US 12,242,259 B2
Model predictive maintenance system with event or condition based performance
Mohammad N. Elbsat, Milwaukee, WI (US); Michael J. Wenzel, Oak Creek, WI (US); Farhad Balali, Milwaukee, WI (US); and Robert D. Turney, Watertown, WI (US)
Assigned to Tyco Fire & Security GmbH
Filed by Johnson Controls Technology Company, Auburn Hills, MI (US)
Filed on Jul. 30, 2020, as Appl. No. 16/943,781.
Application 16/943,781 is a continuation in part of application No. 16/899,220, filed on Jun. 11, 2020.
Application 16/899,220 is a continuation in part of application No. 15/895,836, filed on Feb. 13, 2018, granted, now 11,487,277.
Claims priority of provisional application 62/883,508, filed on Aug. 6, 2019.
Claims priority of provisional application 62/511,113, filed on May 25, 2017.
Prior Publication US 2020/0356087 A1, Nov. 12, 2020
Int. Cl. G05B 23/02 (2006.01); G16Y 10/80 (2020.01); G16Y 20/30 (2020.01); G16Y 40/20 (2020.01); G16Y 40/40 (2020.01)
CPC G05B 23/0283 (2013.01) [G05B 23/024 (2013.01); G16Y 10/80 (2020.01); G16Y 20/30 (2020.01); G16Y 40/20 (2020.01); G16Y 40/40 (2020.01)] 19 Claims
OG exemplary drawing
 
1. A model predictive maintenance (MPM) system for building equipment, the MPM system comprising:
one or more processing circuits comprising one or more processors and memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
at a first time, predicting a future state of the building equipment predicted to occur at a second time after the first time;
obtaining one or more performance indicators for the building equipment indicating an actual state of the building equipment at a second time;
determining whether a trigger condition has been satisfied based on the one or more performance indicators by comparing the actual state of the building equipment at the second time with the predicted future state of the building equipment predicted to occur at the second time;
triggering a model predictive maintenance process to generate a maintenance schedule for the building equipment and operating decisions for the building equipment in response to determining that the trigger condition has been satisfied, wherein the model predictive maintenance process comprises:
predicting a resource consumption of the building equipment over an optimization period as a function of an estimated degradation state of the building equipment;
defining a cost of operating the building equipment over the optimization period as a function of the predicted resource consumption;
defining a cost of performing maintenance on the building equipment over the optimization period as a function of the maintenance schedule for the building equipment; and
optimizing an objective function including the cost of operating the building equipment and the cost of performing maintenance on the building equipment to determine the maintenance schedule;
initiating a maintenance activity for the building equipment in accordance with the maintenance schedule; and
controlling the building equipment by generating electronic control signals based on the operating decisions for the building equipment and causing the building equipment to affect a variable state or condition in a building using the electronic control signals.