Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: The present invention provides a method for controlling nonlinear control problems within particle accelerators. This method involves first utilizing software tools to identify variable inputs and controlled variables associated with the particle accelerator, wherein at least one variable input parameter is a controlled variable. This software tool is further operable to determine relationships between the variable inputs and controlled variables. A control system that provides variable inputs to and acts on controller outputs from the software tools tunes one or more manipulated variables to achieve a desired controlled variable, which in the case of a particle accelerator may be realized as a more efficient collision.

Abstract: A method for controlling a non-linear process includes the steps of first providing a controller that is operable to receive inputs representing measured variables of the process and predicting on an output of the controller predicted control values for manipulatible variables that control the process. An expert system is provided that models the actions of an operator of the process over an operating region of the process that represents a set of rules for actions to be taken by an operator upon the occurrence of predetermined conditions in the operation of the process. The operation of the controller is modified with the expert system when one of the predetermined conditions exists.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A system and method for on-line training of a support vector machine (SVM). The SVM is trained with training sets from a stream of process data. The system detects availability of new training data, and constructs a training set from the corresponding input data. Over time, many training sets are presented to the SVM. When multiple presentations are needed to effectively train the SVM, a buffer of training sets is filled and updated as new training data becomes available. Once the buffer is full, a new training set bumps the oldest training set from the buffer. The training sets are presented one or more times each time a new training set is constructed. An historical database of time-stamped data may be used to construct training sets for the SVM. The SVM may be trained retrospectively by searching the historical database and constructing training sets based on the time-stamped data.

Abstract: 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.

Abstract: The present invention provides a method for controlling nonlinear process control problems. This method involves first utilizing modeling tools to identify variable inputs and controlled variables associated with the process, wherein at least one variable input is a manipulated variable. The modeling tools are further operable to determine relationships between the variable inputs and controlled variables. A control system that provides inputs to and acts on inputs from the modeling tools tunes one or more manipulated variable inputs to achieve a desired result like greater efficiency, higher quality, or greater consistency.

Abstract: 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.

Abstract: A system and method for preprocessing input data to a support vector machine (SVM). The SVM is a system model having parameters that define the representation of the system being modeled, and operates in two modes: run-time and training. A data preprocessor preprocesses received data in accordance with predetermined preprocessing parameters, and outputs preprocessed data. The data preprocessor includes an input buffer for receiving and storing the input data. The input data may be on different time scales. A time merge device determines a desired time scale and reconciles the input data so that all of the input data are placed on the desired time scale. An output device outputs the reconciled data from the time merge device as preprocessed data. The reconciled data may be input to the SVM in training mode to train the SVM, and/or in run-time mode to generate control parameters and/or predictive output information.

Abstract: A plant is operable to receive control inputs c(t) and provide an output y(t). The plant (72) has associated therewith state variables s(t) that are not variable. A control network (74) models the plant by providing a predicted output which is combined with a desired output to generate an error that is back propagated through an inverse control network to generate a control error signal that is input to a distributed control system to vary the control inputs to the plant in order to change the output y(t) to meet the desired output. The inverse model represents the dependencies of the plant output on the control variables parameterized by external influences to the plant.

Abstract: A system and method for historical database training of a support vector machine (SVM). The SVM is trained with training sets from a stream of process data. The system detects availability of new training data, and constructs a training set from the corresponding input data. Over time, many training sets are presented to the SVM. When multiple presentations are needed to effectively train the SVM, a buffer of training sets is filled and updated as new training data becomes available. Once the buffer is full, a new training set bumps the oldest training set from the buffer. The training sets are presented one or more times each time a new training set is constructed. A historical database of time-stamped data may be used to construct training sets for the SVM. The SVM may be trained retrospectively by searching the historical database and constructing training sets based on the time-stamped data.

Abstract: A system and method for preprocessing input data to a support vector machine (SVM). The SVM is a system model having parameters that define the representation of the system being modeled, and operates in two modes: run-time and training. A data preprocessor preprocesses received data in accordance with predetermined preprocessing parameters, and outputs preprocessed data. The data preprocessor includes an input buffer for receiving and storing the input data. The input data may include one or more outlier values. A data filter detects and removes any outlier values in the input data, generating corrected input data. The filter may optionally replace the outlier values in the input data. An output device outputs the corrected data from the data filter as preprocessed data. The corrected data may be input to the SVM in training mode to train the SVM, and/or in run-time mode to generate control parameters and/or predictive output information.

Abstract: A system and method for performing modeling, prediction, optimization, and control, including an enterprise wide framework for constructing modeling, optimization, and control solutions. The framework includes a plurality of base classes that may be used to create primitive software objects. These objects may then be combined to create optimization and/or control solutions. The distributed event-driven component architecture allows much greater flexibility and power in creating, deploying, and modifying modeling, optimization and control solutions. The system also includes various techniques for performing improved modeling, optimization, and control, as well as improved scheduling and control. For example, the system may include a combination of batch and continuous processing frameworks, and a unified hybrid modeling framework which allows encapsulation and composition of different model types, such as first principles models and empirical models.

Abstract: A method for determining an output value having a known relationship to an input value with a predicted value includes the step of first training a predictive model with at least one output for a given set of inputs that exist in a finite dataset. Data is then input to the predictive model that is within the set of given inputs. Thereafter, a prediction is made of an output from the predictive model that corresponds to the given input such that a predicted output value will be obtained which will have associated therewith the errors of the predictive model.

Abstract: Kiln/cooler control and upset recovery using a combination of model predictive control and expert systems. A method for controlling a non-linear process includes the steps of first providing a controller that is operable to receive inputs representing measured variables of the process and predicting on an output of the controller predicted control values for manipulatible variables that control the process. An expert system is provided that models the actions of an operator of the process over an operating region of the process that represents a set of rules for actions to be taken by an operator upon the occurrence of predetermined conditions in the operation of the process. The operation of the controller is overridden with the expert system when one of the predetermined conditions exists and taking the associated action by the expert system to control the operation of the process by changing one or more of the manipulatible variables.

Abstract: 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.