A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Digital twin enabled fault detection and diagnosis process for building HVAC systems
https://orcid.org/0000-0003-4601-9519
https://orcid.org/0000-0001-7580-3164
https://orcid.org/0000-0002-7197-8677
Abstract The emerging concept of digital twins outlines the pathway towards intelligent buildings. Although abundant building data carries an overwhelming amount of information, if not well exploited, the redundant and irrelevant data dimensions result in the overfitting problem and heavy computational load. Taking the fault detection and diagnosis process for building HVAC systems as the case, this paper adopts a symbolic artificial intelligence technique to identify informative sensory dimensions for building-specific faults by exploring the symbolic representation of labelled time-series. To preserve this ad-hoc temporal knowledge in the digital twin ecosystem, machine-readable fault tags are defined to label corresponding sensor entities. A digital twin data platform is developed to annotate the real-time data with fault tags and produce filtered low-latency data streams associated with a specified tag to automate this process. This paper describes a digital twin-based approach to automatically identify and pick up informative data to support dynamic asset management.
Highlights Adopt tagging to represent and preserve knowledge learned through AI techniques. Use Bag-of-Words to identify informative sensory dimensions for case-specific faults. Define machine-readable fault tags to label the sensors and annotate real-time data. Produce low-latency data streams appended with the specified tags to feed the FDD. Informed a way to enable asset management functionalities through digital twin.
Digital twin enabled fault detection and diagnosis process for building HVAC systems
https://orcid.org/0000-0003-4601-9519
https://orcid.org/0000-0001-7580-3164
https://orcid.org/0000-0002-7197-8677
Abstract The emerging concept of digital twins outlines the pathway towards intelligent buildings. Although abundant building data carries an overwhelming amount of information, if not well exploited, the redundant and irrelevant data dimensions result in the overfitting problem and heavy computational load. Taking the fault detection and diagnosis process for building HVAC systems as the case, this paper adopts a symbolic artificial intelligence technique to identify informative sensory dimensions for building-specific faults by exploring the symbolic representation of labelled time-series. To preserve this ad-hoc temporal knowledge in the digital twin ecosystem, machine-readable fault tags are defined to label corresponding sensor entities. A digital twin data platform is developed to annotate the real-time data with fault tags and produce filtered low-latency data streams associated with a specified tag to automate this process. This paper describes a digital twin-based approach to automatically identify and pick up informative data to support dynamic asset management.
Highlights Adopt tagging to represent and preserve knowledge learned through AI techniques. Use Bag-of-Words to identify informative sensory dimensions for case-specific faults. Define machine-readable fault tags to label the sensors and annotate real-time data. Produce low-latency data streams appended with the specified tags to feed the FDD. Informed a way to enable asset management functionalities through digital twin.
Digital twin enabled fault detection and diagnosis process for building HVAC systems
https://orcid.org/0000-0003-4601-9519
https://orcid.org/0000-0001-7580-3164
https://orcid.org/0000-0002-7197-8677
Abstract The emerging concept of digital twins outlines the pathway towards intelligent buildings. Although abundant building data carries an overwhelming amount of information, if not well exploited, the redundant and irrelevant data dimensions result in the overfitting problem and heavy computational load. Taking the fault detection and diagnosis process for building HVAC systems as the case, this paper adopts a symbolic artificial intelligence technique to identify informative sensory dimensions for building-specific faults by exploring the symbolic representation of labelled time-series. To preserve this ad-hoc temporal knowledge in the digital twin ecosystem, machine-readable fault tags are defined to label corresponding sensor entities. A digital twin data platform is developed to annotate the real-time data with fault tags and produce filtered low-latency data streams associated with a specified tag to automate this process. This paper describes a digital twin-based approach to automatically identify and pick up informative data to support dynamic asset management.
Highlights Adopt tagging to represent and preserve knowledge learned through AI techniques. Use Bag-of-Words to identify informative sensory dimensions for case-specific faults. Define machine-readable fault tags to label the sensors and annotate real-time data. Produce low-latency data streams appended with the specified tags to feed the FDD. Informed a way to enable asset management functionalities through digital twin.
Digital twin enabled fault detection and diagnosis process for building HVAC systems
Xie, Xiang (author) / Merino, Jorge (author) / Moretti, Nicola (author) / Pauwels, Pieter (author) / Chang, Janet Yoon (author) / Parlikad, Ajith (author)
2022-11-28
Article (Journal)
Electronic Resource
English
Cross-level fault detection and diagnosis of building HVAC systems
| Online Contents | 2011
Cross-level fault detection and diagnosis of building HVAC systems
| Elsevier | 2011
Cross-level fault detection and diagnosis of building HVAC systems
| British Library Online Contents | 2011
Fault Detection and Diagnosis of HVAC Systems
| British Library Online Contents | 1999
Fault Detection and Diagnosis of HVAC Systems
| British Library Conference Proceedings | 1999