Machine-Learning-Driven Approaches for Assessment, Delegation, and Optimization of Multi-Floor Building

This study presents a novel integrated framework for the structural analysis and optimization of multi-floor buildings by combining validated theoretical models with machine learning and evolutionary algorithms. The proposed Process–Action–Response System (PARS-Solution) accurately computes key stru...

Full description

Saved in:
Bibliographic Details
Main Authors: Abtin Baghdadi, Harald Kloft
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/15/9/1565
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850277558142107648
author Abtin Baghdadi
Harald Kloft
author_facet Abtin Baghdadi
Harald Kloft
author_sort Abtin Baghdadi
collection DOAJ
description This study presents a novel integrated framework for the structural analysis and optimization of multi-floor buildings by combining validated theoretical models with machine learning and evolutionary algorithms. The proposed Process–Action–Response System (PARS-Solution) accurately computes key structural responses—such as deformations, shear forces, and bending moments—based on eleven critical design parameters (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>P</mi><mn>1</mn></msub></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>P</mi><mn>11</mn></msub></semantics></math></inline-formula>). The significance of this research lies in its ability to automate and accelerate complex structural analysis using Adaptive Neuro-Fuzzy Inference Systems (ANFISs), achieving an average error of less than 2% in multi-variable prediction scenarios. The results were compared against reference calculations and ETABS simulations to validate its effectiveness, demonstrating deviations of less than 3%. The methodology combines MATLAB-based coding, interpolation from verified reference diagrams, and iterative stiffness adjustment across floors, offering transparency and accuracy. Optimization is performed using Multi-Objective Particle Swarm Optimization (MOPSO), enabling efficient exploration of Pareto-optimal solutions that balance deformation and material usage. Extensive parametric studies reveal the dominant impact of core wall dimensions and floor number on structural efficiency, while the application of stiffness reduction factors (e.g., <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>P</mi><mn>11</mn></msub></semantics></math></inline-formula>) proves effective in reducing material without compromising performance. This hybrid approach enables the delegation of labor-intensive calculations to a trained ANFIS model and supports rapid pre-validation of structural configurations in early design phases. As such, the framework offers a powerful data-driven tool for engineers seeking optimal, lightweight, and high-performance solutions in high-rise building design.
format Article
id doaj-art-5b756c442fdb4fbbb358926b977f6fad
institution OA Journals
issn 2075-5309
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-5b756c442fdb4fbbb358926b977f6fad2025-08-20T01:49:50ZengMDPI AGBuildings2075-53092025-05-01159156510.3390/buildings15091565Machine-Learning-Driven Approaches for Assessment, Delegation, and Optimization of Multi-Floor BuildingAbtin Baghdadi0Harald Kloft1Institute of Structural Design, Technical University of Brunswick, Pockelsstrasse 4, 38106 Braunschweig, GermanyInstitute of Structural Design, Technical University of Brunswick, Pockelsstrasse 4, 38106 Braunschweig, GermanyThis study presents a novel integrated framework for the structural analysis and optimization of multi-floor buildings by combining validated theoretical models with machine learning and evolutionary algorithms. The proposed Process–Action–Response System (PARS-Solution) accurately computes key structural responses—such as deformations, shear forces, and bending moments—based on eleven critical design parameters (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>P</mi><mn>1</mn></msub></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>P</mi><mn>11</mn></msub></semantics></math></inline-formula>). The significance of this research lies in its ability to automate and accelerate complex structural analysis using Adaptive Neuro-Fuzzy Inference Systems (ANFISs), achieving an average error of less than 2% in multi-variable prediction scenarios. The results were compared against reference calculations and ETABS simulations to validate its effectiveness, demonstrating deviations of less than 3%. The methodology combines MATLAB-based coding, interpolation from verified reference diagrams, and iterative stiffness adjustment across floors, offering transparency and accuracy. Optimization is performed using Multi-Objective Particle Swarm Optimization (MOPSO), enabling efficient exploration of Pareto-optimal solutions that balance deformation and material usage. Extensive parametric studies reveal the dominant impact of core wall dimensions and floor number on structural efficiency, while the application of stiffness reduction factors (e.g., <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>P</mi><mn>11</mn></msub></semantics></math></inline-formula>) proves effective in reducing material without compromising performance. This hybrid approach enables the delegation of labor-intensive calculations to a trained ANFIS model and supports rapid pre-validation of structural configurations in early design phases. As such, the framework offers a powerful data-driven tool for engineers seeking optimal, lightweight, and high-performance solutions in high-rise building design.https://www.mdpi.com/2075-5309/15/9/1565machine learningstructural optimizationANFISMOPSOhigh-rise buildingsparametric modeling
spellingShingle Abtin Baghdadi
Harald Kloft
Machine-Learning-Driven Approaches for Assessment, Delegation, and Optimization of Multi-Floor Building
Buildings
machine learning
structural optimization
ANFIS
MOPSO
high-rise buildings
parametric modeling
title Machine-Learning-Driven Approaches for Assessment, Delegation, and Optimization of Multi-Floor Building
title_full Machine-Learning-Driven Approaches for Assessment, Delegation, and Optimization of Multi-Floor Building
title_fullStr Machine-Learning-Driven Approaches for Assessment, Delegation, and Optimization of Multi-Floor Building
title_full_unstemmed Machine-Learning-Driven Approaches for Assessment, Delegation, and Optimization of Multi-Floor Building
title_short Machine-Learning-Driven Approaches for Assessment, Delegation, and Optimization of Multi-Floor Building
title_sort machine learning driven approaches for assessment delegation and optimization of multi floor building
topic machine learning
structural optimization
ANFIS
MOPSO
high-rise buildings
parametric modeling
url https://www.mdpi.com/2075-5309/15/9/1565
work_keys_str_mv AT abtinbaghdadi machinelearningdrivenapproachesforassessmentdelegationandoptimizationofmultifloorbuilding
AT haraldkloft machinelearningdrivenapproachesforassessmentdelegationandoptimizationofmultifloorbuilding