Journal of Building Engineering · 2024 · 45 citations · 27 references
ArchitectureArchitectural EngineeringBuilding ScienceBuilding Information ModelingBuilding Performance SimulationKnowledge RepresentationBim SimulationBuilding Energy ModelingBuilding Energy PerformanceBuilding Energy SystemsEnergy SimulationSemantic NetworksBuilding Energy Performance SimulationEnergy Performance SimulationLarge Language ModelsSemantic InformationSemantic MatchingSemantic SimilaritySemantic Similarity MatchingSemantic Textual Similarity
To achieve the global targets of the Paris Agreement of limiting global warming, it is necessary to reduce the operational energy of buildings, which are responsible for around 30% of the global greenhouse gas emissions. Building Energy Performance Simulation (BEPS) is an established method to estimate the building’s energy demand in early design stages. Building Information Models (BIM) provides geometric and semantic information to create precise Building Energy Models (BEM) in early design stages. However, manual enrichment of missing semantic information is still a time-consuming and laborious process. Therefore, we propose a novel methodology to automatically enrich missing information to BIM using Semantic Textual Similarity (STS) and fine-tuned Large Language Models (LLM). For every IfcSpace, we match room-specific space types and constructions with missing thermal properties using the semantic most similar pairs of the BIM model and the according databases. We use three real-world case studies to fine-tune LLMs, and two case studies evaluate the whole methodology. Different fine-tuning strategies, such as using different loss functions, adding opposing word pairs or domain-specific abbreviations, significantly improve the accuracy of the matching. At the same time, however, findings show that semantic matching based on multilingual fine-tuned LLM performs worse than translated, monolingually fine-tuned LLM. Finally, BEPS results from automatically enriched BEM only slightly deviate from manually enriched BEM.
27
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Thomas Wolf, Lysandre Debut, Victor Sanh et al. · arXiv (Cornell University) · 2019 · 3.1K citations · Full text
Evaluation methods for unsupervised word embeddings
Tobias Schnabel, Igor Labutov, David Mimno et al. · 2015 · 560 citations · Full text
Multilingual Universal Sentence Encoder for Semantic Retrieval
Yinfei Yang, Daniel Cer, Amin Ahmad et al. · 2020 · 406 citations · Full text