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.)
Damage detection in a novel deep-learning framework: a robust method for feature extraction
Structural Health Monitoring ( IF 5.7 ) Pub Date : 2019-05-27 , DOI: 10.1177/1475921719846051
Tian Guo 1 , Lianping Wu 1 , Cunjun Wang 1 , Zili Xu 1
Affiliation  

Extracting damage features precisely while overcoming the adverse interferences of measurement noise and incomplete data is a problem demanding prompt solution in structural health monitoring (SHM). In this article, we present a deep-learning-based method that can extract the damage features from mode shapes without utilizing any hand-engineered feature or prior knowledge. To meet various requirements of the damage scenarios, we use convolutional neural network (CNN) algorithm and design a new network architecture: a multi-scale module, which helps in extracting features at various scales that can reduce the interference of contaminated data; stacked residual learning modules, which help in accelerating the network convergence; and a global average pooling layer, which helps in reducing the consumption of computing resources and obtaining a regression performance. An extensive evaluation of the proposed method is conducted by using datasets based on numerical simulations, along with two datasets based on laboratory measurements. The transferring parameter methodology is introduced to reduce retraining requirement without any decreases in precision. Furthermore, we plot the feature vectors of each layer to discuss the damage features learned at these layers and additionally provide the basis for explaining the working principle of the neural network. The results show that our proposed method has accuracy improvements of at least 10% over other network architectures.

中文翻译:

新型深度学习框架中的损伤检测:一种鲁棒的特征提取方法

在克服测量噪声和不完整数据的不利干扰的同时准确提取损伤特征是结构健康监测(SHM)中需要及时解决的问题。在本文中,我们提出了一种基于深度学习的方法,该方法可以在不利用任何手工设计的特征或先验知识的情况下从振型中提取损伤特征。为了满足损伤场景的各种要求,我们使用卷积神经网络(CNN)算法,设计了一种新的网络架构:多尺度模块,有助于提取各种尺度的特征,减少污染数据的干扰;堆叠残差学习模块,有助于加速网络收敛;和一个全局平均池化层,这有助于减少计算资源的消耗并获得回归性能。通过使用基于数值模拟的数据集以及基于实验室测量的两个数据集,对所提出的方法进行了广泛的评估。引入转移参数方法以减少再训练要求,而不会降低精度。此外,我们绘制了每一层的特征向量来讨论在这些层学习的损伤特征,并另外为解释神经网络的工作原理提供基础。结果表明,我们提出的方法与其他网络架构相比,精度至少提高了 10%。以及基于实验室测量的两个数据集。引入转移参数方法以减少再训练要求,而不会降低精度。此外,我们绘制了每一层的特征向量来讨论在这些层学习的损伤特征,并另外为解释神经网络的工作原理提供基础。结果表明,我们提出的方法与其他网络架构相比,精度至少提高了 10%。以及基于实验室测量的两个数据集。引入转移参数方法以减少再训练要求,而不会降低精度。此外,我们绘制了每一层的特征向量来讨论在这些层学习的损伤特征,并另外为解释神经网络的工作原理提供基础。结果表明,我们提出的方法与其他网络架构相比,精度至少提高了 10%。我们绘制了每一层的特征向量来讨论在这些层学习到的损伤特征,并另外为解释神经网络的工作原理提供基础。结果表明,我们提出的方法与其他网络架构相比,精度至少提高了 10%。我们绘制了每一层的特征向量来讨论在这些层学习到的损伤特征,并另外为解释神经网络的工作原理提供基础。结果表明,我们提出的方法与其他网络架构相比,精度至少提高了 10%。
更新日期:2019-05-27
down
wechat
bug