基于压缩感知的设备多源信息传输与分类算法

doi:10.11959/j.issn.1000-436x.2020040

通信学报 ›› 2020, Vol. 41 ›› Issue (2): 13-24.doi: 10.11959/j.issn.1000-436x.2020040

基于压缩感知的设备多源信息传输与分类算法

赵小虎^1,²,王刚^1,²(),宋泊明³,于嘉成¹

¹ 矿山互联网应用技术国家地方联合工程实验室，徐州江苏 221000
² 中国矿业大学物联网（感知矿山）研究中心，徐州江苏 221000
³ 西澳大学电气电子与计算机工程系，珀斯 6009

修回日期:2019-12-12 出版日期:2020-02-25 发布日期:2020-03-09
作者简介:赵小虎（1976- ），男，江苏徐州人，博士，中国矿业大学教授、博士生导师，主要研究方向为物联网、机器学习|王刚（1977- ），男，江苏徐州人，博士，中国矿业大学副教授、硕士生导师，主要研究方向为机器学习、设备故障诊断、压缩感知|宋泊明（1989- ），男，江苏徐州人，西澳大学博士生，主要研究方向为机器学习、基于微波信号的雨衰估计、层析重构算法等|于嘉成（1994- ），男，河北沧州人，中国矿业大学硕士生，主要研究方向为机器学习、设备故障诊断等
基金资助:
国家重点研发计划基金资助项目(2017YFC0804404)

Multi-source information transmission and classification algorithm for equipment based on compressed sensing

Xiaohu ZHAO^1,²,Gang WANG^1,²(),Boming SONG³,Jiacheng YU¹

¹ The National Joint Engineering Laboratory of Internet Applied Technology of Mines,Xuzhou 221000,China
² IoT Perception Mine Research Center,China University of Mining and Technology,Xuzhou 221000,China
³ Department of Electrical,Electronic and Computing Engineering,The University of Western Australia,Perth 6009,Australia

Revised:2019-12-12 Online:2020-02-25 Published:2020-03-09
Supported by:
The National Key Research and Development Project of China(2017YFC0804404)

摘要/Abstract

摘要：

针对选煤厂设备种类繁多、监测点分散的特点，提出了一种基于压缩感知的设备多源信息无线传输与分类算法。通过构建一种多跳信息传输模型，将信息传输问题转换为多路测量信号的压缩感知问题，将测量矩阵获取问题转化为多跳信息传输模型的路由问题。针对所获得的测量矩阵存在较大相干性、影响信号重构效果问题，将随机路由的思想引入路由构建当中，提出了一种随机动态自组织路由算法。为了解决重构后的信号时域特征难以对故障类型进行精确分类的问题，针对重构信号，引入了一种新的时域特征——振动信号的全变分，并通过补偿距离评估算法（CDET）验证了引入指标的优越性。通过选煤厂实测数据分析表明，所提多源信息传输与分类算法在提高监测数据实时传输效率情况下，能够有效提高故障识别精度。

关键词: 压缩感知, 多跳网络, 随机路由, 全变分, 故障分类

Abstract:

Aiming at the characteristics of various types of equipment in coal preparation plant and the dispersion of monitoring points,a multi-source information wireless transmission and classification algorithm for equipment based on compressed sensing was proposed.By constructing a multi-hop information transmission model,the information transmission problem was transformed into the compressed sensing problem of multi-path measurement signals,thereby the measurement matrix acquisition was transformed into the routing problem of the multi-hop information transmission model.Aiming at the large coherence of the obtained measurement matrix and affecting the signal reconstruction effect,the idea of random routing was introduced into the routing construction,and a random dynamic self-organizing routing algorithm was proposed.In order to solve the problem that the time domain features of the reconstructed signal were difficult to accurately classify the fault type,a new time domain feature,the total variation (TV) of the vibration signal,was introduced for the reconstructed signal,and the compensation distance estimation algorithm was adopted to verify the superiority of the introduction of indicators.The analysis of the measured data of the coal preparation plant shows that the proposed multi-source information transmission and classification algorithm can effectively improve the fault recognition accuracy under the condition of improving the real-time transmission efficiency of the monitoring data.

Key words: compressed sensing, multi-hop network, random routing, total variation, fault classification

中图分类号:

TP18

赵小虎,王刚,宋泊明,于嘉成. 基于压缩感知的设备多源信息传输与分类算法[J]. 通信学报, 2020, 41(2): 13-24.

Xiaohu ZHAO,Gang WANG,Boming SONG,Jiacheng YU. Multi-source information transmission and classification algorithm for equipment based on compressed sensing[J]. Journal on Communications, 2020, 41(2): 13-24.

图/表 17

图1

图2

表1

振动信号的10个时域特征及其表达式"

序号	特征名称	计算式
1	均值	$\sqrt{\frac{1}{N} \sum_{i = 1}^{N} x_{i}}$
2	标准差	$\sqrt{\frac{1}{N} \sum_{i = 1}^{N} {(x_{i} - μ_{x})}^{2}}$
3	均方根值	$\sqrt{\frac{1}{N} \sum_{i = 1}^{N} {(x_{i})}^{2}}$
4	歪度指标	$\frac{\sum_{i = 1}^{N} {(x_{i} - μ_{x})}^{3}}{N σ_{x}^{3}}$
5	峭度指标	$\frac{\sum_{i = 1}^{N} {(x_{i} - μ_{x})}^{4}}{N σ_{x}^{4}}$
6	波形指标	$\frac{\sqrt{\frac{1}{N} \sum_{i = 1}^{N} {(x_{i})}^{2}}}{\frac{1}{N} \sum_{i = 1}^{N} \| x_{i} \|}$
7	裕度指标	$\frac{\max \| x_{i} \|}{{(\frac{1}{N} \sum_{i = 1}^{N} \sqrt{\| x_{i} \|})}^{2}}$
8	脉冲指标	$\frac{\max \| x_{i} \|}{\frac{1}{N} \sum_{i = 1}^{N} \| x_{i} \|}$
9	峰值指标	$\frac{\max \| x_{i} \|}{\sqrt{\frac{1}{N} \sum_{i = 1}^{N} {(x_{i})}^{2}}}$
10	全变分	$\sum_{i = 1}^{N} \| x_{i + 1} - x_{i} \|$

表1

图3

图4

图5

图6

图7

图8

图9

图10

表2

图11

图12

表3

图14

图13

参考文献 24

[1]	温江涛, 闫常弘, 孙洁娣 ,等. 基于压缩采集与深度学习的轴承故障诊断方法[J]. 仪器仪表学报, 2018,39(1): 171-179.
	WEN J T , YAN C H , SUN J D ,et al. Bearing fault diagnosis method based on compressed acquisition and deep learning[J]. Chinese Journal of Scientific Instrument, 2018,39(1): 171-179.
[2]	FAZEL F , FAZEL M , STOJANOVIC M . Random access compressed sensing for energy-efficient underwater sensor networks[J]. IEEE Journal on Selected Areas in Communications, 2011,29(8): 1660-1670.
[3]	田子建, 贺方圆 . 一种基于分布式压缩感知的矿井目标指纹数据库建立方法[J]. 电子与信息学报, 2019,41(10): 2450-2456.
	TIAN Z J , HE F Y . Method of establishing mine target fingerprint database based on distributed compressed sensing[J]. Journal of Electronics ＆ Information Technology, 2019,41(10): 2450-2456.
[4]	WANG G , ZHAO Z , NING Y . Design of compressed sensing algorithm for coal mine IoT moving measurement data based on a multi-hop network and total variation[J]. Sensors, 2018,18(6): 17-32.
[5]	WANG Z , LIU X . An QoS routing protocol based on ant colony algorithm in WSN[J]. Chinese Journal of Sensors ＆ Actuators, 2011,2(11): 1007-1009.
[6]	兰巨龙, 张学帅, 胡宇翔 ,等. 基于深度强化学习的软件定义网络QoS优化[J]. 通信学报, 2019,40(12): 60-67.
	LAN J L , ZHANG X S , HU Y X ,et al. Software-defined networking QoS optimization based on deep reinforcement learning[J]. Journal on Communications, 2019,40(12): 60-67.
[7]	GELENBE E , NGAI E . Adaptive random re-routing for differentiated QoS in sensor networks[J]. The Computer Journal, 2018,53(7): 1052-1061.
[8]	YANG B S , HAN T , AN J L . ART-Kohonen neural network for fault diagnosis of rotating machinery[J]. Mechanical Systems ＆ Signal Processing, 2004,18(3): 645-657.
[9]	LEI Y , HE Z , ZI Y ,et al. New clustering algorithm-based fault diagnosis using compensation distance evaluation technique[J]. Mechanical Systems ＆ Signal Processing, 2008,22(2): 419-435.
[10]	王前, 王刚, 蒋晗晗 ,等. 基于MFCC与CDET的滚动轴承故障诊断方法研究[J]. 控制工程, 2019,26(9): 1682-1686.
	WANG Q , WANG G , JIANG H H ,et al. Study on fault diagnosis of rolling bearing based on MFCC and CDET[J]. Control Engineering of China, 2019,26(9): 1682-1686.
[11]	LONG Y , LI Z D , XIE M H ,et al. Neural network based preprocessing and dictionary methods for switched current circuit fault diagnosis[J]. Journal of Computational ＆ Theoretical Nanoscience, 2017,14(4): 1914-1924.
[12]	GUO S , YANG T , GAO W ,et al. A novel fault diagnosis method for rotating machinery based on a convolutional neural network[J]. Sensors, 2018,18(5): 14-29.
[13]	YAO C Y , LAI B W ,et al. Fault diagnosis method based on med-vmd and optimized SVM for rolling bearings[J]. China Mechanical Engineering, 2017,28(24): 3001-3012.
[14]	WIDODO A , YANG B . Support vector machine in machine condition monitoring and fault diagnosis[J]. Mechanical Systems and Signal Processing, 2007,21( 6): 2560-2574.
[15]	HAYASHI K , NAGAHARA M , TANAKA T . A user’s guide to compressed sensing for communications systems[J]. IEICE Transactions on Communications, 2013,96(3): 685-712.
[16]	HAUPT J , BAJWA W U , RABBAT M ,et al. Compressed sensing for networked data[J]. IEEE Signal Processing Magazine, 2008,25(2): 92-101.
[17]	LI Q , SHI J , LI Z ,et al. Acoustic sound speed profile inversion based on orthogonal matching pursuit[J]. Acta Oceanologica Sinica, 2019,38(11): 149-157.
[18]	YANG B Y , LIU R N , CHEN X F . Sparse time-frequency representation for incipient fault diagnosis of wind turbine drive train[J]. IEEE Transactions on Instrumentation ＆ Measurement, 2018,67(11): 2616-2627.
[19]	BO L , YI S , RAJAN S ,et al. Theoretical results for sparse signal recovery with noises using generalized OMP algorithm[J]. Signal Processing, 2015,117(C): 270-278.
[20]	DO T T , GAN L , NGUYEN N ,et al. Sparsity adaptive matching pursuit algorithm for practical compressed sensing[C]// Asilomar Conference on Signals,Systems and Computers. IEEE, 2008: 581-587.
[21]	ZHANG Y , SUN G . Stagewise arithmetic orthogonal matching pursuit[J]. International Journal of Wireless Information Networks, 2018,25(2): 221-228.
[22]	DAI W , MILENKOVIC O . Subspace pursuit for compressive sensing signal reconstruction[J]. IEEE Transactions on Information Theory, 2009,55(5): 2230-2249.
[23]	LEI Y , HE Z , ZI Y ,et al. New clustering algorithm-based fault diagnosis using compensation distance evaluation technique[J]. Mechanical Systems and Signal Processing, 2008,22(2): 419-435.
[24]	LU S , WANG X , HE Q ,et al. Fault diagnosis of motor bearing with speed fluctuation via angular resampling of transient sound signals[J]. Journal of Sound and Vibration, 2016,385(12): 16-32.

降维算法	SVM分类精度
LDA	94%
PCA	96%
KPCA	97.73%
CDET	99.33%

降维算法	SVM分类精度
LDA	99.46%
PCA	99.46%
KPCA	99.47%
CDET	99.87%

基于压缩感知的设备多源信息传输与分类算法

Multi-source information transmission and classification algorithm for equipment based on compressed sensing

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 24

相关文章 15

Metrics

推荐阅读 0

[1]	曾嵘, 杭潇. 车联网环境下可重构智能反射面辅助无线信道估计算法[J]. 通信学报, 2022, 43(8): 142-150.
[2]	任花, 牛少彰, 任如勇, 岳桢. 基于二维压缩感知的有意义图像加密算法研究[J]. 通信学报, 2022, 43(5): 45-57.
[3]	徐潇雨, 胡浩, 张红旗, 刘玉岭. 基于深度确定性策略梯度的随机路由防御方法[J]. 通信学报, 2021, 42(6): 41-51.
[4]	廖勇, 蔡志镕. 基于基扩展模型的改进正则化正交匹配追踪V2X快时变SC-FDMA信道估计[J]. 通信学报, 2021, 42(4): 177-184.
[5]	潘作舟,孟宗,李晶,石颖. 基于自适应加速前向后向匹配追踪的压缩感知重构算法[J]. 通信学报, 2020, 41(1): 25-32.
[6]	王天荆,李秀琴,白光伟,沈航. 无线传感器网络中基于自适应网格的多目标定位算法[J]. 通信学报, 2019, 40(7): 197-207.
[7]	袁伟娜,严秋. 基于压缩感知的FBMC/OQAM系统信道估计方法[J]. 通信学报, 2019, 40(12): 98-104.
[8]	芮国胜, 刘歌, 田文飚, 董道广, 张雅楠. 基于二次最优阈值近似消息传递法的蒸发波导去噪重构[J]. 通信学报, 2019, 40(10): 10-19.
[9]	董道广,芮国胜,田文飚,康健,刘歌. 基于结构相似性的非参数贝叶斯字典学习算法[J]. 通信学报, 2019, 40(1): 43-50.
[10]	张奕,李娟,张敏. 基于压缩感知的双麦克风混响多声源定位算法[J]. 通信学报, 2019, 40(1): 102-109.
[11]	董道广, 芮国胜, 田文飚, 康健, 刘歌. 基于结构相似性的非参数贝叶斯字典学习算法[J]. 通信学报, 2018, 99(99): 1-.
[12]	王金铭,叶时平,尉理哲,许森,蒋燕君. 半张量积压缩感知模型的快速重构方法[J]. 通信学报, 2018, 39(7): 26-38.
[13]	伍飞云,杨坤德,童峰. 部分范数约束的稀疏恢复算法及其在单载波水声数据遥测中的应用[J]. 通信学报, 2018, 39(6): 127-132.
[14]	吕新荣,李有明,余明宸. OFDM系统的信道与脉冲噪声的联合估计方法[J]. 通信学报, 2018, 39(3): 191-198.
[15]	张策,李鸥,童昕,杨延平. 基于压缩感知与矩阵补全技术的WSN数据收集算法[J]. 通信学报, 2018, 39(2): 164-173.