12):2712-2719.
[14]丁福利,孙立民.基于支持向量机的不平衡分类研究[J].科学技术与工程,2014,14(3):81-85.
[15]张建国.平顶山东部矿区深井动力灾害多因素耦合统一灾变机理[J].矿业安全与环保,2012,39(5):11-14.
[16]刘云鹏.基于微震监测的“滞后型”动力灾害控制技术研究[J].矿业安全与环保,2017,44(1):74-77.
[2]赵国彦,邓青林,马举.基于FSWT时频分析的矿山微震信号分析与识别[J].岩土工程学报,2015,37(2):306-312.
[3]唐守锋,童敏明,潘玉祥,等.煤岩破裂微震信号的小波特征能谱系数分析法[J].仪器仪表学报,2011,32(7):1521-1527.
[4]徐飞.基于小波变换的爆破振动信号分析方法及应用[J].淮南:安徽理工大学,2011.
[5]朱权洁,姜福兴,尹永明,等.基于小波分形特征与模式识别的矿山微震波形识别研究[J].岩土工程学报,2012,34(11):2036-2042.
[6]MA J,ZHAO G Y,DONG L J,et al.A comparison of mineseismic discriminators based on features of source parametersto waveform characteristics[J].Shock and Vibration,2015(1):1-10.
[7]MALOVICHKO D.Discrimination of blasts in mine seismology[C]//Proceedings of the Deep Mining 2012.Perth:Australian Centre for Geomechanics,2012:1-8.
[8]尚雪义,李夕兵,彭康,等.基于EMD-SVD的矿山微震与爆破信号特征提取及分类方法[J].岩土工程学报,2016,38(10):1849-1858.
[9]ALLMANN B P,SHEARER P M,HAUKSSON E.Spectral discrimination between quarry blasts and earthquakes in Southern California[J].Bulletin of the Seismological Society of America,2008,98(4):2073-2079.
[10]董陇军,孙道元,李夕兵,等.微震与爆破事件统计识别方法及工程应用[J].岩石力学与工程学报,2016,35(7):1423-1433.
[11]许大为,潘一山,李国臻,等.基于小波变换的矿山微震信号滤波方法研究[J].矿业工程,2007,5(2):66-68.
[12]徐锋,刘云飞.基于EMD-SVD的声发射信号特征提取及分类方法[J].应用基础与工程科学学报,2014,22(6):1238-1247.
[13]徐锋,刘云飞,宋军.基于中值滤波-SVD和EMD的声发射信号特征提取[J].仪器仪表学报,2011,32(12):2712-2719.
[14]丁福利,孙立民.基于支持向量机的不平衡分类研究[J].科学技术与工程,2014,14(3):81-85.
[15]张建国.平顶山东部矿区深井动力灾害多因素耦合统一灾变机理[J].矿业安全与环保,2012,39(5):11-14.
[16]刘云鹏.基于微震监测的“滞后型”动力灾害控制技术研究[J].矿业安全与环保,2017,44(1):74-77.