基于Laplace先验和稀疏块相关性的旋转机械振动信号贝叶斯压缩重构

doi:10.3969/j.issn.1000-1093.2021.12.024

摘要/Abstract

摘要： 为通过无线传输实时监测装备状态，针对机械振动信号采样频率较高导致压缩重构困难的问题，将Laplace先验模型和振动信号周期性稀疏块相结合，提出一种改进的贝叶斯压缩感知算法。建立基于Laplace分布的贝叶斯先验模型，相对于高斯先验具有更强的稀疏促进作用。根据机械设备转速和采样频率计算振动信号类周期，对信号进行周期性分块，并基于多稀疏块共享相同超参数的特点，采用快速相关向量机迭代估计出原始信号期望。选取两级平行轴齿轮箱作为研究对象，进行压缩重构仿真实验。结果表明，该方法在相同稀疏基下能有效改善机械振动信号的重构效果。

关键词: 机械振动信号, Laplace先验, 稀疏块, 贝叶斯压缩, 压缩感知

Abstract: For the difficult compression and reconstruction of mechanical vibration signal caused by high sampling frequency，an improved Bayesian compressive sensing algorithm is proposed by combining Laplace prior model with periodic sparse block of vibration signal for monitoring the equipment condition in real-time through wireless transmission. A Laplace distribution-based Bayesian priori model is proposed， which has stronger sparse promotion effect compared to Gaussian priori model. The vibration signal period is calculated according to the rotational speed and sampling frequency of mechanical equipment for dividing the signal periodically.The original signal expectation is estimated iteratively by fast correlation vector machine based on the feature of that multiple sparse blocks share the same hyperparameters.A two-stage parallel gearbox is selected as the research object. The compression and reconstruction simulations were carried out. It is found that the proposed method can effectively improve the reconstruction effect of mechanical vibration signals using the same sparse basis.

Key words: mechanicalvibrationsignal, Laplacepriori, sparseblock, Bayesiancompression, compressivesensing

中图分类号:

TH113.1

马云飞，白华军，温亮，郭驰名，贾希胜. 基于Laplace先验和稀疏块相关性的旋转机械振动信号贝叶斯压缩重构[J]. 兵工学报, 2021, 42(12): 2762-2770.

MA Yunfei， BAI Huajun， WEN Liang， GUO Chiming， JIA Xisheng. Bayesian Compression and Reconstruction for Rotating Mechanical Vibration Signal Based on Laplace Prior and Sparse BlockCorrelation[J]. Acta Armamentarii, 2021, 42(12): 2762-2770.

参考文献

［1］汤宝平，黄庆卿，邓蕾，等.机械设备状态监测无线传感器网络研究进展[J].振动、测试与诊断，2014，34(1):1-7.
TANG B P，HUANG Q Q，DENG L，et al. Research progress and challenges of wireless sensor networks for machinery equipment condition monitoring[J].Journal of Vibration，Measurement & Diagnosis，2014，34(1):1-7.(in Chinese)
[2］齐立群.桥梁结构健康监测的无线传感技术研究[D].哈尔滨：哈尔滨工业大学，2017.
QI L Q.Research on wireless sensor technology applied in bridge structure health monitoring[D].Harbin：Harbin Institute of Technology，2017. (in Chinese)
[3］ HUANG Y，BECK J L，WU S.Bayesian compressive sensing for approximately sparse signals and application to structural health monitoring signals for data loss recovery[J].Probabilistic Engineering Mechanics，2016，46: 62-79.
[4］ SAZONOV E，KRISHNAMURTHY V，SCHILLING R J.Wireless intelligent sensor and actuator network—a scalable platform for time-synchronous applications of structural health monitoring[J].Structural Health Monitoring，2010，9(5):465-476．
[5］ VOGL A，WANG D T，STOR ASP，et al．Design，process and cha-racterisation of a high-performance vibration sensor for wireless condition monitoring[J].Sensors and Actuators A:Physical，2009，153(2): 155-161．
[6］练秋生，富利鹏，陈书贞，等.基于多尺度残差网络的压缩感知重构算法[J].自动化学报，2019，45(11):2082-2091.
LIAN Q S，FU L P，CHEN S Z，et al.A compressed sensing algorithm based on multi-scale residual reconstruction network[J].Acta Automatica Sinica，2019，45(11):2082-2091.(in Chinese)
[7］ CANDS E J，TAO T.Decoding by linear programming[J].IEEE Transactions on Information Theory，2005，51(12):4203-4215．
[8］ DONOHO D L.Compressed sensing[J].IEEE Transactions on Information Theory，2006，52(4):1289-1306．
[9］ TROPP J A，WRIGHT S J.Computational methods for sparse solution of linear inverse problems[J].Proceedings of the IEEE，2010，98(6):948-958.
[10］ TROPP J A，GILBERT A C.Signal recovery from random mea-surements via orthogonal matching pursuit[J].IEEE Transactions on Information Theory，2007，53(12): 4655-4666．
[11］ JI S H，XUE Y，CARIN L.Bayesian compressive sensing[J].IEEE Transactions on Signal Process，2008，56 (6):2346-2356.
[12］ TIPPING M E.Sparse Bayesian learning and the relevance vector machine[J].Journal of Machine Learning Research，2001，1:211-244.
[13］ BABACAN S D，MOLINA R，KATSAGGELOS A K.Bayesian compressive sensing using Laplace priors[J].IEEE Transactions on Image Processing，2010，19(1):53-63.
[14］ JI S H，DUNSON D B，CARIN L.Multi-task compressive sensing[J].IEEE Transactiopns on Signal Process，2009，57(1):92-106.
[15］ HE Y，FENG K，HU M H，et al.An MCM-enhanced compressive sensing for weak fault feature extraction of rolling element bearings under variable speeds[J].Shock and Vibration，2020，21:1-21.
[16］温广瑞，栾日雄，任延晖，等.相空间稀疏化的信号压缩感知与重构方法[J].振动、测试与诊断，2017，37(2): 228-234.
WEN G R，LUAN R X，REN Y H，et al. Compressed sensing and reconstruction method based on sparsity in phase space[J].Journal of Vibration，Measurement & Diagnosis，2017，37(2):228-234.(in Chinese)
[17］崔兴梅，吴键，徐云鹏.基于改进m序列的压缩采样观测矩阵设计[J].振动、测试与诊断，2017，37(6):1163-1168.
CUI X M，WU J，XU Y P.Design of compressed sampling observation matrix based on improved m sequence[J]. Journal of Vibration，Measurement & Diagnosis，2017，37(6): 1163-1168.(in Chinese)

[1]	单泽彪, 常立民, 刘小松, 王宇祥. 基于自然对数复合函数近似l₀范数的DOA估计[J]. 兵工学报, 2023, 44(5): 1521-1528.
[2]	陈新华，郑恩明，李嶷，杨鹤，周权斌. 复域压缩感知近场声图测量方法[J]. 兵工学报, 2021, 42(8): 1735-1743.
[3]	曹渊，崔东华，刘兴辉. 基于部分传输序列与压缩感知的正交频分复用系统峰值平均功率比降低算法[J]. 兵工学报, 2020, 41(6): 1151-1156.
[4]	黄惠祥，郭秋涵，童峰. 基于分布式压缩感知的麦克风阵列声源定位[J]. 兵工学报, 2019, 40(8): 1725-1731.
[5]	张永顺，朱卫纲，孟祥航，贾鑫，曾创展，王满喜. 基于块稀疏贝叶斯学习的跳频通信梳状干扰抑制[J]. 兵工学报, 2018, 39(9): 1864-1872.
[6]	王志鹏，王星，田元荣，周一鹏. 基于压缩感知的辐射源信号数据级融合识别方法[J]. 兵工学报, 2017, 38(8): 1547-1554.
[7]	朱甦，薄煜明，何亮. 基于冗余字典的多特征压缩感知目标跟踪算法[J]. 兵工学报, 2017, 38(6): 1140-1146.
[8]	焦传海，李永成，谢恺，杨运甫. 基于期望偏差和广义似然比检验的非重构宽带压缩盲感知[J]. 兵工学报, 2016, 37(10): 1837-1843.
[9]	周跃海，曹秀岭，童峰，陈东升. 单输入多输出水声信道的联合稀疏恢复估计[J]. 兵工学报, 2015, 36(12): 2321-2329.
[10]	王彪, 李超, 戴跃伟. 基于空域压缩采样的水声目标DOA估计方法[J]. 兵工学报, 2013, 34(11): 1479-1483.
[11]	朱丰1,2，张群1，李松3，冯有前4，张维强5. 稀疏线性调频步进信号弹道导弹进动微多普勒特征重构与提取方法[J]. 兵工学报, 2013, 34(1): 76-81.