Real time identification of microseismic events based on ridge regression improved normative variable analysis
-
摘要: 微震事件判识是煤矿微震监测的基础。现有的微震监测技术大多基于单物理量变化规律而开发，在处理含有大量噪声和干扰信号的煤矿微震数据时易产生误判情况。针对该问题，基于岭回归算法改进规范变量分析（CVA）的损失函数，实现稀疏化建模，以提升模型泛化能力。采用岭回归改进CVA对多通道煤矿微震监测数据进行融合分析，进而实时判识复杂微震监测数据状态。采用模拟数据和实际煤矿微震监测数据对岭回归改进CVA进行实验验证。在基于模拟数据的实验中，随着噪声方差由5×10−6增大至5×10−2，岭回归改进CVA的判识准确率较CVA提升了0.6%～5.4%，误报率和漏报率之和较CVA下降4.8%～17.3%。在基于实际微震监测数据的实验中，岭回归改进CVA对20个通道的微震监测数据融合分析结果能够反映出微震信号处于波动状态，验证了该方法具备微震事件实时判识能力，平均判识准确率为97.14%，较CVA高2.39%，误报率与漏报率之和为31.06%，较CVA降低0.07%，错误率为2.86%，较CVA降低2.4%。Abstract: The identification of microseismic events is the foundation of microseismic monitoring in coal mines. Most existing microseismic monitoring technologies are developed based on the variation law of single physical quantities, which can easily lead to misjudgment when processing coal mine microseismic data containing a large amount of noise and interference signals. In order to solve the above problem, the loss function of canonical variate analysis (CVA) is optimized and improved using ridge regression algorithm to achieve sparse modeling and enhance the model's generalization capability. The ridge regression improved CVA is used for fusion analysis of multi-channel coal mine microseismic monitoring data, and then real-time identification of complex microseismic monitoring data status is achieved. The simulated data and actual coal mine microseismic monitoring data are used for experimental verification of ridge regression improved CVA. In experiments based on simulated data, as the noise variance increases from 5×10−6 to 5×10−2, the recognition accuracy of ridge regression improved CVA increases by 0.6%-5.4% compared to CVA, and the sum of false alarm rate and omission rate decreases by 4.8%-17.3% compared to CVA. In experiments based on actual microseismic monitoring data, ridge regression improved CVA can reflect the fluctuation of microseismic signals in the fusion analysis results of 20 channels of microseismic monitoring data. It verifies that this method has the capability to identify microseismic events in real-time. The average identification accuracy is 97.14%, which is 2.39% higher than CVA. The sum of false alarm rate and omission rate is 31.06%, which is 0.07% lower than CVA. The error rate is 2.86%, which is 2.4% lower than CVA.
-
图 4 微震监测数据融合分析统计结果
Figure 4. Statistics of fusion analysis of monitored microseismic data
表 1 微震数据实验结果
Table 1. Experiment results by microseismic data
% 测试集 CAC RFP+RFN RE 岭回归
改进CVACVA 岭回归
改进CVACVA 岭回归
改进CVACVA 1 97.95 95.64 2.0 5 4.36 2.05 4.36 2 98.08 94.65 1.9 2 5.35 1.92 5.35 3 99.07 94.89 0.9 3 5.11 0.93 5.11 4 96.10 94.76 63.4 49.33 3.90 5.24 5 93.95 93.00 53.80 58.94 6.05 7.00 6 97.70 95.53 64.27 63.66 2.30 4.47 平均值 97.14 94.75 31.06 31.13 2.86 5.26 
下载: 导出CSV
-
[1] 康红普. 我国煤矿巷道围岩控制技术发展70年及展望[J]. 岩石力学与工程学报,2021,40(1):1-30.KANG Hongpu. Seventy years development and prospects of strata control technologies for coal mine roadways in China[J]. Chinese Journal of Rock Mechanics and Engineering,2021,40(1):1-30. [2] 窦林名,李振雷,何学秋. 厚煤层综放开采的降载减冲原理及其应用研究[J]. 中国矿业大学学报,2018,47(2):221-230.DOU Linming,LI Zhenlei,HE Xueqiu. Principle of rockburst control by weakening static and dynamic loading using top-coal caving in the mining of thick coal seams[J]. Journal of China University of Mining & Technology,2018,47(2):221-230. [3] CAO Anye,DOU Linming,WANG Changbin,et al. Microseismic precursory characteristics of rock burst hazard in mining areas near a large residual coal pillar:a case study from Xuzhuang Coal Mine,Xuzhou,China[J]. Rock Mechanics and Rock Engineering,2016,49(11):1-16. [4] 程健,杨凌凯,王全魁,等. 基于半监督过采样非平衡学习的矿山微震信号识别[J]. 煤炭科学技术,2018,46(2):213-218,202.CHENG Jian,YANG Lingkai,WANG Quankui,et al. Mine microseismic signal recognition based on semi-supervised over-sampling imbalanced learning[J]. Coal Science and Technology,2018,46(2):213-218,202. [5] 程健,杨凌凯,崔宁,等. 基于流形嵌入过采样的非平衡数据分类方法[J]. 中国矿业大学学报,2018,47(6):1325-1333.CHENG Jian,YANG Lingkai,CUI Ning,et al. A novel pattern classification method for imbalanced data set based on manifold embedded over-sampling[J]. Journal of China University of Mining & Technology,2018,47(6):1325-1333. [6] HE Jiang,DOU Linming,GONG Siyuan,et al. Rock burst assessment and prediction by dynamic and static stress analysis based on micro-seismic monitoring[J]. International Journal of Rock Mechanics and Mining Sciences,2017,93:46-53. doi: 10.1016/j.ijrmms.2017.01.005 [7] 魏立科,姜德义,王翀,等. 煤矿冲击地压灾害风险监察智能分析系统关键技术架构[J]. 煤炭学报,2021,46(增刊1):63-73.WEI Like,JIANG Deyi,WANG Chong,et al. Key technological architecture of the intelligent monitoring-analysis system for coal mine rockburst risk supervision[J]. Journal of China Coal Society,2021,46(S1):63-73. [8] WANG Shuren,LI Chunyang,YAN Wenfa,et al. Multiple indicators prediction method of rock burst based on microseismic monitoring technology[J]. Arabian Journal of Geosciences,2017,10(6). DOI: 10.1007/s12517-017-2946-8. [9] 姜耀东,赵毅鑫. 我国煤矿冲击地压的研究现状:机制、预警与控制[J]. 岩石力学与工程学报,2015,34(11):2188-2204.JIANG Yaodong,ZHAO Yixin. State of the art:investigation on mechanism,forecast and control of coal bumps in China[J]. Chinese Journal of Rock Mechanics and Engineering,2015,34(11):2188-2204. [10] YU J J,BENTLY D E,GOLDMAN P,et al. Rolling element bearing defect detection and diagnostics using displacement transducers[J]. Journal of Engineering for Gas Turbines and Power,2002,124(3):517-527. doi: 10.1115/1.1456092 [11] BOURBON R,NGUEVEU S U,ROBOAM X,et al. Energy management optimization of a smart wind power plant comparing heuristic and linear programming methods[J]. Mathematics and Computers in Simulation,2019,158:418-431. doi: 10.1016/j.matcom.2018.09.022 [12] KAMRANI H,ZOLGHADREASLI A,MARKOPOULOS P,et al. Reduced-rank L1-norm principal-component analysis with performance guarantees[J]. IEEE Transactions on Signal Processing,2021,69:240-255. doi: 10.1109/TSP.2020.3039599 [13] PENG Kaixiang,ZHANG Kai,YOU Bo,et al. Quality-relevant fault monitoring based on efficient projection to latent structures with application to hot strip mill process[J]. IET Control Theory and Applications,2015,9(7):1135-1145. doi: 10.1049/iet-cta.2014.0732 [14] JIANG Benben,HUANG Dexian,ZHU Xiaoxiang,et al. Canonical variate analysis-based contributions for fault identification[J]. Journal of Process Control,2015,26:17-25. doi: 10.1016/j.jprocont.2014.12.001 [15] EVAN L R,RICHARD D B. Model reduction for the robustness margin computation of large scale uncertain systems[J]. Computers and Chemical Engineering,1998,22(7):913-926. [16] BRANDOLINI-BUNLON M,MÉLANIE P,GAUDREAU P,et al. Multi-block PLS discriminant analysis for the joint analysis of metabolomic and epidemiological data[J]. Metabolomics,2019,15(10):1-9. [17] LUO Lijia,PENG Xin,TONG Chudong. A multigroup framework for fault detection and diagnosis in large-scale multivariate systems[J]. Journal of Process Control,2021,100:65-79. doi: 10.1016/j.jprocont.2021.02.007 [18] HUANG Linzhe,CAO Yuping,TIAN Xuemin,et al. A nonlinear quality-relevant process monitoring method with Kernel input-output canonical variate analysis[J]. IFAC PapersOnline,2015,48(8):611-616. doi: 10.1016/j.ifacol.2015.09.035 [19] WANG Xuemei,WU Ping. Nonlinear dynamic process monitoring based on ensemble kernel canonical variate analysis and Bayesian inference[J]. ACS Omega,2022,7(22):18904-18921. doi: 10.1021/acsomega.2c01892 [20] CAI Jia,TANG Yi. A new randomized Kaczmarz based kernel canonical correlation analysis algorithm with applications to information retrieval[J]. Neural Networks,2018,98:178-191. doi: 10.1016/j.neunet.2017.11.013 [21] WITTEN D M,TIBSHIRANI R J. Extensions of sparse canonical correlation analysis with applications to genomic data[J]. Statistical Applications in Genetics and Molecular Biology,2009,8(1). DOI: 10.2202/1544-6115.1470. [22] LU Qiugang,JIANG Benben,GOPALUNI R B,et al. Sparse canonical variate analysis approach for process monitoring[J]. Journal of Process Control,2018,71:90-102. doi: 10.1016/j.jprocont.2018.09.009 [23] ZHENG Jiale,ZHAO Chunhui. Enhanced canonical variate analysis with slow feature for dynamic process status analytics[J]. Journal of Process Control,2020,95:10-31. doi: 10.1016/j.jprocont.2020.09.005 [24] SUN Tingkai,CHEN Songcan. Locality preserving CCA with applications to data visualization and pose estimation[J]. Image and Vision Computing,2006,25(5):531-543. [25] JIANG Benben,RICHARD D B. Fault detection of process correlation structure using canonical variate analysis-based correlation features[J]. Journal of Process Control,2017,58:131-138. doi: 10.1016/j.jprocont.2017.09.003 -
点击查看大图
图(4) / 表(1)
计量
- 文章访问数: 103
- HTML全文浏览量: 50
- PDF下载量: 11
- 被引次数: 0
