AI-based Lagrange optimization for designing reinforced concrete columns

Structural engineers face several code-restricted design decisions. Codes impose many conditions and requirements to the designs of structural frames, such as columns and beams. However, it is difficult to intuitively find optimized solutions, while satisfying all code requirements simultaneously. E...

Full description

Saved in:
Bibliographic Details
Main Authors: Won-Kee Hong, Manh Cuong Nguyen
Format: Article
Language:English
Published: Taylor & Francis Group 2022-11-01
Series:Journal of Asian Architecture and Building Engineering
Subjects:
Online Access:http://dx.doi.org/10.1080/13467581.2021.1971998
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846166727045414912
author Won-Kee Hong
Manh Cuong Nguyen
author_facet Won-Kee Hong
Manh Cuong Nguyen
author_sort Won-Kee Hong
collection DOAJ
description Structural engineers face several code-restricted design decisions. Codes impose many conditions and requirements to the designs of structural frames, such as columns and beams. However, it is difficult to intuitively find optimized solutions, while satisfying all code requirements simultaneously. Engineers commonly make design decisions based on empirical observations. Optimization techniques can be employed to make more rational engineering decisions, which result in designs that can meet various code restrictions simultaneously. Lagrange optimization techniques with constraints, not based on explicit parameterization, are implemented to make rational engineering decisions and find minimized or maximized design values by solving nonlinear optimization problems under strict constraints imposed by design codes. It is difficult to express objective functions analytically directly in terms of design variables to use derivative methods, such as Lagrange multipliers. This study proposes the use of neural network to approximate well-behaved objective functions and other output parameters into one universal function that can also give a generalizable solution for operating Jacobian and Hessian matrices to solve the Lagrangian function. The proposed method was applied successfully in optimizing a cost of a reinforced concrete column under various design requirements. An efficacy of optimal results was also proven by 5 million datasets.
format Article
id doaj-art-0593d92a632e418eb9e0737bd63d798a
institution Kabale University
issn 1347-2852
language English
publishDate 2022-11-01
publisher Taylor & Francis Group
record_format Article
series Journal of Asian Architecture and Building Engineering
spelling doaj-art-0593d92a632e418eb9e0737bd63d798a2024-11-15T10:36:00ZengTaylor & Francis GroupJournal of Asian Architecture and Building Engineering1347-28522022-11-012162330234410.1080/13467581.2021.19719981971998AI-based Lagrange optimization for designing reinforced concrete columnsWon-Kee Hong0Manh Cuong Nguyen1Kyung Hee UniversityKyung Hee UniversityStructural engineers face several code-restricted design decisions. Codes impose many conditions and requirements to the designs of structural frames, such as columns and beams. However, it is difficult to intuitively find optimized solutions, while satisfying all code requirements simultaneously. Engineers commonly make design decisions based on empirical observations. Optimization techniques can be employed to make more rational engineering decisions, which result in designs that can meet various code restrictions simultaneously. Lagrange optimization techniques with constraints, not based on explicit parameterization, are implemented to make rational engineering decisions and find minimized or maximized design values by solving nonlinear optimization problems under strict constraints imposed by design codes. It is difficult to express objective functions analytically directly in terms of design variables to use derivative methods, such as Lagrange multipliers. This study proposes the use of neural network to approximate well-behaved objective functions and other output parameters into one universal function that can also give a generalizable solution for operating Jacobian and Hessian matrices to solve the Lagrangian function. The proposed method was applied successfully in optimizing a cost of a reinforced concrete column under various design requirements. An efficacy of optimal results was also proven by 5 million datasets.http://dx.doi.org/10.1080/13467581.2021.1971998ai-based lagrange optimizationgeneralizable optimization algorithmai-based kkt conditionsann-based hessian calculus
spellingShingle Won-Kee Hong
Manh Cuong Nguyen
AI-based Lagrange optimization for designing reinforced concrete columns
Journal of Asian Architecture and Building Engineering
ai-based lagrange optimization
generalizable optimization algorithm
ai-based kkt conditions
ann-based hessian calculus
title AI-based Lagrange optimization for designing reinforced concrete columns
title_full AI-based Lagrange optimization for designing reinforced concrete columns
title_fullStr AI-based Lagrange optimization for designing reinforced concrete columns
title_full_unstemmed AI-based Lagrange optimization for designing reinforced concrete columns
title_short AI-based Lagrange optimization for designing reinforced concrete columns
title_sort ai based lagrange optimization for designing reinforced concrete columns
topic ai-based lagrange optimization
generalizable optimization algorithm
ai-based kkt conditions
ann-based hessian calculus
url http://dx.doi.org/10.1080/13467581.2021.1971998
work_keys_str_mv AT wonkeehong aibasedlagrangeoptimizationfordesigningreinforcedconcretecolumns
AT manhcuongnguyen aibasedlagrangeoptimizationfordesigningreinforcedconcretecolumns