US 11,927,609 B2
Condition monitoring via energy consumption audit in electrical devices and electrical waveform audit in power networks
WenZhan Song, Alpharetta, GA (US); Yang Shi, Athens, GA (US); Fangyu Li, Athens, GA (US); and Jin Ye, Bogart, GA (US)
Assigned to UNIVERSITY OF GEORGIA RESEARCH FOUNDATION, INC., Athens, GA (US)
Appl. No. 17/312,976
Filed by University of Georgia Research Foundation, Inc., Athens, GA (US)
PCT Filed Dec. 13, 2019, PCT No. PCT/US2019/066340
§ 371(c)(1), (2) Date Jun. 11, 2021,
PCT Pub. No. WO2020/124010, PCT Pub. Date Jun. 18, 2020.
Claims priority of provisional application 62/779,735, filed on Dec. 14, 2018.
Claims priority of provisional application 62/944,032, filed on Dec. 5, 2019.
Prior Publication US 2022/0050130 A1, Feb. 17, 2022
Int. Cl. G01R 19/25 (2006.01); G01R 21/133 (2006.01); G06F 9/448 (2018.01); G06F 11/07 (2006.01); G06Q 50/06 (2012.01); H02J 13/00 (2006.01); H04L 9/40 (2022.01)
CPC G01R 19/2513 (2013.01) [G01R 21/133 (2013.01); G06F 9/4498 (2018.02); G06F 11/079 (2013.01); G06Q 50/06 (2013.01); H02J 13/00002 (2020.01); H04L 63/1416 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
an electrical device coupled to a network;
an energy meter coupled to the electrical device, the energy meter configured to monitor an energy profile of the electrical device, the energy meter isolated from an internet of things (IoT) system including the electrical device; and
at least one application executable in a computing device coupled to the energy meter, wherein, when executed, the at least one application causes the computing device to at least:
analyze energy profile data of the electrical device, the energy profile data being received from the energy meter based on the monitoring of the energy profile;
monitor one or more conditions of the electrical device based on the energy profile data;
detect an anomaly in the electrical device based on a change in the one or more conditions;
determine a type of anomaly based at least in part on a trained classification model; and
diagnose a root cause of the anomaly based at least in part on one or more characteristics in the energy profile data and the type of anomaly, the root cause comprising at least one of a threat source or a malfunctioning component of the electrical device.