当前位置: X-MOL 学术Struct. Health Monit. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Continuous missing data imputation with incomplete dataset by generative adversarial networks–based unsupervised learning for long-term bridge health monitoring
Structural Health Monitoring ( IF 5.7 ) Pub Date : 2021-06-04 , DOI: 10.1177/14759217211021942
Huachen Jiang 1 , Chunfeng Wan 1 , Kang Yang 1 , Youliang Ding 1 , Songtao Xue 2, 3
Affiliation  

Wireless sensors are the key components of structural health monitoring systems. During the signal transmission, sensor failure is inevitable, among which, data loss is the most common type. Missing data problem poses a huge challenge to the consequent damage detection and condition assessment, and therefore, great importance should be attached. Conventional missing data imputation basically adopts the correlation-based method, especially for strain monitoring data. However, such methods often require delicate model selection, and the correlations for vehicle-induced strains are much harder to be captured compared with temperature-induced strains. In this article, a novel data-driven generative adversarial network (GAN) for imputing missing strain response is proposed. As opposed to traditional ways where correlations for inter-strains are explicitly modeled, the proposed method directly imputes the missing data considering the spatial–temporal relationships with other strain sensors based on the remaining observed data. Furthermore, the intact and complete dataset is not even necessary during the training process, which shows another great superiority over the model-based imputation method. The proposed method is implemented and verified on a real concrete bridge. In order to demonstrate the applicability and robustness of the GAN, imputation for single and multiple sensors is studied. Results show the proposed method provides an excellent performance of imputation accuracy and efficiency.



中文翻译:

通过基于生成对抗网络的无监督学习对不完整数据集进行连续缺失数据插补,用于长期桥梁健康监测

无线传感器是结构健康监测系统的关键组件。在信号传输过程中,传感器故障在所难免,其中数据丢失是最常见的类型。缺失数据问题对后续的损伤检测和状态评估提出了巨大的挑战,因此应予以高度重视。传统的缺失数据插补基本上采用基于相关的方法,特别是对于应变监测数据。然而,这些方法通常需要精细的模型选择,并且与温度诱导的应变相比,车辆诱导的应变的相关性更难捕获。在本文中,提出了一种用于估算缺失应变响应的新型数据驱动生成对抗网络 (GAN)。与显式建模应变间相关性的传统方法相反,所提出的方法考虑到基于剩余观测数据的其他应变传感器的时空关系,直接估算缺失数据。此外,在训练过程中甚至不需要完整完整的数据集,这显示了相对于基于模型的插补方法的另一个巨大优势。所提出的方法在一个真实的混凝土桥梁上得到实施和验证。为了证明 GAN 的适用性和鲁棒性,研究了单个和多个传感器的插补。结果表明,所提出的方法提供了良好的插补精度和效率性能。所提出的方法根据剩余的观测数据,考虑与其他应变传感器的时空关系,直接估算缺失的数据。此外,在训练过程中甚至不需要完整完整的数据集,这显示了相对于基于模型的插补方法的另一个巨大优势。所提出的方法在一个真实的混凝土桥梁上得到实施和验证。为了证明 GAN 的适用性和鲁棒性,研究了单个和多个传感器的插补。结果表明,所提出的方法提供了良好的插补精度和效率性能。所提出的方法根据剩余的观测数据,考虑与其他应变传感器的时空关系,直接估算缺失的数据。此外,在训练过程中甚至不需要完整完整的数据集,这显示了相对于基于模型的插补方法的另一个巨大优势。所提出的方法在一个真实的混凝土桥梁上得到实施和验证。为了证明 GAN 的适用性和鲁棒性,研究了单个和多个传感器的插补。结果表明,所提出的方法提供了良好的插补精度和效率性能。这显示了基于模型的插补方法的另一个巨大优势。所提出的方法在一个真实的混凝土桥梁上得到实施和验证。为了证明 GAN 的适用性和鲁棒性,研究了单个和多个传感器的插补。结果表明,所提出的方法提供了良好的插补精度和效率性能。这显示了基于模型的插补方法的另一个巨大优势。所提出的方法在一个真实的混凝土桥梁上得到实施和验证。为了证明 GAN 的适用性和鲁棒性,研究了单个和多个传感器的插补。结果表明,所提出的方法提供了良好的插补精度和效率性能。

更新日期:2021-06-04
down
wechat
bug