Empirical modeling with globally enforced general constraints
AssigneeRockwell Automation Technologies, Inc.
InventorsBijan Sayyar-Rodsari, Eric Jon Hartman, Carl Anthony Schweiger
Life of this patent
Estimating the term…
Abstract
In certain embodiments, a method includes formulating an optimization problem to determine a plurality of model parameters of a system to be modeled. The method also includes solving the optimization problem to define an empirical model of the system. The method further includes training the empirical model using training data. The empirical model is constrained via general constraints relating to first-principles information and process knowledge of the system.
Claims20
A system, comprising:
- a processor;
- a tangible, non-transitory, computer-readable medium, comprising instructions configured to be executed by the processor, the instructions comprising:
- receiving a plurality of operational parameters associated with inputs and outputs of an industrial automation process for an industrial system;
- formulating an optimization problem to determine a plurality of model parameters of an empirical model based on the plurality of operational parameters;
- randomly selecting a subset of model parameters from the plurality of model parameters to determine a subset of boundary types of a model space;
- and
- solving the optimization problem to define the empirical model subject to general constraints based on the determined subset of boundary types of the model space.
A computer-implemented method comprising:
- receiving a plurality of updated model parameters associated with an empirical model used for an industrial automation process to control an industrial system;
- randomly selecting a subset of updated model parameters from the plurality of updated model parameters to determine a subset of boundary types of a model space;
- and
- tuning the empirical model to generate an updated empirical model by solving an optimization problem to define the updated empirical model, wherein the updated empirical model is subject to general constraints based on the determined subset of boundary types of the model space and the empirical model.
A tangible, non-transitory, computer-readable medium configured to store instructions executable by processing circuitry, wherein the instructions comprise instructions to cause the processing circuitry to perform operations comprising:
- receiving a plurality of operational parameters associated with inputs and outputs of an industrial automation process for an industrial system;
- formulating an optimization problem to determine a plurality of model parameters of an empirical model based on the plurality of operational parameters;
- assigning a probability value to each model parameter of the plurality of model parameters;
- randomly selecting a subset of model parameters from the plurality of model parameters based on the probability value assigned to each model parameter of the plurality of model parameters to determine a subset of boundary types of a model space;
- solving the optimization problem to define the empirical model subject to one or more constraints based on the determined subset of boundary types of the model space;
- and
- controlling the industrial automation process based on the empirical model.
Dependencies are inferred from the claim text.