Patents by Inventor Mark Gerules
Mark Gerules has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 7624079Abstract: Method and apparatus for training a system model with gain constraints. A method is disclosed for training a steady-state model, the model having an input and an output and a mapping layer for mapping the input to the output through a stored representation of a system. A training data set is provided having a set of input data u(t) and target output data y(t) representative of the operation of a system. The model is trained with a predetermined training algorithm which is constrained to maintain the sensitivity of the output with respect to the input substantially within user defined constraint bounds by iteratively minimizing an objective function as a function of a data objective and a constraint objective. The data objective has a data fitting learning rate and the constraint objective has constraint learning rate that are varied as a function of the values of the data objective and the constraint objective after selective iterative steps.Type: GrantFiled: April 3, 2006Date of Patent: November 24, 2009Assignee: Rockwell Automation Technologies, Inc.Inventors: Eric Jon Hartman, Stephen Piche, Mark Gerules
-
Patent number: 7315846Abstract: Method and apparatus for training a system model with gain constraints. A method is disclosed for training a steady-state model, the model having an input and an output and a mapping layer for mapping the input to the output through a stored representation of a system. A training data set is provided having a set of input data u(t) and target output data y(t) representative of the operation of a system. The model is trained with a predetermined training algorithm which is constrained to maintain the sensitivity of the output with respect to the input substantially within user defined constraint bounds by iteratively minimizing an objective function as a function of a data objective and a constraint objective. The data objective has a data fitting learning rate and the constraint objective has constraint learning rate that are varied as a function of the values of the data objective and the constraint objective after selective iterative steps.Type: GrantFiled: April 3, 2006Date of Patent: January 1, 2008Assignee: Pavilion Technologies, Inc.Inventors: Eric Jon Hartman, Stephen Piche, Mark Gerules
-
Patent number: 7213006Abstract: Method and apparatus for training a system model with gain constraints. A method is disclosed for training a steady-state model having an input and an output and a mapping layer for mapping the input to the output, the model comprising a stored representation of a plant or process, and including a linear portion and a non-linear portion, where the non-linear portion includes a function. Input is received to the model, and predicted output computed corresponding to attribute(s) of the plant or process. The predicted output is stored, and is usable to manage the plant or process. The model is trained to optimize a specified objective function subject to one or more constraints, e.g., via a non-linear programming (NLP) optimizer, the constraints including, hard constraint(s) comprising strict limitations on the training in optimizing the objective function, and/or soft constraint(s) comprising a weighted penalty function included in the objective function.Type: GrantFiled: November 4, 2005Date of Patent: May 1, 2007Assignee: Pavilion Technologies, Inc.Inventors: Eric Jon Hartman, Stephen Piche, Mark Gerules
-
Patent number: 7139619Abstract: A kiln thermal and combustion control. A predictive model is provided of the dynamics of selected aspects of the operation of the system for modeling the dynamics thereof. The model has at least two discrete models associated therewith that model at least two of the selected aspects, the at least two discrete models having different dynamic responses. An optimizer receives desired values for the selected aspects of the operation of the system modeled by the model and optimizes the inputs to the model to minimize error between the predicted and desired values. A control input device then applies the optimized input values to the system after optimization thereof.Type: GrantFiled: December 22, 2005Date of Patent: November 21, 2006Assignee: Pavilion Technologies, Inc.Inventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener, Steven J. McGarel
-
Publication number: 20060224534Abstract: Method and apparatus for training a system model with gain constraints. A method is disclosed for training a steady-state model, the model having an input and an output and a mapping layer for mapping the input to the output through a stored representation of a system. A training data set is provided having a set of input data u(t) and target output data y(t) representative of the operation of a system. The model is trained with a predetermined training algorithm which is constrained to maintain the sensitivity of the output with respect to the input substantially within user defined constraint bounds by iteratively minimizing an objective function as a function of a data objective and a constraint objective. The data objective has a data fitting learning rate and the constraint objective has constraint learning rate that are varied as a function of the values of the data objective and the constraint objective after selective iterative steps.Type: ApplicationFiled: April 3, 2006Publication date: October 5, 2006Inventors: Eric Hartman, Stephen Piche, Mark Gerules
-
Patent number: 7110834Abstract: A kiln thermal and combustion control. A predictive model is provided of the dynamics of selected aspects of the operation of the system for modeling the dynamics thereof. The model has at least two discrete models associated therewith that model at least two of the selected aspects, the at least two discrete models having different dynamic responses. An optimizer receives desired values for the selected aspects of the operation of the system modeled by the model and optimizes the inputs to the model to minimize error between the predicted and desired values. A control input device then applies the optimized input values to the system after optimization thereof.Type: GrantFiled: September 23, 2003Date of Patent: September 19, 2006Assignee: Pavilion Technologies, Inc.Inventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener, Steven J. McGarel
-
Publication number: 20060184477Abstract: Method and apparatus for training a system model with gain constraints. A method is disclosed for training a steady-state model, the model having an input and an output and a mapping layer for mapping the input to the output through a stored representation of a system. A training data set is provided having a set of input data u(t) and target output data y(t) representative of the operation of a system. The model is trained with a predetermined training algorithm which is constrained to maintain the sensitivity of the output with respect to the input substantially within user defined constraint bounds by iteratively minimizing an objective function as a function of a data objective and a constraint objective. The data objective has a data fitting learning rate and the constraint objective has constraint learning rate that are varied as a function of the values of the data objective and the constraint objective after selective iterative steps.Type: ApplicationFiled: April 3, 2006Publication date: August 17, 2006Inventors: Eric Hartman, Stephen Piche, Mark Gerules
-
Patent number: 7058617Abstract: Method and apparatus for training a system model with gain constraints. A method is disclosed for training a steady-state model, the model having an input and an output and a mapping layer for mapping the input to the output through a stored representation of a system. A training data set is provided having a set of input data u(t) and target output data y(t) representative of the operation of a system. The model is trained with a predetermined training algorithm which is constrained to maintain the sensitivity of the output with respect to the input substantially within user defined constraint bounds by iteratively minimizing an objective function as a function of a data objective and a constraint objective. The data objective has a data fitting learning rate and the constraint objective has constraint learning rate that are varied as a function of the values of the data objective and the constraint objective after selective iterative steps.Type: GrantFiled: September 14, 2000Date of Patent: June 6, 2006Assignee: Pavilion Technologies, Inc.Inventors: Eric Jon Hartman, Stephen Piche, Mark Gerules
-
Patent number: 7050866Abstract: A method for providing independent static and dynamic models in a prediction, control and optimization environment utilizes an independent static model (20) and an independent dynamic model (22). The static model (20) is a rigorous predictive model that is trained over a wide range of data, whereas the dynamic model (22) is trained over a narrow range of data. The gain K of the static model (20) is utilized to scale the gain k of the dynamic model (22). The forced dynamic portion of the model (22) referred to as the bi variables are scaled by the ratio of the gains K and k. The bi have a direct effect on the gain of a dynamic model (22). This is facilitated by a coefficient modification block (40). Thereafter, the difference between the new value input to the static model (20) and the prior steady-state value is utilized as an input to the dynamic model (22). The predicted dynamic output is then summed with the previous steady-state value to provide a predicted value Y.Type: GrantFiled: May 17, 2004Date of Patent: May 23, 2006Assignee: Pavilion Technologies, Inc.Inventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener
-
Patent number: 7047089Abstract: A method and apparatus for controlling a non-linear mill. A linear controller is provided having a linear gain k that is operable to receive inputs representing measured variables of the plant and predict on an output of the linear controller predicted control values for manipulatible variables that control the plant. A non-linear model of the plant is provided for storing a representation of the plant over a trained region of the operating input space and having a steady-state gain K associated therewith. The gain k of the linear model is adjusted with the gain K of the non-linear model in accordance with a predetermined relationship as the measured variables change the operating region of the input space at which the linear controller is predicting the values for the manipulatible variables. The predicted manipulatible variables are then output after the step of adjusting the gain k.Type: GrantFiled: May 11, 2004Date of Patent: May 16, 2006Assignee: Pavilion TechnologiesInventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener
-
Publication number: 20060100720Abstract: A kiln thermal and combustion control. A predictive model is provided of the dynamics of selected aspects of the operation of the system for modeling the dynamics thereof. The model has at least two discrete models associated therewith that model at least two of the selected aspects, the at least two discrete models having different dynamic responses. An optimizer receives desired values for the selected aspects of the operation of the system modeled by the model and optimizes the inputs to the model to minimize error between the predicted and desired values. A control input device then applies the optimized input values to the system after optimization thereof.Type: ApplicationFiled: December 22, 2005Publication date: May 11, 2006Inventors: Gregory Martin, Eugene Boe, Stephen Piche, James Keeler, Douglas Timmer, Mark Gerules, John Havener, Steven McGarel
-
Publication number: 20060074501Abstract: Method and apparatus for training a system model with gain constraints. A method is disclosed for training a steady-state model, the model having an input and an output and a mapping layer for mapping the input to the output through a stored representation of a system. A training data set is provided having a set of input data u(t) and target output data y(t) representative of the operation of a system. The model is trained with a predetermined training algorithm which is constrained to maintain the sensitivity of the output with respect to the input substantially within user defined constraint bounds by iteratively minimizing an objective function as a function of a data objective and a constraint objective. The data objective has a data fitting learning rate and the constraint objective has constraint learning rate that are varied as a function of the values of the data objective and the constraint objective after selective iterative steps.Type: ApplicationFiled: November 4, 2005Publication date: April 6, 2006Inventors: Eric Hartman, Stephen Piche, Mark Gerules
-
Patent number: 7024252Abstract: A method and apparatus for controlling a non-linear mill. A linear controller is provided having a linear gain k that is operable to receive inputs representing measured variables of the plant and predict on an output of the linear controller predicted control values for manipulatible variables that control the plant. A non-linear model of the plant is provided for storing a representation of the plant over a trained region of the operating input space and having a steady-state gain K associated therewith. The gain k of the linear model is adjusted with the gain K of the non-linear model in accordance with a predetermined relationship as the measured variables change the operating region of the input space at which the linear controller is predicting the values for the manipulatible variables. The predicted manipulatible variables are then output after the step of adjusting the gain k.Type: GrantFiled: September 26, 2005Date of Patent: April 4, 2006Assignee: Pavilion Technologies, Inc.Inventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener
-
Publication number: 20060020352Abstract: A method and apparatus for controlling a non-linear mill. A linear controller is provided having a linear gain k that is operable to receive inputs representing measured variables of the plant and predict on an output of the linear controller predicted control values for manipulatible variables that control the plant. A non-linear model of the plant is provided for storing a representation of the plant over a trained region of the operating input space and having a steady-state gain K associated therewith. The gain k of the linear model is adjusted with the gain K of the non-linear model in accordance with a predetermined relationship as the measured variables change the operating region of the input space at which the linear controller is predicting the values for the manipulatible variables. The predicted manipulatible variables are then output after the step of adjusting the gain k.Type: ApplicationFiled: September 26, 2005Publication date: January 26, 2006Inventors: Gregory Martin, Eugene Boe, Stephen Piche, James Keeler, Douglas Timmer, Mark Gerules, John Havener
-
Publication number: 20050075737Abstract: A method for providing independent static and dynamic models in a prediction, control and optimization environment utilizes an independent static model (20) and an independent dynamic model (22). The static model (20) is a rigorous predictive model that is trained over a wide range of data, whereas the dynamic model (22) is trained over a narrow range of data. The gain K of the static model (20) is utilized to scale the gain k of the dynamic model (22). The forced dynamic portion of the model (22) referred to as the bi variables are scaled by the ratio of the gains K and k. The bi have a direct effect on the gain of a dynamic model (22). This is facilitated by a coefficient modification block (40). Thereafter, the difference between the new value input to the static model (20) and the prior steady-state value is utilized as an input to the dynamic model (22). The predicted dynamic output is then summed with the previous steady-state value to provide a predicted value Y.Type: ApplicationFiled: May 17, 2004Publication date: April 7, 2005Inventors: Gregory Martin, Eugene Boe, Stephen Piche, James Keeler, Douglas Timmer, Mark Gerules, John Havener
-
Publication number: 20040210325Abstract: A method and apparatus for controlling a non-linear mill. A linear controller is provided having a linear gain k that is operable to receive inputs representing measured variables of the plant and predict on an output of the linear controller predicted control values for manipulatible variables that control the plant. A non-linear model of the plant is provided for storing a representation of the plant over a trained region of the operating input space and having a steady-state gain K associated therewith. The gain k of the linear model is adjusted with the gain K of the non-linear model in accordance with a predetermined relationship as the measured variables change the operating region of the input space at which the linear controller is predicting the values for the manipulatible variables.Type: ApplicationFiled: May 11, 2004Publication date: October 21, 2004Inventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener
-
Patent number: 6738677Abstract: A method for providing independent static and dynamic models in a prediction, control and optimization environment utilizes an independent static model (20) and an independent dynamic model (22). The static model (20) is a rigorous predictive model that is trained over a wide range of data, whereas the dynamic model (22) is trained over a narrow range of data. The gain K of the static model (20) is utilized to scale the gain k of the dynamic model (22). The forced dynamic portion of the model (22) referred to as the bi variables are scaled by the ratio of the gains K and k. The bi have a direct effect on the gain of a dynamic model (22). This is facilitated by a coefficient modification block (40). Thereafter, the difference between the new value input to the static model (20) and the prior steady-state value is utilized as an input to the dynamic model (22). The predicted dynamic output is then summed with the previous steady-state value to provide a predicted value Y.Type: GrantFiled: November 22, 2002Date of Patent: May 18, 2004Assignee: Pavilion Technologies, Inc.Inventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener
-
Patent number: 6735483Abstract: A method and apparatus for controlling a non-linear mill. A linear controller is provided having a linear gain k that is operable to receive inputs representing measured variables of the plant and predict on an output of the linear controller predicted control values for manipulatible variables that control the plant. A non-linear model of the plant is provided for storing a representation of the plant over a trained region of the operating input space and having a steady-state gain K associated therewith. The gain k of the linear model is adjusted with the gain K of the non-linear model in accordance with a predetermined relationship as the measured variables change the operating region of the input space at which the linear controller is predicting the values for the manipulatible variables.Type: GrantFiled: December 9, 2002Date of Patent: May 11, 2004Assignee: Pavilion Technologies, Inc.Inventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener
-
Publication number: 20040059441Abstract: A kiln thermal and combustion control. A predictive model is provided of the dynamics of selected aspects of the operation of the system for modeling the dynamics thereof. The model has at least two discrete models associated therewith that model at least two of the selected aspects, the at least two discrete models having different dynamic responses. An optimizer receives desired values for the selected aspects of the operation of the system modeled by the model and optimizes the inputs to the model to minimize error between the predicted and desired values.Type: ApplicationFiled: September 23, 2003Publication date: March 25, 2004Inventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener
-
Patent number: 6625501Abstract: A kiln thermal and combustion control. A predictive model is provided of the dynamics of selected aspects of the operation of the plant for modeling the dynamics thereof. The model has at least two discrete models associated therewith that model at least two of the selected aspects, the at least two discrete models having different dynamic responses. An optimizer receives desired values for the selected aspects of the operation of the plant modeled by the model and optimizes the inputs to the model to minimize error between the predicted and desired values. A control input device then applies the optimized input values to the plant after optimization thereof.Type: GrantFiled: August 14, 2002Date of Patent: September 23, 2003Assignee: Pavilion Technologies, Inc.Inventors: Gregory D. Martin, Eugene Boe, Stephen Piche, James David Keeler, Douglas Timmer, Mark Gerules, John P. Havener