Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures
This paper explores the use of data-driven approximation algorithms, often called surrogate modeling, in the early-stage design of structures. The use of surrogate models to rapidly evaluate design performance can lead to a more in-depth exploration of a design space and reduce computational time of...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Elsevier
2018
|
| Online Access: | http://hdl.handle.net/1721.1/119411 https://orcid.org/0000-0002-9554-8292 https://orcid.org/0000-0003-1538-9787 https://orcid.org/0000-0001-7646-8505 |
| _version_ | 1826215319929094144 |
|---|---|
| author | Tseranidis, Stavros Brown, Nathan Collin Mueller, Caitlin T |
| author2 | Massachusetts Institute of Technology. Department of Architecture |
| author_facet | Massachusetts Institute of Technology. Department of Architecture Tseranidis, Stavros Brown, Nathan Collin Mueller, Caitlin T |
| author_sort | Tseranidis, Stavros |
| collection | MIT |
| description | This paper explores the use of data-driven approximation algorithms, often called surrogate modeling, in the early-stage design of structures. The use of surrogate models to rapidly evaluate design performance can lead to a more in-depth exploration of a design space and reduce computational time of optimization algorithms. While this approach has been widely developed and used in related disciplines such as aerospace engineering, there are few examples of its application in civil engineering. This paper focuses on the general use of surrogate modeling in the design of civil structures and examines six model types that span a wide range of characteristics. Original contributions include novel metrics and visualization techniques for understanding model error and a new robustness framework that accounts for variability in model comparison. These concepts are applied to a multi-objective case study of an airport terminal design that considers both structural material volume and operational energy consumption. Key Words: surrogate modelling, machine learning, approximation, structural design |
| first_indexed | 2024-09-23T16:23:39Z |
| format | Article |
| id | mit-1721.1/119411 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:23:39Z |
| publishDate | 2018 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | mit-1721.1/1194112022-10-02T07:54:43Z Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures Tseranidis, Stavros Brown, Nathan Collin Mueller, Caitlin T Massachusetts Institute of Technology. Department of Architecture Massachusetts Institute of Technology. Computation for Design and Optimization Program Mueller, Caitlin T. Tseranidis, Stavros Brown, Nathan Collin Mueller, Caitlin T This paper explores the use of data-driven approximation algorithms, often called surrogate modeling, in the early-stage design of structures. The use of surrogate models to rapidly evaluate design performance can lead to a more in-depth exploration of a design space and reduce computational time of optimization algorithms. While this approach has been widely developed and used in related disciplines such as aerospace engineering, there are few examples of its application in civil engineering. This paper focuses on the general use of surrogate modeling in the design of civil structures and examines six model types that span a wide range of characteristics. Original contributions include novel metrics and visualization techniques for understanding model error and a new robustness framework that accounts for variability in model comparison. These concepts are applied to a multi-objective case study of an airport terminal design that considers both structural material volume and operational energy consumption. Key Words: surrogate modelling, machine learning, approximation, structural design 2018-12-04T16:07:42Z 2018-12-04T16:07:42Z 2016-12 Article http://purl.org/eprint/type/JournalArticle 0926-5805 http://hdl.handle.net/1721.1/119411 Tseranidis, Stavros, Nathan C. Brown, and Caitlin T. Mueller. “Data-Driven Approximation Algorithms for Rapid Performance Evaluation and Optimization of Civil Structures.” Automation in Construction 72 (December 2016): 279–293. https://orcid.org/0000-0002-9554-8292 https://orcid.org/0000-0003-1538-9787 https://orcid.org/0000-0001-7646-8505 en_US http://dx.doi.org/10.1016/j.autcon.2016.02.002 Automation in Construction Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier Caitlin Mueller |
| spellingShingle | Tseranidis, Stavros Brown, Nathan Collin Mueller, Caitlin T Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures |
| title | Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures |
| title_full | Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures |
| title_fullStr | Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures |
| title_full_unstemmed | Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures |
| title_short | Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures |
| title_sort | data driven approximation algorithms for rapid performance evaluation and optimization of civil structures |
| url | http://hdl.handle.net/1721.1/119411 https://orcid.org/0000-0002-9554-8292 https://orcid.org/0000-0003-1538-9787 https://orcid.org/0000-0001-7646-8505 |
| work_keys_str_mv | AT tseranidisstavros datadrivenapproximationalgorithmsforrapidperformanceevaluationandoptimizationofcivilstructures AT brownnathancollin datadrivenapproximationalgorithmsforrapidperformanceevaluationandoptimizationofcivilstructures AT muellercaitlint datadrivenapproximationalgorithmsforrapidperformanceevaluationandoptimizationofcivilstructures |