.png){kind=icon}
.png){kind=icon}
Return
Sequential broad learning system modeling framework for finite element model updating using incomplete modal data
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engstruct.2026.122687.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A sequential BLS surrogate modeling framework is proposed for finite element model updating using incomplete modal data. • The sample pool is first recursively expanded through purposeful sampling and then periodically pruned to restore its size. • BLS surrogate model is incrementally updated with newly generated samples and full updated after sample pruning. • A hybrid optimization method using analytical first- and second-order derivatives is proposed for purposeful sampling.
Keywords:
BLS surrogate modeling
finite element model updating
incomplete modal data
purposeful sampling
hybrid optimization
Journal
IF:
6.4
Papers:
2.1W
Citations:
8.7W