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 in
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.
대표청구항▼
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 conf
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; anda 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 current pH level of the applied reactant with the measured current pH level of the applied reactant corresponding to the received signal, and to determine the validity of the measured current pH level based on the comparison, and (ii) if the process is the SCR process, to compare the estimated current amount of reactant exhausted by the process with the measured current amount of reactant exhausted by the process corresponding to the received signal, and to determine the validity of the measured current amount based on the comparison. 3. 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;a first 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; anda second processor configured with logic, (i) if the process is the WFGD process, to compare the estimated current pH level of the applied reactant with the measured current pH level of the applied reactant corresponding to the received signal, and to determine the validity of the measured current pH level based on the comparison, and (ii) if the process is the SCR process, to compare the estimated current amount of reactant exhausted by the process with the measured current amount of reactant exhausted by the process corresponding to the received signal, and to determine the validity of the measured current amount based on the comparison;wherein the first processor estimates the current pH level of the applied reactant or the current amount of the reactant exhausted by the process, in real time during performance of the process; andwherein the second processor compares the estimated current pH level with the measured current pH level of the applied reactant and determines the validity of the measured current pH level, or compares the estimated current amount with the measured current amount of reactant exhausted by the process and determines the validity of the measured current 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. 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; anda 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;wherein the processor estimates the current pH level of the applied reactant or the current amount of the reactant exhausted by the process, in real time during performance of the process. 6. A virtual analyzer for estimating an attribute of a reactant applied during performance of 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 a signal corresponding to a measured current pH level of the applied reactant;one of a neural network process model and a non-neural network process model, the one model representing a relationship between 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; anda processor configured with logic 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;wherein the reactant is a limestone slurry;wherein the process is a wet flue gas desulfurization (WFGD) process which applies the limestone slurry to remove SO2 from SO2 laden wet flue gas, and exhausts desulfurized flue gas;wherein 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;wherein 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; andwherein the processor estimates the current 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. A virtual analyzer for estimating 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 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 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; anda processor configured with logic 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;wherein the reactant is ammonia;wherein the process is a selective catalytic reduction (SCR) process which applies ammonia to remove NOx from NOx laden flue gas and exhausts reduced NOx flue gas;wherein the attributes of the MPPs include an amount of NOx in the NOx laden flue gas and an amount of NOx in the exhausted desulfurized flue gas;wherein the one model represents a relationship between the amount of the ammonia in the exhausted reduced NOx flue gas and the amount of NOx in the NOx laden flue gas and the amount of NOx in the exhausted reduced NOx flue gas; andwherein the processor estimates the current amount of the ammonia in the exhausted reduced NOx flue gas based on the amount of NOx in the NOx laden flue gas and the amount of NOx in the exhausted reduced NOx flue gas that correspond to the received signals, and on the one model. 8. A virtual analyzer for estimating an attribute of a reactant applied during performance of 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 a signal corresponding to a measured current pH level of the applied reactant;one of a neural network process model and a non-neural network process model, the one model representing a relationship between 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; anda processor configured with logic 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;wherein the one network process model is a dynamic neural or non-neural network process model which represents a relationship over time between the current pH level of the reactant and the applicable other attributes. 9. 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 current 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 current 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 current 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; anda processor having the logic to compare the estimated current pH level of the applied limestone slurry with the measured current pH level of the applied limestone slurry, and to determine the validity of the measured current pH level of the applied limestone slurry based on the comparison. 10. The system of claim 9, 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; anda third sensor configured to measure the actual amount of SO2 in the exhausted desulfurized flue gas; anda feed-back loop configured to transmit the measured current 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 current 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. 11. A selective catalytic reduction system, comprising: selective catalytic reducter configured (i) to receive NOx laden flue gas, (ii) to apply ammonia to remove NOx from the received NOx laden flue gas, and (iii) to exhaust reduced NOx flue gas;an ammonia sensor to measure an current amount of ammonia in the exhausted reduced NOx flue gas;one of a neural network process model and a non-neural network process model, the one model representing a relationship between the current amount of the ammonia in the exhausted reduced NOx flue gas and an actual amount of NOx in the received NOx laden flue gas and an actual amount of NOx in the exhausted reduced NOx flue gas;a virtual analyzer having the logic to estimate the current amount of ammonia in the exhausted reduced NOx flue gas based on the actual amount of NOx in the received NOx laden flue gas and the actual amount of NOx in the exhausted reduced NOx flue gas, and on the one model; and a processor having the logic to compare the estimated current amount of ammonia in the exhausted reduced NOx flue gas with the measured current amount of ammonia in the exhausted reduced NOx flue gas, and to determine the validity of the measured current amount of ammonia in the exhausted reduced NOx flue gas based on the comparison. 12. The system of claim 11, wherein the sensor is a first sensor, and further comprising: a second sensor to measure the actual amount of NOx in the received NOx laden flue gas;a third sensor configured to measure the actual amount of NOx in the exhausted reduced NOx flue gas; anda feed-back loop configured to transmit the measured current amount of NOx in the received NOx laden flue gas, and the measured amount of NOx in the exhausted reduced NOx flue gas, to the virtual analyzer in real time;wherein the virtual analyzer estimates the current amount of ammonia in the exhausted reduced NOx flue gas based on the transmitted measured amounts of NOx in the received NOx laden flue gas and in the exhausted reduced NOx flue gas in real time.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (33)
Keeler James D. ; Hartman Eric J. ; Godbole Devendra B. ; Piche Steve ; Arbila Laura ; Ellinger Joshua ; Ferguson ; II R. Bruce ; Krauskop John ; Kempf Jill L. ; O'Hara Steven A. ; Strauss Audrey ; T, Automated method for building a model.
Gregory D. Martin ; Eugene Boe ; Stephen Piche ; James David Keller ; Douglas Timmer ; Mark Gerules ; John P. Havener, Method and apparatus for controlling a non-linear mill.
Martin Gregory D. ; Boe Eugene ; Piche Stephen ; Keeler James David ; Timmer Douglas ; Gerules Mark ; Havener John P., Method and apparatus for dynamic and steady state modeling over a desired path between two end points.
Keeler James D. ; Hartman Eric J. ; O'Hara Steven A. ; Kempf Jill L. ; Godbole Devendra B., Method and apparatus for preprocessing input data to a neural network.
Piche Stephen ; Keeler James David ; Hartman Eric ; Johnson William D. ; Gerules Mark ; Liano Kadir, Method for steady-state identification based upon identified dynamics.
Hirata, Hajime; Uehara, Masatsugu; Nakai, Yasuhiro; Terao, Jiro, Method of manufacturing sheet, device and program for controlling sheet thickness, and sheet.
Hsiung,Chang Meng B.; Munoz,Bethsabeth; Roy,Ajoy Kumar; Steinthal,Michael Gregory; Sunshine,Steven A.; Vicic,Michael Allen; Zhang,Shou Hua, Monitoring system for an industrial process using one or more multidimensional variables.
Keeler James D. ; Hartman Eric J. ; O'Hara Steven A. ; Kempf Jill L. ; Godbole Devendra B., Predictive network with graphically determined preprocess transforms.
Keeler James D. (Austin TX) Hartman Eric J. (Austin TX) O\Hara Steven A. (Round Rock TX) Kempf Jill L. (Austin TX) Godbole Devandra B. (Austin TX), Predictive network with learned preprocessing parameters.
Shimizu Taku,JPX ; Iwashita Koichiro,JPX ; Endo Yoshikazu,JPX ; Onizuka Masakazu,JPX ; Takashina Toru,JPX, Slurry thickening tank and absorption tower for use in wet flue gas desulfurization systems.
Hsiung, Chang-Meng B.; Munoz, Bethsabeth; Roy, Ajoy Kumar; Steinthal, Michael Gregory; Sunshine, Steven A.; Vicic, Michael Allen; Zhang, Shou-Hua, System for providing control to an industrial process using one or more multidimensional variables.
Keeler James D. (Austin TX) Havener John P. (Austin TX) Godbole Devendra (Austin TX) Ferguson Ralph B. (Austin TX), Virtual continuous emission monitoring system.
Keeler James D. (Austin TX) Havener John P. (Austin TX) Godbole Devendra (Austin TX) Ferguson Ralph B. (Austin TX), Virtual continuous emission monitoring system with sensor validation.
Klingspor Jonas S. (Birmingham AL) Bakke Even (Stamford CT) Bresowar Gerald E. (Homewood AL), Wet scrubbing method and apparatus for removing sulfur oxides from combustion effluents.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.