Comparison of Hybrid Methods with Different Meta Model Used in Bridge Model-Updating
Two hybrid model updating methods by integration of Gaussian mutation particle swarm optimization method, Latin Hypercube Sampling technique and meta models of Kriging and Back-Propagation Neural Network respectively were proposed, and the methods make the convergence speed of the model updating pro...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Riga Technical University Press
2017-09-01
|
| Series: | The Baltic Journal of Road and Bridge Engineering |
| Subjects: | |
| Online Access: | https://bjrbe-journals.rtu.lv/article/view/3265 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846093576457420800 |
|---|---|
| author | Zhiyuan Xia Aiqun Li Jianhui Li Maojun Duan |
| author_facet | Zhiyuan Xia Aiqun Li Jianhui Li Maojun Duan |
| author_sort | Zhiyuan Xia |
| collection | DOAJ |
| description | Two hybrid model updating methods by integration of Gaussian mutation particle swarm optimization method, Latin Hypercube Sampling technique and meta models of Kriging and Back-Propagation Neural Network respectively were proposed, and the methods make the convergence speed of the model updating process faster and the Finite Element Model more adequate. Through the application of the hybrid methods to model updating process of a self-anchored suspension bridge in-service with extra-width, which showed great necessity considering the ambient vibration test results, the comparison of the two proposed methods was made. The results indicate that frequency differences between test and modified model were narrowed compared to results between test and original model after model updating using both methods as all the values are less than 6%, which is 25%−40% initially. Furthermore, the Model Assurance Criteria increase a little illustrating that more agreeable mode shapes are obtained as all of the Model Assurance Criteria are over 0.86. The particular advancements indicate that a relatively more adequate Finite Element Model is yielded with high efficiency without losing accuracy by both methods. However, the comparison among the two hybrid methods shows that the one with Back-Propagation Neural Network meta model is better than the one with Kriging meta model as the frequency differences of the former are mostly under 5%, but the latter ones are not. Furthermore, the former has higher efficiency than the other as the convergence speed of the former is faster. Thus, the hybrid method, within Gaussian mutation particle swarm optimization method and Back-Propagation Neural Network meta model, is more suitable for model updating of engineering applications with large-scale, multi-dimensional parameter structures involving implicit performance functions. |
| format | Article |
| id | doaj-art-6dafe3bcf48e43f2a1f8ea6dfdb3e433 |
| institution | Kabale University |
| issn | 1822-427X 1822-4288 |
| language | English |
| publishDate | 2017-09-01 |
| publisher | Riga Technical University Press |
| record_format | Article |
| series | The Baltic Journal of Road and Bridge Engineering |
| spelling | doaj-art-6dafe3bcf48e43f2a1f8ea6dfdb3e4332025-01-02T16:54:50ZengRiga Technical University PressThe Baltic Journal of Road and Bridge Engineering1822-427X1822-42882017-09-0112310.3846/bjrbe.2017.241791Comparison of Hybrid Methods with Different Meta Model Used in Bridge Model-UpdatingZhiyuan Xia0Aiqun Li1Jianhui Li2Maojun Duan3School of Civil Engineering, Southeast University, Sipailou 2 Xuanwu District, 210096 Nanjing, ChinaSchool of Civil Engineering, Southeast University, Sipailou 2 Xuanwu District, 210096 Nanjing, China Beijing Advanced Innovation Center for Future Urban Design, Beijing University of Civil Engineering Architecture, 1 Xicheng District, 100044 Beijing, ChinaSchool of Civil Engineering, Nanjing Forestry University, Longpanzhonglu 159 Xuanwu District, Nanjing, ChinaSchool of Civil Engineering, Nanjing Forestry University, Longpanzhonglu 159 Xuanwu District, 210037 Nanjing, ChinaTwo hybrid model updating methods by integration of Gaussian mutation particle swarm optimization method, Latin Hypercube Sampling technique and meta models of Kriging and Back-Propagation Neural Network respectively were proposed, and the methods make the convergence speed of the model updating process faster and the Finite Element Model more adequate. Through the application of the hybrid methods to model updating process of a self-anchored suspension bridge in-service with extra-width, which showed great necessity considering the ambient vibration test results, the comparison of the two proposed methods was made. The results indicate that frequency differences between test and modified model were narrowed compared to results between test and original model after model updating using both methods as all the values are less than 6%, which is 25%−40% initially. Furthermore, the Model Assurance Criteria increase a little illustrating that more agreeable mode shapes are obtained as all of the Model Assurance Criteria are over 0.86. The particular advancements indicate that a relatively more adequate Finite Element Model is yielded with high efficiency without losing accuracy by both methods. However, the comparison among the two hybrid methods shows that the one with Back-Propagation Neural Network meta model is better than the one with Kriging meta model as the frequency differences of the former are mostly under 5%, but the latter ones are not. Furthermore, the former has higher efficiency than the other as the convergence speed of the former is faster. Thus, the hybrid method, within Gaussian mutation particle swarm optimization method and Back-Propagation Neural Network meta model, is more suitable for model updating of engineering applications with large-scale, multi-dimensional parameter structures involving implicit performance functions.https://bjrbe-journals.rtu.lv/article/view/3265back-propagation neural network meta modelgaussian mutationkriging meta modellatin hypercube samplingmodel updatingparticle swarm optimizationself-anchored suspension bridge. |
| spellingShingle | Zhiyuan Xia Aiqun Li Jianhui Li Maojun Duan Comparison of Hybrid Methods with Different Meta Model Used in Bridge Model-Updating The Baltic Journal of Road and Bridge Engineering back-propagation neural network meta model gaussian mutation kriging meta model latin hypercube sampling model updating particle swarm optimization self-anchored suspension bridge. |
| title | Comparison of Hybrid Methods with Different Meta Model Used in Bridge Model-Updating |
| title_full | Comparison of Hybrid Methods with Different Meta Model Used in Bridge Model-Updating |
| title_fullStr | Comparison of Hybrid Methods with Different Meta Model Used in Bridge Model-Updating |
| title_full_unstemmed | Comparison of Hybrid Methods with Different Meta Model Used in Bridge Model-Updating |
| title_short | Comparison of Hybrid Methods with Different Meta Model Used in Bridge Model-Updating |
| title_sort | comparison of hybrid methods with different meta model used in bridge model updating |
| topic | back-propagation neural network meta model gaussian mutation kriging meta model latin hypercube sampling model updating particle swarm optimization self-anchored suspension bridge. |
| url | https://bjrbe-journals.rtu.lv/article/view/3265 |
| work_keys_str_mv | AT zhiyuanxia comparisonofhybridmethodswithdifferentmetamodelusedinbridgemodelupdating AT aiqunli comparisonofhybridmethodswithdifferentmetamodelusedinbridgemodelupdating AT jianhuili comparisonofhybridmethodswithdifferentmetamodelusedinbridgemodelupdating AT maojunduan comparisonofhybridmethodswithdifferentmetamodelusedinbridgemodelupdating |