APC PROCESS PARAMETER ESTIMATION

• US 20110104015A1
• Filed: 11/02/2010
• Published: 05/05/2011
• Est. Priority Date: 08/27/2004
• Status: Active Grant

• Current Assignee: General Electric Technology GmbH (General Electric Company)
• Original Assignee: Alstom Technology Ltd. (Alstom SA)
• Inventors: BOYDEN, Scott A., Piche, Stephen
• Granted Patent: US 8,197,753 B2
• Time in Patent Office: Days
• US Class Current: 422/168
• 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 virtual analyzer is provided to estimate either an attribute of a reactant applied during performance of, or an amount of a reactant exhausted by, a process having multiple process parameters (MPPs) that is performed to control an amount of a pollutant emitted into the air. The virtual analyzer includes an interface which receives signals corresponding to attributes of the MPPs. If the process is a wet flue gas desulfurization (WFGD) process, the signals include a signal corresponding to a measured pH level of the applied reactant. If the process is a selective catalytic reduction (SCR) process, the signals include a signal corresponding to a measured amount of the reactant exhausted by the process.

Claims

1. A virtual analyzer for estimating either an attribute of a reactant applied during performance of, or an amount of a reactant exhausted by, a process having multiple process parameters (MPPs) that is performed to control an amount of a pollutant emitted into the air, comprising:

an interface configured to receive signals corresponding to attributes of the MPPs, including (i) if the process is a wet flue gas desulfurization (WFGD) process, a signal corresponding to a measured current pH level of the applied reactant, and (ii) if the process is a selective catalytic reduction (SCR) process, a signal corresponding to a measured current amount of the reactant exhausted by the process;

one of a neural network process model and a non-neural network process model, the one model representing a relationship between either (i) if the process is a WFGD process, the current pH level of the applied reactant and the attributes of the MPPs other than the measured current pH level of the applied reactant or (ii) if the process is the SCR process, the current amount of the reactant exhausted by the process and the attributes of the MPPs other than the measured current amount of the reactant exhausted by the process; and

a processor configured with logic (i) if the process is the WFGD process, to estimate a current pH level of the applied reactant based on the attributes of the MPPs, other than the measured current pH level of the applied reactant, that correspond to the received signals and on the one model, and (ii) if the process is the SCR process, to estimate a current amount of the reactant exhausted by the process based on the attributes of the MPPs, other than the measured current amount of the reactant exhausted by the process, that correspond to the received signals and on the one model.

2. The virtual analyzer according to claim 1, wherein the processor is a first processor and further comprising:

a second processor configured with logic, (i) if the process is the WFGD process, to compare the estimated pH level of the applied reactant with the measured pH level of the applied reactant corresponding to the received signal, and to determine the validity of the measured pH level based on the comparison, and (ii) if the process is the SCR process, to compare the estimated amount of reactant exhausted by the process with the measured amount of reactant exhausted by the process corresponding to the received signal, and to determine the validity of the measured amount based on the comparison.

3. The virtual analyzer according to claim 2, wherein:

the first processor estimates the pH level of the applied reactant or the amount of the reactant exhausted by the process, in real time during performance of the process; and

the second processor compares the estimated pH level with the measured pH level of the applied reactant and determines the validity of the measured pH level, or compares the estimated amount with the measured amount of reactant exhausted by the process and determines the validity of the measured amount, in real time during performance of the process.

4. The virtual analyzer according to claim 1, wherein:

the attributes of the MPPs corresponding to the received signals include one or more of (i) an attribute of one of the MPPs measured during performance of the process and (ii) an attribute of one of the MPPs computed based on attributes of other of the MPPs measured during performance of the process.

5. The virtual analyzer according to claim 1, wherein:

the processor estimates the pH level of the applied reactant or the amount of the reactant exhausted by the process, in real time during performance of the process.

6. The virtual analyzer according to claim 1, wherein:

the reactant is a limestone slurry;

the process is a WFGD process which applies the limestone slurry to remove SO₂ from SO₂ laden wet flue gas, and exhausts desulfurized flue gas;

the attributes of the MPPs include an amount of SO₂ in the SO₂ laden flue gas and an amount of SO₂ in the exhausted desulfurized flue gas;

the one model represents a relationship between the pH level of the applied limestone slurry and the amount of SO₂ in the SO₂ laden flue gas and the amount of SO₂ in the exhausted desulfurized flue gas; and

the processor estimates the pH level of the applied limestone slurry based on the amount of SO₂ in the SO₂ laden flue gas and the amount of SO₂ in the exhausted desulfurized flue gas that correspond to the received signals, and on the one model.

7. The virtual analyzer according to claim 1, wherein:

the reactant is ammonia;

the process is a SCR process which applies ammonia to remove NO_x from NO_x laden flue gas and exhausts reduced NO_x flue gas;

the attributes of the MPPs include an amount of NO_x in the NO_x laden flue gas and an amount of NO_x in the exhausted desulfurized flue gas;

the one model represents a relationship between the amount of the ammonia in the exhausted reduced NO_x flue gas and the amount of NO_x in the NO_x laden flue gas and the amount of NO_x in the exhausted reduced NO_x flue gas; and

the processor estimates the amount of the ammonia in the exhausted reduced NO_x flue gas based on the amount of NO_x in the NO_x laden flue gas and the amount of NO_x in the exhausted reduced NO_x flue gas that correspond to the received signals, and on the one model.

19. The virtual analyzer according to claim 1, wherein:

the one network process model is a dynamic neural or non-neural network process model which represents a relationship over time between the pH level of the reactant and the applicable other attributes.

8-14. -14. (canceled)

15. A wet flue gas desulfurizing system, comprising:

a wet flue gas desulfurizer configured (i) to receive SO₂ laden wet flue gas, (ii) to apply limestone slurry to remove SO₂ from the received SO₂ laden wet flue gas, and (iii) to exhaust desulfurized flue gas;

a pH sensor to measure a pH level of the applied limestone slurry;

one of a neural network process model and a non-neural network process model, the one model representing a relationship between the pH level of the applied limestone slurry and an amount of SO₂ in the received SO₂ laden wet flue gas and an amount of SO₂ in the exhausted desulfurized flue gas;

a virtual analyzer having the logic to estimate the pH level of the applied limestone slurry based on an actual amount of SO₂ in the received SO₂ laden wet flue gas, an actual amount of SO₂ in the exhausted desulfurized flue gas and the one model; and

a processor having the logic to compare the estimated pH level of the applied limestone slurry with the measured pH level of the applied limestone slurry, and to determine the validity of the measured pH level of the applied limestone slurry based on the comparison.

16. The system of claim 15, wherein the sensor is a first sensor, and further comprising:

a second sensor to measure the actual amount of SO₂ in the received SO₂ laden wet flue gas values; and

a third sensor configured to measure the actual amount of SO₂ in the exhausted desulfurized flue gas; and

a feed back loop configured to transmit the measured pH level of the applied limestone slurry, the measured amount of SO₂ in the received SO₂ laden wet flue gas, and the measured amount of SO₂ in the exhausted desulfurized flue gas, to the virtual analyzer in real time;

wherein the virtual analyzer estimates the pH level of the applied limestone slurry based on the transmitted measured amounts of SO₂ in the received SO₂ laden wet flue gas and in the exhausted desulfurized flue gas in real time.

17. A selective catalytic reduction system, comprising:

selective catalytic reducter configured (i) to receive NO_x laden flue gas, (ii) to apply ammonia to remove NO_x from the received NO_x laden flue gas, and (iii) to exhaust reduced NO_x flue gas;

a ammonia sensor to measure an amount of ammonia in the exhausted reduced NO_x flue gas;

one of a neural network process model and a non-neural network process model, the one model representing a relationship between the amount of the ammonia in the exhausted reduced NO_x flue gas and an actual amount of NO_x in the received NO_x laden flue gas and an actual amount of NO_x in the exhausted reduced NO_x flue gas;

a virtual analyzer having the logic to estimate the amount of ammonia in the exhausted reduced NO_x flue gas based on the actual amount of NO_x in the received NO_x laden flue gas and the actual amount of NO_x in the exhausted reduced NO_x flue gas, and on the one model; and

a processor having the logic to compare the estimated amount of ammonia in the exhausted reduced NO_x flue gas with the measured amount of ammonia in the exhausted reduced NO_x flue gas, and to determine the validity of the measured amount of ammonia in the exhausted reduced NO_x flue gas based on the comparison.

18. The system of claim 17, wherein the sensor is a first sensor, and further comprising:

a second sensor to measure the actual amount of NO_x in the received NO_x laden flue gas; and

a third sensor configured to measure the actual amount of NO_x in the exhausted reduced NO_x flue gas; and

a feed back loop configured to transmit the measured amount of NO_x in the received NO_x laden flue gas, and the measured amount of NO_x in the exhausted reduced NO_x flue gas, to the virtual analyzer in real time;

wherein the virtual analyzer estimates the amount of ammonia in the exhausted reduced NO_x flue gas based on the transmitted measured amounts of NO_x in the received NO_x laden flue gas and in the exhausted reduced NO_x flue gas in real time.