(1. College of Information Science and Engineering，Shandong University of Science and Technology，Qingdao，Shandong 266590，China；2. State Key Laboratory Breeding Base for Mining Disaster Prevention and Control，Shandong University of Science and Technology，Qingdao，Shandong 266590，China)
Abstract：A new model and method of identification precursor information was presented based on the monitoring of ground sound to provide an early warning of rockburst. Using the actual monitored data of ground sound as the training samples，eleven multidimensional feature vectors characterizing the rockburst hazard precursors were obtained from the ground sound signals in a fixed time window by the method of time-frequency domain feature extraction. A new support vector machine(SVM) learning method was applied to solve the training problems with imbalanced data sets in the application of large-scale engineering practice and to improve the classification accuracy and the training speed of SVM. Adopting the measured data as the learning samples on SVMs for training and establishing the appropriate precursor identification model，the accuracy reached 93.87%. Experiments show that this method is effective and reliable，and which is capable of fast sample identification meeting the online monitoring requirements.
[1] 齐庆新，窦林名. 冲击地压理论与技术[M]. 徐州：中国矿业大学出版社，2008：32–38.(QI Qingxin，DOU Linming. Theory and technology of rock burst[J]. Xuzhou： China University of Mining and Technology Press，2008：32–38.(in Chinese))
[2] 窦林名，何学秋. 冲击地压防治理论与技术[M]. 徐州：中国矿业大学出版社，2001：1–109.(DOU Linming，HE Xueqiu. Rock burst control theory and technology[M]. Xuzhou：China University of Mining and Technology Press，2001：1–109.(in Chinese))
[3] 钱鸣高，石平五，许家林. 矿山压力与岩层控制[M]. 徐州：中国矿业大学出版社，2010：294–330.(QIAN Minggao，SHI Pingwu，XU Jialin. Mining pressure and strata control[M]. Xuzhou：China University of Mining and Technology Press，2010：294–330.(in Chinese))
[4] 潘俊锋，蓝 航，毛德兵，等. 冲击地压危险源层次化辨识理论研究[J]. 岩石力学与工程学报，2011，30(增1)：2 843–2 849.(PAN Junfeng，LAN Hang，MAO Debing，et al. Study of hierarchical recognition theory of hazard source of rockburst[J]. Chinese Journal of Rock Mechanics and Engineering，2011，30(Supp.1)：2 843–2 849.(in Chinese))
[5] 姜福兴，苗小虎，王存文，等. 构造控制型冲击地压的微地震监测预警研究与实践[J]. 煤炭学报，2010，35(6)：900–903.(JIANG Fuxing，MIAO Xiaohu，WANG Cunwen，et al. Predicting research and practice of tectonic-controlled coal burst by microseismic monitoring[J]. Journal of China Coal Society，2010，35(6)：900–903.(in Chinese))
[6] 夏永学，康立军，齐庆新，等. 基于微震监测的5个指标及其在冲击地压预测中的应用[J]. 煤炭学报，2010，35(12)：2 011–2 016. (XIA Yongxue，KANG Lijun，QI Qingxin，et al. Five indices of microseismic and their application in rock burst forecastion[J]. Journal of China Coal Society，2010，35(12)：2 011–2 016.(in Chinese))
[7] 王云海，何学秋，窦林名. 煤样变形破坏声电效应的演化规律及机理研究[J]. 地球物理学报，2007，50(5)：1 569–1 575.(WANG Yunhai，HE Xueqiu，DOU Linming. Study on regularity and mechanism of acoustic emission and electromagnetic emission during fracture process of coal samples[J]. Chinese Journal of Geophysics，2007，50(5)：1 569–1 575.(in Chinese))
[8] 陆菜平，窦林名，郭晓强，等. 顶板岩层破断诱发矿震的频谱特征[J].
岩石力学与工程学报，2010，29(5)：1 017–1 022.(LU Caiping，DOU Linming，GUO Xiaoqiang，et al. Frequency-spectrum characters of microseismic signals induced by roof stratum fracture[J]. Chinese Journal of Rock Mechanics and Engineering，2010，29(5)：1 017– 1 022.(in Chinese))
[9] 窦林名，王云海，何学秋，等. 煤样变形破坏峰值前后电磁辐射特征研究[J]. 岩石力学与工程学报，2007，26(5)：908–914.(DOU Linming，WANG Yunhai，HE Xuqiu，et al. Study on electromagnetic emission characteristic for coal sample deformation and failure during pre- and post-peaking phases[J]. Chinese Journal of Rock Mechanics and Engineering，2007，26(5)：908–914.(in Chinese))
[10] HE M C，MIAO J L，FENG J L. Rock burst process of limestone and its acoustic emission characteristics under true-triaxial unloading conditions[J]. International Journal of Rock Mechanics and Mining Sciences，2010，47(2)：286–298.
[11] EL-WARDANY T I，GAO D，ELBESTAWI M A. Tool condition monitoring in drilling using vibration signature analysis[J]. International Journal of Machine Tools and Manufacture，1996，36(6)：687–711.
[12] 朱权洁，姜福兴，于正兴，等. 爆破震动与岩石破裂微震信号能量分布特征研究[J]. 岩石力学与工程学报，2012，31(4)：723–730. (ZHU Quanjie，JIANG Fuxing，YU Zhengxing，et al. Study on energy distribution characters about blasting vibration and rock fracture microseismic signal[J]. Chinese Journal of Rock Mechanics and Engineering，2012，31(4)：723–730.(in Chinese))
[13] VLADIMIR V. The nature of statistical learning theory[M]. New York：Wiley，1998：1–21.
[14] VLADIMIR V，STEVEN E G，ALEX J S. Support vector method for function approximation regression estimation and signal processing[C]// Neural Information Processing Systems-NIPS. [S.l.]：[s.n.]，1996： 281–287.
[15] 刘永斌. 基于非线性信号分析的滚动轴承状态监测诊断研究[博士学位论文][D]. 合肥：中国科学技术大学，2011.(LIU Yongbin. Nonlinear signal analysis for rolling bearing condition manitaring and fault diagnosis[Ph. D. Thesis][D]. Hefei：University of Science and Technology of China，2011.(in Chinese))
[16] ZHANG Y. Enhanced statistical analysis of nonlinear processes using KPCA，KICA and SVM[J]. Chemical Engineering Science，2009，64(5)：801–811.
[17] LIU Y G，YOU Z H，CAO L P. A novel and quick SVM-based multi- class classifier[J]. Pattern Recognition，2006，39(11)：2 258–2 264.
[18] 方瑞明. 支持向量机理论及其应用分析[M]. 北京：中国电力出版社，2007：10–15.(FANG Ruiming. Theory and application analysis of support vector machine[M]. Beijing：China Electric Power Press，2007：10–15.(in Chinese))
[19] KUBAT M，MATWIN S. Addressing the curse of unbalanced training sets：one-sided selection[C]// Proceedings of the 14th International Conference on Machine Learning. [S.l.]：[s.n.]，1997：217–225.
[20] 杨智明. 面向不平衡数据的支持向量机分类方法研究[博士学位论文][D]. 哈尔滨：哈尔滨工业大学，2009.(YANG Zhiming. Research on SVM classification method for imbalanced datasets[Ph. D. Thesis][D]. Harbin：Harbin Institute of Technology，2009.(in Chinese))
[21] 徐启华，耿 帅，师 军. 基于大规模训练集SVM的发动机故障诊断[J]. 航空动力学报，2011，26(12)：2 841–2 848.(XU Qihua，GENG Shuai，SHI Jun. Fault diagnosis method for aero-engine based on SVM with large-scale training set[J]. Journal of Aerospace Power，2011，26(12)：2 841–2 848.(in Chinese))
[22] 姜万录，吴胜强. 基于SVM和证据理论的多数据融合故障诊断方法[J]. 仪器仪表学报，2010，31(8)：1 738–1 743.(JIANG Wanlu，WU Shengqiang. Multi-data fusion fault diagnosismethod based on SVM and evidence theory[J]. Chinese Journal of Scientific Instrument，2010，31(8)：1 738–1 743.(in Chinese))
2014, Vol. 33 
