Estimated parameter based control of a process for controlling emission of a pollutant into the air

• US 20060047366A1
• Filed: 12/07/2004
• Published: 03/02/2006
• Est. Priority Date: 08/27/2004
• Status: Active Grant

• Current Assignee: General Electric Technology GmbH (GE Vernova, Inc.)
• Original Assignee: Alstom Technology Ltd. (Alstom SA)
• Inventors: Piche, Stephen, Boyden, Scott A.
• Granted Patent: US 7,640,067 B2
• Time in Patent Office: Days
• US Class Current: 700/266
• CPC Class Codes: B01D 2257/302 Sulfur oxides
• CPC Class Codes: B01D 2257/404 Nitrogen oxides other than dinitrogen oxide
• CPC Class Codes: G05B 13/027 using neural networks only
• CPC Class Codes: G05B 13/048 using a predictor
• CPC Class Codes: Y10T 436/12 Condition responsive control

Abstract

A controller directs a process primarily performed to control emission of a particular pollutant into the air. The process has multiple process parameters (MPPs), including a parameter representing an amount of the particular pollutant. The controller includes either a neural network process model or a non-neural network process model. In either case, the model represents a relationship between a first of the MPPs and one or more of the other MPPs. The one or more other MPPs include a second of the MPPs which is other than the parameter representing the amount of the emitted particular pollutant. Also included is a processor configured with logic to estimate a value of the second MPP, and to direct control of the first MPP based on the estimated value of the second MPP and the model.

Claims

1. A controller for directing a process primarily performed to control emission of a particular pollutant into the air, the process having multiple process parameters (MPPs) including a parameter representing an amount of the particular pollutant, comprising:

one of a neural network process model and a non-neural network process model, the one model representing a relationship between a first of the MPPs and one or more of the other MPPs, the one or more other MPPs including a second of the MPPs which is other than the parameter representing the amount of the emitted particular pollutant; and

a processor configured with logic to estimate a value of the second MPP, and to direct control of the first MPP based on the estimated value of the second MPP and the one model.

2. The controller according to claim 1, wherein:

the particular pollutant is one of NO_x and SO₂.

3. The controller according to claim 1, wherein:

the one or more other MPPs also includes a third of the MPPs.

the value of the third MPP is either (i) a value measured during the performance of the process or (ii) a value estimated based on one or more other values of the MPPs measured during the performance of the process.

4. The controller according to claim 1, wherein:

directing control of the first MPP includes directing the first MPP to be set at a first value;

the estimated value of the second MPP is an estimated first value of the second MPP; and

the processor is further configured with logic to estimate a second value of the second MPP, and to further direct control of the first MPP by directing the first MPP to be set at a second value based on the estimated first and the estimated second values of the second MPP, the first value of the first MPP, and the one model.

5. The controller according to claim 1, wherein the second MPP is either:

a pH level of matter applied in the process to absorb the particular pollutant and thereby control its emission into the air;

a purity of a by-product produced in performing the process;

an amount of oxygen dissolved in matter applied in the process to absorb the particular pollutant and thereby control its emission into the air;

an amount of ammonia applied in the process to absorb the particular pollutant that is emitted into the air with the particular pollutant that is not absorbed;

or

an amount of applied ammonia in exhausted reduced NOx flue gas, the particular pollutant being NO_x, and the first MPP is an amount of the applied ammonia.

6. The controller according to claim 1, wherein:

the processor controls the first MPP by predicting, based on the one model, how a change in value of the first MPP will change the estimated value of the second MPP, and by directing control of the first MPP based on the predicted change in the estimated value of the second MPP.

7. The controller according to claim 1, wherein:

the processor is further configured with logic to update the one model based on the estimated value of the second MPP.

8. The controller according to claim 7, wherein:

the updating of the one model includes updating the represented relationship between the first MPP and the second MPP, based on the estimated value of the second MPP.

9. The controller according to claim 1, wherein:

the process is a selective catalytic reduction (SCR) process that applies ammonia to remove NO_x from the NO_x laden flue gas and thereby control emissions of NO_x, and exhausts reduced NO_x flue gas; and

the second MPP is an amount of the applied ammonia in the exhausted reduced NO_x flue gas and the first MPP is an amount of the applied ammonia.

10. The controller according to claim 1, wherein:

the process is a wet flue gas desulfurization (WFGD) process that distributes limestone slurry, applies the distributed limestone slurry to remove SO₂ from SO₂ laden wet flue gas and thereby control emissions of SO₂, and exhausts desulfurized flue gas;

the second MPP is a pH level of the applied limestone slurry; and

the first MPP is one of an amount of SO₂ in the SO₂ laden wet flue gas, an amount of SO₂ in the exhausted desulfurized flue gas, and the distribution of the applied limestone slurry.

11. The controller according to claim 1, wherein:

the process is a wet flue gas desulfurization (WFGD) process that (i) applies oxidation air to limestone slurry, (ii) distributes the oxidized limestone slurry, (iii) applies the distributed limestone slurry to remove and crystallize SO₂ from SO₂ laden wet flue gas and thereby control emissions of SO₂ and produce gypsum as a by-product, and (iv) exhausts desulfurized flue gas;

the second MPP is either a quality of the produced gypsum or an amount of dissolved oxygen in the oxidized limestone slurry; and

the first MPP is one of a pH level of the applied limestone slurry, a distribution of the applied limestone slurry and an amount of the applied oxidation air.

12. A method for controlling a process primarily performed to control emission of a particular pollutant into the air, the process having multiple process parameters (MPPs) including a parameter representing an amount of the particular pollutant, comprising:

estimating a value of a first of the MPPs which is other than the parameter representing the amount of the emitted particular pollutant; and

directing control of a second of the MPPs based on (i) the estimated value of the first MPP and (ii) one of a neural network process model and a non-neural network process model;

wherein the one model represents a relationship between the second MPP and one or more of the other MPPs including the first MPP.

13. The method according to claim 12, wherein:

the one or more other MPPs also includes a third of the MPPs.

the value of the third MPP is either (i) a value measured during the performance of the process or (ii) a value estimated based on one or more other values of the MPPs measured during the performance of the process.

14. The method according to claim 12, wherein the estimated value of the first MPP is an estimated first value of the first MPP, and the directing of control of the second MPP includes directing the second MPP to be set at a first value, and further comprising:

estimating a second value of the first MPP; and

directing control of the second MPP by directing the second MPP to be set at a second value based on the estimated first and the estimated second values of the first MPP, the first value of the second MPP, and the one model.

15. The method according to claim 12, wherein the first MPP is either:

a pH level of matter applied in the process to absorb the particular pollutant and thereby control its emission into the air;

a purity of a by-product produced in performing the process;

an amount of oxygen dissolved in matter applied in the process to absorb the particular pollutant and thereby control its emission into the air;

an amount of ammonia applied in the process to absorb the particular pollutant that is emitted into the air with the particular pollutant that is not absorbed;

or

an amount of applied ammonia in exhausted reduced NO_x flue gas, the particular pollutant being NO_x, and the first MPP is an amount of the applied ammonia.

16. The method according to claim 12, wherein:

directing control of the second MPP includes predicting, based on the one model, how a change in value of the second MPP will change the estimated value of the first MPP, and directing control of the second MPP based on the predicted change in the estimated value of the first MPP.

17. The method according to claim 12, further comprising:

updating the one model based on the estimated value of the first MPP.

18. The method according to claim 17, wherein:

the updating of the one model includes updating the represented relationship between the second MPP and the first MPP, based on the estimated value of the first MPP.

19. The method according to claim 12, wherein:

the process is a selective catalytic reduction (SCR) process that applies ammonia to remove NO_x from the NO_x laden flue gas and thereby control emissions of NO_x, and exhausts reduced NO_x flue gas; and

the first MPP is an amount of the applied ammonia in the exhausted reduced NO_x flue gas and the second MPP is an amount of the applied ammonia.

20. The method according to claim 12, wherein:

the process is a wet flue gas desulfurization (WFGD) process that distributes limestone slurry, applies the distributed limestone slurry to remove SO₂ from SO₂ laden wet flue gas and thereby control emissions of SO₂, and exhausts desulfurized flue gas;

the first MPP is a pH level of the applied limestone slurry; and

the second MPP is one of an amount of SO₂ in the SO₂ laden wet flue gas, an amount of SO₂ in the exhausted desulfurized flue gas, and the distribution of the applied limestone slurry.

21. The method according to claim 12, wherein:

the process is a wet flue gas desulfurization (WFGD) process that (i) applies oxidation air to limestone slurry, (ii) distributes the oxidized limestone slurry, (iii) applies the distributed limestone slurry to remove and crystallize SO₂ from SO₂ laden wet flue gas and thereby control emissions of SO₂ and produce gypsum as a by-product, and (iv) exhausts desulfurized flue gas;

the first MPP is either a quality of the produced gypsum or an amount of dissolved oxygen in the oxidized limestone slurry; and

the second MPP is one of a pH level of the applied limestone slurry, a distribution of the applied limestone slurry and an amount of the applied oxidation air.