PLANT CONTROL SYSTEMS AND METHODS

• US 20140257526A1
• Filed: 03/07/2013
• Published: 09/11/2014
• Est. Priority Date: 03/07/2013
• Status: Active Grant

• Current Assignee: GE Infrastructure Technology, LLC (GE Vernova, Inc.)
• Original Assignee: General Electric Company
• Inventors: Tiwari, Awadesh Kumar, Asati, Mahesh Kumar, Smith, Raub Warfield, Pandey, Achalesh Kumar
• Granted Patent: US 9,477,214 B2
• Time in Patent Office: Days
• US Class Current: 700/29
• CPC Class Codes: F01K 13/02 Controlling, e.g. stopping or starting
• CPC Class Codes: F01K 23/067 the combustion heat coming from a gasification or pyrolysis process, e.g. coal gasification gas turbines with fuel gasifiers F02C3/28
• CPC Class Codes: F01K 23/068 in combination with an oxygen producing plant, e.g. an air separation plant
• CPC Class Codes: F01K 23/101 Regulating means specially adapted therefor F01K23/105, F01K23/108 take precedence
• CPC Class Codes: G05B 13/02 electric
• CPC Class Codes: Y02E 20/16 Combined cycle power plant [CCPP], or combined cycle gas turbine [CCGT]
• CPC Class Codes: Y02E 20/18 Integrated gasification combined cycle [IGCC], e.g. combined with carbon capture and storage [CCS]

Abstract

Systems and methods provided herein. In one embodiment, a system includes an advisory system including a loss computation engine configured to derive a total system loss for an industrial plant based on a first sensor positioned in a first industrial plant component and on a first physical model of the first industrial plant component. The advisory system further includes a cost model configured to use a cost function to derive a cost based on the total system loss, and a control strategy system configured to derive an advisory report, a control correction factor, or a combination thereof, based on the cost, wherein a control system is configured to apply the control correction factor to control a process in the industrial plant.

Claims

1. A system comprising:

an advisory system comprising;

a loss computation engine configured to derive a total system loss for an industrial plant based on a first sensor positioned in a first industrial plant component and on a first physical model of the first industrial plant component;

a cost model configured to use a cost function to derive a cost based on the total system loss; and

a control strategy system configured to derive an advisory report, a control correction factor, or a combination thereof, based on the cost, wherein a control system is configured to apply the control correction factor to control a process in the industrial plant.

2. The system of claim 1, wherein the total system loss comprises a loss due to age, degradation, an unplanned event, a planned event, an unplanned maintenance, a planned maintenance, or a combination thereof.

3. The system of claim 2, wherein the degradation comprises a comparison between a sensor reading and an International Organization for Standardization (ISO) rated value.

4. The system of claim 1, wherein the first sensor comprises a temperature sensor, a flow rate sensor, a pressure sensor, a fuel utilization sensor, a chemical analysis sensor, a speed sensor, a clearance sensor, or a combination thereof.

5. The system of claim 1, comprising an estimator system configured to derive an estimated measure for a flow, a pressure, a speed, a clearance, or a combination thereof, based on a second sensor positioned in a second industrial plant component, and wherein the loss computation engine is configured to derive the total system loss based on the first sensor and on the estimated measure.

6. The system of claim 1, wherein the first industrial plant component comprises a heat recovery steam generation (HRSG) system, a gas turbine, a steam turbine, a condenser, a gasifier, a syngas cleaning system, a carbon capture system, a valve, a pump, a compressor, a cooler or a combination thereof.

7. The system of claim 1, wherein the cost function comprises at least one objective function comprising a cost of producing power for the industrial plant.

8. The system of claim 1, wherein the control system comprises a controller having a linear programming (LP) solver, a second order cone programming (SOCP) solver, a semi-definite programming (SDP) solver, a conic programming solver, a non-linear programming solver, a constraint satisfaction solver, a heuristic solver, or a combination thereof, suitable for solving the cost function.

9. The system of claim 1, wherein the advisory system comprises a k-nearest neighbor (k-NN) system, an expert system, a neural network, a genetic algorithm (GA), a state vector machine, or a combination thereof.

10. The system of claim 1, wherein the industrial plant comprises a turbine system having a first combustor stage, and wherein the control strategy system is configured to choose an operating point at part load of the turbine system that is derived to consume less turbine life based on a first combustor stage temperature, rate of degradation of components of the turbine system, or a combination thereof.

11. A method, comprising:

creating a first component loss model configured to derive a first loss for a first component of an industrial plant;

creating a second component loss model configured to derive a second loss for a second component of an industrial plant;

combining the first and second loss models into a total loss model configured to model a total loss;

receiving a first data related to operations of the first component, and a second data related to operations of the second component; and

computing the total loss using the first and second data as inputs to the total loss model.

12. The method of claim 11, comprising:

building a first cost model configured to derive a first cost for operations of the first component by using the first loss;

building a second cost model configured to derive a second cost for operations of the second component by using the second loss;

combining the first and second cost models into a total cost model configured to derive a total cost based on a commercial input; and

deriving the total cost.

13. The method of claim 11, wherein the total cost model comprises at least one objective function comprising a cost of producing power for the industrial plant.

14. The method of claim 13, comprising applying a mathematical optimization to the objective cost function to derive the total cost.

15. The method of claim 13, comprising using a linear programming (LP) solver, a second order cone programming (SOCP) solver, a semi-definite programming (SDP) solver, a conic programming solver, a non-linear programming solver, a constraint satisfaction solver, a heuristic solver, or a combination thereof, to solve the objective function.

16. A system comprising:

a memory comprising non-transitory, computer-readable medium comprising code configured to;

create a first component loss model configured to derive a first loss for a first component of an industrial plant;

create a second component loss model configured to derive a second loss for a second component of an industrial plant;

combine the first and second loss models into a total loss model configured to model a total loss;

receive a first data related to operations of the first component, and a second data related to operations of the second component; and

compute the total loss using the first and second data as inputs to the total loss model.

17. The system of claim 16, wherein the cod comprises code configured to:

build a first cost model configured to derive a first cost for operations of the first component by using the first loss;

build a second cost model configured to derive a second cost for operations of the second component by using the second loss;

combine the first and second cost models into a total cost model configured to derive a total cost based on a commercial input; and

derive the total cost.

18. The system of claim 16, wherein the total cost model comprises at least one objective function comprising a cost of producing power for the industrial plant.

19. The system of claim 18, wherein the code comprises code configured to apply a mathematical optimization to the objective cost function to derive the total cost

20. The system of claim 18, wherein the code comprises code configured to use a linear programming (LP) solver, a second order cone programming (SOCP) solver, a semi-definite programming (SDP) solver, a conic programming solver, a non-linear programming solver, a constraint satisfaction solver, a heuristic solver, or a combination thereof, to solve the objective function.