Digital Twin Parameter Updating for Steady-State Plant Synchronization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current digital twin technology struggles to reflect real-time changes in facility data due to updating data at regular intervals and using predetermined models, making it difficult to adapt to facility changes.
Innovation Solution
A method and system for creating a digital twin that updates parameters using plant data in a steady state, determining steady state through variance analysis, and generating prediction data to synchronize the digital twin with the facility in real time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is updated at regular intervals using a predetermined model, then the system structure is simple and easy to implement, but the digital twin cannot reflect real-time changes in facility data
Solution Approach 1:
The patent implements dynamic parameter updates by continuously monitoring plant data and automatically adjusting prediction model parameters when steady state conditions are detected, rather than using fixed predetermined models. This allows the digital twin to adapt to changing facility conditions in real-time, resolving the contradiction between representation accuracy and system complexity
Solution Approach 2:
The system changes parameters of the prediction model based on detected steady state conditions in plant data. By dynamically adjusting parameters rather than using fixed values, the digital twin maintains high accuracy while avoiding the need for completely complex reconfiguration mechanisms
2Adaptability or versatility
If a predetermined model is used to create the digital twin, then the model creation process is simple, but the model cannot adapt to changes in facilities
Solution Approach 1:
The system incorporates feedback mechanisms by continuously comparing actual plant data with prediction model outputs, detecting steady state conditions, and using this feedback to automatically update model parameters. This closed-loop approach enables the model to adapt to facility changes without requiring complex manual reconfiguration
Solution Approach 2:
The prediction model performs self-updating by automatically detecting steady state conditions in incoming plant data and adjusting its own parameters accordingly. This self-service capability allows the model to adapt to facility changes autonomously, reducing the need for complex external intervention while maintaining high adaptability
3Speed
If data is collected frequently to achieve real-time updates, then the real-time representation is improved, but the data processing load and system complexity increase
Solution Approach 1:
The system uses periodic sampling of plant data at predetermined intervals and applies steady state detection algorithms only at these periodic points. This approach achieves real-time representation by updating the digital twin whenever steady state conditions are detected, while avoiding the need for continuous high-frequency processing that would increase system complexity
Data Source
AI summary
Provided are a system and method for creating a digital twin. The method performed by at least one processor includes receiving, by the processor, plant data generated by sensing a target facility which is a target of a digital twin, determining, by the processor, whether the plant data is in a steady state on the basis of the plant data, when the plant data is in a steady state, updating, by the processor, parameters of a prediction model on the basis of the plant data, inputting, by the processor, the plant data into the prediction model based on the updated parameters to generate prediction data, and outputting, by the processor, the prediction data.