利用复合特征对电磁辐射监测进行模式识别的冲击地压预测研究
|
摘要
如何从电磁辐射监测数据中预测冲击地压危险性,一直是冲击地压预测领域研究的重点。目前,运用较多的有临界指标法、综合指数法、指标变化偏差法等,但这些方法都只注重数据的表面变化,忽视了隐藏及蕴含在监测时序中许多有助于识别冲击地压危险的特征和有用信息,模式识别方法通过提取监测时序中的时域、频域及小波域特征构成复合特征向量,以欧氏距离测度作为类内类间可分离性判据对特征向量进行压缩变换,运用Fisher准则构造冲击危险性识别的模式识别器,识别器用压缩后的特征向量进行训练学习,得到识别器的结构参数:权向量和分界值(阈值)后,即可成为性能稳定的冲击地压危险性预测的模式识别系统,运用该系统就能实现对其他样本的预测识别。通过对检验样本的预测表明,预测精度要优于临界指标法等传统预测方法。
How to predict rock burst according to electromagnetic emission observation data has been always the hot topic in this research field.The methods more often used now are critical value method,synthetically index method and index change error method,etc..But all these methods lie stress only on the superficial change of data and overlook a lot of features of rock burst and useful information which are concealed and hidden in observation time series.Pattern recognition extracts the feature value of time domainf,requency domain and wavelet domain in observation time series to form multi-feature vectors,use Euclidean distance measure as separable criterion between the same type and different types to compress and transform feature vectors,applies Fisher criterion to form pattern recognizer for dangeorous recognition.The pattern recognizer uses feature vectors being compressed to carry out training and study and gets the structure parameter:discriminate coefficient(weight value) and discriminate threshold.It has become the pattern recognition system with stable function.It is proved by prediction of test sample that predicting precision is prior to traditional predicting methods such as critical value method and so on.
How to predict rock burst according to electromagnetic emission observation data has been always the hot topic in this research field.The methods more often used now are critical value method,synthetically index method and index change error method,etc..But all these methods lie stress only on the superficial change of data and overlook a lot of features of rock burst and useful information which are concealed and hidden in observation time series.Pattern recognition extracts the feature value of time domainf,requency domain and wavelet domain in observation time series to form multi-feature vectors,use Euclidean distance measure as separable criterion between the same type and different types to compress and transform feature vectors,applies Fisher criterion to form pattern recognizer for dangeorous recognition.The pattern recognizer uses feature vectors being compressed to carry out training and study and gets the structure parameter:discriminate coefficient(weight value) and discriminate threshold.It has become the pattern recognition system with stable function.It is proved by prediction of test sample that predicting precision is prior to traditional predicting methods such as critical value method and so on.
引文
[1]王恩元,何学秋,聂百胜,等.电磁辐射法预测煤与瓦斯突出原理[J].中国矿业大学学报,2000,29(3):1-2.(Wang Enyuan,He Xueqiu,Nie Baisheng,et al.Principle of predicting coal and gas outburst using electromagnetic emission[J].Journal of China University of Mining and Technology,2000,29(3):1-2.(in Chinese))
[2]邹正喜,窦名林,徐方军.分维在电磁幅射技术预测冲击矿压中的应用[J].辽宁工程技术大学学报,2002,21(4):432-435.(Zou Zhengxi,Dou Minglin,Xu Fangjun.Study and practice of fractal dimension in prediction of rock burst by technology of electromagnetic emmision(EME)[J].Journal of Liaoning Technical University,2002,21(4):432-435.(in Chinese))
[3]温熙森,胡茑庆,邱静.模式识别与状态监控[M].长沙:国防科技大学出版社,1997.231-240.(Wen Xisen,Hu Yanqing,Qiu Jing.Pattern Recognition and State Monitor[M].Changsha:National University of Defense Technology Press,1997.231-240.(in Chinese))
[4]王群,倪宏伟,徐毅刚.利用复合特征进行模式识别的探雷研究[J].应用科学学报,2003,21(1):53-58.(Wang Qun,Ni Hongwei,Xu Yigang.A study on mine detection and identification through pattern recognition with the heid of multi-features[J].Journal of Applied Sciences,2003,21(1):53-58.(in Chinese))
[5]Van Kempen L.Singal processing and pattern recognition methods for radar apmine detection and identification[A].In:IEE the Second International Conference on the Detection of Abandoned Landmines(MD′98)[C].[s.l.]:[s.n.],1998.981-985.
[6]王群,何云龙,王春和,等.基于神经网络的探地雷达探雷研究[J].电波科学学报,2001,16(3):398-403.(Wang Qun,He Yunlong,Wang Chunhe,et al.Study on mine detection with GPR based on neural networks[J].Chinese Journal of Radio Science,2001,16(3):398-403.(in Chinese))
[7]边肇祺,张学工,阎平凡,等.模式识别[M].北京:清华大学出版社,2000.(Bian Zhaoqi,Zhang Xuegong,Yan Pingfan.Pattern Recognition[M].Beijing:Tsinghua University Press,2000.(in Chinese))
[8]蓝金辉,李虹,周兆英,等.目标地震动信号的特征提取及识别研究[J].振动与冲击,2001,20(4):42-44.(Lan Jinhui,Li Hong,Zhou Zhaoying,et al.Research on feature extraction of seismic signal for vehicle targets and neural networks recognition[J].Journal of Vibration and Shock,2001,20(4):42-44.(in Chinese))
[9]吴耀军,陶宝祺,史习智.基于小波包技术的复合材料损伤检测[J].复合材料学报,1997,14(4):95-100.(Wu Yaojun,Tao Baoqi,Shi Xizhi.Damage detection of the composite materials based on wavelet packets[J].Acta Materiae Compositae Sinica,1997,14(4):95-100.(in Chinese))
[10]吕金虎,陆君安,陈士华.混沌时间序列及其分析[M].武汉:武汉大学出版社,2002.(Lu Jinhu,Lu Jun′an,Chen Shihua.The Analysis of Chaotic Time Series and Its Application[M].Wuhan:Wuhan University Press,2002.(in Chinese))
[2]邹正喜,窦名林,徐方军.分维在电磁幅射技术预测冲击矿压中的应用[J].辽宁工程技术大学学报,2002,21(4):432-435.(Zou Zhengxi,Dou Minglin,Xu Fangjun.Study and practice of fractal dimension in prediction of rock burst by technology of electromagnetic emmision(EME)[J].Journal of Liaoning Technical University,2002,21(4):432-435.(in Chinese))
[3]温熙森,胡茑庆,邱静.模式识别与状态监控[M].长沙:国防科技大学出版社,1997.231-240.(Wen Xisen,Hu Yanqing,Qiu Jing.Pattern Recognition and State Monitor[M].Changsha:National University of Defense Technology Press,1997.231-240.(in Chinese))
[4]王群,倪宏伟,徐毅刚.利用复合特征进行模式识别的探雷研究[J].应用科学学报,2003,21(1):53-58.(Wang Qun,Ni Hongwei,Xu Yigang.A study on mine detection and identification through pattern recognition with the heid of multi-features[J].Journal of Applied Sciences,2003,21(1):53-58.(in Chinese))
[5]Van Kempen L.Singal processing and pattern recognition methods for radar apmine detection and identification[A].In:IEE the Second International Conference on the Detection of Abandoned Landmines(MD′98)[C].[s.l.]:[s.n.],1998.981-985.
[6]王群,何云龙,王春和,等.基于神经网络的探地雷达探雷研究[J].电波科学学报,2001,16(3):398-403.(Wang Qun,He Yunlong,Wang Chunhe,et al.Study on mine detection with GPR based on neural networks[J].Chinese Journal of Radio Science,2001,16(3):398-403.(in Chinese))
[7]边肇祺,张学工,阎平凡,等.模式识别[M].北京:清华大学出版社,2000.(Bian Zhaoqi,Zhang Xuegong,Yan Pingfan.Pattern Recognition[M].Beijing:Tsinghua University Press,2000.(in Chinese))
[8]蓝金辉,李虹,周兆英,等.目标地震动信号的特征提取及识别研究[J].振动与冲击,2001,20(4):42-44.(Lan Jinhui,Li Hong,Zhou Zhaoying,et al.Research on feature extraction of seismic signal for vehicle targets and neural networks recognition[J].Journal of Vibration and Shock,2001,20(4):42-44.(in Chinese))
[9]吴耀军,陶宝祺,史习智.基于小波包技术的复合材料损伤检测[J].复合材料学报,1997,14(4):95-100.(Wu Yaojun,Tao Baoqi,Shi Xizhi.Damage detection of the composite materials based on wavelet packets[J].Acta Materiae Compositae Sinica,1997,14(4):95-100.(in Chinese))
[10]吕金虎,陆君安,陈士华.混沌时间序列及其分析[M].武汉:武汉大学出版社,2002.(Lu Jinhu,Lu Jun′an,Chen Shihua.The Analysis of Chaotic Time Series and Its Application[M].Wuhan:Wuhan University Press,2002.(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