|
| Finite element model updating based on SGMD and LWOA-ELM |
| Received:September 23, 2021 Revised:February 11, 2022 |
| View Full Text View/Add Comment Download reader |
| DOI：10.7511/jslx20210923001 |
| KeyWord:model updating symplectic geometry mode decomposition energy entropy increment method extreme learning machine whale optimization algorithm |
| Author | Institution |
| 赵宇 |
兰州交通大学 机电工程学院, 兰州 ;天水师范学院 电子信息与电气工程学院, 天水 |
| 彭珍瑞 |
兰州交通大学 机电工程学院, 兰州 |
|
| Hits: 451 |
| Download times: 280 |
| Abstract: |
| In order to obtain the relationship between updating parameters and structural responses,and improve the efficiency and accuracy of model updating,finite element model updating (FEMU) method based on symplectic geometry mode decomposition (SGMD) and extreme learning machine (ELM) optimized by Lévy flight based whale optimization algorithm (LWOA) is proposed.Firstly,SGMD is applied to decompose acceleration frequency response function (AFRF) data.The reconstructed symplectic geometry components (SGCs) are selected by energy entropy increment method to make the SGC matrix.Then,to improve the prediction accuracy,LWOA is used to optimize the weightings and thresholds of ELM.LWOA-ELM model is established as the surrogate model for the mapping between updating parameters and the SGC matrix of experimental AFRF.Finally,with the minimum Frobenius norm of error between the SGC matrix from tests and those from LWOA-ELM model as the objective function,the updating parameters are obtained by LWOA.Case studies demonstrate that the proposed method is feasible and effective for FEMU.The updating method with SGC to indicate AFRF has good noise robustness.As the surrogate model,LWOA-ELM has high prediction accuracy and strong generalization ability. |
|
|
|