東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Integrated Building Envelope Assessm...

Mirzabeigi, Shayan,

Linked to FindBook

Google Book

Amazon

博客來

Integrated Building Envelope Assessment Towards Automation of Energy Retrofits: Drone-Based Data Acquisition, Automated Thermal Anomaly Detection, and Workflow Development /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Integrated Building Envelope Assessment Towards Automation of Energy Retrofits: Drone-Based Data Acquisition, Automated Thermal Anomaly Detection, and Workflow Development // Shayan Mirzabeigi.
Author:	Mirzabeigi, Shayan,
Description:	1 electronic resource (204 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-10, Section: B.
Contained By:	Dissertations Abstracts International86-10B.
Subject:	Energy efficiency. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31897749
ISBN:	9798311903660

Integrated Building Envelope Assessment Towards Automation of Energy Retrofits: Drone-Based Data Acquisition, Automated Thermal Anomaly Detection, and Workflow Development /
Mirzabeigi, Shayan,

Integrated Building Envelope Assessment Towards Automation of Energy Retrofits: Drone-Based Data Acquisition, Automated Thermal Anomaly Detection, and Workflow Development /Shayan Mirzabeigi. - 1 electronic resource (204 pages)

Source: Dissertations Abstracts International, Volume: 86-10, Section: B.

Buildings in the United States consume over 70% of the country's electricity and significantly contribute to carbon emissions. Approximately 65% of these buildings were constructed before 1992. Retrofitting these existing buildings presents a substantial opportunity to meet clean energy goals, as evidenced by the 50-90% operational energy reductions achieved through deep retrofits. Despite the potential benefits, energy audits - the initial step in retrofit processes - remain largely unautomated, time-consuming, and relatively expensive compared to more advanced, automated approaches. This dissertation aims to contribute to the field of building energy retrofitting by integrating advanced technologies, such as drones and artificial intelligence (AI), to automate the building inspection process and data collection. The primary objectives are to develop a drone-based approach for building envelope assessment, improve thermal anomaly detection using deep learning, and create automated workflows for building model generation for energy modeling purposes. Therefore, this research explores the use of Unmanned Aerial Systems (UAS) for efficient and accurate envelope data collection. Various scanning techniques, sensor configurations, and flight parameters necessary for effective data capture and compliance with drone operation regulations are evaluated. This research also enhances envelope thermal anomaly detection by combining thermal imaging with visionbased techniques and semantic segmentation. Leveraging deep learning, this approach improves the accuracy of identifying thermal anomalies such as thermal bridges and insulation gaps. Finally, the dissertation develops an automated workflow for transforming 3D point clouds into Building Information Models for retrofit design and energy simulation. This workflow facilitates the creation of models for accurate and reliable performance analysis in energy retrofit applications, detailing steps to develop semantically rich models that reflects existing building conditions. Overall, this research makes significant contributions to the field of building energy retrofits by providing innovative solutions for inspection, assessment, and potential use in performance verification. The integration of drones and AI advances sustainable construction practices, supporting broader environmental and social goals by making retrofit processes more affordable and accessible. The outcomes align with clean energy targets and climate action plans, particularly those of New York State, and have the potential for replication in other building types, regions and countries.

English

ISBN: 9798311903660Subjects--Topical Terms:

3555643
Energy efficiency.

Integrated Building Envelope Assessment Towards Automation of Energy Retrofits: Drone-Based Data Acquisition, Automated Thermal Anomaly Detection, and Workflow Development /
LDR:04050nmm a22003733i 4500 001 2434540
005 20250912102038.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798311903660
035 $a (MiAaPQD)AAI31897749
035 $a AAI31897749
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Mirzabeigi, Shayan, $e author. $3 3824547
245 1 0 $a Integrated Building Envelope Assessment Towards Automation of Energy Retrofits: Drone-Based Data Acquisition, Automated Thermal Anomaly Detection, and Workflow Development / $c Shayan Mirzabeigi.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (204 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-10, Section: B.
500 $a Advisors: Razkenari, Mohamad; Crovella, Paul.
502 $b Ph.D. $c State University of New York College of Environmental Science and Forestry $d 2024.
520 $a Buildings in the United States consume over 70% of the country's electricity and significantly contribute to carbon emissions. Approximately 65% of these buildings were constructed before 1992. Retrofitting these existing buildings presents a substantial opportunity to meet clean energy goals, as evidenced by the 50-90% operational energy reductions achieved through deep retrofits. Despite the potential benefits, energy audits - the initial step in retrofit processes - remain largely unautomated, time-consuming, and relatively expensive compared to more advanced, automated approaches. This dissertation aims to contribute to the field of building energy retrofitting by integrating advanced technologies, such as drones and artificial intelligence (AI), to automate the building inspection process and data collection. The primary objectives are to develop a drone-based approach for building envelope assessment, improve thermal anomaly detection using deep learning, and create automated workflows for building model generation for energy modeling purposes. Therefore, this research explores the use of Unmanned Aerial Systems (UAS) for efficient and accurate envelope data collection. Various scanning techniques, sensor configurations, and flight parameters necessary for effective data capture and compliance with drone operation regulations are evaluated. This research also enhances envelope thermal anomaly detection by combining thermal imaging with visionbased techniques and semantic segmentation. Leveraging deep learning, this approach improves the accuracy of identifying thermal anomalies such as thermal bridges and insulation gaps. Finally, the dissertation develops an automated workflow for transforming 3D point clouds into Building Information Models for retrofit design and energy simulation. This workflow facilitates the creation of models for accurate and reliable performance analysis in energy retrofit applications, detailing steps to develop semantically rich models that reflects existing building conditions. Overall, this research makes significant contributions to the field of building energy retrofits by providing innovative solutions for inspection, assessment, and potential use in performance verification. The integration of drones and AI advances sustainable construction practices, supporting broader environmental and social goals by making retrofit processes more affordable and accessible. The outcomes align with clean energy targets and climate action plans, particularly those of New York State, and have the potential for replication in other building types, regions and countries.
546 $a English
590 $a School code: 0213
650 4 $a Energy efficiency. $3 3555643
650 4 $a High rise buildings. $3 3560072
650 4 $a Heat detection. $3 3824548
650 4 $a Energy consumption. $3 631630
650 4 $a Building information modeling. $3 1361709
650 4 $a Neural networks. $3 677449
690 $a 0800
690 $a 0729
710 2 $a State University of New York College of Environmental Science and Forestry. $e degree granting institution. $3 3818965
720 1 $a Razkenari, Mohamad $e degree supervisor.
720 1 $a Crovella, Paul $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-10B.
790 $a 0213
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31897749