Clustering analysis of acoustic emission signals based on unsupervised deep learning
-
摘要: 为提高声发射信号检测诊断的自动化程度，直接从声发射波形出发，提出了一种基于深度神经网络与聚类分析的声发射信号分类方法。针对声发射信号标签数据难以获取的问题，采用无监督学习方式，根据大量声发射实测波形进行深度一维卷积自编码器训练，实现了声发射信号特征的自动提取，进而结合K均值聚类算法准确区分不同类型的声发射信号。铅芯在复合材料板上突然断裂和摩擦的声发射试验表明，提出的方法能自动识别不同类别的声发射信号，识别效果优于基于人为设定声发射信号特征的聚类方法。Abstract: Based on acoustic emission (AE) waveform, this paper proposes a method of AE signal classification based on deep neural network and cluster analysis. In order to avoid the difficulty of making AE signal label manually, a large number of measured AE waveforms are used for deep one-dimensional convolutional autoencoder training in an unsupervised learning method to realize the automatic extraction of AE signal characteristics, and then the k-means clustering algorithm is combined to accurately distinguish different types of AE signals. The AE experiments of sudden fracture and friction of lead core on composite plates show that the proposed method can automatically identify different types of AE signals, and the identification accuracy is higher than the clustering method based on the artificial characteristics of AE signals.
-
-
[1] 刘怀喜,张恒,马润香. 复合材料无损检测方法[J]. 无损检测,2003,25(12):631-634,656. [2] 倪迎鸽,杨宇,吕毅,等.声发射在复合材料损伤机理研究的应用现状及发展趋势[J].玻璃钢/复合材料,2019(8):115-126. [3] ZHAO L,KANG L,YAO S.Research and application of acoustic emission signal processing technology[J].IEEE Access,2018(7):984-993.
[4] 沈功田,耿荣生,刘时风.声发射信号的参数分析方法[J].无损检测,2002,24(2):72-77. [5] 万乐,闫小青,张纯,等.玻璃纤维复合材料拉伸损伤的声发射信号模式识别分析[J].南昌大学(工科版),2020,42(1):23-27. [6] 陈玉华,刘时风,耿荣生,等.声发射信号的谱分析和相关分析[J].无损检测,2002,24(9):395-399. [7] 李伟,姜智通,张璐莹,等.碳纤维复合材料损伤声发射信号模式识别方法[J].中国测试,2020,46(6):121-128. [8] 卢宏涛,张秦川.深度卷积神经网络在计算机视觉中的应用研究综述[J].数据采集与处理,2016,31(1):1-17. [9] BARAT V,KOSTENKO P,BARDAKOV V,et al.Acoustic signals recognition by convolutional neural network[J].International Journal of Applied Engineering Research,2017,12(12):3461-3469.
[10] ISLAM M M M,KIM J M.Automated bearing fault diagnosis scheme using 2D representation of wavelet packet transform and deep convolutional neural network[J].Computers in Industry,2019,106:142-153.
[11] NASIRI A,BAO J,MCCLEEARY D,et al.Online damage monitoring of SiCf-SiCm composite materials using acoustic emission and deep learning[J].IEEE Access,2019(99):1.
[12] ABDELJABER O,AVCI O, KIRANYAZ S, et al. Real-time vibration-based structural damage dectection using one-dimentional convolutional neural networks[J]. Journal of Sound & Vibration, 2017,388:154-170.
[13] 王伟魁,李一博,杜刚,等.基于聚类分析的罐底声发射检测信号融合方法[J].振动与冲击,2012,31(17):181-185. [14] 赵文政.复合材料变形损伤监测及声发射特征信号的聚类分析[D].保定:河北大学,2018. [15] 杨俊闯,赵超.K-Means聚类算法研究综述[J].计算机工程与应用,2019,55(23):7-14,63. [16] 金志浩,叶陈,陆景阳,等.聚类分析在声发射信号处理中的应用[J].沈阳化工大学学报,2014,28(4):360-364. [17] 康海松.基于声发射信号分析的热障涂层损伤模式识别研究[D].湘潭:湘潭大学,2014. [18] OSKOUEI A R,HEIDARY H,AHMADI M,et al.Unsupervised acoustic emission data clustering for the analysis of damage mechanisms in glass/polyester composites[J].Materials & Design,2012,37:416-422.
计量
- 文章访问数: 18
- HTML全文浏览量: 3
- PDF下载量: 7
下载:
