Digital twin modeling and optimization of production processes
AssigneeNortheastern University
InventorMohammad Dehghanimohammadabadi
Life of this patent
Estimating the term…
Abstract
A machine learning system and method for optimizing a production process. For instance, the method includes several steps as follows: selecting different values for a plurality of input parameters of a digital model of the production process for simulation; running the digital model using the different values for the plurality of input parameters and at least some of real-time data of the production process; determining a plurality of output parameters of the digital model; analyzing the plurality of output parameters; learning an optimized plurality of input parameters corresponding to the plurality of output parameters; and programming the production process to use the optimized plurality of input parameters to run the production process.
Claims8
A machine learning system for optimizing a production process, the machine learning system comprising:
- a production planning system, the production planning system comprising real-time data of the production process;
- a simulation system, the simulation system configured with a digital model of the production process, the digital model accepting a plurality of input parameters and producing a plurality of output parameters;
- an analytics system, the analytics system configured to interface with the simulation system, wherein the simulation system interfaces with the analytics system using an application programming interface, the application programming interface including commands for providing the plurality of input parameters and receiving the plurality of output parameters,
- wherein the analytics system communicates different values for the plurality of input parameters to the simulation system using the application programming interface,
- wherein the simulation system runs the digital model using the different values for the plurality of input parameters received from the analytics system and at least some of the real-time data of the production process received from the production planning system,
- wherein the simulation system communicates the plurality of output parameters to the analytics system,
- wherein the analytics system analyzes the plurality of output parameters to learn an optimized plurality of input parameters corresponding to the plurality of output parameters, and
- wherein the production planning system is programmed to use the optimized plurality of input parameters learned using the digital model to run the production process.
Dependencies are inferred from the claim text.