Research on Sparse Reconstruction of Engineering Equipment Bearing Signal under Strong Noise
-
摘要: 工程装备轴承故障工况特征常被外在信息淹没，为了对故障数据有效提取，提出了粒子群寻优与稀疏重构相结合的降噪滤波方法，选取Laplace小波基进行参数寻优与字典预构，进而对轴承的振动信号进行稀疏重构。通过对实验数据施加2 dB的高斯白噪声模拟工程环境下的轴承信号，将优化的稀疏重构算法与巴特沃斯滤波器、小波阈值去噪算法进行对比。结果显示：在峰值信噪比与波形相似性等参数上，所提方法的效果更优，所得的重构信号内外圈故障特征频率与理论特征频率相接近，在充分过滤噪声后，可保留原始特征信息，为后期的故障诊断提供良好的数据基础。Abstract: The characteristics of engineering equipment bearing fault conditions are often overwhelmed by the external information. In order to effectively extract the fault data, a noise reduction filtering method combining the particle swarm optimization with the sparse reconstruction is proposed. Laplace wavelet base is selected for parameter optimization and dictionary prediction structure, and then the vibration signal of the bearing is sparsely reconstructed. By applying 2 dB Gaussian white noise to the experimental data to simulate the bearing signal in the engineering environment, the optimal sparse reconstruction algorithm is compared with the Butterworth filter and wavelet threshold denoising algorithm. The results show that the present method is more effective in terms of parameters such as peak signal-to-noise ratio and waveform similarity. The fault characteristic frequencies of the inner and outer rings of the reconstructed signal are close to the theoretical characteristic frequencies. After the noise is fully filtered, the original characteristic information provides a good data basis for the later fault diagnosis.
-
表 1 待测故障滚动轴承参数
参数 类型或数值 轴承型号 6205-2RS JEM SKF 轴承内径/mm 25 轴承外径/mm 52 轴承节径/mm 52 滚动体个数 9 测量位置 驱动端 宽度/mm 15 采样频率/kHz 12 
下载: 导出CSV
表 2 去噪算法结果对比
算法 PSNR NCC 内圈 外圈 内圈 外圈 巴特沃斯滤波器 0.7874 0.8336 −0.1426 −0.2461 小波阈值 1.2325 1.2953 0.6999 0.7656 稀疏重构 2.4213 2.5758 0.7671 0.8878
下载: 导出CSV
-
[1] 隆勇, 郭瑜, 伍星, 等. 基于振动信号分离的行星轴承故障特征提取[J]. 振动与冲击, 2020, 39(13): 78-83, 109LONG Y, GUO Y, WU X, et al. Fault feature extraction of planet bearings based on vibration signal separation[J]. Journal of Vibration and Shock, 2020, 39(13): 78-83, 109 (in Chinese) [2] 郭俊锋, 石斌, 魏兴春, 等. 基于K-SVD字典学习算法的稀疏表示振动信号压缩测量重构方法[J]. 机械工程学报, 2018, 54(7): 97-106 doi: 10.3901/JME.2018.07.097GUO J F, SHI B, WEI X C, et al. A method of reconstruction of compressed measuring for mechanical vibration signals based on K-SVD dictionary-training algorithm sparse representation[J]. Journal of Mechanical Engineering, 2018, 54(7): 97-106 (in Chinese) doi: 10.3901/JME.2018.07.097 [3] 马宏伟, 张大伟, 曹现刚, 等. 基于EMD的振动信号去噪方法研究[J]. 振动与冲击, 2016, 35(22): 38-40MA H W, ZHANG D W, CAO X G, et al. Vibration signal de-noising method based on empirical mode decomposition[J]. Journal of Vibration and Shock, 2016, 35(22): 38-40 (in Chinese) [4] 曹现刚, 张鑫媛, 吴少杰, 等. 基于小波包神经网络的轴承故障识别模型[J]. 机床与液压, 2019, 47(5): 181-186CAO X G, ZHANG X Y, WU S J, et al. Bearing fault identification model based on wavelet packet neural network[J]. Machine Tool & Hydraulics, 2019, 47(5): 181-186 (in Chinese) [5] WANG J J, ZHAO K, WANG F, et al. Application of short-time energy method in the analysis of mechanical vibration signal of circuit breaker[C]//2019 IEEE 3rd International Electrical and Energy Conference (CIEEC). Beijing: IEEE, 2019: 121-125 [6] 张泽宇, 惠记庄, 石泽. 小波包最优基分解树的降噪滤波方法研究[J]. 机械科学与技术, 2020, 39(1): 28-34ZHANG Z Y, HUI J Z, SHI Z. Research on denoising and filtering method based on wavelet packet optimal base decomposition tree[J]. Mechanical Science and Technology for Aerospace Engineering, 2020, 39(1): 28-34 (in Chinese) [7] 樊薇. 信号瞬态成分稀疏表示方法及其机械故障特征提取应用研究[D]. 苏州: 苏州大学, 2015FAN W. Sparse representation of signal transients and its application in machinery fault feature extraction[D]. Suzhou: Soochow University, 2015 (in Chinese) [8] 雷亚国, 贾峰, 孔德同, 等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 54(5): 94-104 doi: 10.3901/JME.2018.05.094LEI Y G, JIA F, KONG D T, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering, 2018, 54(5): 94-104 (in Chinese) doi: 10.3901/JME.2018.05.094 [9] ZHU X X, ZHAO J H, HOU D N, et al. An SDP characteristic information fusion-based CNN vibration fault diagnosis method[J]. Shock and Vibration, 2019, 2019: 3926963 [10] VERSTRAETE D, FERRADA A, DROGUETT E L, et al. Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings[J]. Shock and Vibration, 2017, 2017: 5067651 [11] 昝涛, 王辉, 刘智豪, 等. 基于多输入层卷积神经网络的滚动轴承故障诊断模型[J]. 振动与冲击, 2020, 39(12): 147-149, 163ZAN T, WANG H, LIU Z H, et al. A fault diagnosis model for rolling bearings based on a multi-input layer convolutional neural network[J]. Journal of Vibration and Shock, 2020, 39(12): 147-149, 163 (in Chinese) [12] VAN DEN BERG W, FRIEDLANDER M P. Probing the Pareto frontier for basis pursuit solutions[J]. SIAM Journal on Scientific Computing, 2009, 31(2): 890-912 doi: 10.1137/080714488 [13] VAN DEN BERG E, FRIEDLANDER M P. Sparse optimization with least-squares constraints[J]. SIAM Journal on Optimization, 2011, 21(4): 1201-1229 doi: 10.1137/100785028 [14] CWRU, Bearing date center, seeded fault test data [EB/OL]. http://csegroups.case.edu/bearingdatacenter/ [15] 唐炬, 高丽, 彭莉, 等. 非平稳振荡局放信号去噪效果评价参数研究[J]. 高电压技术, 2007, 33(12): 66-70 doi: 10.3969/j.issn.1003-6520.2007.12.016TANG J, GAO L, PENG L, et al. Study on new evaluation parameters for de-noising performance of non-stationary oscillating partial discharge[J]. High Voltage Engineering, 2007, 33(12): 66-70 (in Chinese) doi: 10.3969/j.issn.1003-6520.2007.12.016 [16] 盛兆顺, 尹琦岭. 设备状态监测与故障诊断技术及应用[M]. 北京: 化学工业出版社, 2003SHENG Z S, YIN Q L. Technology and application of equipment condition monitoring and fault diagnosis[M]. Beijing: Chemical Industry Press, 2003 (in Chinese) -
点击查看大图
图(17) / 表(2)
计量
- 文章访问数: 86
- HTML全文浏览量: 61
- PDF下载量: 4
- 被引次数: 0
