A method for predicting emissions from an emissions source. Test values of process variables relating to operation of the emissions source are gathered, along with corresponding time-correlated test values of the emissions variable to be predicted. Using the test values of the process variables, te
A method for predicting emissions from an emissions source. Test values of process variables relating to operation of the emissions source are gathered, along with corresponding time-correlated test values of the emissions variable to be predicted. Using the test values of the process variables, test values of a plurality of first coefficients are calculated for each process variable and associated with the process variable, and test values of a plurality of second coefficients are calculated for each value of each process variable and associated with the value of the process variable. Comparison values of the process variables relating to operation of the emissions source are gathered, along with corresponding time-correlated comparison values of the emissions variable to be predicted. Using the comparison values of the process variables, comparison values of a plurality of first coefficients are calculated for each process variable and associated with the process variable, and comparison values of a plurality of second coefficients are calculated for each value of each process variable and associated with the value of the process variable. Predetermined combinations of the comparison values of the variables and their associated coefficients are then iteratively compared with the test values of the respective variables and associated coefficients. Where the comparison yields matches between the comparison values and test values of the variables and their associated coefficients, the test values of the emissions variable associated with the matched test values of the variables are averaged and assigned as a predicted value of the emissions variable.
대표청구항▼
What is claimed is: 1. A method for predicting a power plant emission value of a first variable based on values of a plurality of additional variables, comprising the steps of: acquiring a plurality of test values of the first variable, each test value of the plurality of first variable test values
What is claimed is: 1. A method for predicting a power plant emission value of a first variable based on values of a plurality of additional variables, comprising the steps of: acquiring a plurality of test values of the first variable, each test value of the plurality of first variable test values being measured at a corresponding point in time; for each additional variable of the plurality of additional variables, acquiring a plurality of test values of the additional variable, each value of the plurality of additional variable values being associated with a value of the plurality of first variable values, each test value of the plurality of additional variable test values being measured at a point in time substantially simultaneous with a point in time at which one of the test values of the plurality of first variable test values is measured; for each first coefficient of a plurality of first coefficients, providing a separate test value of the first coefficient associated with each additional variable of the plurality of variables, each separate test value of the first coefficient being a function of at least a portion of the test values of the plurality of test values of the associated additional variable; for each second coefficient of a plurality of second coefficients, providing a separate test value of the second coefficient associated with each test value of each additional variable of the plurality of variables, each separate test value of the second coefficient being a function of at least a portion of the test values of the plurality of test values of the associated additional variable; for each selected one of a plurality of selected ones of the additional variables of the plurality of additional variables, acquiring a plurality of comparison values of the additional variable; for each first coefficient of the plurality of first coefficients, providing a separate comparison value of the first coefficient associated with the additional variable, each separate comparison value of the first coefficient being a function of at least a portion of the comparison values of the plurality of comparison values of the associated additional variable; for each second coefficient of the plurality of second coefficients, providing a separate comparison value of the second coefficient associated with the comparison value of each additional variable, each separate comparison value of the second coefficient being a function of at least a portion of the comparison values of the plurality of comparison values of the associated additional variable; for each additional variable in each predetermined combination of a plurality of predetermined combinations of the selected ones of the additional variables, iteratively comparing: each comparison value of the additional variable with each test value of the additional variable; and the comparison values of selected ones of the second coefficients associated with the comparison value of the variable with the test values of the selected ones of the second coefficients associated with the test value of the variable; for each additional variable in each predetermined combination of a plurality of predetermined combinations of the selected ones of the additional variables, identifying all test values of the additional variable where the test value differs from a comparison value of the additional variable by an amount equal to or less than an associated predetermined amount, and where, for each of the selected ones of the second coefficients associated with each test value of the additional variable, all test values of the selected ones of the second coefficients differ from the comparison values of the selected ones of the second coefficients by an amount equal to or less than an associated predetermined amount; and assigning, as the predicted value of the first variable, an average of all of the test values of the first variable that are associated with respective test values of each additional variable for which the test first variable values differ from the comparison additional variable values by the associated predetermined amount. 2. The method of claim 1 wherein the first variable describes a characteristic of a product of a process and each variable of the plurality of additional variables describes a parameter of the process. 3. The method of claim 1 wherein the first variable describes a parameter of a process, at least one of the variables of the plurality of additional variables describes a characteristic of a product of the process, and the remaining ones of the variables of the plurality of additional variables describe a parameter of the process. 4. The method of claim 1 wherein a coefficient of the plurality of first coefficients comprises a correlation factor providing a quantitative indication of a correlation between the first variable and the additional variable associated with the first coefficient. 5. The method of claim 4 wherein each additional variable of each predetermined combination of the plurality of predetermined combinations of ones of the additional variables has a correlation with the first variable indicated by a correlation factor that exceeds a predetermined threshold value. 6. The method of claim 5 wherein the predetermined threshold value of the correlation factor is equal to about 0.50. 7. The method of claim 1 wherein a coefficient of the plurality of first coefficients comprises an initial tolerance value describing a range of values within which the value of the additional variable resides. 8. The method of claim 7 wherein a coefficient of the plurality of second coefficients comprises a delta value equal to a difference between a first value and a second value of a pair of time-successive values of the plurality of values of the additional variable. 9. The method of claim 8 wherein a coefficient of the plurality of second coefficients comprises an indicator variable indicating a result of a comparison between a predetermined one of the first coefficients and a predetermined one of the second coefficients. 10. The method of claim 9 further comprising the steps of: for each value of the plurality of values of each additional variable of the plurality of additional variables, where a delta value associated with the variable value is greater than a tolerance value associated with the variable, specifying a value of the indicator variable indicating that the delta value associated with the variable value is greater than the tolerance value for the variable; for each value of the plurality of values of each variable of the plurality of additional variables, where a delta value associated with the variable value is less than or equal to a tolerance value associated with the variable, specifying a value of the indicator variable indicating that the delta value for the variable value is less than or equal to the tolerance value for the variable. 11. The method of claim 10 further comprising the steps of: where a delta value associated with the variable value is greater than a tolerance value associated with the variable, for each value of the plurality of values of each additional variable of the plurality of additional variables, specifying a value of the indicator variable equal to a time elapsed between the point in time of measurement of the variable value and a point in time of measurement of a closest time-sequential prior value of the variable. 12. The method of claim 10 further comprising the steps of: for each value of the plurality of values of each additional variable of the plurality of additional variables, where a delta value associated with the variable value is less than or equal to a tolerance value associated with the variable, incrementing a value of the indicator variable associated with a closest time-sequential prior value of the variable value by an amount equal to a time elapsed between the point in time of measurement of the variable value and a point in time of measurement of the closest time-sequential prior variable value. 13. The method of claim 7 wherein each of the additional variables describes a characteristic of a process, and wherein the step of providing a separate test value of a first coefficient associated with each additional variable of the plurality of variables comprises the steps of: for each additional variable of the plurality of additional variables, determining if the test values of the plurality of test values of the additional variable were measured over a period of operation of the process including startup and shutdown of the process; where the test values of the plurality of test values of the additional variable were measured over a period of operation of the process including startup and shutdown of the process, calculating a standard deviation of the test values of the plurality of test values of the additional variable and setting the initial tolerance value associated with the additional variable to one half the standard deviation; where the test values of the plurality of test values of the additional variable were not measured over a period of operation of the process including startup and shutdown of the process, calculating a range of measured values of the additional variable equal to a difference between a maximum measured value of the plurality of test values of the additional variable and a minimum measured value of the plurality of test values of the additional variable, and setting the initial tolerance value associated with the additional variable to 2.5% of the range of measured values of the additional variable. 14. The method of claim 1 wherein a coefficient of the plurality of second coefficients comprises a delta value equal to a difference between a first value and a second value of a pair of time-successive values of the plurality of values of the additional variable. 15. The method of claim 1 wherein a coefficient of the plurality of second coefficients comprises an indicator variable indicating a result of a comparison between a predetermined one of the first coefficients and a predetermined one of the second coefficients. 16. The method of claim 15 wherein the predetermined one of the first coefficients is an initial tolerance value specifying a range of values within which the value of the additional variable resides, and the predetermined one of the second coefficients is a delta value equal to a difference between a first value and a second value of a pair of time-successive values of the plurality of values of the additional variable. 17. The method of claim 1 wherein the first variable describes a characteristic of a product resulting from implementation of a process, and wherein each variable of the plurality of additional variables describes a characteristic of the process which results in the product. 18. The method of claim 1 wherein the first variable describes a first characteristic of a process, and wherein the plurality of additional variables describe additional characteristics of the process and a characteristic of a product resulting from implementation of the process. 19. The method of claim 1 further comprising the step of storing each test value of the plurality of test values of the first variable, each test value of the plurality of test values of each additional variable of the plurality of additional variables, each test value of each first coefficient of the plurality of first coefficients, and each test value of each second coefficient of the plurality of second coefficients in a relational database. 20. The method of claim 19 further comprising the step of storing each comparison value of each additional variable of the plurality of additional variables in a relational database.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (90)
Owens Aaron J. (Newark DE), Apparatus and method for controlling a process using a trained parallel distributed processing network.
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.
Puskorius Gintaras V. (Redford MI) Feldkamp Lee A. (Plymouth MI), Catalyst monitor with direct prediction of hydrocarbon conversion efficiency by dynamic neural networks.
Bhat Naveen V. (2100 S. Gessner ; Apt. 1506 Houston TX 77063) Braden William B. (2229 W. Alabama Houston TX 77098) Heckendoorn Kent E. (2718 Cason Houston TX 77005) Graettinger Timothy J. (221 Bluest, Control system using an adaptive neural network for target and path optimization for a multivariable, nonlinear process.
Juneau, Phillip J.; Baxter, Robert, Device and method for introducing a known dust concentration spike for calibrating particulate matter continuous emission monitoring systems.
Godbole Devendra Bhalchandra ; O'Hara Steven Arthur ; Harding Mary Anne ; Ellinger Joshua Brennan, Method and apparatus for automatically constructing a data flow architecture.
Godbole Devendra Bhalchandra ; O'Hara Steven Arthur ; Harding Mary Anne ; Ellinger Joshua Brennan, Method and apparatus for automatically constructing a data flow architecture.
Keeler James David ; Hartman Eric J. ; Liano Kadir, Method and apparatus for determining the sensitivity of inputs to a neural network on output parameters.
Keeler James David ; Hartman Eric Jon ; Liano Kadir, Method and apparatus for determining the sensitivity of inputs to a neural network on output parameters.
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 David; Hartman, Eric Jon; Ferguson, Ralph Bruce, Method and apparatus for operating a neural network with missing and/or incomplete data.
Keeler James D. (Austin TX) Hartman Eric J. (Austin TX) Ferguson Ralph B. (Austin TX), Method and apparatus for operating neural network with missing and/or incomplete data.
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.
Frerichs Donald K. (Shaker Heights OH) Kaya Azmi (Akron OH) Keyes ; IV Marion A. (Chagrin Falls OH), Method and procedure for neural control of dynamic processes.
Inoue Haruki (Katsuta JPX) Funabashi Motohisa (Sagamihara JPX) Yahiro Masakazu (Hitachi JPX) Satoh Yoshiyuki (Hitachi JPX), Method and system for process control with complex inference mechanism using qualitative and quantitative reasoning.
Bourg, Jr.,Wilfred M.; Bresnahan,Steven A.; Haarsma,Gabe Jan; MacGregor,John F.; Martin,Paul Allan; Yu,Honglu, Method for on-line machine vision measurement, monitoring and control of product features during on-line manufacturing processes.
Piche Stephen ; Keeler James David ; Hartman Eric ; Johnson William D. ; Gerules Mark ; Liano Kadir, Method for steady-state identification based upon identified dynamics.
Bagepalli, Srinivas Krishnasnamy; DeRose, Lynn Ann; Hung, Stephen Lan-Sun; Kim, Bang Mo; Wight, Tara Healy; Salvo, Joseph James, Methods and systems for energy and emissions monitoring.
Buchhop Thomas Robert (Canton MI) D\Alleva Randall (St. Clair Shores MI) Darnell Ronald Keith (Ortonville MI) Little Jack Ryan (Metamora MI) Pedersen Curtis Thomas (Fenton MI), Parametric emissions monitoring system having operating condition deviation feedback.
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.
Nomura Masahide (Hitachi JPX) Saito Tadayoshi (Hitachi JPX) Matsumoto Hiroshi (Ibaraka JPX) Shimoda Makoto (Katsuta JPX) Kondoh Masakazu (Hitachi JPX) Miyagaki Hisanori (Ohta JPX) Sugano Akira (Katsu, Process control method and system for performing control of a controlled system by use of a neural network.
Hileman,Michael J.; Broadfoot,Robert; Jones,Richard B., System and method for determining equivalency factors for use in comparative performance analysis of industrial facilities.
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.
Keeler James D. (Austin TX) Havener John P. (Austin TX) Godbole Devendra (Austin TX) Ferguson ; II Ralph B. (Austin TX), Virtual emissions monitor for automobile.
Keeler James David (Austin TX) Havener John Paul (Austin TX) Godbole Devendra (Austin TX) Ferguson ; II Ralph Bruce (Austin TX), Virtual emissions monitor for automobile and associated control system.
Düll, Siegmund; Hentschel, Alexander; Sterzing, Volkmar; Udluft, Steffen, Method for the computer-supported generation of a data-driven model of a technical system, in particular of a gas turbine or wind turbine.
Raoux, Sebastien; Curry, Mark W.; Porshnev, Peter; Fox, Allen, Methods and apparatus for improving operation of an electronic device manufacturing system.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.