WIKINDX |
![]() |
Xie, X., Lu, Q., Parlikad, A. K., & Schooling, J. M. (2020). Digital twin enabled asset anomaly detection for building facility management. IFAC-PapersOnLine, 53(3), 380–385. |
Resource type: Journal Article BibTeX citation key: Xie2020 View all bibliographic details |
Categories: Artificial Intelligence, Complexity Science, Computer Science, Data Sciences, Decision Theory, Engineering, General Subcategories: Autonomous systems, Behavioral analytics, Big data, Decision making, Deep learning, Edge AI, Informatics, Internet of things, Machine learning, Neural nets, Robotics, Simulations, Virtual reality Creators: Lu, Parlikad, Schooling, Xie Publisher: Collection: IFAC-PapersOnLine |
Attachments |
Abstract |
Assets play a significant role in building utilities by undertaking the majority of their service functionalities. However, a comprehensive facility management solution that can help to monitor, detect, record and communicate asset anomalous issues is till nowhere to be found. The digital twin concept is gaining increasing popularity in architecture, engineering and construction/facility management (AEC/FM) sector, and a digital twin enabled asset condition monitoring and anomaly detection framework is proposed in this paper. A Bayesian change point detection methodology is tentatively embedded to reveal the suspicious asset anomalies in a real time manner. A demonstrator on cooling pumps is developed and implemented based on Centre for Digital Built Britain (CDBB) West Cambridge Digital Twin Pilot. The results demonstrate that supported by the data management capability provided by digital twin, the proposed framework realizes a continuous condition monitoring and anomaly detection for single asset, which contributes to efficient and automated asset monitoring in O&M management.
|