Digital Twin Control Using Reduced-Order Models at the Edge
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing manufacturing processes face challenges in efficiently utilizing high-fidelity simulation models due to computational complexity and data entry complexity, limiting their effectiveness in real-time process control and optimization.
Innovation Solution
Implementing reduced order models and neural network-based deep learning models trained on design of experiments data, deployed on edge computers to facilitate real-time data processing and control through a digital twin framework, utilizing protocols like Unified Name Space and MQTT for data transfer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If high-fidelity simulation models are used for manufacturing process control, then accuracy and reliability of process optimization is improved, but computational complexity and data entry complexity increase
Solution Approach 1:
The patent creates a digital twin model that is a virtual copy of the physical manufacturing process. This digital twin replicates the behavior and characteristics of the actual process, allowing high-fidelity simulation without the computational burden of repeatedly running complex physical process simulations. The digital twin model captures essential process dynamics and can be updated with real-time data to maintain accuracy while enabling faster computations.
Solution Approach 2:
The patent performs preliminary simulation and analysis using high-fidelity models during the digital twin model creation phase. Complex computational work is done upfront to build an accurate digital representation, which can then be used for real-time control and optimization without repeating the full computational burden. This preliminary action separates the heavy computational tasks from the real-time operational tasks.
2Manufacturing precision
If high-fidelity simulation models are used for manufacturing process control, then accuracy and reliability of process optimization is improved, but data entry complexity increases
Solution Approach 1:
The digital twin model automatically receives and processes data from the physical manufacturing process through integrated data acquisition systems. The model self-updates with real-time process data, eliminating the need for manual data entry. Sensors and measurement systems connected to the physical process automatically feed data into the digital twin, which then uses this data for continuous optimization without human intervention in data collection and entry.
Solution Approach 2:
The patent introduces an automated data acquisition and processing layer that acts as an intermediary between the physical manufacturing process and the simulation model. This intermediary layer handles data collection, validation, and formatting automatically, translating raw process data into the appropriate format for the digital twin model without requiring manual data entry operations.
3Productivity
If real-time data processing is implemented for process control, then productivity and responsiveness are improved, but computational resources and system complexity increase
Solution Approach 1:
The patent implements a dynamic digital twin model that adapts its computational requirements based on real-time process conditions. The model can adjust its level of detail and computational intensity depending on the operational phase, process stability, and criticality of control decisions. This dynamic approach allows real-time processing when needed while reducing computational burden during stable operations, optimizing the balance between productivity and system complexity.
Data Source
AI summary
A method of controlling a manufacturing process includes: creating a digital twin model representing one of the manufacturing process or a manufactured article that is formed or modified by the manufacturing process; revising the digital twin model with real-time data regarding a physical instance of the one of the manufacturing process or the manufactured article; making a decision, based on the digital twin model, regarding the physical instance of the one of the manufacturing process or the manufactured article; and causing or modifying an action, based on the decision regarding the physical instance of the one of the manufacturing process or the manufactured article.