Meta databases of steel frame buildings for surrogate modelling and machine learning-based feature importance analysis
Traditionally, nonlinear time history analysis (NLTHA) is used to assess the performance of structures under future hazards which is necessary to develop effective disaster risk management strategies. However, this method is computationally intensive and not suitable for analyzing a large number of...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-03-01
|
Series: | Resilient Cities and Structures |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2772741623000716 |
_version_ | 1797372010814242816 |
---|---|
author | Delbaz Samadian Imrose B. Muhit Annalisa Occhipinti Nashwan Dawood |
author_facet | Delbaz Samadian Imrose B. Muhit Annalisa Occhipinti Nashwan Dawood |
author_sort | Delbaz Samadian |
collection | DOAJ |
description | Traditionally, nonlinear time history analysis (NLTHA) is used to assess the performance of structures under future hazards which is necessary to develop effective disaster risk management strategies. However, this method is computationally intensive and not suitable for analyzing a large number of structures on a city-wide scale. Surrogate models offer an efficient and reliable alternative and facilitate evaluating the performance of multiple structures under different hazard scenarios. However, creating a comprehensive database for surrogate modelling at the city level presents challenges. To overcome this, the present study proposes meta databases and a general framework for surrogate modelling of steel structures. The dataset includes 30,000 steel moment-resisting frame buildings, representing low-rise, mid-rise and high-rise buildings, with criteria for connections, beams, and columns. Pushover analysis is performed and structural parameters are extracted, and finally, incorporating two different machine learning algorithms, random forest and Shapley additive explanations, sensitivity and explainability analyses of the structural parameters are performed to identify the most significant factors in designing steel moment resisting frames. The framework and databases can be used as a validated source of surrogate modelling of steel frame structures in order for disaster risk management. |
first_indexed | 2024-03-08T18:29:14Z |
format | Article |
id | doaj.art-e2ae0a2f96374a84ade53c2d8e537203 |
institution | Directory Open Access Journal |
issn | 2772-7416 |
language | English |
last_indexed | 2024-03-08T18:29:14Z |
publishDate | 2024-03-01 |
publisher | Elsevier |
record_format | Article |
series | Resilient Cities and Structures |
spelling | doaj.art-e2ae0a2f96374a84ade53c2d8e5372032023-12-30T04:45:25ZengElsevierResilient Cities and Structures2772-74162024-03-01312043Meta databases of steel frame buildings for surrogate modelling and machine learning-based feature importance analysisDelbaz Samadian0Imrose B. Muhit1Annalisa Occhipinti2Nashwan Dawood3Corresponding author.; School of Computing, Engineering, and Digital Technologies, Teesside University, Middlesbrough TS1 3BX, United KingdomSchool of Computing, Engineering, and Digital Technologies, Teesside University, Middlesbrough TS1 3BX, United KingdomSchool of Computing, Engineering, and Digital Technologies, Teesside University, Middlesbrough TS1 3BX, United KingdomSchool of Computing, Engineering, and Digital Technologies, Teesside University, Middlesbrough TS1 3BX, United KingdomTraditionally, nonlinear time history analysis (NLTHA) is used to assess the performance of structures under future hazards which is necessary to develop effective disaster risk management strategies. However, this method is computationally intensive and not suitable for analyzing a large number of structures on a city-wide scale. Surrogate models offer an efficient and reliable alternative and facilitate evaluating the performance of multiple structures under different hazard scenarios. However, creating a comprehensive database for surrogate modelling at the city level presents challenges. To overcome this, the present study proposes meta databases and a general framework for surrogate modelling of steel structures. The dataset includes 30,000 steel moment-resisting frame buildings, representing low-rise, mid-rise and high-rise buildings, with criteria for connections, beams, and columns. Pushover analysis is performed and structural parameters are extracted, and finally, incorporating two different machine learning algorithms, random forest and Shapley additive explanations, sensitivity and explainability analyses of the structural parameters are performed to identify the most significant factors in designing steel moment resisting frames. The framework and databases can be used as a validated source of surrogate modelling of steel frame structures in order for disaster risk management.http://www.sciencedirect.com/science/article/pii/S2772741623000716Surrogate modelsMeta databasePushover analysisSteel moment resisting framesSensitivity and explainability analysesMachine learning |
spellingShingle | Delbaz Samadian Imrose B. Muhit Annalisa Occhipinti Nashwan Dawood Meta databases of steel frame buildings for surrogate modelling and machine learning-based feature importance analysis Resilient Cities and Structures Surrogate models Meta database Pushover analysis Steel moment resisting frames Sensitivity and explainability analyses Machine learning |
title | Meta databases of steel frame buildings for surrogate modelling and machine learning-based feature importance analysis |
title_full | Meta databases of steel frame buildings for surrogate modelling and machine learning-based feature importance analysis |
title_fullStr | Meta databases of steel frame buildings for surrogate modelling and machine learning-based feature importance analysis |
title_full_unstemmed | Meta databases of steel frame buildings for surrogate modelling and machine learning-based feature importance analysis |
title_short | Meta databases of steel frame buildings for surrogate modelling and machine learning-based feature importance analysis |
title_sort | meta databases of steel frame buildings for surrogate modelling and machine learning based feature importance analysis |
topic | Surrogate models Meta database Pushover analysis Steel moment resisting frames Sensitivity and explainability analyses Machine learning |
url | http://www.sciencedirect.com/science/article/pii/S2772741623000716 |
work_keys_str_mv | AT delbazsamadian metadatabasesofsteelframebuildingsforsurrogatemodellingandmachinelearningbasedfeatureimportanceanalysis AT imrosebmuhit metadatabasesofsteelframebuildingsforsurrogatemodellingandmachinelearningbasedfeatureimportanceanalysis AT annalisaocchipinti metadatabasesofsteelframebuildingsforsurrogatemodellingandmachinelearningbasedfeatureimportanceanalysis AT nashwandawood metadatabasesofsteelframebuildingsforsurrogatemodellingandmachinelearningbasedfeatureimportanceanalysis |