Application of deep learning in facility management and maintenance for heating, ventilation, and air conditioning
Publication date
June 23, 2022
Abstract
Despite the promising results of deep learning research, construction industry applications are still limited. Facility Management (FM) in construction has yet to take full advantage of the efficiency of deep learning techniques in daily operations and maintenance. Heating, Ventilation, and Air Conditioning (HVAC) is a major part of Facility Management and Maintenance (FMM) operations, and an occasional HVAC malfunction can lead to a huge monetary loss. The application of deep learning techniques in FMM can optimize building performance, especially in predictive maintenance, by lowering energy consumption, scheduling maintenance, as well as monitoring equipment. This review covers 100 papers that show how neural networks have evolved in this area and summarizes deep learning applications in facility management. Furthermore, it discusses the current challenges and foresees how deep learning applications can be useful in this field for researchers developing specific deep learning models for FMM. The paper also highlights how establishing public datasets relevant to FM for predictive maintenance is crucial for the effectiveness of deep learning techniques. The utilization of deep learning methods for predictive maintenance on Thermal-Storage Air-Conditioning (TS-AC) in HVAC is necessary for environmental sustainability, as well as to improve the cost-efficiency of buildings.
Item Type
Article
Associated Schools / Departments
Department of Civil Engineering
School of Computer Science (MY)
Date Deposited
February 19, 2026
Except where otherwise noted, this item's license is described as
File(s)![Thumbnail Image]()
Name
Application of deep learning in facility management and maintenance for heating, ventilation, and air conditioning-10.1016j.autcon.2022.104445.pdf
Type
Full-text
Description
Published
Size
1.83 MB
Format
Adobe PDF
Checksum (MD5)
ea13ecd7f2e3b35054fb081d660c2186