基于深度学习的分布式光纤损伤识别方法

doi:10.3901/JME.2022.08.088

机械工程学报 ›› 2022, Vol. 58 ›› Issue (8): 88-95.doi: 10.3901/JME.2022.08.088

• 特邀专栏：机械装备的光纤传感检测与应用 • 上一篇下一篇

扫码分享

基于深度学习的分布式光纤损伤识别方法

李建乐¹, 张佳奇¹, 黄念², 李腾腾¹, 徐浩¹, 夏梓旭¹, 武湛君¹

1. 大连理工大学工业装备结构分析国家重点实验室大连 116024;
2. 北京空天技术研究所北京 100074

收稿日期:2021-01-09 修回日期:2021-09-06 出版日期:2022-04-20 发布日期:2022-06-13
通讯作者: 徐浩(通信作者),男,1983年出生,副教授。主要研究方向为结构健康监测、复合材料结构设计。E-mail:xuhao@dlut.edu.cn
作者简介:李建乐,男,1995年出生,博士研究生。主要研究方向为结构健康监测及分布式光纤传感技术。E-mail:ljldllgdx@mail.dlut.edu.cn
基金资助:
国家重点研发计划(2018YFA0702800)和某国防基础科研(XXXX2018204BXXX)资助项目。

Distributed Optical Fiber Damage Identification Method Based on Deep Learning

LI Jianle¹, ZHANG Jiaqi¹, HUANG Nian², LI Tengteng¹, XU Hao¹, XIA Zixu¹, WU Zhanjun¹

1. State key Lab. of Structural Analysis for Industrial Equipment, Dalian University of Technology, Dalian 116024;
2. Beijing Aerospace Technology Research Institute, Beijing 100074

Received:2021-01-09 Revised:2021-09-06 Online:2022-04-20 Published:2022-06-13

摘要/Abstract

摘要： 航空航天复合材料结构服役环境恶劣，为保证结构安全运行需要发展结构健康监测技术，基于背向瑞利散射的分布式光纤传感器因其便于埋入、抗干扰能力强等优点被广泛应用于结构健康监测领域。如何从复杂的光纤数据中识别结构损伤是健康监测的研究难点之一，基于此问题提出一种用于损伤识别的深度学习方法，采用一维卷积神经网络对复合材料层合板中的脱粘和裂纹损伤进行识别。为了验证方法的可靠性，设置预制损伤的酚醛树脂层合板的悬臂加载试验，其埋入的分布式光纤传感器很好地监测到了损伤区域的应变变化特征，采用试验数据对网络结构进行参数调整，最终确定卷积核大小和卷积层数目。试验结果表明，训练后的一维卷积神经网络能够从复杂的应变曲线中识别出损伤特征，并对损伤特征进行准确定位。在目前的研究中，该方法能够准确识别3 cm²的脱粘损伤和20 mm长的裂纹损伤，同时定位精度小于4 mm。

关键词: 结构健康监测, 分布式光纤, 卷积神经网络, 损伤识别

Abstract: The service environment of aerospace composite structures is harsh. In order to ensure the safe operation of structures, it is necessary to develop structural health monitoring technology. Distributed optical fiber sensor based on back Rayleigh scattering is widely used in the field of structural health monitoring because of its advantages of easy embedding and strong anti-interference ability. How to identify structural damage from complex optical fiber data is one of the research difficulties of health monitoring. Based on this problem, a deep learning method for damage identification is proposed. One dimensional convolution neural network is used to identify debonding and crack damage in composite laminates. In order to verify the reliability of the method, the cantilever loading test of prefabricated damaged phenolic resin laminates is set up. The embedded distributed optical fiber sensor can well monitor the strain change characteristics of the damaged area. The parameters of the network structure are adjusted by using the experimental data, and the convolution core size and the number of convolution layers are finally determined. The experimental results show that the trained one-dimensional convolutional neural network can identify the damage features from the complex strain curve and accurately locate the damage features. In the current research, this method can accurately identify 3cm² debonding damage and 20 mm long crack damage, and the positioning accuracy is less than 4mm.

Key words: structural health monitoring, distributed optical fiber, convolution neural network, damage identification

中图分类号:

TG156

李建乐, 张佳奇, 黄念, 李腾腾, 徐浩, 夏梓旭, 武湛君. 基于深度学习的分布式光纤损伤识别方法[J]. 机械工程学报, 2022, 58(8): 88-95.

LI Jianle, ZHANG Jiaqi, HUANG Nian, LI Tengteng, XU Hao, XIA Zixu, WU Zhanjun. Distributed Optical Fiber Damage Identification Method Based on Deep Learning[J]. Journal of Mechanical Engineering, 2022, 58(8): 88-95.

参考文献

[1] 武湛君,渠晓溪,高东岳,等.航空航天复合材料结构健康监测技术研究进展[J].航空制造技术,2016(15):92-102. WU Zhanjun,QU Xiaoxi,GAO Dongyue,et al. Research progress of structural health monitoring technology for aerospace composite materials[J]. Aerospace Manufact-uring Technology,2016(15):92-102.
[2] 卿新林,王奕首,赵琳.结构健康监测技术及其在航空航天领域中的应用[J].实验力学,2012,27(5):517-526. QING Xinlin,WANG Yishou,ZHAO Lin. Structural health monitoring technology and its application in aerospace field[J]. Experimental Mechanics,2012,27(5):517-526.
[3] GLISIC B,INAUDI D. Development of method for in-service crack detection based on distributed fiber optic sensors[J]. Structural Health Monitoring,2011,11(2):161-171.
[4] 吕睿.基于分布式光纤的飞行器典型构件多参量识别[D].大连:大连理工大学,2019. LU Rui. Multi parameter identification of typical aircraft components based on distributed optical fiber[D]. Dalian:Dalian University of Technology,2019.
[5] 单一男,武湛君,徐新生,等.基于分布式光纤传感的隔热层脱粘识别研究[J].压电与声光,2020,42(1):25-28. SHAN Yinan,WU Zhanjun,XU Xinsheng,et al. Research on debonding recognition of thermal insulation layer based on distributed optical fiber sensing[J]. Piezoelectric and Acousto Optic,2020,42(1):25-28.
[6] 雷亚国,贾峰,周昕,等.基于深度学习理论的机械装备大数据健康监测方法[J].机械工程学报,2015,51(21):49-56. LEI Yaguo,JIA Feng,ZHOU Xin,et al. Health monitoring method of mechanical equipment big data based on deep learning theory[J]. Journal of Mechanical Engineering,2015,51(21):49-56.
[7] CANTERO-CHINCHILLA S,CHIACHÍO J,CHIACHÍO M,et al. A robust Bayesian methodology for damage localization in plate-like structures using ultrasonic guided-waves[J]. Mechanical Systems and Signal Processing,2019,122(1):192-205.
[8] VAKIL-BAGHMISHEH M-T,PEIMANI M,SADEGHI M H,et al. Crack detection in beam-like structures using genetic algorithms[J]. Applied Soft Computing,2008,8(2):1150-1160.
[9] 孙宗光,高赞明,倪一清.基于神经网络的桥梁损伤位置识别[J].工程力学,2004,21(1):42-47. SUN Zongguang,GAO Zanming,NI Yiqing. Identification of bridge damage location based on neural network[J]. Engineering Mechanics,2004,21(1):42-47.
[10] ABDELJABER O,AVCI O,KIRANYAZ M S,et al. 1-D CNNs for structural damage detection:Verification on a structural health monitoring benchmark data[J]. Neurocomputing,2017,275:1308-1317.
[11] JANG K Y,KIM B,CHO S,et al. Deep learning-based concrete crack detection using hybrid images[C/CD]//Sensors and Smart Structures Technologies for Civil,Mechanical,and Aerospace Systems,2018.
[12] LECUN Y,BENGIO Y,HINTON G. Deep learning[J]. Nature,2015,521(7553):436-444.
[13] LIU T,XU H,RAGULSKIS M,et al. A data-driven damage identification framework based on transmissibility function datasets and one-dimensional convolutional neural networks:Verification on a structural health monitoring benchmark structure[J]. Sensors,2020,20(4):1059-1084.
[14] SONG Q,ZHANG C,TANG G,et al. Deep learning method for detection of structural microcracks by Brillouin scattering based distributed optical fiber sensors[J]. Smart Materials and Structures,2020,29(7):075008-075020.
[15] LECUN Y,BOTTOU L,BENGIO Y,et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE,1998,86(11):2278-2324.
[16] FROGGATT M,MOORE J. High-spatial-resolution distributed strain measurement in optical fiber with Rayleigh scatter[J]. Applied Optics,1998,37(10):1735-1740.

基于深度学习的分布式光纤损伤识别方法

Distributed Optical Fiber Damage Identification Method Based on Deep Learning

PDF

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]	孙仕林, 王天杨, 褚福磊. 基于振动及声学测量的风电叶片结构健康监测研究综述[J]. 机械工程学报, 2024, 60(7): 79-92.
[2]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[3]	陈健, 孟义兴, 袁慎芳, 徐秋慧, 王卉. 融合导波监测的搭接结构裂纹扩展寿命孪生预测[J]. 机械工程学报, 2024, 60(16): 34-42.
[4]	任元强, 严嘉慧, 袁慎芳, 张巾巾. 时变影响下导波健康HMM的损伤定量诊断方法[J]. 机械工程学报, 2024, 60(16): 54-61.
[5]	袁静, 任港星, 蒋会明, 赵倩, 魏臣隽, 朱骏. 基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究[J]. 机械工程学报, 2024, 60(12): 51-64.
[6]	陈钱, 陈康康, 董兴建, 皇甫一樊, 彭志科, 孟光. 一种面向机械设备故障诊断的可解释卷积神经网络[J]. 机械工程学报, 2024, 60(12): 65-76.
[7]	王振亚, 刘韬, 伍星. 互信息规范的卷积神经网络及其在轴承故障特征提取中的应用[J]. 机械工程学报, 2024, 60(12): 137-146.
[8]	邓磊鑫, 谢清林, 陶功权, 温泽峰. 基于轴箱振动与动力学模型驱动的高速列车车轮失圆状态识别方法[J]. 机械工程学报, 2023, 59(3): 110-121.
[9]	于宗营, 沈功田, 赵章焰, 吴占稳, 刘渊. 计算机视觉结构健康监测的研究进展及在大型游乐设施上的应用展望[J]. 机械工程学报, 2023, 59(16): 167-181.
[10]	孙凤山, 范孟豹, 曹丙花, 刘林. 基于时频关键信息融合的热障涂层太赫兹准确测厚方法[J]. 机械工程学报, 2023, 59(14): 10-22.
[11]	刘正勇, LIN Htein, 刘繄, 钟永康, 谭华耀. 特种微结构光纤振动传感器及其铁路监测应用[J]. 机械工程学报, 2022, 58(8): 63-70.
[12]	尹国路, 蒋锐, 徐州, 周雷, 牛洋洋, 吕雷, 朱涛. 快速、高空间分辨分布式光纤传感技术及其在机械形变和温度监测中的应用[J]. 机械工程学报, 2022, 58(8): 96-104.
[13]	杨炜, 黄立红, 屈晓磊. 融合双注意力机制EfficientNet的沥青路面状态分类方法[J]. 机械工程学报, 2022, 58(24): 211-222.
[14]	孙誉宁, 毛磊, 黄伟国, 章恒, 陆守香. 基于磁场的质子交换膜燃料电池故障诊断方法[J]. 机械工程学报, 2022, 58(22): 106-114.
[15]	高凯, 李勋豪, 胡林, 陈彬, 杜荣华. 基于多头注意力的CNN-LSTM的换道意图预测[J]. 机械工程学报, 2022, 58(22): 369-378.