基于卷积自编码和相关函数的钢框架损伤识别研究

杨银枪; 康帅; 王自法; 赫中营; 滕辉

doi:10.3724/j.gyjzG23102311

基于卷积自编码和相关函数的钢框架损伤识别研究

doi: 10.3724/j.gyjzG23102311

杨银枪¹,
康帅^1, ,,
王自法^1,2,
赫中营¹,
滕辉¹

1. 河南大学土木建筑学院, 河南开封 475004;
2. 中震科建(广东)防灾减灾研究院有限公司, 广东韶关 512000

基金项目:

河南省科技厅科技攻关项目(162102210173)。

河南省自然科学基金项目(182300410150)

详细信息

作者简介:
杨银枪,硕士研究生,主要从事防灾减灾方面研究,1399407071@qq.com。

通讯作者:
康帅,工学博士,副教授,硕士生导师,kangshuai@henu.edu.cn。

计量
- 文章访问数: 32
- HTML全文浏览量: 8
- PDF下载量: 2
- 被引次数: 0
出版历程
- 收稿日期: 2023-10-23
- 网络出版日期: 2024-12-05

Research on Damage Identification for Steel Frames Based on Convolutional Autoencoder and Correlation Function

1. School of Civil Engineering and Architecture, Henan University, Kaifeng 475004, China;
2. Zhongzhen Science and Technology Construction(Guangdong) Disaster Prevention and Mitigation Research Institute Co., Ltd., Shaoguan 512000, China

摘要

摘要: 针对深度学习模型在数据样本不均衡和噪声影响下的损伤识别精度下降这一问题,提出了基于卷积自编码和相关函数相结合的结构损伤识别方法。以卡塔尔大学看台缩尺试验为例,将健康工况样本数据输入卷积自编码模型进行学习,通过构建的卷积自编码模型对健康结构数据样本进行数据重构,以数据重构误差最大值作为阈值判别结构是否发生损伤。然后,在包含健康工况样本和损伤工况样本的数据集中加入不同信噪比的高斯白噪声,通过自相关函数对加入噪声的数据样本进行预处理,将预处理后的数据集和未经过自相关函数处理的数据集分别输入模型进行训练和预测,并对模型的预测结果进行对比分析。结果表明,该方法在未加入噪声数据样本不均衡的情况下可以准确进行结构损伤识别,识别准确率可达100%。而数据在加入噪声的影响下,经过自相关函数的处理,数据原始特征得以凸显,在施加信噪比为5的噪声工况下,识别准确率仍能达到100%,可以有效提高损伤识别精度并具有较强抗噪性。
- 深度学习 /
- 损伤识别 /
- 卷积自编码 /
- 自相关函数 /
- 框架结构
Abstract: Aiming at the problem that the damage recognition accuracy of the deep learning model decreases under the influence of data sample imbalance and noise, a structural damage recognition method based on the combination of convolutional autoencoder and correlation function was proposed. Taking the stand scale test of Qatar University as an example, the sample data of healthy working conditions were input into the convolutional autoencoder model for learning, and the constructed convolutional autoencoder model was used to reconstruct the data samples of the healthy structural data samples, and the maximum error of data reconstruction was used as a threshold to judge whether the structure was damaged. Then, Gaussian white noise with different signal-to-noise ratios was added to the data set containing healthy working condition samples and damaged working condition samples, and the data samples added with noise were preprocessed by autocorrelation function. The data set processed by the autocorrelation function was input into the model for training and prediction respectively, and the prediction results of the model were compared and analyzed. The results showed that the method could accurately identify structural damage when the data samples without noise were not balanced, and the identification accuracy could reach 100%. However, under the influence of adding noise, the original characteristics of the data could be highlighted after being processed by the autocorrelation function. Under the noise condition with a signal-to-noise ratio of 5, the recognition accuracy could still reach 100%, which proved that the method could effectively improve the accuracy of damage recognition of the autoencoder model and had better noise resistance.
- deep learning /
- damage identification /
- convolutional autoencoder /
- autocorrelation function /
- framework structure

HTML全文

参考文献(31)

[1]	赵一男, 公茂盛, 杨游.结构损伤识别方法研究综述[J].世界地震工程, 2020, 36(2):73-84.
[2]	ALVANDI A, CREMONA C.Assessment of vibration-based damage identification techniques[J].Journal of Sound and Vibration, 2006, 292(1/2):179-202.
[3]	TOMASZEWSKA A.Influence of statistical errors on damage detection based on structural flexibility and mode shape curvature[J].Computers and Structures, 2010, 88(3/4):154-164.
[4]	RADZIENSKI M, KRAWCZUK M, PALACZ M.Improvement of damage detection methods based on experimental modal parameters[J]. Mechanical Systemsand Signal Processing, 2011, 25(6):2169-2190.
[5]	WORDEN K, MANSON G, FIELLER N R J. Damage detectionusing outlier analysis [J].Journal of Soundand Vibration, 2000, 229(3):647-667.
[6]	BALSAMO L, BETTI R. Data-based structural health monitoring using small training datasets[J].Structural Control and Health Monitoring, 2015, 22(10): 1240-1264.
[7]	GARCIA D, TCHERNIAK D.An experimental study on the data-driven structural health monitoring of large wind turbine blades using a single accelerometer and actuator [J].Mechanical Systems and Signal Processing, 2019, 127(15):102-119.
[8]	颜王吉, 王朋朋, 孙倩, 等.基于振动响应传递比函数的系统识别研究进展[J].工程力学, 2018, 35(5):1-9.
[9]	YAN W J, ZHAO M Y, SUN Q, et al.Transmissibility-based system identification for structural health monitoring:fundamentals, approaches, and applications[J].Mechanical Systems and Signal Processing, 2019, 117:453-482.
[10]	宗周红, 任伟新, 阮毅. 土木工程结构损伤诊断研究进展[J]. 土木工程学报, 2003, 36(5):105-110.
[11]	杨铄, 许清风, 王卓琳.基于卷积神经网络的结构损伤识别研究进展[J].建筑科学与工程学报, 2022, 39(4):38-57.
[12]	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, 2018, 275:1308-1317.
[13]	LIN Y, NIE Z, MA H. Structural damage detection with automatic feature-extraction through deep learning[J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(12):1025-1046.
[14]	李雪松, 马宏伟, 林逸洲.基于卷积神经网络的结构损伤识别[J].振动与冲击, 2019, 38(1):159-167.
[15]	骆勇鹏, 王林堃, 廖飞宇, 等.基于一维卷积神经网络的结构损伤识别[J].地震工程与工程振动, 2021, 41(4):145-156.
[16]	成浩维, 资文杰, 彭双, 等.基于半监督学习的三维Mesh建筑物立面提取与语义分割方法[J].郑州大学学报(理学版), 2023, 55(4):8-15.
[17]	GUO Y, JI T, WANG Q, et al. Unsupervised anomaly detection in IoT systems for smart cities[J]. IEEE Transactions on Network Science and Engineering, 2020, 7(4): 2231-2242.
[18]	NI F T, ZHANG J, NOORI M N.Deep learning for data anomaly detection and datacompression of a long-span suspension bridge[J].Computer-Aided Civil and Infrastructure Engineering, 2019, 35 (7):685-700.
[19]	LIN S Z, SHI Y, XUE Z.Character-level intrusion detection based on convolutional neural networks[C]//International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro: 2018:1-8.
[20]	郑婷婷. 基于堆叠稀疏自编码器和分布式应变的桥梁表面裂缝检测[D].西安:长安大学, 2021.
[21]	YU J, ZHOU X. One-dimensional residual convolutional autoencoder based feature learning for gearbox fault diagnosis[J].IEEE Transactions on Industrial Informatics, 2020, 16 (10):6347-6358.
[22]	CUI M L, WANG Y Q, LIN X S, et al.Fault diagnosis of rolling bearings based on an improved stack autoencoder and support vector machine[J].IEEE Sensors Journal, 2020, 21(4):4927-4937.
[23]	滑世辉, 韩立国.基于深度卷积自编码网络地震数据去噪方法[J].地球物理学进展, 2023, 38(2):654-661.
[24]	刘建华, 杨皓楠, 何静, 等.基于约束对抗卷积自编码记忆融合网络的故障诊断[J].电机与控制学报, 2023, 27(6):148-159.
[25]	方能炜, 刘兰徽, 邢镔, 等.自相关结合灰色关联度的轴承早期故障诊断方法[J].机械科学与技术, 2023, 42(12):1972-1976.
[26]	王玉山, 田良, 郭惠勇.基于加速度内积向量和灰云模型的结构损伤识别[J].重庆大学学报, 2018, 41(1):9-16.
[27]	YANG Z C, WANG L, WANG H, et al.Damage detection in composite structures using vibration response under stochastic excitation[J].Journal of Sound and Vibration, 2009, 325:755-768.
[28]	胡鑫, 杨智春, 王乐.基于振动响应内积向量和数据融合的结构损伤检测方法试验研究[J].振动与冲击, 2013, 32(14):109-115.
[29]	付茂森. 基于卷积自编码神经网络的桥梁损伤识别研究[D].石家庄:石家庄铁道大学, 2022.
[30]	AVCI O, ABDELJABER O, KIRANYAZ S, et al.Convolutional neural networks for real-time and wireless damage detection[J]. Dynamics of Civil Structures, 2020, 2:129-136.
[31]	DYKE S, BERNAL D, BECK J, et al. Experimental phase II of the structural health monitoring benchmark problem[C]//Proc 16th ASCE Engineering Mechanics Conference. Colorado: 2003.