Detection of District Heating Pipe Network Leakage Fault Using UCB Arm Selection Method

• Published in: Buildings (Basel) Vol. 11; no. 7; p. 275
• Main Authors: Shen, Yachen, Chen, Jianping, Fu, Qiming, Wu, Hongjie, Wang, Yunzhe, Lu, You
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2021
• Subjects: Accuracy; Algorithms; Artificial intelligence; contextual bandit; Decision making; District heating; district heating pipe network; Electrical faults; Fault detection; Fault location; Heat; Heat pipes; Heating; Leakage; linear upper confidence bound; Machine learning; Methods; Neural networks; reinforcement learning; Sensors; Simulation; Troubleshooting; User needs

District heating networks make up an important public energy service, in which leakage is the main problem affecting the safety of pipeline network operation. This paper proposes a Leakage Fault Detection (LFD) method based on the Linear Upper Confidence Bound (LinUCB) which is used for arm selectio...