Structural health monitoring using extremely compressed data through deep learning
Structural health monitoring using extremely compressed data through deep learning
复制标题
通过深度学习利用极度压缩的数据进行结构健康监测
DOI：
10.1111/mice.12517
复制
发表时间：
2019-11-22
影响因子：
9.6
通讯作者：
Pekcan, Gokhan
中科院分区：
文献类型：
--
作者：
Azimi, Mohsen;Pekcan, Gokhan
这项研究介绍了一种新的基于卷积神经网络（CNN）的结构健康监测（SHM）方法，该方法通过基于迁移学习（TL）的技术利用一种形式的测量压缩响应数据。所提出的方法的实施允许在一个现实的大规模系统的损伤识别和定位。为了验证所提出的方法，首先，一个著名的基准模型进行了数值模拟。使用加速度响应历史以及离散直方图方面的压缩响应数据，训练CNN模型，并评估CNN架构的鲁棒性。最后，基于响应均值、标准差和比例因子，对预训练的CNN进行微调，以适应三参数、极度压缩的响应数据。每个CNN实现的性能都是使用训练准确性历史和混淆矩阵沿着其他性能指标来评估的。除了数值研究，所提出的方法的性能证明使用实验振动响应数据进行验证和确认。结果表明，采用不同类型的传感器可以有效地实现类似结构系统的SHM。
This study introduces a novel convolutional neural network (CNN)-based approach for structural health monitoring (SHM) that exploits a form of measured compressed response data through transfer learning (TL)-based techniques. The implementation of the proposed methodology allows damage identification and localization within a realistic large-scale system. To validate the proposed method, first, a well-known benchmark model is numerically simulated. Using acceleration response histories, as well as compressed response data in terms of discrete histograms, CNN models are trained, and the robustness of the CNN architectures is evaluated. Finally, pretrained CNNs are fine-tuned to be adaptable for three-parameter, extremely compressed response data, based on the response mean, standard deviation, and a scale factor. The performance of each CNN implementation is assessed using training accuracy histories as well as confusion matrices, along with other performance metrics. In addition to the numerical study, the performance of the proposed method is demonstrated using experimental vibration response data for verification and validation. The results indicate that deep TL can be implemented effectively for SHM of similar structural systems with different types of sensors.