US 11,747,776 B2
Adaptive training and deployment of single device and clustered device fault detection models for connected equipment
Young M. Lee, Old Westbury, NY (US); Sugumar Murugesan, Santa Clara, CA (US); ZhongYi Jin, Santa Clara, CA (US); Jaume Amores, Cork (IE); Kelsey Carle Schuster, Wauwatosa, WI (US); Steven R. Vitullo, Milwaukee, WI (US); and Henan Wang, Milwaukee, WI (US)
Assigned to JOHNSON CONTROLS TYCO IP HOLDINGS LLP, Milwaukee, WI (US)
Filed by Johnson Controls Tyco IP Holdings LLP, Milwaukee, WI (US)
Filed on Oct. 11, 2022, as Appl. No. 17/963,699.
Application 17/963,699 is a continuation of application No. 16/198,456, filed on Nov. 21, 2018, granted, now 11,474,485.
Claims priority of provisional application 62/685,618, filed on Jun. 15, 2018.
Prior Publication US 2023/0033206 A1, Feb. 2, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G05B 13/04 (2006.01); F24F 11/38 (2018.01); F24F 11/63 (2018.01); G06N 20/00 (2019.01); F24F 11/64 (2018.01); G05B 13/02 (2006.01); G06N 5/04 (2023.01)
CPC G05B 13/048 (2013.01) [F24F 11/38 (2018.01); F24F 11/63 (2018.01); F24F 11/64 (2018.01); G05B 13/0265 (2013.01); G05B 13/04 (2013.01); G06N 20/00 (2019.01); G05B 13/027 (2013.01); G05B 13/028 (2013.01); G06N 5/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A fault prediction system for building equipment, the system comprising:
one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to:
receive device data for a plurality of devices of the building equipment, the device data indicating performance of the plurality of devices;
generate, based on the received device data, a plurality of prediction models comprising at least one of single device prediction models generated for each of the plurality of devices or cluster prediction models generated for device clusters of the plurality of devices;
label each of the plurality of prediction models as an accurately predicting model or an inaccurately predicting model based on a performance of each of the plurality of prediction models; and
predict a device fault with each of the plurality of prediction models labeled as an accurately predicting model.