基于Mel频谱和LSTM-DCNN的矿山微震信号混合识别模型

doi:10.12068/j.issn.1005-3026.2023.10.015

东北大学学报（自然科学版） ›› 2023, Vol. 44 ›› Issue (10): 1481-1489.DOI: 10.12068/j.issn.1005-3026.2023.10.015

基于Mel频谱和LSTM-DCNN的矿山微震信号混合识别模型

赵永，焦诗卉，赵乾百

(东北大学资源与土木工程学院，辽宁沈阳110819)

发布日期:2023-10-27
通讯作者: 赵永
作者简介:赵永(1991-)，男，山东临沂人，东北大学讲师，博士.
基金资助:
国家自然科学基金资助项目(52004052)；中央高校基本科研业务费专项资金资助项目(N2101027).

Hybrid Recognition Model of Microseismic Signals for Mining Based on Mel Spectrum and LSTM-DCNN

ZHAO Yong， JIAO Shi-hui， ZHAO Qian-bai

School of Resources & Civil Engineering， Northeastern University， Shenyang 110819， China.

Published:2023-10-27
Contact: JIAO Shi-hui
About author:-
Supported by:
-

摘要/Abstract

摘要： 微震监测是保证矿山安全生产的有效手段，微震信号识别精度直接影响着微震事件的判定及分析结果.鉴于此，以夏甸金矿微震监测数据作为样本，建立了基于Mel频谱和长短时记忆(long short-term memory，LSTM)神经网络与深度卷积神经网络(deep convolutional neural networks，DCNN)混合的矿山微震信号识别模型.首先对监测信号进行预处理，利用Mel时频谱降低干扰频段的权重并减小样本尺寸.然后利用LSTM和DCNN模型分别提取信号的时间特征及空间特征.通过多种模型的对比分析，结果表明本文提出的Mel-LSTM-DCNN混合模型对微震信号识别准确率最高.该模型为矿山准确识别微震信号提供参考.

关键词: 神经网络；深度学习；信号识别；微震监测；Mel频谱

Abstract: Microseismic monitoring can ensure safe production in mines， and the accuracy of microseismic signal recognition directly affects the analysis of microseismic events. The microseismic monitoring data of Xiadian Gold Mine were used as samples to establish a mining microseismic signal recognition model based on Mel spectrum and a combination of long short-term memory(LSTM)and deep convolutional neural networks(DCNN). Firstly， the monitoring signal was preprocessed， and the Mel time spectrum was used to reduce the weight of the interference frequency band and sample size. Then， LSTM and DCNN models were employed to extract the temporal and spatial features of the signal， respectively. Through comparative analysis of multiple models， the results showed that the proposed Mel-LSTM-DCNN hybrid model has the highest accuracy in identifying microseismic signals. The model proposed provides reference for accurately identifying microseismic signals in mines.

Key words: neural network; deep learning; signal identification; microseismic monitoring; Mel spectrum

中图分类号:

TD76

赵永，焦诗卉，赵乾百. 基于Mel频谱和LSTM-DCNN的矿山微震信号混合识别模型[J]. 东北大学学报（自然科学版）, 2023, 44(10): 1481-1489.

ZHAO Yong， JIAO Shi-hui， ZHAO Qian-bai. Hybrid Recognition Model of Microseismic Signals for Mining Based on Mel Spectrum and LSTM-DCNN[J]. Journal of Northeastern University(Natural Science), 2023, 44(10): 1481-1489.

参考文献

[1]Zhang C，Jin G H，Liu C，et al.Prediction of rockbursts in a typical island working face of a coal mine through microseismic monitoring technology［J］.Tunnelling and Underground Space Technology，2021，113:103972.
[2]Xue R X，Liang Z Z，Xu N W.Rockburst prediction and analysis of activity characteristics within surrounding rock based on microseismic monitoring and numerical simulation［J］.International Journal of Rock Mechanics and Mining Sciences，2021，142:104750.
[3]刘建坡，武峰，王人，等.基于模糊综合评价的深部巷道破坏定量风险评估［J］.东北大学学报(自然科学版)，2022，43(5):733-739.(Liu Jian-po，Wu Feng，Wang Ren，et al.Quantitative risk assessment for deep tunnel failure based on fuzzy comprehensive evaluation［J］.Journal of Northeastern University(Natural Science)，2022，43(5):733-739.)
[4]Wang J C，Chen G Q，Xiao Y X，et al.Effect of structural planes on rock burst distribution:case study of a deep tunnel in Southwest China［J］.Engineering Geology，2021，292(4):106250.
[5]Dong L L，Yang Y，Qian B，et al.Deformation analysis of large-scale rock slopes considering the effect of microseismic events［J］.Applied Sciences，2019，9(16):3409.
[6]Gu J X，Wang Z H，Kuen J，et al.Recent advances in convolutional neural networks［J］.Pattern Recognition，2018，77:354-377.
[7]Krizhevsky A，Sutskever I，Hinton G E.Imagenet classification with deep convolutional neural networks［J］.Communications of the ACM，2017，60(6):84-90.
[8]郭峰.基于CNN+LSTM的运动想象脑电四分类研究［D］.广州:广东工业大学，2022.(Guo Feng.Study on four classification of motor imagery EEG based on CNN+LSTM［D］.Guangzhou:Guangdong University of Technology，2022.)
[9]Bengio Y，Simard P，Frasconi P.Learning long-term dependencies with gradient descent is difficult［J］.IEEE Transactions on Neural Networks，1994，5(2):157-166.
[10]Hochreiter S，Schmidhuber J.Long short-term memory［J］.Neural Computation，1997，9(8):1735-1780.
[11]Hsueh Y L，Yang Y R.A short-term traffic speed prediction model based on LSTM networks［J］.International Journal of Intelligent Transportation Systems Research，2021，19(3):510-524.
[12]Dudek G，Peka P，Smyl S.A hybrid residual dilated LSTM and exponential smoothing model for mid-term electric load forecasting［J］.IEEE Transactions on Neural Networks and Learning Systems，2021，33(7):2879-2891.
[13]Abduh Z，Nehary E A，Wahed M A，et al.Classification of heart sounds using fractional Fourier transform based Mel-frequency spectral coefficients and traditional classifiers［J］.Biomedical Signal Processing and Control，2020，57:101788.
[14]刘云鹏，罗世豪，王博闻，等.基于Mel时频谱-卷积神经网络的变压器铁芯夹件松动故障声纹模式识别［J］.华北电力大学学报(自然科学版)，2020，47(6):52-60，67.(Liu Yun-peng，Luo Shi-hao，Wang Bo-wen，et al.Voiceprint recognition of transformer core clamp looseness fault by Mel-spectrum and convolutional neural network［J］.Journal of North China Electric Power University(Natural Science Edition)，2020，47(6):52-60，67.)
[15]Mei Q P，Gül M，Boay M.Indirect health monitoring of bridges using Mel-frequency cepstral coefficients and principal component analysis［J］.Mechanical Systems and Signal Processing，2019，119:523-546.
[16]周飞燕，金林鹏，董军.卷积神经网络研究综述［J］.计算机学报，2017，40(6):1229-1251.(Zhou Fei-yan，Jin Lin-peng，Dong Jun.Review of convolutional neural network ［J］.Journal of Computer Science，2017，40(6):1229-1251.)(上接第1473页)
[10]Shi Y P，Xia Y M，Zhang Y M，et al.Intelligent identification for working-cycle stages of excavator based on main pump pressure ［J］.Automation in Construction，2020，109:102991.
[11]Shi Y P，Xia Y M，Luo L L，et al.Working stage identification of excavators based on control signals of operating handles ［J］.Automation in Construction，2021，130:103873.
[12]He K M，Sun J.Convolutional neural networks at constrained time cost［C］// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Boston:IEEE，2015:5353-5360.
[13]He K M，Zhang X Y，Ren S Q，et al.Deep residual learning for image recognition［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Seattle，2016:770-778.
[14]Zhuang F Z，Qi Z Y，Duan K Y，et al.A comprehensive survey on transfer learning ［J］.Proceedings of the IEEE，2021，109(1):43-76.
[15]Yu Y，Si X S，Hu C H，et al.A review of recurrent neural networks:LSTM cells and network architectures ［J］.Neural Computation，2019，31(7):1235-1270.
[16]Zhao Z，Chen W H，Wu X M，et al.LSTM network:a deep learning approach for short-term traffic forecast ［J］.IET Intelligent Transport Systems，2017，11(2):68-75.

基于Mel频谱和LSTM-DCNN的矿山微震信号混合识别模型

Hybrid Recognition Model of Microseismic Signals for Mining Based on Mel Spectrum and LSTM-DCNN

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	徐帅，侯朋远，梁瑞余，杜永亮. 高湿多尘采空区三维激光探测数据误差分析与修正[J]. 东北大学学报:自然科学版, 2019, 40(9): 1330-1336.
[2]	梁力，刘奇，李明. 基于变权综合层次分析法的尾矿库溃坝风险模型[J]. 东北大学学报:自然科学版, 2017, 38(12): 1790-1794.
[3]	王运森，李元辉，徐帅. 巷道收敛监测三维动态可视化系统开发[J]. 东北大学学报:自然科学版, 2017, 38(1): 116-120.
[4]	黄俊杰，罗周全，秦亚光，张文芬. 复杂采空区三维散乱点建模技术研究及应用[J]. 东北大学学报:自然科学版, 2016, 37(12): 1784-1788.
[5]	秦亚光，罗周全，汪伟，郑开欢. 采空区三维激光扫描点云数据处理技术[J]. 东北大学学报:自然科学版, 2016, 37(11): 1635-1639.
[6]	秦亚光，罗周全，周吉明，汪伟. 采空区三维实体模型的交互接口技术[J]. 东北大学学报:自然科学版, 2016, 37(10): 1474-1479.
[7]	张鹏海，杨天鸿，赵永川，夏冬. 岩石破坏过程中波速变化特征[J]. 东北大学学报:自然科学版, 2015, 36(1): 134-137.
[8]	熊立新，罗周全，罗贞焱，谢承煜. 深部复杂环境下采空区激光扫描异常点云数据修正[J]. 东北大学学报:自然科学版, 2014, 35(3): 438-443.
[9]	李元辉，陈治洋，徐世达. 波速赋值范围对PSO定位算法精度的影响[J]. 东北大学学报（自然科学版）, 2021, 42(4): 561-566.
[10]	赵永，古旭升，王述红，高煬. 不同岩性岩石单轴压缩破坏共性前兆特征[J]. 东北大学学报（自然科学版）, 2023, 44(9): 1309-1317.