.png){kind=icon}
返回
Multi-Role collaborative framework for structural damage identification considering measurement noise effect
.png){kind=icon}
PRE
AI
DOI：10.1016/j.measurement.2025.117106.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Swarm intelligence has been extensively applied in structural damage identification, but a single method may not perform well in identification, especially using limited and noised vibration data. In this context, the objective landscape of the formulated identification problem is often ill-posed, indicating the optimized landscape is filled with many local optimal points. If the algorithm gets trapped in local optimal points, it will not obtain satisfactory identification results. To address this issue, this study introduces the sparse regularization technique to construct a well-posed objective function. Furthermore, a novel multi-role collaborative framework is proposed, which integrates different swarm intelligent and enables the individual in the algorithm to switch different roles, meaning employing different updating strategies, for the demands of different identification cases. Therefore, a more accurate identification results can be obtained. A series of numerical simulations and a laboratory validation on a box-section beam with multiple notches are carried out. The features of multi-role adaptive mechanism and diversity search strategies in the proposed framework guarantee its advantages and superiority on obtaining better identifications compared with single swarm intelligence algorithm, providing a new way in developing high-efficiency model updating and damage detection algorithms.
Keyword:
Multi-role collaborative framework
Seagull optimization algorithm
Sine cosine algorithm
Sparse regularization
Noise effect
期刊
IF:
5.6
论文数:
2.1W
被引数:
5.4W
机构
引用论文
Structural damage identification based on unsupervised feature-extraction via Variational Auto-encoder.png)
MEASUREMENT
MEASUREMENTIF5.6
PREAI
分享收藏A Multi Ant System based hybrid heuristic algorithm for Vehicle Routing Problem with Service Time Customization基于多蚂蚁系统的混合启发式算法求解具有服务时间定制的车辆路径问题
PREAI
分享收藏Substructure approach for Bayesian probabilistic model updating using response reconstruction technique使用响应重构技术进行贝叶斯概率模型更新的子结构方法
PREAI
分享收藏分享收藏
查看更多内容