Abstract: A technique is disclosed for reducing an error in a controlled variable via model predictive control. A predicted error in the controlled variable is determined for a forward-looking control horizon based upon measured or computed variables. The integral of the predicted error is computed. If the error or the integral exceed a tolerance for a determined time period, the model predictive control algorithm is modified to drive the error or the integral to within a tolerance. The modifications to the control algorithm may include changes to coefficients for terms based upon the error and/or the integral of the error.

Abstract: The present invention provides novel techniques for controlling batch reaction processes. In particular, a parametric hybrid model may be used to parameterize inputs and outputs of batch reaction processes. The parametric hybrid model may include an empirical model, a parameter model, and a dynamic model. Critical quality parameters, which are correlated with, but not the same as, end-of-batch quality values for the batch reaction processes may be monitored during cycles of the batch reaction processes. The quality parameters may be used to generate desired batch trajectories, which may be used to control the batch reaction processes during the cycles of the batch reaction processes.

Abstract: The present invention provides novel techniques for controlling energy systems. In particular, parametric hybrid models may be used to parameterize inputs and outputs of groups of equipment of energy systems. Each parametric hybrid model may include an empirical model, a parameter model, and a dynamic model. Critical parameters for groups of equipment modeled by the parametric hybrid models, which are correlated with, but not the same as, input and output variables of the groups of equipment may be monitored during operation of the energy system. The critical parameters may be used to generate optimal trajectories for the energy system, which may be used to control the energy system.

Abstract: A technique is disclosed for reducing an error in a controlled variable via model predictive control. A predicted error in the controlled variable is determined for a forward-looking control horizon based upon measured or computed variables. The integral of the predicted error is computed. If the error or the integral exceed a tolerance for a determined time period, the model predictive control algorithm is modified to drive the error or the integral to within a tolerance. The modifications to the control algorithm may include changes to coefficients for terms based upon the error and/or the integral of the error.

Abstract: System and method for modeling a nonlinear process. A combined model for predictive optimization or control of a nonlinear process includes a nonlinear approximator, coupled to a parameterized dynamic or static model, operable to model the nonlinear process. The nonlinear approximator receives process inputs, and generates parameters for the parameterized dynamic model. The parameterized dynamic model receives the parameters and process inputs, and generates predicted process outputs based on the parameters and process inputs, where the predicted process outputs are useable to analyze and/or control the nonlinear process. The combined model may be trained in an integrated manner, e.g.

Abstract: The present invention provides novel techniques for optimizing and controlling production plants using parametric multifaceted models. In particular, the parametric multifaceted models may be configured to convert a first set of parameters (e.g., control parameters) relating to a production plant into a second set of parameters (e.g., optimization parameters) relating to the production plant. In general, the first set of parameters will be different than the second set of parameters. For example, the first set of parameters may be indicative of low-level, real-time control parameters and the second set of parameters may be indicative of high-level, economic parameters. Utilizing appropriate parameterization may allow the parametric multifaceted models to deliver an appropriate level of detail of the production plant within a reasonable amount of time.

Abstract: A technique is disclosed for reducing an error in a controlled variable via model predictive control. A predicted error in the controlled variable is determined for a forward-looking control horizon based upon measured or computed variables. The integral of the predicted error is computed. If the error or the integral exceed a tolerance for a determined time period, the model predictive control algorithm is modified to drive the error or the integral to within a tolerance. The modifications to the control algorithm may include changes to coefficients for terms based upon the error and/or the integral of the error.

Abstract: System and method for modeling a nonlinear process. A combined model for predictive optimization or control of a nonlinear process includes a nonlinear approximator, coupled to a parameterized dynamic or static model, operable to model the nonlinear process. The nonlinear approximator receives process inputs, and generates parameters for the parameterized dynamic model. The parameterized dynamic model receives the parameters and process inputs, and generates predicted process outputs based on the parameters and process inputs, where the predicted process outputs are useable to analyze and/or control the nonlinear process. The combined model may be trained in an integrated manner, e.g.

Abstract: System and method for modeling a nonlinear process. A combined model for predictive optimization or control of a nonlinear process includes a nonlinear approximator, coupled to a parameterized dynamic or static model, operable to model the nonlinear process. The nonlinear approximator receives process inputs, and generates parameters for the parameterized dynamic model. The parameterized dynamic model receives the parameters and process inputs, and generates predicted process outputs based on the parameters and process inputs, where the predicted process outputs are useable to analyze and/or control the nonlinear process. The combined model may be trained in an integrated manner, e.g.

Abstract: System and method for modeling a nonlinear process. A combined model for predictive optimization or control of a nonlinear process includes a nonlinear approximator, coupled to a parameterized dynamic or static model, operable to model the nonlinear process. The nonlinear approximator receives process inputs, and generates parameters for the parameterized dynamic model. The parameterized dynamic model receives the parameters and process inputs, and generates predicted process outputs based on the parameters and process inputs, where the predicted process outputs are useable to analyze and/or control the nonlinear process. The combined model may be trained in an integrated manner, e.g.

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 system and method for optimizing transactions in an e-marketplace. An e-marketplace optimization server couples to a plurality of participant computers through a network, each of which is operated on behalf of a participant. The server hosts a site which provides the e-marketplace where goods and/or services are bought and sold among participants. The server also includes a transaction optimization program which mediates a transaction among the participants which best serves the needs of two or more of the participants. Each of the participant computers provides transaction information to the server, including constraints and/or objectives related to the transaction.

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.