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
李治甫(1996—),男,硕士研究生。主要从事抗震研究。E‑mail: LZF@henu.edu.cn
康帅(1983—),男,副教授,博士。主要从事抗震研究。 E‑mail: kangshuai@henu.edu.cn
收稿:2022-10-12,
修回:2023-02-10,
纸质出版:2023-12-15
移动端阅览
李治甫,康帅,王自法等.基于时频变换和卷积神经网络的结构损伤识别[J].防灾减灾工程学报,2023,43(06):1275-1283.
LI Zhifu,KANG Shuai,WANG Zifa,et al.Structural Damage Identification Based on Time‑frequency Transform and Convolutional Neural Network[J].Journal of Disaster Prevention and Mitigation Engineering,2023,43(06):1275-1283.
李治甫,康帅,王自法等.基于时频变换和卷积神经网络的结构损伤识别[J].防灾减灾工程学报,2023,43(06):1275-1283. DOI: 10.13409/j.cnki.jdpme.20221010002.
LI Zhifu,KANG Shuai,WANG Zifa,et al.Structural Damage Identification Based on Time‑frequency Transform and Convolutional Neural Network[J].Journal of Disaster Prevention and Mitigation Engineering,2023,43(06):1275-1283. DOI: 10.13409/j.cnki.jdpme.20221010002.
为了解决将单传感器时域数据直接作为卷积神经网络(CNN)的输入所引起的损伤识别精度不高的问题,提出基于小波包变换(DWPT)和快速傅里叶变换(FFT)的卷积神经网络识别方法。以短钢梁桥现场试验测得的数据集为例,将单传感器数据样本分别进行DWPT和FFT变换,使用变换后的特征训练1D‑CNN网络,训练好的网络测试精度有明显的提升,其识别精度均高于多个传感器数据直接作为输入的识别精度。同时分析了对噪声样本和异源(结构上未曾参与网络训练的传感器)数据的识别情况,结果表明对含噪声样本先进行时频变换再训练网络能显著提升对噪声样本的识别精度,而且能改善训练好的网络难以对异源传感器数据进行识别的问题,最后通过卡塔尔大学看台现场试验数据进一步论证上述结论。
To solve the problem of low accuracy in damage identification caused by using single sensor time-domain data directly as input for a convolutional neural network, a convolutional neural network identification method based on wavelet packet transform and fast Fourier transform is proposed. Taking the dataset measured in the field experiment on a short steel bridge as an example, single sensor data samples are transformed using DWPT and FFT respectively, and the transformed data are used to train the 1D-CNN network. The test accuracy of the trained network is obviously improved, and its recognition accuracy is higher than that of multiple sensor data directly as input. At the same time, the recognition of noise samples and data from sensors that have not participated in network training in structure is analyzed. The results show that the time-frequency transformation of noise samples before training the network can significantly improve the recognition accuracy of noise samples, and can improve the problem that the trained network is difficult to identify data from the sensor that have not participated in network training. Finally, the above conclusions are further demonstrated by test data from the grandstand of Qatar University.
朱宏平 , 余璟 , 张俊兵 . 结构损伤动力检测与健康监测研究现状与展望 [J]. 工程力学 , 2011 , 28 ( 2 ): 1 ‑ 11,17 .
Zhu H P , Yu J , Zhang J B . A summary review and advantages of vibration‑based damage identification methods in structural health monitoring [J]. Engineering Mechanics , 2011 , 28 ( 2 ): 1 ‑ 11,17 . (in Chinese)
杨秋伟 . 基于振动的结构损伤识别方法研究进展 [J]. 振动与冲击 , 2007 , 26 ( 10 ): 86 ‑ 91,100,190 .
Yang Q W . A review of vibration‑based structural damage identification methods [J]. Journal of Vibration and Shock , 2007 , 26 ( 10 ): 86 ‑ 91,100,190 . (in Chinese)
鲍跃全 , 李惠 . 人工智能时代的土木工程 [J]. 土木工程学报 , 2019 , 52 ( 5 ): 1 ‑ 11 .
Bao Y Q , Li H . Artificial intelligence for civil engineering [J]. China Civil Engineering Journal , 2019 , 52 ( 5 ): 1 ‑ 11 . (in Chinese)
Le C Y , Bottou L , Bengio Y , et al . Gradient‑based learning applied to document recognition [J]. Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 ‑ 2324 .
Abdeljaber O , Avci O , Kiranyaz S , et al . Real‑time vibration‑based structural damage detection using one‑dimensional convolutional neural networks [J]. Journal of Sound & Vibration , 2017 , 388 : 154 ‑ 170 .
Han Q H , Pan Y Z , Yang D B , et al . CNN‑based bolt loosening identification framework for prefabricated large‑span spatial structures [J]. Journal of Civil Structural Health Monitoring , 2022 , 12 : 517 ‑ 536 .
Teng S , Chen G . Vibration signal‑based structural damage detection through deep learning and digital image correlation [C]∥ IOP Conference Series: Earth and Environmental Science . China : IOP Publishing Ltd , 2021 , 719 ( 2 ): 022047 .
罗雨舟 , 向天宇 , 郝柳青 . 卷积神经网络在结构损伤检测中的应用 [J]. 土木工程与管理学报 , 2020 , 37 ( 3 ): 155 ‑ 161,173 .
Luo Y Z , Xiang T Y , Hao L Q . Application of convolutional neural networks in structural damage detection [J]. Journal of Civil Engineering and Management , 2020 , 37 ( 3 ): 155 ‑ 161,173 . (in Chinese)
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 .
Luo Y P , Wang L K , Liao F Y , et al . Vibration‑based structural damage identification by 1‑dimensional convolutional neural network [J]. Earthquake Engineering and Engineering Dynamics , 2021 , 41 ( 4 ): 145 ‑ 156 . (in Chinese)
骆剑彬 , 刘越生 , 姜绍飞 , 等 . 基于卷积神经网络和迁移学习的结构损伤识别 [J]. 福州大学学报(自然科学版) , 2022 , 50 ( 4 ): 546 ‑ 552 .
Luo J B , Liu Y S , Jiang S F , et al . Structural damage detection based on convolutional neural networks and transfer learning [J]. Journal of Fuzhou University(Natural Science Edition) , 2022 , 50 ( 4 ): 546 ‑ 552 . (in Chinese)
李书进 , 赵源 , 孔凡 , 等 . 卷积神经网络在结构损伤诊断中的应用 [J]. 建筑科学与工程学报 , 2020 , 37 ( 6 ): 29 ‑ 37 .
Li S J , Zhao Y , Kong F , et al . Application of convolutional neural networks in structural damage diagnosis [J]. Journal of Building Science and Engineering , 2020 , 37 ( 6 ): 29 ‑ 37 . (in Chinese)
Zou B J , Li W , Yang N , et al . Impact‑induced damage recognition of aluminium alloy stiffened plate structure based on convolutional neural network [J]. IEEE Sensors Journal , 2021 , 21 ( 18 ): 2 0283‑ 20295 .
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 .
Yang S , Xu Q F , Wang Z L . Research progress on structural damage detection based on convolutional neural networks [J]. Journal of Architecture and Engineering , 2022 , 39 ( 4 ): 38 ‑ 57 . (in Chinese)
李书进 , 熊书琪 , 范沛然 , 等 . 考虑残差学习的深层卷积神经网络在结构损伤识别中的应用研究 [J/OL]. 工业建筑 : 1 ‑ 12 [ 2022‑08‑18 ].
Li S J , Xiong S Q , Fan P R , et al . Application study on deep convolutional neural network considering residual learning in structural damage identification [J/OL]. Industrial Construction : 1 ‑ 12 [ 2022‑08‑18 ]. (in Chinese)
季长清 , 高志勇 , 秦静 , 等 . 基于卷积神经网络的图像分类算法综述 [J]. 计算机应用 , 2022 , 42 ( 4 ): 1044 ‑ 1049 .
Ji C Q , Gao Z Y , Qin J , et al . Review of image classification algorithms based on convolutional neural network [J]. Journal of Computer Applications , 2022 , 42 ( 4 ): 1044 ‑ 1049 . (in Chinese)
Meng Z J , Ni B B , Li T , et al . Robust geometric ℓp‑norm feature pooling for image classification and action recognition [J]. Image & Vision Computing , 2016 , 55 : 64 ‑ 76 .
周飞燕 , 金林鹏 , 董军 . 卷积神经网络研究综述 [J]. 计算机学报 , 2017 , 40 ( 6 ): 1229 ‑ 1251 .
Zhou F Y , Jin L P , Dong J . Review of the researches on convolutional neural networks [J]. Chinese Journal of Computer , 2017 , 40 ( 6 ): 1229 ‑ 1251 . (in Chinese)
Zhang Y , Miyamori Y , Mikami S , et al . Vibration‐based structural state identification by a 1‐dimensional convolutional neural network [J]. Computer‐Aided Civil and Infrastructure Engineering , 2019 , 34 ( 9 ): 822 ‑ 839 .
范春旸 , 吴守鹏 , 刘晓文 , 等 . 基于小波包变换与随机森林的滚动轴承故障特征分析方法 [J]. 机械设计与制造 , 2020 , 57 ( 10 ): 59 ‑ 63,70 .
Fan C Y , Wu S P , Liu X W , et al . Fault feature analysis method of rolling bearing based on wavelet packet transform and random forest [J]. Machinery Design & Manufacture , 2020 , 57 ( 10 ): 59 ‑ 63,70 . (in Chinese)
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 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
苏公网安备32010202012147号
