Granted Patent B2

US 10,402,767 · App. 14/179,672 · Granted Sep 3, 2019

Abstract

Claims (87)

1. A method for monetizing faults in a building, the method comprising:

operating building equipment to affect a variable state or condition within the building by interacting with a physical environment of the building, wherein operating the building equipment affects an amount of energy consumed by the building;

evaluating, at a processing circuit, an energy consumption model for the building to estimate the amount of energy consumed by the building as a function of a plurality of parameters;

modulating, by the processing circuit, a fault parameter of the energy consumption model and using the energy consumption model to estimate the amount of energy consumed by the building at multiple different values of the fault parameter;

generating, by the processing circuit, a first set of variables comprising multiple first differences in the fault parameter, each of the multiple first differences generated by calculating a difference between a target value of the fault parameter and one of the multiple different values of the fault parameter;

generating, by the processing circuit, a second set of variables comprising multiple second differences in the amount of energy estimated by the energy consumption model, each of the multiple second differences generated by calculating a difference between the amount of energy estimated by the energy consumption model with the fault parameter at the target value and one of the amounts of energy estimated by the energy consumption model with the fault parameter at one of the multiple different values;

using the first set of variables and the second set of variables to develop, by the processing circuit, a regression model for the fault parameter, the regression model different than the energy consumption model and estimating a change in the amount of energy consumed by the building as a direct function of a change in the fault parameter;

detecting, by the processing circuit, a fault associated with the fault parameter;

in response to detecting the fault, initiating, by the processing circuit, expanded data logging related to the fault to collect additional data indicating a current value of the fault parameter; and

determining, by the processing circuit, a cost of the fault associated with the fault parameter using the regression model and the current value of the fault parameter.

2. The method of claim 1 , further comprising:

repeating the ‘modulating,’ first ‘generating,’ second ‘generating,’ and ‘using’ steps for a plurality of different fault parameters of the energy consumption model to develop a plurality of regression models, each of the plurality of regression models estimating a change in the amount of energy consumed by the building as a function of a change in a different fault parameter of the energy consumption model.

3. The method of claim 1 , further comprising:

detecting multiple faults at the processing circuit, each of the multiple faults corresponding to a different fault parameter of the energy consumption model; and

using multiple different regression models to determine a cost associated with each of the multiple faults, wherein each of the multiple different regression models is developed for one of the different fault parameters of the energy consumption model.

4. The method of claim 3 , further comprising:

prioritizing the multiple faults based on the cost associated with each of the multiple faults.

5. The method of claim 1 , wherein determining the cost of the fault associated with the fault parameter using the regression model comprises:

determining a difference between the current value of the fault parameter and the target value of the fault parameter;

applying the difference between the current value of the fault parameter and the target value of the fault parameter as an input to the regression model developed for the fault parameter; and

using the regression model to estimate a change in energy consumption resulting from the difference in the fault parameter.

6. The method of claim 1 , further comprising:

determining a cost of correcting the fault;

comparing the cost of the fault with the cost of correcting the fault; and

displaying or storing an indication of whether it would be cost effective to correct the fault based on a result of the comparison.

7. The method of claim 1 , further comprising:

displaying or storing a fault correction priority based at least partially on the cost of the fault, wherein the fault correction priority includes at least one of:

a priority of correcting the fault relative to other faults,

an indication of whether it would be cost effective to correct the fault, and

an indication of whether the cost of the fault exceeds a cost threshold.

8. The method of claim 1 , wherein the regression model estimates a cost of the fault per unit area, the method further comprising:

identifying an area of the building affected by the fault; and

calculating an energy cost of the fault by multiplying an estimated energy cost per unit area by the area of the building affected by the fault.

9. The method of claim 1 , wherein determining the cost of the fault using the regression model comprises:

estimating an energy cost of the fault using the regression model; and

determining a monetary cost of the fault by multiplying the energy cost of the fault by a price per unit energy.

10. The method of claim 1 , wherein the regression model is a univariate regression model comprising:

one or more regression model coefficients; and

a variable corresponding to the difference between the target value of the fault parameter and one of the multiple different values of the fault parameter.

11. The method of claim 1 , wherein the regression model is a multivariate regression model comprising:

a plurality of regression model coefficients;

a variable corresponding to the difference between the target value of the fault parameter and one of the multiple different values of the fault parameter; and

one or more predictor variables comprising at least one of a variable dependent on a weather condition or a variable dependent on a building condition.

12. The method of claim 1 , wherein the target value of the fault parameter corresponds to a value of the fault parameter in an absence of a fault; and

wherein modulating the fault parameter comprises modulating the fault parameter while maintaining other parameters of the energy consumption model at fixed values.

13. A system for monetizing faults in a building, the system comprising:

building equipment operable to affect a variable state or condition within the building by interacting with a physical environment of the building, wherein operating the building equipment affects an amount of energy consumed by the building; and

a processing circuit configured to:

use an energy consumption model for the building to estimate the amount of energy consumed by the building as a function of a plurality of parameters;

modulate a fault parameter of the energy consumption model and use the energy consumption model to estimate the amount of energy consumed by the building at multiple different values of the fault parameter;

generate a first set of variables comprising multiple first differences in the fault parameter, each of the multiple first differences generated by calculating a difference between a target value of the fault parameter and one of the multiple different values of the fault parameter;

generate a second set of variables comprising multiple second differences in the amount of energy estimated by the energy consumption model, each of the multiple second differences generated by calculating a difference between the amount of energy estimated by the energy consumption model with the fault parameter at the target value and one of the amounts of energy estimated by the energy consumption model with the fault parameter at one of the multiple different values;

use the first set of variables and the second set of variables to develop a regression model for the fault parameter, the regression model different than the energy consumption model and estimating a change in the amount of energy consumed by the building as a direct function of a change in the fault parameter;

detect a fault associated with the fault parameter;

in response to detecting the fault, initiate expanded data logging related to the fault to collect additional data indicating a current value of the fault parameter; and

determine a cost of the fault associated with the fault parameter using the regression model and the current value of the fault parameter.

14. The system of claim 13 , wherein the processing circuit is configured to develop a plurality of regression models, each of the plurality of regression models estimating a change in the amount of energy consumed by the building as a function of a change in a different fault parameter of the energy consumption model.

15. The system of claim 13 , wherein the processing circuit is configured to:

detect multiple faults, each of the multiple faults corresponding to a different fault parameter of the energy consumption model;

use multiple different regression models to determine a cost associated with each of the multiple faults, wherein each of the multiple different regression models is developed for one of the different fault parameters of the energy consumption model; and

prioritize the multiple faults based on the cost associated with each of the multiple faults.

16. The system of claim 13 , wherein determining the cost of the fault associated with the fault parameter using the regression model comprises:

determining a difference between the current value of the fault parameter and the target value of the fault parameter;

applying the difference between the current value of the fault parameter and the target value of the fault parameter as an input to the regression model developed for the fault parameter; and

using the regression model to estimate a change in energy consumption resulting from the difference in the fault parameter.

17. The system of claim 13 , wherein the processing circuit is configured to output a fault correction priority based at least partially on the cost of the fault, wherein the fault correction priority includes at least one of:

a priority of correcting the fault relative to other faults,

an indication of whether it would be cost effective to correct the fault, and

an indication of whether the cost of the fault exceeds a cost threshold.

18. The system of claim 13 , wherein the regression model is at least one of a univariate regression model and a multivariate regression model;

wherein the univariate regression model comprises one or more regression model coefficients, and a variable corresponding to the difference between the target value of the fault parameter and one of the multiple different values of the fault parameter; and

wherein the multivariate regression model comprises a plurality of regression model coefficients, a variable corresponding to the difference between the target value of the fault parameter and one of the multiple different values of the fault parameter, and a variable dependent on a weather condition.

19. A system for prioritizing faults in a building, the system comprising:

building equipment operable to affect a variable state or condition within the building by interacting with a physical environment of the building, wherein operating the building equipment affects an amount of energy consumed by the building; and

a processing circuit configured to:

modulate a fault parameter of an energy consumption model and use the energy consumption model to estimate the amount of energy consumed by the building at multiple different values of the fault parameter;

generate a first set of variables comprising multiple first differences in the fault parameter, each of the multiple first differences generated by calculating a difference between a target value of the fault parameter and one of the multiple different values of the fault parameter;

generate a second set of variables comprising multiple second differences in the amount of energy estimated by the energy consumption model, each of the multiple second differences generated by calculating a difference between the amount of energy estimated by the energy consumption model with the fault parameter at the target value and one of the amounts of energy estimated by the energy consumption model with the fault parameter at one of the multiple different values;

use the first set of variables and the second set of variables to develop an energy cost regression model for the fault parameter, the energy cost regression model different than the energy consumption model and estimating a change in the amount of energy consumed by the building as a direct function of a change in the fault parameter;

detect a fault associated with the fault parameter;

in response to detecting the fault, initiate expanded data logging related to the fault to collect additional data indicating a current value of the fault parameter; and

determine a cost of the fault associated with the fault parameter using the energy cost regression model developed for the fault parameter and the current value of the fault parameter.

20. The system of claim 19 , wherein the processing circuit is configured to determine multiple different costs associated with multiple different degrees of the fault using the energy cost regression model developed for the fault parameter, each of the multiple different degrees of fault corresponding to a different change in the fault parameter.

21. The system of claim 19 , wherein the processing circuit is configured to:

detect multiple faults, each of the multiple faults corresponding to a different fault parameter of the energy consumption model;

develop and use multiple different energy cost regression models to determine a cost associated with each of the multiple faults, wherein each of the multiple different energy cost regression models is developed for one of the different fault parameters of the energy consumption model; and

prioritize the multiple faults based on the cost associated with each of the multiple faults.

Assignments (3)

Cited By (12)

US 1,092,505 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 12,456,362 US 12,554,383 US 12,687,314 US 12,695,189 US 12,719,167