计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 319-326.doi: 10.11896/jsjkx.210700034
周俊1,2, 尹悦2, 夏斌3
ZHOU Jun1,2, YIN Yue2, XIA Bin3
摘要： 声发射检测不需要进入被检对象中进行检测,与其他无损检测技术相比具有实时性、整体性和高灵敏度等独特优势。早期参数分析、小波分析等方法在声发射信号特征提取上缺乏理论指导,具有一定主观性,BP神经网络应用于声发射信号识别中时网络训练容易陷入局部极值,LSTM神经网络可以对输入序列数据进行逐层学习并自适应提取特征,避免了特征的人工选择和提取,较好地解决了存在的问题。文中提出一种基于LSTM的声发射信号识别模型,在声发射信号z-score标准化基础上,对比不同学习算法、隐层神经元数、正则化dropout rate下的测试集正确识别率,优化声发射信号识别模型,与BP神经网络的声发射信号识别准确率进行对比,实验结果表明,LSTM神经网络在Adam算法中,当隐层神经元数为250,dropout rate为0.5时,声发射信号识别率最高且为76.51%,优于BP神经网络53.9%的最高识别率。
中图分类号:
| [1]FAN Z,HU M,ZHANG K,et al.A review of research on acoustic emission on-line monitoring of oil and gas pipe corrosion in acidic environments[J].Surface Technology,2019,48(4):245-252. [2]CHI D Z,QI C C.Review of domestic research on acoustic nondestructive testing of welding defects[J].Precision Forming Engineering,2018,10(1):74-81. [3]LIU G H.Research on key technologies of acoustic emission[D].Hangzhou:Zhejiang University,2008. [4]SHIWA M.Recognition of rub-impact acoustic emission signal based on fuzzy entropy[J].Journal of Mechanical Engineering,2010,46(3):71-75. [5]LIM J,MICRO K T.Cracking in stainless steel pipe detection by using acoustic emission and crest factor technique[C]//Instrumentation and Measurement Technology Conference.Warsaw,Poland,2007:1-3. [6]MA Y H,LIU K,YANG D Z,et al.Based on typical BP network tensile acoustic emission signal feature recognition of metal specimens [J].Journal of Sichuan University (Engineering Science Edition),2011,43(2):252-255. [7]SAUSE M G R,GRIBOV A,UNWIN A R.Pattern recognition approach to identify natural clusters of acoustic emission signals[J].Pattern Recognition Letters,2012,33(1):17-23. [8]SUZUKI H,KINJO T,TAKEMOTO M,et al.Fracture-mode determination of glass-fiber composites by various AE processing[J].Japanese Journal of Applied Physics,1997,36(5B),3281. [9]GANG Q,ALAN B,JAVAD H,et al.The wavelet transform in the acoustic emission signal feature extraction of the rubbing fault[C]//1st International Workshop on Database Technology and Applications,DBTA 2009.Wuhan,China,2009:283-286. [10]CUI Y,LI X L,PENG H X,et al.Interface characterization of discontinuous reinforced metal matrix composites based on acoustic emission wavelet analysis[J].Science Bulletin,2010,43(6):656-657. [11]FENG Z G,SUN R K,GOU J J,et al.Acoustic emission source location method based on wavelet packet analysis [J].Journal of Jiangsu University,2010,31(1):109-111. [12]ZHANG Z,WU X Q,TAN J B.In-situ monitoring of stress corrosion cracking of 304 stainless steel in high-temperature water by analyzing acoustic emission waveform[J].Corrosion Science,2018,146:90-98. [13]SACHES W,GRABEC I.Intelligent processing of acoustic emission signals[J].Materials Evaluation,1992,50(7):826-854. [14]INGRAHAM M D,ISSEN K A,HOLCOMB D J.Use of acoustic emissions to investigate localization in high-porosity sandstone subjected to true triaxial stresses[J].Acta Geotechnica,1998,8(6). [15]KOSEL T,GRABEC I,MUŽI P.Location of acoustic emission sources generated by air flow[J].Ultrasonics,2000,38(1-8):824-826. [16]ZHAO Y X,XU Y G,GAO L X,et al.Rolling bearing acoustic emission fault pattern recognition technology based on harmonic wavelet packet and BP neural network[J].Vibration and Shock,2010,29(10):163-166. [17]MAO H Y,CHENG J G,HUANG Z F.Extraction of characteristic parameters of acoustic emission signal of metal crack based on BP neural network [J].Mechanical Design,2010,27(2):84-86. [18]ZHOU J,WANG Q,YI M,et al.Acoustic emission signal recognition based on wavelet transform and RBF network[J].Journal of Petrochemical College,2015,28(3):80-85. [19]GUAN S,PANG H Y,SONG W J,et al.Tool wear status recognition based on MF-DFA features and LS-SVM algorithm[J].Transactions of the Chinese Society of Agricultural Engineering,2018,34(14):61-68. [20]SI L,BI G H,WEI Y G,et al.Acoustic emission signal detection and recognition method based on RQA and SVM[J].Vibration and Shock,2016,35(2):97-103,123. [21]WANG X Y,JIANG Z W,CHEN H Q,et al.Research on pipeline leak diagnosis method combining SVM and DS[J].Computer Engineering and Applications,2016,52(5):262-265,270. [22]HU Y,LUO D Y,HUA K,et al.A review and discussion on deep learning [J].Journal of Intelligent Systems.2019,14(1):1-19. [23]ELDAN R,SHAMIR O.The power of depth for feedforward neural networks[C]//JMLR:Workshop and Conference Proceedings.2016:1-34. [24]HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507. [25]HOCHREITER S,SCHMIDHUBER J.Long short-term memory [J].Neural computation,1997,9(8):1735-1780. [26]SILVER D,HUANG A,MADDISON C J,et al.Mastering the game of Go with deep neural networks and tree search[J].Nature,2016,529(7587):484-489. [27]ZHU Y,GAO X,ZHANG W,et al.A bi-directional LSTM-CNN model with attention for aspect-level text classification [J].Future Internet,2018,10(12):116. [28]YIN Z K,LIAO W H,WANG R J,et al.Simulation and prediction of rainfall and runoff based on long and short-term memory neural network (LSTM)[J].South-to-North Water Diversion and Water Conservancy Science and Technology,2019,17(6):1-9,27. [29]FISCHER T,KRAUSS C.Deep learning with long short-term memory networks for financial market predictions [J].European Journal of Operational Research,2018,270(2):654-669. [30]ZENG W G,LI S H,LI Y,et al.Evaluation of uniform corrosion defects of oil,gas and water gathering pipelines based on radial basis function neural network prediction model[J].Corrosion and Protection,2020,41(10):50-56. [31]ZHANG J K,ZHAO J,ZHANG R,et al.A review of image instance segmentation methods based on deep learning [J].Small Microcomputer System,2021,42(1):161-171. [32]YAMASHITA T,ZHANG M.Graphical Deep Learning [M].Beijing:People's Posts and Telecommunications Press,2018:46-47. [33]ZHOU J.Research on Acoustic Emission Signal Processing Algorithm Based on Machine Learning [M].Beijing:Publishing House of Electronics Industry,2020:31-32. [34]CHOLET F.Python Deep Learning [M].Beijing:People's Posts and Telecommunications Press,2018:59-60. [35]KINGMA D,BA J.Adam:A Method for Stochastic Optimization[J].Computer Science,2014. [36]ZHU J Y,WANG R B,HUANG X X,et al.Multi-level metaphor recognition method based on Bi-LSTM [J].Journal of Dalian University of Technology,2020,60(2):209-215. [37]JIANG Z L.Introduction to Artificial Neural Networks [M].Beijing:Higher Education Press,2002:32-33. |
| [1] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
| [2] | 胡安祥, 尹小康, 朱肖雅, 刘胜利. 基于数据流特征的比较类函数识别方法 Strcmp-like Function Identification Method Based on Data Flow Feature Matching 计算机科学, 2022, 49(9): 326-332. https://doi.org/10.11896/jsjkx.220200163 |
| [3] | 陈坤峰, 潘志松, 王家宝, 施蕾, 张锦. 基于双目叠加仿生的微换衣行人再识别 Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation 计算机科学, 2022, 49(8): 165-171. https://doi.org/10.11896/jsjkx.210600140 |
| [4] | 杨炳新, 郭艳蓉, 郝世杰, 洪日昌. 基于数据增广和模型集成策略的图神经网络在抑郁症识别上的应用 Application of Graph Neural Network Based on Data Augmentation and Model Ensemble in Depression Recognition 计算机科学, 2022, 49(7): 57-63. https://doi.org/10.11896/jsjkx.210800070 |
| [5] | 徐鸣珂, 张帆. Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法 Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition 计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085 |
| [6] | 孟月波, 穆思蓉, 刘光辉, 徐胜军, 韩九强. 基于向量注意力机制GoogLeNet-GMP的行人重识别方法 Person Re-identification Method Based on GoogLeNet-GMP Based on Vector Attention Mechanism 计算机科学, 2022, 49(7): 142-147. https://doi.org/10.11896/jsjkx.210600198 |
| [7] | 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138 |
| [8] | 费星瑞, 谢逸. 基于HMM-NN的用户点击流识别 Click Streams Recognition for Web Users Based on HMM-NN 计算机科学, 2022, 49(7): 340-349. https://doi.org/10.11896/jsjkx.210600127 |
| [9] | 高荣华, 白强, 王荣, 吴华瑞, 孙想. 改进注意力机制的多叉树网络多作物早期病害识别方法 Multi-tree Network Multi-crop Early Disease Recognition Method Based on Improved Attention Mechanism 计算机科学, 2022, 49(6A): 363-369. https://doi.org/10.11896/jsjkx.210500044 |
| [10] | 张嘉淏, 刘峰, 齐佳音. 一种基于Bottleneck Transformer的轻量级微表情识别架构 Lightweight Micro-expression Recognition Architecture Based on Bottleneck Transformer 计算机科学, 2022, 49(6A): 370-377. https://doi.org/10.11896/jsjkx.210500023 |
| [11] | 肖治鸿, 韩晔彤, 邹永攀. 基于多源数据和逻辑推理的行为识别技术研究 Study on Activity Recognition Based on Multi-source Data and Logical Reasoning 计算机科学, 2022, 49(6A): 397-406. https://doi.org/10.11896/jsjkx.210300270 |
| [12] | 黄璞, 杜旭然, 沈阳阳, 杨章静. 基于局部正则二次线性重构表示的人脸识别 Face Recognition Based on Locality Regularized Double Linear Reconstruction Representation 计算机科学, 2022, 49(6A): 407-411. https://doi.org/10.11896/jsjkx.210700018 |
| [13] | 王建明, 陈响育, 杨自忠, 史晨阳, 张宇航, 钱正坤. 不同数据增强方法对模型识别精度的影响 Influence of Different Data Augmentation Methods on Model Recognition Accuracy 计算机科学, 2022, 49(6A): 418-423. https://doi.org/10.11896/jsjkx.210700210 |
| [14] | 黄璞, 沈阳阳, 杜旭然, 杨章静. 基于局部约束特征线表示的人脸识别 Face Recognition Based on Locality Constrained Feature Line Representation 计算机科学, 2022, 49(6A): 429-433. https://doi.org/10.11896/jsjkx.210300169 |
| [15] | 刘伟业, 鲁慧民, 李玉鹏, 马宁. 指静脉识别技术研究综述 Survey on Finger Vein Recognition Research 计算机科学, 2022, 49(6A): 1-11. https://doi.org/10.11896/jsjkx.210400056 |
|
||
首页