Granted Patent B2

US 10,890,904 · App. 16/232,309 · Granted Jan 12, 2021

Inventors: Robert D. Turney (Watertown, WI); Sudhi R. Sinha (Milwaukee, WI)

Assignee: Johnson Controls Technology Company

G05B23/0283G05B23/0294G06Q10/20G06Q30/0206

Abstract

Claims (63)

1. A model predictive maintenance system for building equipment, the model predictive maintenance system comprising:

an operational cost predictor configured to predict a first cost of operating the building equipment over a duration of a time including an optimization period as a function of maintenance performed on the building equipment during the time;

a maintenance cost predictor configured to predict a second cost of performing the maintenance on the building equipment over the duration of the time;

an objective function optimizer configured to optimize an objective function to predict a third cost associated with the building equipment over the duration of the time and determine one or more times during the optimization period to perform the maintenance on the building equipment by comparing a decrease to the first cost of operating the building equipment resulting from performing the maintenance at the one or more times with an increase to the second cost of performing the maintenance on the building equipment resulting from performing the maintenance at the one or more times, and determine one or more operating parameters of the building equipment, the objective function comprising the first cost of operating the building equipment and the second cost of performing maintenance on the building equipment; and

an output manager configured to cause a user interface of a user device to display a notification to perform the maintenance on the building equipment at the one or more times, an indication of the one or more operating parameters of the building equipment, and one or more control interface elements, wherein user interaction with the one or more control interface elements via the user device controls operation of the building equipment.

2. The model predictive maintenance system of claim 1 , further comprising a capital cost predictor configured to predict a fourth cost of purchasing or replacing the building equipment over the duration of the optimization period;

wherein the objective function further comprises the fourth cost of purchasing or replacing the building equipment.

3. The model predictive maintenance system of claim 1 , further comprising an objective function generator configured to dynamically update the objective function on a real-time basis based on closed-loop feedback from the building equipment.

4. The model predictive maintenance system of claim 1 , wherein the maintenance cost predictor is configured to predict the second cost of performing maintenance on the building equipment as a function of a plurality of binary decision variables that indicate whether the maintenance will be performed on the building equipment during times of the optimization period.

5. The model predictive maintenance system of claim 1 , wherein the operational cost predictor is configured to:

determine an operating efficiency of the building equipment at time steps of the optimization period; and

predict the first cost of operating the building equipment as a function of the operating efficiency at the time steps of the optimization period.

6. The model predictive maintenance system of claim 1 , wherein the operational cost predictor is configured to:

determine an initial operating efficiency of the building equipment using equipment performance information received as feedback from the building equipment;

identify an efficiency degradation factor defining an amount by which an operating efficiency of the building equipment degrades between consecutive time steps of the optimization period; and

determine the operating efficiency of the building equipment at the time steps of the optimization period using the initial operating efficiency and the efficiency degradation factor.

7. The model predictive maintenance system of claim 6 , wherein the objective function comprises a plurality of binary decision variables that indicate whether the maintenance will be performed on the building equipment during times of the optimization period;

wherein the operational cost predictor is configured to reset the operating efficiency of the building equipment to a post-maintenance efficiency value at particular time steps during which the plurality of binary decision variables indicate that the maintenance will be performed.

8. A model predictive maintenance system for building equipment, the model predictive maintenance system comprising:

an operational cost predictor configured to predict a first cost of operating the building equipment over a duration of a time including a period as a function of maintenance performed on the building equipment during the time;

a maintenance cost predictor configured to predict a second cost of performing the maintenance on the building equipment over the duration of the time;

an objective function provider configured to provide a function to predict a third cost associated with the building equipment over the duration of the time and determine one or more times during the period to perform the maintenance on the building equipment by comparing a decrease to the first cost of operating the building equipment resulting from performing the maintenance at the one or more times with an increase to the second cost of performing the maintenance on the building equipment resulting from performing the maintenance at the one or more times, the function comprising the first cost of operating the building equipment and the second cost of performing maintenance on the building equipment; and

an equipment controller configured to operate the building equipment to affect a variable state or condition in a building in accordance with values of one or more decision variables obtained from the function.

9. The model predictive maintenance system of claim 8 , wherein the maintenance cost predictor is configured to predict the second cost of performing the maintenance on the building equipment over the duration of the time as a function of a plurality of binary decision variables that indicate whether the maintenance will be performed on the building equipment during the time;

wherein the maintenance cost predictor is configured to:

determine a reliability of the building equipment at time steps of the period using equipment performance information received as feedback from the building equipment; and

determine values for the plurality of binary decision variables based on the reliability of the building equipment at each time step of the period.

10. The model predictive maintenance system of claim 8 , further comprising a capital cost predictor configured to predict a fourth cost of purchasing or replacing the building equipment over the duration of the period;

wherein the function further comprises the fourth cost of purchasing or replacing the building equipment.

11. The model predictive maintenance system of claim 8 , wherein the operational cost predictor is configured to predict the first cost of operating the building equipment over the duration of the period as a function of a plurality of binary decision variables.

12. The model predictive maintenance system of claim 11 , wherein the operational cost predictor is configured to:

determine an operating efficiency of the building equipment at time steps of the period; and

predict the first cost of operating the building equipment as a function of the operating efficiency at the time steps of the period.

13. The model predictive maintenance system of claim 11 , wherein the operational cost predictor is configured to:

determine an initial operating efficiency of the building equipment using equipment performance information received as feedback from the building equipment;

identify an efficiency degradation factor defining an amount by which an operating efficiency of the building equipment degrades between consecutive time steps of the period; and

determine the operating efficiency of the building equipment at the time steps of the period using the initial operating efficiency and the efficiency degradation factor.

14. The model predictive maintenance system of claim 13 , wherein the operational cost predictor is configured to reset the operating efficiency of the building equipment to a post-maintenance efficiency value at particular time steps during which the plurality of binary decision variables indicate that the maintenance will be performed.

15. One or more non-transitory computer-readable media containing program instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

predicting a first cost of operating building equipment over a duration of a time including a time period as a function of maintenance performed on the building equipment during the time;

predicting a second cost of performing the maintenance on the building equipment over the duration of the time;

performing an optimization of an objective function to determine a strategy for operating and maintaining the building equipment over the duration of the time, the strategy indicating one or more times during the time period to perform the maintenance on the building equipment determined by comparing a decrease to the first cost of operating the building equipment resulting from performing the maintenance at the one or more times with an increase to the second cost of performing the maintenance on the building equipment resulting from performing the maintenance at the one or more times, the objective function comprising the first cost of operating the building equipment and the second cost of performing maintenance on the building equipment; and

operating the building equipment to affect a variable state or condition in a building in accordance with the strategy determined by performing the optimization.

16. The one or more non-transitory computer-readable media of claim 15 , wherein:

the first cost of operating the building equipment is predicted as a function of a predicted energy consumption of the building equipment during time steps of the time period; and

the second cost of performing maintenance on the building equipment is predicted as a function of a plurality of binary decision variables that indicate whether the maintenance will be performed on the building equipment during the time steps of the time period; and

performing the optimization of the objective function comprises determining values for the plurality of binary decision variables.

17. The one or more non-transitory computer-readable media of claim 16 , the operations further comprising:

determining an operating efficiency of the building equipment at the time steps of the time period; and

predicting the predicted energy consumption of the building equipment during the time steps of the time period as a function of the operating efficiency during at the time steps of the time period.

18. The one or more non-transitory computer-readable media of claim 16 , the operations further comprising:

determining an initial operating efficiency of the building equipment using equipment performance information received as feedback from the building equipment;

identifying an efficiency degradation factor defining an amount by which an operating efficiency of the building equipment degrades between consecutive steps of the time steps of the time period; and

determining the operating efficiency of the building equipment at the time steps of the time period using the initial operating efficiency and the efficiency degradation factor.

19. The one or more non-transitory computer-readable media of claim 18 , the operations further comprising resetting the operating efficiency of the building equipment to a post-maintenance efficiency value at particular time steps during which the plurality of binary decision variables indicate that the maintenance will be performed.

20. The one or more non-transitory computer-readable media of claim 16 , the operations further comprising predicting a third cost of purchasing or replacing the building equipment over the duration of the time period;

wherein the objective function further comprises the third cost of purchasing or replacing the building equipment.

21. A method of model predictive maintenance and replacement of building equipment, the method comprising:

predicting a first cost of operating the building equipment over a duration of a time as a function of degradation of the building equipment during the time, the degradation based on at least maintenance performed on the building equipment during the time;

predicting a second cost of replacing the building equipment over the duration of the time as a function of a reliability of the building equipment, the reliability based at least on the maintenance performed on the building equipment;

predicting a third cost of performing the maintenance on the building equipment over the duration of the time;

optimizing an objective function to predict a fourth cost associated with the building equipment over the duration of the time and determine one or more first times during the time to perform the maintenance on the building equipment, determine one or more second times during the time to replace the building equipment, and determine one or more operating parameters of the building equipment by comparing a decrease to the first cost of operating the building equipment resulting from performing the maintenance at the one or more first times with an increase to the second cost of performing the maintenance on the building equipment resulting from performing the maintenance at the one or more first times, the objective function comprising the first cost of operating the building equipment, the second cost of replacing the building equipment, and the third cost of performing maintenance on the building equipment; and

an output manager configured to cause a user interface of a user device to display a notification to perform the maintenance on the building equipment at the one or more first times, an indication of the one or more operating parameters of the building equipment, and one or more control interface elements, wherein user interaction with the one or more control interface elements via the user device controls operation of the building equipment.

Assignments (4)

Continuity (3)

Cited By (9)

US 12,260,140 US 12,282,975 US 12,393,385 US 12,406,218 US 12,424,329 US 12,431,621 US 12,687,314 US 12,695,189 US 12,719,167