Method and apparatus for optimizing operation of a power generating plant using artificial intelligence techniques

• US 7,584,024 B2
• Filed: 02/08/2005
• Issued: 09/01/2009
• Est. Priority Date: 02/08/2005
• Status: Active Grant

• Current Assignee: GE Digital Holdings LLC (GE Aerospace)
• Original Assignee: Pegasus Technologies Incorporated (Evergreen Energy, Inc.)
• Inventors: Parikh, Neel J., Katrompas, Alexander M., Wroblewski, David
• Primary Examiner(s): DeCady; Albert
• Assistant Examiner(s): Gami; Tejal
• Application Number:
  US11/053,734
• Publication Number:
  US 20060178762A1
• Time in Patent Office: 1,666 Days
• Field of Search: 700/30, 700/36, 700/46
• US Class Current: 700/300
• CPC Class Codes: G05B 13/027 using neural networks only

Abstract

A method and apparatus for optimizing the operation of a power generating plant using artificial intelligence techniques. One or more decisions D are determined for at least one consecutive time increment, where at least one of the decisions D is associated with a discrete variable for the operation of a power plant device in the power generating plant. In an illustrated embodiment, the power plant device is a soot cleaning device associated with a boiler.

Claims

1. A method for optimizing operation of a power generating plant having a plurality of power plant device groups, each power plant device group comprised of one or more power plant devices, the method comprising:

evaluating the results of an optimization process for identifying a power plant device group for activation;

for each power plant device group, determining a target factor value for at least one associated time value parameter, wherein the greater the target factor value, the higher the rank of the power plant device group;

comparing the target factor value to predefined threshold ranges to determine a respective weight value for each power plant device group, wherein each weight value is respectively associated with one of the following operating conditions;

(a) do not activate power plant devices in the power plant device group,

(b) may not activate power plant devices in the power plant device group,

(c) may activate power plant devices in the power plant device group, and

(d) activate power plant devices in the power plant device group;

determining a plurality of decisions D of an initial time increment (t₀) in accordance with the determined weight values, wherein each said decision D is associated with a discrete variable having a finite set of possible values for operation of one of the power plant device groups;

obtaining a model of the power generating plant that predicts one or more output parameter values that are a function of one or more input parameter values of the power generating plant, the output parameter values are associated with goals in operation of the power generating plant, wherein optimized input parameter values are determined by iteratively varying one or more input parameter values received by the model until the predicted output parameter values are substantially equal to said goals;

determining one or more subsequent decisions D of one or more subsequent time increments after the initial time increment (t₀), in accordance with optimized input parameter values that are determined using said model;

selecting one of said decisions D determined for the initial time increment (t₀) as a decision for operation of the power generating plant at the initial time increment (t₀), wherein said selection is based upon analysis of the output parameter values obtained in connection with each of said decisions D of the initial time increment and the output parameter values obtained in connection with each said subsequent decisions D of the one or more subsequent time increments; and

operating a power plant device group of the power generating plant for the initial time increment in accordance with the selected decision D, wherein said power plant devices include a soot cleaning device.

2. A method according to claim 1, wherein said at least one discrete variable has a value of ON or OFF with respect to activation of said power plant device group.

3. A method according to claim 1, wherein said method further comprises:

determining whether each decision D will violate any rules or constraints associated with operation of said power generating plant.

4. A method according to claim 1, wherein said plurality of power plant device groups include soot cleaning device groups, wherein each soot cleaning device group includes one or more soot cleaning devices.

5. A method according to claim 1, wherein said decisions D for the time increments form a decision tree.

6. A method according to claim 1, wherein said method further comprises:

ranking said decisions D for each time increment, wherein said rank is associated with achievement of a desired goal for the power generating plant.

13. A method according to claim 4, wherein said input parameter values are associated with at least one time value parameter for operation of each soot cleaning device group, and at least one plant parameter.

14. A method according to claim 13, wherein said at least one time value parameter is selected from the group consisting of:

(1) a DutyCycle parameter representative of a total duration of time for which soot cleaning devices in a soot cleaning device group were active within a defined time period;

(2) an OffTime parameter representative of a total duration of time for which soot cleaning devices in a soot cleaning device group were inactive;

(3) an OnTime parameter representative of a total duration of time for which soot cleaning devices in a soot cleaning device group were active;

(4) a MaxOffTime parameter representative of a maximum total duration of time for which soot cleaning devices in a soot cleaning device group may be left inactive subsequent to a soot cleaning operation; and

(5) a MinOffTime parameter representative of a minimum total duration of time for which soot cleaning devices in a soot cleaning device group should be kept inactive subsequent to a soot cleaning operation.

15. A method according to claim 13, wherein said at least one plant parameter is selected from the group consisting of:

combustion parameters, fuel parameters, post-combustion parameters, emissions parameters, performance parameters, given conditions and state indicators.

16. A method according to claim 1, wherein said output parameter values are associated with the group consisting of:

NOx emission, heat rate, and boiler efficiency.

17. A method according to claim 1, wherein said method further comprises the step of:

dynamically adjusting the desired goals associated with said one or more output parameter values.

18. A method according to claim 4, wherein said method further comprises:

ranking the decisions D in accordance with a predetermined criteria, said ranking includes the steps of;

determining for each soot cleaning device group an associated DutyCycle parameter value (Opt Result) associated with said adjusted input parameters;

determining for each soot cleaning device group a current DutyCycle parameter value (CurrentValue); and

determining for each soot cleaning device group an optimization cycle time value (OptCycleTime).

19. A method according to claim 18, wherein said step of ranking the decisions D in accordance with the predetermined criteria further comprises:

determining a Target Factor by the following expression;

Target Factor=(OptResult−

CurrentValue)/OptCycleTime.

7. A system for optimizing operation of a power generating plant including a plurality of power plant device groups, each power plant device group comprised of one or more power plant devices, the system comprising:

means for evaluating the results of an optimization process for identifying a power plant device group for activation;

means for determining a target factor value for at least one associated time value parameter, for each power plant device group, wherein the greater the target factor value, the higher the rank of the power plant group;

means for comparing the target factor value to predefined threshold ranges to determine a respective weight value for each power plant device group, wherein each weight value is respectively associated with one of the following operating conditions;

(a) do not activate power plant devices in the power plant device group,

(b) may not activate power plant devices in the power plant device group,

(c) may activate power plant devices in the power plant device group, and

(d) activate power plant devices in the power plant device group;

means for determining a plurality of decisions D of an initial time increment (t₀) in accordance with the determined weight values, wherein each said decision D is associated with a discrete variable having a finite set of possible values for operation of one of the power plant device groups;

a model of the power generating plant that predicts one or more output parameter values that are a function of one or more input parameter values of the power generating plant, the output parameter values are associated with goals in operation of the power generating plant, wherein optimized input parameter values are determined by iteratively varying one or more input parameter values received by the model until the predicted output parameter values are substantially equal to said goals;

means for determining one or more subsequent decisions D of one or more subsequent time increments after the initial time increment (t₀), in accordance with optimized input parameter values that are determined using said model;

means for selecting one of said decisions D determined for the initial time increment (t₀) as a decision for operation of the power generating plant at the initial time increment (t₀), wherein said selection is based upon analysis of the output parameter values obtained in connection with each of said decisions D of the initial time increment and the output parameter values obtained in connection with each of said subsequent decisions D of the one or more subsequent time increments; and

means for operating the power generating plant for the initial time increment in accordance with the selected decision D, thereby optimizing operation of the power generating plant, wherein said power plant devices include a soot cleaning device.

8. A system according to claim 7, wherein said discrete variable has a value of ON or OFF with respect to activation of said power plant device group.

9. A system according to claim 7, wherein said system further comprises:

means for determining whether each decision D will violate any rules or constraints associated with operation of said power generating plant.

10. A system according to claim 9, wherein said plurality of power plant device groups include soot cleaning device groups, wherein each soot cleaning device group includes one or more soot cleaning devices.

11. A system according to claim 7, wherein said decisions D for the time increments form a decision tree.

12. A system according to claim 7, wherein said system further comprises:

means for ranking each of said decisions D for each time increment, wherein said rank is associated with achievement of a desired goal for the power generating plant.

20. A system according to claim 10, wherein said input parameter values are associated with at least one time value parameter for operation of each soot cleaning device group, and at least one plant parameter.

21. A system according to claim 20, wherein said at least one time value parameter is selected from the group consisting of:

(1) a DutyCycle parameter representative of a total duration of time for which soot cleaning devices in a soot cleaning device group were active within a defined time period;

(2) an OffTime parameter representative of a total duration of time for which soot cleaning devices in a soot cleaning device group were inactive;

(3) an OnTime parameter representative of a total duration of time for which soot cleaning devices in a soot cleaning device group were active;

(4) a MaxOffTime parameter representative of a maximum total duration of time for which soot cleaning devices in a soot cleaning device group may be left inactive subsequent to a soot cleaning operation; and

(5) a MinOffTime parameter representative of a minimum total duration of time for which soot cleaning devices in a soot cleaning device group should be kept inactive subsequent to a soot cleaning operation.

22. A system according to claim 20, wherein said at least one plant parameter is selected from the group consisting of:

combustion parameters, fuel parameters, post-combustion parameters, emissions parameters, performance parameters, given conditions and state indicators,

23. A system according to claim 7, wherein said output parameter values are associated with the group consisting of:

NOx emission, heat rate, and boiler efficiency.

24. A system according to claim 7, wherein said system further comprises:

means for dynamically adjusting the desired goals associated with said one or more output parameter values.

25. A system according to claim 10, wherein said system further comprises means for ranking the decisions D in accordance with a predetermined criteria, said means for ranking includes:

means for determining for each soot cleaning device group an associated DutyCycle parameter value (Opt Result) associated with said adjusted input parameters;

means for determining for each soot cleaning device group a current DutyCycle parameter value (CurrentValue); and

means for determining for each soot cleaning device group an optimization cycle time value (OptCycleTime).

26. A system according to claim 25, wherein said means for ranking the decisions D in accordance with the predetermined criteria further comprises:

means for determining a Target Factor by the following expression;

Target Factor=(OptResult−

CurrentValue)/OptCycleTime.