Saved in:
Bibliographic Details
Main Authors: Chen, Xia, Lv, Guoquan, Zhuang, Xinwei, Duarte, Carlos, Schiavon, Stefano, Geyer, Philipp
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.00800
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912102308904960
author Chen, Xia
Lv, Guoquan
Zhuang, Xinwei
Duarte, Carlos
Schiavon, Stefano
Geyer, Philipp
author_facet Chen, Xia
Lv, Guoquan
Zhuang, Xinwei
Duarte, Carlos
Schiavon, Stefano
Geyer, Philipp
contents Symbolic neural networks, such as Kolmogorov-Arnold Networks (KAN), offer a promising approach for integrating prior knowledge with data-driven methods, making them valuable for addressing inverse problems in scientific and engineering domains. This study explores the application of KAN in building physics, focusing on predictive modeling, knowledge discovery, and continuous learning. Through four case studies, we demonstrate KAN's ability to rediscover fundamental equations, approximate complex formulas, and capture time-dependent dynamics in heat transfer. While there are challenges in extrapolation and interpretability, we highlight KAN's potential to combine advanced modeling methods for knowledge augmentation, which benefits energy efficiency, system optimization, and sustainability assessments beyond the personal knowledge constraints of the modelers. Additionally, we propose a model selection decision tree to guide practitioners in appropriate applications for building physics.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00800
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Integrating Symbolic Neural Networks with Building Physics: A Study and Proposal
Chen, Xia
Lv, Guoquan
Zhuang, Xinwei
Duarte, Carlos
Schiavon, Stefano
Geyer, Philipp
Machine Learning
68T30
Symbolic neural networks, such as Kolmogorov-Arnold Networks (KAN), offer a promising approach for integrating prior knowledge with data-driven methods, making them valuable for addressing inverse problems in scientific and engineering domains. This study explores the application of KAN in building physics, focusing on predictive modeling, knowledge discovery, and continuous learning. Through four case studies, we demonstrate KAN's ability to rediscover fundamental equations, approximate complex formulas, and capture time-dependent dynamics in heat transfer. While there are challenges in extrapolation and interpretability, we highlight KAN's potential to combine advanced modeling methods for knowledge augmentation, which benefits energy efficiency, system optimization, and sustainability assessments beyond the personal knowledge constraints of the modelers. Additionally, we propose a model selection decision tree to guide practitioners in appropriate applications for building physics.
title Integrating Symbolic Neural Networks with Building Physics: A Study and Proposal
topic Machine Learning
68T30
url https://arxiv.org/abs/2411.00800