Thermal Bridge Detection Using Multi-Modality Imaging
Thermal bridges in building envelopes are localized weaknesses that significantly affect energy performance and occupant comfort. These areas of elevated heat transfer can increase energy consumption by up to 40 %, highlighting the need for precise identification and mitigation strategies. Recent advancements in remote sensing and machine learning offer promising avenues for non-destructive monitoring of material performance in urban buildings. By integrating aerial multi-modality imaging, which combines visible, thermal, and LiDAR data, researchers can achieve real-time, city-scale diagnostics, providing a foundation for energy-efficient retrofitting and sustainable urban development.
Development of a Deep Learning Framework
This study presents a customized deep learning (DL) approach based on YOLOv9, tailored for thermal bridge detection using a multimodal dataset of 6,927 images. By leveraging the complementary strengths of visible, thermal, and LiDAR data, the model effectively identifies thermal bridges, achieving a precision of 0.72 and detecting an average of 3.33 bridges per image. The model demonstrates real-time inference capabilities, with processing times under 30.3 milliseconds on an NVIDIA A100 GPU, positioning it as a scalable solution for urban-scale energy diagnostics.
Physics-Based Heat Loss Modeling
To complement the DL detection approach, a physics-based heat loss model was developed to quantify the thermal impact of identified bridges. Surface heat losses were estimated to range from 4.02 to 37.85 W/m², with an average of 22.37 W/m². This approach allows for the translation of detected anomalies into actionable energy metrics, providing stakeholders with critical insights into potential energy inefficiencies and informing retrofitting decisions for improved building performance.
Post-Processing with Artificial Neural Networks
Post-processing of the DL model outputs using an artificial neural network (ANN) further refined the bounding box predictions. This step increased detection precision to 0.763 while reducing localization error by 14.7 %. The integration of ANN post-processing demonstrates the importance of hybrid approaches in enhancing model accuracy and reliability, particularly for high-stakes applications such as urban energy monitoring and building diagnostics.
Validation and Comparative Analysis
Validation on the AGAP dataset, which fuses RGB and thermal imagery, confirmed the generalizability of the proposed approach, achieving 80 % precision. Comparative evaluation indicated that YOLOv9-E outperformed other state-of-the-art models, including MaskRCNN and YOLOv7. These findings underscore the effectiveness of combining multimodal data with advanced DL architectures for detecting thermal anomalies, providing a benchmark for future research in automated non-destructive testing of building envelopes.
Energy Implications and Smart City Applications
Projections based on the integrated framework suggest that undetected thermal bridges on a 100 m² façade may lead to up to 11,409 kWh of excess heating demand over six months. By enabling real-time detection and quantification of thermal inefficiencies, the proposed methodology offers a scalable solution for smart cities seeking to optimize energy consumption and retrofit existing buildings. This research emphasizes the potential of combining AI, remote sensing, and physics-based modeling to drive energy efficiency and sustainability in urban environments.
Architecture Engineers Awards
🔗 Nominate now! 👉 https://architectureengineers.com/award-nomination/?ecategory=Awards&rcategory=Awardee
🌐 Visit: architectureengineers.com
📩 Contact: contact@architectureengineers.com
Get Connected Here:
*****************
Instagram : https://www.instagram.com/architecture_engineers_awards/
Facebook : https://www.facebook.com/profile.php?id=61576995475934
Tumblr : https://www.tumblr.com/blog/architectureengineers
Pinterest : https://in.pinterest.com/
Blogger : https://architectureengineers.blogspot.com/
Twitter : https://twitter.com/
#ThermalBridges
#BuildingEnvelope
#EnergyEfficiency
#UrbanDiagnostics
#NonDestructiveTesting
#DeepLearning
#YOLOv9
#ThermalImaging
#LiDAR
#ArtificialIntelligence
#HeatLossModel
#SmartCities
#SustainableBuildings
#RetrofitSolutions
#MultimodalData
#BuildingPerformance
#EnergyModeling
#MachineLearning
#AIinConstruction
#BuildingScience
Comments
Post a Comment