损伤声发射信号小波包神经网络特征识别方法

doi:10.13190/j.jbupt.2020-118

北京邮电大学学报 ›› 2021, Vol. 44 ›› Issue (1): 124-130.doi: 10.13190/j.jbupt.2020-118

• 研究报告 • 上一篇

损伤声发射信号小波包神经网络特征识别方法

齐添添¹, 陈尧¹, 何才厚^1,2, 龙盛蓉¹, 李秋锋¹

1. 无损检测技术教育部重点实验室南昌航空大学, 南昌 330063;
2. 江西省特种设备检验检测研究院鹰潭分院, 鹰潭 335000

收稿日期:2020-08-14 出版日期:2021-02-28 发布日期:2021-09-30
通讯作者: 李秋锋(1976-),男,教授,E-mail:qiufenglee@163.com. E-mail:qiufenglee@163.com
作者简介:齐添添(1995-),女,硕士生.
基金资助:
国家自然科学基金项目（11764030，51705232）；江西省自然科学基金项目（20192BAB216026）；江西省质监局科技计划项目（GZJKE201810）

A Wavelet Packet Neural Network Feature Recognition Method for Damage Acoustic Emission Signals

QI Tian-tian¹, CHEN Yao¹, HE Cai-hou^1,2, LONG Sheng-rong¹, LI Qiu-feng¹

1. Key Laboratory of Nondestructive Testing, Nanchang Hangkong University, Nanchang 330063, China;
2. Yingtan Branch of Special Equipment Inspection and Research Institute of Jiangxi, Yingtan 335000, China

Received:2020-08-14 Online:2021-02-28 Published:2021-09-30

摘要/Abstract

摘要： 在材料损伤的检测和评价时，为了在大量接收信号中识别有效声发射信号，提出了一种基于小波包特征提取的损伤声信号神经网络识别方法，首先利用小波包全局分解的优势，准确提取非平稳信号的特征信息，建立相应特征向量，对有效声发射信号和干扰噪声信号进行表征；然后根据特征向量和识别输出要求，建立了3层结构的反向传播神经网络对信号进行分析和识别，滤除噪声信号，保留有效声发射信号；最后，在玻璃钢复合材料的声发射实验中，采集了400组信号对该方法进行验证，准确性达到97.5%，能够满足工程需要.

关键词: 声发射检测, 小波包分解, 特征向量, BP神经网络, 信号识别

Abstract: In the testing and evaluation of material damage, in order to identify effective acoustic emission (AE) signals among a large number of received signals, a neural network recognition method based on wavelet packet feature extraction is proposed. Firstly,the advantage of wavelet packet global decomposition is used to accurately extract the feature information from non-stationary signals,so, the corresponding feature vectors are established to characterize effective AE signals and interfering noise signals. Then,according to feature vectors and recognition output requirements,a three-layer back propagation neural network is established to analyze and identify signals,which could filter out noise signals and retain effective AE signals. Finally,400 sets of AE signals are collected in the experiment of glass fiber reinforced plastics to verify the method. The collected AE signals are identified with an accuracy of 97.5%,which can meet requirements of engineering.

Key words: acoustic emission testing, wavelet packet decomposition, feature vector, back propagation neural network, signal recognition

中图分类号:

TH87

齐添添, 陈尧, 何才厚, 龙盛蓉, 李秋锋. 损伤声发射信号小波包神经网络特征识别方法[J]. 北京邮电大学学报, 2021, 44(1): 124-130.

QI Tian-tian, CHEN Yao, HE Cai-hou, LONG Sheng-rong, LI Qiu-feng. A Wavelet Packet Neural Network Feature Recognition Method for Damage Acoustic Emission Signals[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(1): 124-130.

参考文献

[1] Mccrory J P, Al-Jumaili S K, Crivelli D, et al. Damage classification in carbon fibre composites using acoustic emission:A comparison of three techniques[J]. Composites Part B:Engineering, 2015, 68:424-430.
[2] Wei Xinchen, Chen Yao, Lu Chao, et al. Acoustic emission source localization method for high-speed train bogie[J]. Multimedia Tools and Applications, 2020, 79:14933-14949.
[3] 李昕, 罗更生, 龙盛蓉, 等. 钢板声发射时间反转聚焦增强定位方法[J]. 仪器仪表学报, 2016, 37(8):1792-1799. Li Xin, Luo Gengsheng, Long Shengrong, et al. Location method of acoustic emission by time reversal focusing and enhancing for steel plate[J]. Chinese Journal of Scientific Instrument, 2016, 37(8):1792-1799.
[4] 齐添添, 陈尧, 李昕, 等. 基于时间反转的玻璃钢复合板材声发射源定位方法[J]. 仪器仪表学报, 2020, 41(6):208-217. Qi Tiantian, Chen Yao, Li Xin, et al. AE source location method based on time reversal for GFRP plate[J]. Chinese Journal of Scientific Instrument, 2020, 41(6):208-217.
[5] 于金涛, 赵树延, 王祁. 基于经验模态分解和小波变换声发射信号去噪[J]. 哈尔滨工业大学学报, 2011, 43(10):88-92. Yu Jintao, Zhao Shuyan, Wang Qi. De-nosing of acoustic emission signals based on empirical mode decomposition and wavelet transform[J]. Journal of Harbin Institute of Technology, 2011, 43(10):88-92.
[6] 蒋佳炜, 胡以怀, 柯赟, 等. 基于小波包特征提取和模糊熵特征选择的柴油机故障分析[J]. 振动与冲击, 2020, 39(4):273-277, 298. Jiang Jiawei, Hu Yihuai, Ke Yun, et al. Fault diagnosis of diesel engines based on wavelet packet energy spectrum feature extraction and fuzzy entropy feature selection[J]. Journal of Vibration and Shock, 2020, 39(4):273-277, 298.
[7] 陈世平, 王振忠, 俞辉, 等. 改进小波包多阈值去噪法及其工程应用[J]. 中国机械工程, 2017, 28(20):2414-2419. Chen Shiping, Wang Zhenzhong, Yu Hui, et al. Improved wavelet packet multi threshold denoising method and its engineering applications[J]. China Mechanical Engineering, 2017, 28(20):2414-2419.
[8] Bianchi D, Mayrhofer E, Groschl M, et al. Wavelet packet transform for detection of single events in acoustic emission signals[J]. Mechanical Systems & Signal Processing, 2015, 64:441-451.
[9] 梁晓敏, 周伟, 庞艳荣, 等. 基于小波分析的复合材料层间损伤声发射行为[J]. 玻璃钢/复合材料, 2014, (8):44-48. Liang Xiaomin, Zhou Wei, PangYanrong, et al. Acoustic emission behavior on interlaminar damage of composite based on wavelet analysis[J]. Fiber Reinforced Plastics/Composites, 2014, (8):44-48.
[10] Sachse W, Grabec I. Intelligent processing of acoustic emission signals[J]. Materials Evaluation, 1992, 50:826-832.
[11] Bhat C, Bhat M, Murthy C. Acoustic emission characterization of failure modes in composites with ANN[J]. Composite Structures, 2003, 61(3):213-220.
[12] 郭飞, 张培伟, 张大海, 等. 基于小波包能量特征向量的光纤布拉格光栅低速冲击定位[J]. 振动与冲击, 2017, 36(8):184-189. Guo Fei, Zhang Peiwei, Zhang Dahai, et al. Localization of low-velocity impact by using fiber Bragg grating sensors based on wavelet packet energy eigenvector[J]. Journal of Vibration and Shock, 2017, 36(8):184-189.
[13] Lu Jiyun, Wang Bangfeng, Liang Dakai. Wavelet packet energy characterization of low velocity impacts and load localization by optical fiber Bragg grating sensor technique[J]. Applied Optics, 2013, 52:2346-2352.
[14] 宁方立, 韩鹏程, 段爽, 等. 基于改进CNN的阀门泄漏超声信号识别方法研究[J]. 北京邮电大学学报, 2020, 43(3):38-44. Ning Fangli, Han Pengcheng, Duan Shuang, et al. Research on identification method of valve leakage ultrasonic signal based on improved CNN[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(3):38-44.
[15] 蒋芳, 张南飞, 胡艳军, 等. 基于BP神经网络的CSI无源目标分类方法[J]. 北京邮电大学学报, 2020, 43(1):40-45. Jiang Fang, Zhang Nanfei, Hu Yanjun, et al. BP neural network based CSI device-free target classification method[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(1):40-45.

损伤声发射信号小波包神经网络特征识别方法

A Wavelet Packet Neural Network Feature Recognition Method for Damage Acoustic Emission Signals

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	普运伟, 郭江, 刘涛涛, 吴海潇. 基于多学习单元卷积神经网络的雷达辐射源信号识别[J]. 北京邮电大学学报, 2021, 44(6): 74-82.
[2]	戴剑勇, 邓先红, 王彬, 汪恒浩. 基于改进萤火虫优化神经网络的WSNs分簇路由协议[J]. 北京邮电大学学报, 2020, 43(3): 131-137.
[3]	田昊旻, 尹良, 马跃, 李书芳. 基于对信号功率谱拟合特征提取的信号识别方法[J]. 北京邮电大学学报, 2018, 41(2): 114-118.
[4]	姚赟政, 杨安, 石志强, 孙利民. 工控设备状态检测中BP神经网络模型的应用[J]. 北京邮电大学学报, 2016, 39(s1): 14-18.
[5]	亓峰, 李琪, 韩骞, 杜益, 邱雪松. 基于神经网络的电力通信网风险评估方法[J]. 北京邮电大学学报, 2014, 37(1): 90-93.
[6]	张闯姜杨吴铭肖文君李泰. 基于社会化媒体节点属性的信息预测[J]. 北京邮电大学学报, 2012, 35(4): 24-27.
[7]	张磊;陈俊亮;孟祥武; 沈筱彦;段锟. 基于BP神经网络的协作过滤推荐算法[J]. 北京邮电大学学报, 2009, 32(6): 42-46.
[8]	白自权,李道本. 基于EVA的改进型盲均衡算法[J]. 北京邮电大学学报, 2005, 28(4): 10-13.
[9]	徐海东,李冶文,江峰,宋俊德. 基于神经网络的UTRAN网络质量综合评价[J]. 北京邮电大学学报, 2005, 28(4): 41-44.
[10]	丁开盛, 张学渊, 梁雄健. 电信网可靠性的综合评价方法[J]. 北京邮电大学学报, 1999, 22(1): 66-70.