Automatic identification of operating parameters for power plants

• US 9,200,591 B2
• Filed: 07/06/2011
• Issued: 12/01/2015
• Est. Priority Date: 07/06/2011
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Du, Yu, Zhang, Xiaoyan
• Primary Examiner(s): Feliciano, Eliseo Ramos
• Assistant Examiner(s): STIFTER JR, TERENCE E
• Application Number:
  US13/177,324
• Publication Number:
  US 20130013255A1
• Time in Patent Office: 1,609 Days
• Field of Search: 702/183
• US Class Current: 1/1
• CPC Class Codes: F01K 13/02 Controlling, e.g. stopping or starting
• CPC Class Codes: F02K 1/00 Plants characterised by the form or arrangement of the jet pipe or nozzle; Jet pipes or nozzles peculiar thereto rocket nozzles F02K9/97
• CPC Class Codes: G05B 13/041 in which a variable is automatically adjusted to optimise the performance
• CPC Class Codes: G05B 23/0272 Presentation of monitored results, e.g. selection of status reports to be displayed; Filtering information to the user
• CPC Class Codes: G05B 23/0294 Optimizing process, e.g. process efficiency, product quality
• CPC Class Codes: G06F 18/23213 with fixed number of clusters, e.g. K-means clustering
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: Y02P 90/82 Energy audits or management systems therefor

Abstract

A method for obtaining operating parameters of a power plant includes data mining a historical operating condition database for the power plant with a partitional clustering algorithm to generate a statistical model, and calculating dynamic operating condition target values from the statistical model taking into account current operating condition data of the power plant. The method further includes performing a real-time energy-loss analysis based on the dynamic operating condition target values and automatically identifying at least one operating parameter of the power plant from the energy-loss analysis. The partitional clustering algorithm can be a k-means clustering algorithm.

Claims

1. A method for operating of a power plant, comprising:

providing a processor implementing an operating parameter determination algorithm stored in a non-transitory memory accessible by said processor, said algorithm including;

data mining a historical operating condition database for the power plant with a first partitional clustering algorithm to generate a statistical model;

calculating dynamic operating condition target values from the statistical model taking into account current operating condition data of the power plant by performing a second partitional clustering algorithm which comprises a k-means clustering algorithm upon the statistical model and the current operating condition data and sorting said operating condition target values resulting from the k-means clustering algorithm using a bubble sort algorithm;

performing a real-time energy-loss analysis based on the dynamic operating condition target values;

automatically identifying a plurality of operating parameters of the power plant from the energy-loss analysis, and

manipulating a first operating parameter selected from the plurality of operating parameters using an adjustment device in the power plant during operation of the power plant.

2. The method of claim 1, wherein the current operating condition data is provided by sensors in said power plant as real-time data to said processor.

3. The method of claim 2, wherein the power plant comprises a fossil fuel power plant or coal fired power plant.

4. The method of claim 1, wherein the first partitional clustering algorithm comprises a k-means clustering algorithm.

5. The method of claim 1, wherein the step of performing a real-time energy-loss analysis further comprises:

analyzing boiler efficiency based on the dynamic operating condition target values.

6. The method of claim 1, wherein the step of performing a real-time energy-loss analysis further comprises:

using an equivalent enthalpy drop method based on the dynamic operating condition target values.

7. The method of claim 1, wherein the step of performing the real-time energy-loss analysis further comprises:

analyzing a steam turbine heat rate based on the dynamic operating condition target values.

8. The method of claim 1, wherein the plurality of operating parameters include at least one of:

main steam pressure, main steam temperature, reheat steam temperature, exhaust steam pressure, final feed water temperature, exhaust gas temperature, oxygen percentage in exhaust gas, carbon percentage in fly ash, carbon percentage in slag, terminal temperature difference (TTD) of high pressure heaters, TTD of low pressure heaters, subcooling of condensate water, inlet steam flow rate of auxiliary turbine for boiler feedwater pump, and reheat attemperation flow rate.

9. A system for operating a power plant, comprising:

a non-transitory memory for storing historical operating condition data for the power plant and an operating parameter determination algorithm;

a processor coupled to access said operating parameter determination algorithm and for implementing the operating parameter determination algorithm, said algorithm including;

data mining a historical operating condition database for the power plant with a partitional clustering algorithm to generate a statistical model;

calculating dynamic operating condition target values from the statistical model taking into account current operating condition data of the power plant by performing a second partitional clustering algorithm which comprises a k-means clustering algorithm upon the statistical model and the current operating condition data, and sorting said operating condition target values resulting from the k-means clustering algorithm using a bubble sort algorithm;

performing a real-time energy-loss analysis based on the dynamic operating condition target values, and

automatically identifying a plurality of operating parameters of the power plant from the energy-loss analysis, and

adjustment devices coupled within the power plant for adjusting respective ones of the plurality of operating parameters.

10. The system of claim 9, further comprising:

an interface for displaying the at least one operating parameter of the power plant.

11. The system of claim 9, further comprising:

one or more sensors communicably coupled with the power plant, wherein said one or more sensors garner and transmit the current operating condition data as real-time data to said processor.

12. The system of claim 11, wherein the processor is further configured for receiving data associated with the power plant from the one or more sensors and calculating the current operating condition data of the power plant based on the data that was received.

13. The system of claim 9, wherein the processor is further configured for sending commands to the adjustment devices to adjust the plurality of operating parameters.