Enhancing building Facade Resilience through Machine Learning
Improving Workflow for Seismic and Heat Wave resilience measures
S. Shrotria (TU Delft - Architecture and the Built Environment)
Alessandra Luna Navarro – Mentor (TU Delft - Architectural Technology)
Simona Bianchi – Graduation committee member (TU Delft - Architectural Technology)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
With the increasing number of disruptive events impacting the built environment, identifying and enhancing the resilience of building facades has become crucial. This study focuses on improving the resilience of building facades against seismic and thermal hazards using machine learning techniques. A comprehensive methodology is developed, integrating thermal and seismic resilience analyses within a unified framework. The study utilizes extensive simulations and machine learning models to predict resilience metrics, such as thermal autonomy and seismic drift angles, based on various building parameters. The approach enables architects and engineers to optimize building designs for enhanced resilience efficiently.
The research is specifically applied to low-cost housing in New Delhi, India, an area prone to both extreme weather and seismic activity. Detailed simulations are conducted using data on building materials, geometries, and environmental conditions. The results are used to develop predictive models that inform design improvements and resilience strategies. The study demonstrates significant improvements in the accuracy and efficiency of resilience assessments, providing actionable recommendations to enhance building performance. This integrated methodology offers substantial benefits for both academia and practice, paving the way for more resilient and sustainable building designs in vulnerable regions.
Keywords: Façade Resilience, Multi-hazard Approach, Unsupervised Machine learning, Supervised Machine learning, Prediction model, Quantitative Resilience Assessment, Resilience-based Design, Multi-attribute decision-making