AI SearchData-driven numerical model updating of reinforced concrete structures using artificial neural networks
Call Number: AIT Thesis no.ST-25-12 Material type:
SeriesSeries: Asian Institute of Technology. Thesis ; no. ST-25-12Publication details: Pathum Thani, Thailand : Asian Institute of Technology, 2025Description: 79 leaves : ill.+ 1 online resourceSubject(s): Online resources: Dissertation note: Thesis (M. Eng.) - Asian Institute of Technology, 2025 Summary: This research develops and evaluates a data-driven model updating framework for reinforced concrete (RC) building structures using Artificial Neural Networks (ANN) and the 3D Applied Element Method (AEM). The proposed method aims to improve the accuracy of gradient-based model updating by providing more realistic initial estimates of material properties based on measured modal parameters.Databases were generated by varying Young{u2019}s modulus in 3D AEM models and recording corresponding modal responses. ANN models trained on these databases achieved high predictive accuracy in low- and moderate-resolution configurations. Verification on a controlled numerical model demonstrated improved convergence and robustness compared to conventional random-initial-guess approaches. Validation on two experimental case studies showed that the method produces updated models with plausible material properties and improved agreement with measured modal data.The results confirm that the proposed framework effectively integrates data-driven prediction with numerical updating, providing a practical and efficient approach for RC building model updating.
| Cover image | Item type | Current library | Home library | Collection | Shelving location | Call number | Materials specified | Vol info | URL | Copy number | Status | Notes | Date due | Barcode | Item holds | Item hold queue priority | Course reserves | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
67-Electronic Resource
|
Asian Institute of Technology Library Archives | AIT Thesis no.ST-25-12 (Browse shelf(Opens below)) | 1 | Not for loan |
A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Structural Engineering
Thesis (M. Eng.) - Asian Institute of Technology, 2025
This research develops and evaluates a data-driven model updating framework for reinforced concrete (RC) building structures using Artificial Neural Networks (ANN) and the 3D Applied Element Method (AEM). The proposed method aims to improve the accuracy of gradient-based model updating by providing more realistic initial estimates of material properties based on measured modal parameters.Databases were generated by varying Young{u2019}s modulus in 3D AEM models and recording corresponding modal responses. ANN models trained on these databases achieved high predictive accuracy in low- and moderate-resolution configurations. Verification on a controlled numerical model demonstrated improved convergence and robustness compared to conventional random-initial-guess approaches. Validation on two experimental case studies showed that the method produces updated models with plausible material properties and improved agreement with measured modal data.The results confirm that the proposed framework effectively integrates data-driven prediction with numerical updating, providing a practical and efficient approach for RC building model updating.
There are no comments on this title.