US 12,305,874 B2
Cost savings from fault prediction and diagnosis
Priti Shinde, Vambori (IN); Kathiresan Rajagopal, Kalyan West (IN); Abu Bakr Khan, Franklin, WI (US); and Young M. Lee, Old Westbury, NY (US)
Assigned to Tyco Fire & Security GmbH, Neuhausen am Rheinfall (CH)
Filed by Johnson Controls Tyco IP Holdings LLP, Milwaukee, WI (US)
Filed on Sep. 6, 2023, as Appl. No. 18/242,976.
Application 18/242,976 is a continuation of application No. 17/318,877, filed on May 12, 2021, granted, now 11,859,846.
Application 17/318,877 is a continuation in part of application No. 16/198,456, filed on Nov. 21, 2018, granted, now 11,474,485.
Application 17/318,877 is a continuation in part of application No. 16/198,416, filed on Nov. 21, 2018, granted, now 11,531,310.
Application 17/318,877 is a continuation in part of application No. 16/198,377, filed on Nov. 21, 2018, granted, now 11,604,441.
Claims priority of provisional application 62/685,618, filed on Jun. 15, 2018.
Prior Publication US 2024/0068693 A1, Feb. 29, 2024
Int. Cl. F24F 11/63 (2018.01); G05B 19/042 (2006.01); G06N 20/10 (2019.01); G06Q 50/06 (2024.01)
CPC F24F 11/63 (2018.01) [G05B 19/042 (2013.01); G06N 20/10 (2019.01); G06Q 50/06 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A heating, ventilation, and air conditioning (HVAC) performance prediction system for a building, comprising a processing circuit including a processor and memory, the memory having instructions stored thereon that, when executed by the processor, cause the processing circuit to:
receive operational HVAC data relating to a plurality of HVAC components, the operational HVAC data indicating performance of the plurality of HVAC components;
train a machine learning system using historic HVAC data;
generate, using the operational HVAC data and the machine learning system, predicted operational parameters corresponding to a future time period, wherein the predicted operational parameters comprise a predicted value of a physical condition and a predicted setpoint for the physical condition;
determine a predicted HVAC performance by comparing the predicted setpoint for the physical condition to the predicted value of the physical condition; and
cause a change in operation of the HVAC components based on the predicted HVAC performance, the change comprising at least one of maintenance or repair, adjustment of a setpoint used by at least one of the plurality of HVAC components, or disabling at least one of the plurality of HVAC components.