基于声发射的铝蜂窝板超高速撞击损伤模式识别方法

doi:10.7527/S1000-6893.2017.220401

固体力学与飞行器总体设计

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于声发射的铝蜂窝板超高速撞击损伤模式识别方法

刘源, 庞宝君, 迟润强, 才源

哈尔滨工业大学航天学院, 哈尔滨 150080

收稿日期:2016-05-05 修回日期:2017-02-13 出版日期:2017-05-15 发布日期:2017-03-03
通讯作者: 迟润强 E-mail:chirq@hit.edu.cn
基金资助:
国家"十二五"空间碎片专项（K0203210）；中央高校基本科研业务费专项资金（HIT.NSRIF.2015029）

A damage pattern recognition method for hypervelocity impact on aluminum honeycomb core sandwich based on acoustic emission

LIU Yuan, PANG Baojun, CHI Runqiang, CAI Yuan

School of Astronautics, Harbin Institute of Technology, Harbin 150080, China

Received:2016-05-05 Revised:2017-02-13 Online:2017-05-15 Published:2017-03-03
Supported by:
National Special Project for Space Debris during the Twelfth Five-year Plan Period (K0203210);the Fundamental Research Funds for Central Universities (HIT.NSRIF.2015029)

摘要/Abstract

摘要：

为通过声发射技术识别铝合金蜂窝板超高速撞击（HVI）的损伤状态，提出一种基于神经网络的损伤模式识别方法。通过超高速撞击实验获取声发射信号，结合精确源定位技术、时频分析技术、小波分析技术及模态声发射技术，提出了10个与损伤相关的特征参数，通过非参数检验分析其与损伤的关系，设计了一种基于贝叶斯正则化BP神经网络的超高速撞击损伤模式识别方法。建立最优网络模型，通过不同参数组合识别能力分析，优选出2种特征参数组合，通过非同源样本对其损伤模式识别能力进行验证。结果表明：传播距离与损伤模式无关，却是识别损伤模式的重要参数；125~250 kHz频域的自动加窗小波能量比会降低损伤模式的识别能力；采用贝叶斯正则化的BP神经网络可以较好地识别蜂窝板超高速撞击损伤模式，参数组合为传播距离、上升时间、持续时间、截止频率、4个自动加窗小波能量比及小波能量熵，共9个参数，对任意选取非同源样本识别错分率仅为9.38%。

关键词: 空间碎片, 超高速撞击, 声发射, 损伤模式识别, 神经网络

Abstract:

A damage pattern recognition method based on neural network is proposed to recognize the damage state of aluminum honeycomb core sandwich under hypervelocity impact (HVI) through acoustic emission. A variety of experimental signals are obtained, 10 characteristic parameters related to damage are presented by test of nonparametric analysis the relationship with damage pattern, combining with precise source localization, time-frequency analysis, wavelet transformation and modal acoustic emission technology. The BP neural net mode based on Bayesian regularization is established by analyzing the relationship with damage pattern using nonparametric analysis. After establishing the optimal network model, two optimal combinations are selected by analyzing the recognition ability of different parameter combinations, the damage pattern recognition ability is verified with non-same source sample. The result shows that propagation distance is a significant parameter but irrelevant to damage pattern. Automatic window wavelet energy ratio within 125-250 kHz frequency range decrease the ability of damage pattern recognition. Using a Bayesian regularization neural network with combination of 9 parameters, including propagation distance, rise time, hold time, cut-off frequency, 4 kinds of automatic window wavelet energy ratio and wavelet energy entropy, presents 9.38% wrong point rate to a group of random non-same source sample.

Key words: space debris, hypervelocity impact (HVI), acoustic emission, damage pattern recognition, neural network

中图分类号:

V19
X949

刘源, 庞宝君, 迟润强, 才源. 基于声发射的铝蜂窝板超高速撞击损伤模式识别方法[J]. 航空学报, 2017, 38(5): 220401-220401.

LIU Yuan, PANG Baojun, CHI Runqiang, CAI Yuan. A damage pattern recognition method for hypervelocity impact on aluminum honeycomb core sandwich based on acoustic emission[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2017, 38(5): 220401-220401.

参考文献

[1] Upper stage explosion places LEO satellites at risk[N]. Orbital Debris Quarterly News, 2013-01-17.
[2] LIOU J C, GIOVANE F, CORSARO R, et al. LAD-C-A large area debris collector on the ISS[C]//36th COSPAR Scientific Assembly. Paris:Committee on Space Research (COSPAR), 2006.
[3] PROSSER W H, MADARAS E I. Distributed impact detector system (DIDS) health monitoring system evaluation:NASA/TM-2010-216694[R]. Hampton, VA:Langley Research Center, 2010.
[4] SPENCER G, SCHAFER F, TANAKA M, et al. Design and initial calibration of micrometeoroid space debris detector (MDD)[C]//Proceedings of the 4th European Conference on Space Debris. Pairs:European Space Agency, 2005, 587:2275.
[5] SCHAFER F, JANOVSKY R. Impact sensor network for detection of hypervelocity impacts on spacecraft[J]. Acta Astronautica, 2007, 61(10):901-911.
[6] SCHWANETHAL J P, MCBRIDE N, GREEN S F, et al. Analysis of impact data from the DEBIE (debris in-orbit evaluator) sensor in polar low earth orbit[C]//Proceedings of the 4th European Conference on Space Debris. Pairs:European Space Agency, 2005, 587:177.
[7] 唐颀, 庞宝君, 韩增尧, 等. 单层板超高速撞击声发射波的频谱特征分析[J]. 宇航学报, 2007, 28(4):1059-1064. TANG Q, PANG B J, HAN Z Y, et al. Analysis of frequency spectrum character of acoustic emission wave from hypervelocity impact on single-sheet plate[J]. Journal of Astronautics, 2007, 28(4):1059-1064 (in Chinese).
[8] 王晓宇, 张超, 孙维, 等. 航天器密封舱加筋壁板碎片撞击监测技术研究[J]. 实验流体力学, 2014, 28(4):70-77. WANG X Y, ZHANG C, SUN W, et al. Research on structural health monitoring method for locating space debris impact on spacecraft seal structure[J]. Journal of Experiments in Fluid Mechanics, 2014, 28(4):70-77 (in Chinese).
[9] 刘武刚, 庞宝君, 韩增尧, 等. 基于小波分析技术的高速撞击声发射源定位[J]. 高技术通讯, 2009, 19(2):181-187. LIU W G, PANG B J, HAN Z Y, et al. Acoustic emission detection and location for hypervelocity impacts based on wavelet transform[J]. Chinese High Technology Letters, 2009, 19(2):181-187 (in Chinese).
[10] LIU Z D, PANG B J. A method based on acoustic emission for locating debris cloud impact[C]//Proceedings of the SPIE 7522, 4th International Conference on Experimental Mechanics. Bellingham, WA:SPIE, 2010.
[11] 庞宝君, 刘治东, 唐颀. 基于HHT变换的声发射源平面定位方法[J]. 无损检测, 2010(1):1-5. PANG B J, LIU Z D, TANG Q. A method based on HHT for acoustic emission source location[J]. Nondestructive Testing, 2010(1):1-5 (in Chinese).
[12] 张凯, 庞宝君, 林敏. 碎片云撞击声发射信号能量特征小波包分析[J]. 振动与冲击, 2012, 31(12):125-128. ZHANG K, PANG B J, LIN M. Wavelet packet analysis for acoustic emission signals caused by debris cloud impact[J]. Journal of Vibration and Shock, 2012, 31(12):125-128 (in Chinese).
[13] 熊秋鹏. 基于神经网络技术的空间碎片损伤模式识别研究[D]. 哈尔滨:哈尔滨工业大学, 2012:31-35. XIONG Q P. Research on space debris damage pattern recognition based on neutral network technology[D]. Harbin:Harbin Institute of Technology, 2012:31-35 (in Chinese).
[14] EMMA A T, JONATHAN P G, CLEGG R A, et al. Hypervelocity impact on spacecraft honeycomb:Hydrocode simulation and damage laws[J]. International Journal of Impact Engineering, 2003, 29(1-10):691-702.
[15] ALAVI N A, RAZAVI S B, MAJZOOBI H H. Ballistic limit determination of aluminum honeycombs-Experimental study[J]. Materials Science and Engineering A, 2008, 488(1):273-280.
[16] LIU Y, PANG B J, JIA B, et al. Modal acoustic emission based location method in honeycomb core sandwich structure[C]//Proceedings of the 6th European Conference on Space Debris. Pairs:European Space Agency, 2013, 723:183.
[17] CHAKRABORTY N, RATHOD V T, MAHAPATRA D R, et al. Guided wave based detection of damage in honeycomb core sandwich structures[J]. NDT&E International, 2012, 49(7):27-33.
[18] ROSSO O A, BLANCO S, YORDANOVA J, et al. Wavelet entropy:A new tool for analysis of short duration brain electrical signals[J]. Journal of Neurosci Methods, 2001, 105(1):65-75.
[19] MACKAY D J C. Bayesian interpolation[J]. Neural Computation, 1992; 4(3):415-447.
[20] ORRE R, LANSNER A, BATE A, et al. Bayesian neural networks with confidence estimations applied to data mining[J]. Computational Statistics & Data Analysis, 2000, 34(4):473-493.
[21] WONG B M L, LEE S Y, LEUNG K S. Data mining of Bayesian networks using cooperative coevolution[J]. Decision Support Systems, 2004, 38(3):451-472.

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于声发射的铝蜂窝板超高速撞击损伤模式识别方法

A damage pattern recognition method for hypervelocity impact on aluminum honeycomb core sandwich based on acoustic emission

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	胡伟, 万文章, 陈谋. 基于神经网络和干扰观测器的UAV自动着舰控制[J]. 航空学报, 2022, 43(S1): 726963-726963.
[2]	陈博, 岳凯, 王如生, 胡明南. 基于学习策略的多速率多传感器融合定位方法[J]. 航空学报, 2022, 43(S1): 726904-726904.
[3]	王宇斐, 刘骁佳, 刘欢, 曹立俊, 罗志强. 孪生神经网络在航天产品电性能测试方面的应用[J]. 航空学报, 2022, 43(S1): 727048-727048.
[4]	王子玲, 熊振宇, 顾祥岐. 可见光与SAR多源遥感图像关联学习算法[J]. 航空学报, 2022, 43(S1): 727239-727239.
[5]	韩淞宇, 邵海东, 姜洪开, 张笑阳. 基于提升卷积神经网络的航空发动机高速轴承智能故障诊断[J]. 航空学报, 2022, 43(9): 625479-625479.
[6]	杨特, 杨智春, 梁舒雅, 康在飞, 贾有. 平稳随机载荷的信号特征提取与深度神经网络识别[J]. 航空学报, 2022, 43(9): 225952-225952.
[7]	刘佳奇, 冯蕴雯, 路成, 薛小锋, 潘维煌. 基于智能神经网络的航空发动机运行安全分析[J]. 航空学报, 2022, 43(9): 625375-625375.
[8]	邵怡韦, 陈嘉宇, 林翠颖, 万程, 葛红娟, 石智龙. 小训练样本下齿轮箱故障诊断:一种基于改进深度森林的方法[J]. 航空学报, 2022, 43(8): 625429-625429.
[9]	杨宇, 王彬文, 祁小凤. 面向全尺寸民机结构疲劳试验的声发射监测技术[J]. 航空学报, 2022, 43(6): 527044-527044.
[10]	熊伟, 朱洪峰, 崔亚奇. 在线学习的循环自适应机动目标跟踪算法[J]. 航空学报, 2022, 43(5): 325250-325250.
[11]	董珍一, 林莉, 雷明凯, 马志远. 基于BPNN的封严涂层孔隙分布均匀性超声表征[J]. 航空学报, 2022, 43(5): 425294-425294.
[12]	王因翰, 范世鹏, 吴广, 王江, 何绍溟. 基于GRU的敌方拦截弹制导律快速辨识方法[J]. 航空学报, 2022, 43(2): 325024-325024.
[13]	奕建苗, 邓枫, 覃宁, 刘学强. 快速预测跨声速流场的深度学习方法[J]. 航空学报, 2022, 43(11): 526747-526747.
[14]	蔡国飙, 张百一, 贺碧蛟, 翁惠焱, 刘立辉. 真空羽流智能化计算[J]. 航空学报, 2022, 43(10): 527352-527352.
[15]	王辉, 贾自凯, 金忍, 林德福, 范军芳, 徐超. 无人机视觉引导对接过程中的协同目标检测[J]. 航空学报, 2022, 43(1): 324854-324854.