基于多源时序生成对抗网络的结构加速度响应数据重构
张亚丽 , 付继东 , 段政滕 , 段元锋 , 朴星月
结构工程师 ›› 2025, Vol. 41 ›› Issue (05) : 176 -181.
基于多源时序生成对抗网络的结构加速度响应数据重构
Structural Acceleration Response Data Reconstruction Based on Multi-Source Time Series Generative Adversarial Networks
在桥梁健康监测中,由于传感器故障、维护不当或外部环境因素的影响,常常会导致收集到的传感器数据出现缺失。传统的数据处理方法往往依赖于线性插值、最近邻插值等技术,这些方法在处理大规模或高维度的时序数据时,常难以恢复数据的真实动态特性。为解决上述问题,本文提出一种多源时序生成对抗网络(MTSGAN),并针对一个三跨连续梁进行了数据重构研究。结果表明,当传感器故障率高达60%时,MTSGAN仍可以对其实现高精度数据重构,最高误差仅为10.3%。
In structural health monitoring, sensor data often suffer from missing values due to sensor faults, inadequate maintenance, or adverse environmental conditions. When dealing with large-scale or high-dimensional time-series data, traditional data processing methods, such as linear interpolation or nearest-neighbor interpolation, struggle to accurately reconstruct the true dynamic characteristics. To address this challenge, this study proposes a Multi-source Time Series Generative Adversarial Network (MTSGAN) for data reconstruction. The proposed method is then applied to a three-span continuous beam model to accurately predict structural acceleration responses. Results demonstrate that even when the sensor fault rate reaches 60%, MTSGAN achieves high-accuracy data reconstruction, with a maximum error of only 10.3%.
| [1] |
李惠,鲍跃全,李顺龙,结构健康监测数据科学与工程[J].工程力学,2015,32:1-7. |
| [2] |
LI Hui,BAO Yuequan,LI Shunlong,et al.Data science and engineering for structural health monitoring[J].Engineering Mechanics,2015,32:1-7.(in Chinese) |
| [3] |
TEFERA B,ZEKARIA A,GEBRE A.Challenges in applying vibration-based damage detection to highway bridge structures[J].Asian Journal of Civil Engineering,2023,24(6):1875-1894. |
| [4] |
SUN L,SHANG Z,XIA Y,et al.Review of bridge structural health monitoring aided by big data and artificial intelligence:From condition assessment to damage detection[J].Journal of Structural Engineering,2020,146(5):04020073. |
| [5] |
邓建新,单路宝,贺德强,缺失数据的处理方法及其发展趋势[J].统计与决策,2019,35(23):28-34. |
| [6] |
DENG Jianxin,SHAN Lubao,HE Deqiang,et al.Methods for handling missing data and development trends[J].Statistics and Decision,2019,35(23):28-34.(in Chinese) |
| [7] |
PAN Q,BAO Y,LI H.Transfer learning-based data anomaly detection for structural health monitoring[J].Structural Health Monitoring,2023,22(5):3077-3091. |
| [8] |
SVENDSEN B T,FRØSETH G T,ØISETH O,et al.A data-based structural health monitoring approach for damage detection in steel bridges using experimental data[J].Journal of Civil Structural Health Monitoring,2022,12(1):101-115. |
| [9] |
SUN H,SONG L,YU Z.A deep learning-based bridge damage detection and localization method[J].Mechanical Systems and Signal Processing,2023,193:110277. |
| [10] |
LI S,LAIMA S,LI H.Cluster analysis of winds and wind-induced vibrations on a long-span bridge based on long-term field monitoring data[J].Engineering Structures,2017,138:245-259. |
| [11] |
LIU G,DUNDAR A,SHIH K J,et al.Partial convolution for padding,inpainting,and image synthesis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,45(5):6096-6110. |
| [12] |
WANG X,WU K,ZHANG Y,et al.A GAN-based denoising method for Chinese stele and rubbing calligraphic image[J].The Visual Computer,2023,39(4):1351-1362. |
| [13] |
LEI X,SUN L,XIA Y.Lost data reconstruction for structural health monitoring using deep convolutional generative adversarial networks[J].Structural Health Monitoring,2021,20(4):2069-2087. |
/
| 〈 |
|
〉 |