scholarly journals Structural Damage Identification Based on Mode Shape Transformations and Supervised Learning

2019 ◽  
Author(s):  
◽  
Rims Janeliukštis
Keyword(s):  
Supervised Learning ◽  
Mode Shape ◽  
Structural Damage ◽  
Damage Identification ◽  
Structural Damage Identification ◽  
Shape Transformations

Attribute-based structural damage identification by few-shot meta learning with inter-class knowledge transfer

2020 ◽  
pp. 147592172092113
Author(s):  
Yang Xu ◽  
Yuequan Bao ◽  
Yufeng Zhang ◽  
Hui Li
Keyword(s):  
Supervised Learning ◽  
Structural Damage ◽  
Damage Identification ◽  
Learning Model ◽  
Classification Model ◽  
Parameter Study ◽  
Image Dataset ◽  
Structural Damage Identification ◽  
Meta Learning ◽  
Damage Types

Image archives of multi-class structural damages can be collected by manual inspection and then used for structural damage identification. On one hand, conventional image-processing-based approaches rely on optimal designs of hand-crafted feature detectors and lack universal adaptability for various application cases; on the other hand, regular supervised learning techniques require complete damage types and sufficient training examples to establish a robust damage recognition model, which brings up a time-labor-consuming image collection process. To solve these problems, this study proposes a nested attribute-based few-shot meta learning paradigm for structural damage identification. First, an external few-shot meta learning module is established based on different classification tasks named as meta-batches to produce robust classifiers for new damage types, in which support and query subsets including partial damage types and a few examples are randomly sampled from the original image dataset. Second, an embedded internal attribute-based transfer learning model is trained by minimizing the l2-norm and angular losses of attribute representation vectors in an end-to-end manner, where damage attributes act as the common inter-class knowledge and are transferred from the source damage space of support set to the target damage space of query set. Finally, the proposed approach is validated on a real-world structural damage image dataset, which contains 1000 examples of 10 representative damage types in total. Results show the proposed approach produces an overall accuracy of 93.5% and an average area under the ROC curve of 0.96 for 10 damage types. The general equilibrium of average precision and recall indicates that the trained model is balanced to both positive and negative examples for each damage type. Compared with a regular supervised learning model by directly classifying input images with one-hot vector labels, the proposed approach generates higher accuracy and better robustness. Parameter study suggests the proposed paradigm enables to train a stable and reliable meta learning classification model that can perform well across a series of settings about the ratio between support and query subsets. Theoretical analysis is also performed to explain why meta learning surpasses regular supervised learning.

Optimal Sensor Placement Algorithm for Structural Damage Identification

2020 ◽  
Vol 14 (1) ◽  
pp. 69-81
Author(s):  
C.H. Li ◽  
Q.W. Yang
Keyword(s):  
Structural Damage ◽  
Damage Identification ◽  
Sensor Placement ◽  
Optimization Procedure ◽  
Frame Structure ◽  
Truss Structures ◽  
Optimal Sensor Placement ◽  
Structural Damage Identification ◽  
Placement Algorithm ◽  
Sensor Locations

Background: Structural damage identification is a very important subject in the field of civil, mechanical and aerospace engineering according to recent patents. Optimal sensor placement is one of the key problems to be solved in structural damage identification. Methods: This paper presents a simple and convenient algorithm for optimizing sensor locations for structural damage identification. Unlike other algorithms found in the published papers, the optimization procedure of sensor placement is divided into two stages. The first stage is to determine the key parts in the whole structure by their contribution to the global flexibility perturbation. The second stage is to place sensors on the nodes associated with those key parts for monitoring possible damage more efficiently. With the sensor locations determined by the proposed optimization process, structural damage can be readily identified by using the incomplete modes yielded from these optimized sensor measurements. In addition, an Improved Ridge Estimate (IRE) technique is proposed in this study to effectively resist the data errors due to modal truncation and measurement noise. Two truss structures and a frame structure are used as examples to demonstrate the feasibility and efficiency of the presented algorithm. Results: From the numerical results, structural damages can be successfully detected by the proposed method using the partial modes yielded by the optimal measurement with 5% noise level. Conclusion: It has been shown that the proposed method is simple to implement and effective for structural damage identification.

Sign in / Sign up

Export Citation Format

Share Document