Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative Models

The design process of heating, ventilation, and air conditioning (HVAC) systems is complex and time consuming due to the need to follow design codes. Since the design standards are not fixed, the final outcome often depends on the designer’s experience. The development of building information modeli...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongxin Wang, Ruiying Jin, Peng Xu, Jiefan Gu
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/14/11/3405
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217160983445504
author Hongxin Wang
Ruiying Jin
Peng Xu
Jiefan Gu
author_facet Hongxin Wang
Ruiying Jin
Peng Xu
Jiefan Gu
author_sort Hongxin Wang
collection DOAJ
description The design process of heating, ventilation, and air conditioning (HVAC) systems is complex and time consuming due to the need to follow design codes. Since the design standards are not fixed, the final outcome often depends on the designer’s experience. The development of building information modeling (BIM) technology has made information throughout the building lifecycle more integrated. BIM-based forward design is now widely used, providing a data foundation for combining HVAC system design with machine learning. This paper proposes an unsupervised learning method based on deep graph generative models to uncover hidden design patterns and optimization strategies from the design results. We trained and validated four deep graph generative models—GAE, GNF, GAN, and diffusion—using HVAC system terminal pipeline layout data. Accuracy and precision metrics were used to compare the generated designs with automated forward design solutions, assessing the models’ ability to capture both local variations and broader changes in design logic. A graph-neural-network-based evaluation method was employed to measure the models’ capacity to detect changes. The results indicate that all four models achieved prediction accuracies exceeding 90% and precision rates above 75%. The models effectively captured both local modifications made by designers and global design changes, showing greater sensitivity to global layout adjustments than to local updates. When comparing the results generated by deep graph generative models and the actual design, it is obvious that the accuracy of the predictions varies significantly due to the complexity of the test buildings.
format Article
id doaj-art-af987d72120446ec9224a671e2c0a56e
institution OA Journals
issn 2075-5309
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-af987d72120446ec9224a671e2c0a56e2025-08-20T02:08:08ZengMDPI AGBuildings2075-53092024-10-011411340510.3390/buildings14113405Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative ModelsHongxin Wang0Ruiying Jin1Peng Xu2Jiefan Gu3School of Mechanical Engineering, Tongji University, Shanghai 201804, ChinaSchool of Mechanical Engineering, Tongji University, Shanghai 201804, ChinaSchool of Mechanical Engineering, Tongji University, Shanghai 201804, ChinaCollege of Architecture and Urban Planning, Tongji University, Shanghai 200092, ChinaThe design process of heating, ventilation, and air conditioning (HVAC) systems is complex and time consuming due to the need to follow design codes. Since the design standards are not fixed, the final outcome often depends on the designer’s experience. The development of building information modeling (BIM) technology has made information throughout the building lifecycle more integrated. BIM-based forward design is now widely used, providing a data foundation for combining HVAC system design with machine learning. This paper proposes an unsupervised learning method based on deep graph generative models to uncover hidden design patterns and optimization strategies from the design results. We trained and validated four deep graph generative models—GAE, GNF, GAN, and diffusion—using HVAC system terminal pipeline layout data. Accuracy and precision metrics were used to compare the generated designs with automated forward design solutions, assessing the models’ ability to capture both local variations and broader changes in design logic. A graph-neural-network-based evaluation method was employed to measure the models’ capacity to detect changes. The results indicate that all four models achieved prediction accuracies exceeding 90% and precision rates above 75%. The models effectively captured both local modifications made by designers and global design changes, showing greater sensitivity to global layout adjustments than to local updates. When comparing the results generated by deep graph generative models and the actual design, it is obvious that the accuracy of the predictions varies significantly due to the complexity of the test buildings.https://www.mdpi.com/2075-5309/14/11/3405building information modelingHVAC system designgenerative designmachine learningdeep graph generative models
spellingShingle Hongxin Wang
Ruiying Jin
Peng Xu
Jiefan Gu
Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative Models
Buildings
building information modeling
HVAC system design
generative design
machine learning
deep graph generative models
title Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative Models
title_full Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative Models
title_fullStr Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative Models
title_full_unstemmed Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative Models
title_short Generation Method for HVAC Systems Design Schemes in Office Buildings Based on Deep Graph Generative Models
title_sort generation method for hvac systems design schemes in office buildings based on deep graph generative models
topic building information modeling
HVAC system design
generative design
machine learning
deep graph generative models
url https://www.mdpi.com/2075-5309/14/11/3405
work_keys_str_mv AT hongxinwang generationmethodforhvacsystemsdesignschemesinofficebuildingsbasedondeepgraphgenerativemodels
AT ruiyingjin generationmethodforhvacsystemsdesignschemesinofficebuildingsbasedondeepgraphgenerativemodels
AT pengxu generationmethodforhvacsystemsdesignschemesinofficebuildingsbasedondeepgraphgenerativemodels
AT jiefangu generationmethodforhvacsystemsdesignschemesinofficebuildingsbasedondeepgraphgenerativemodels