System-of-Systems Digital Twin for Environmental Asset Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital twin solutions fail to capture the end-to-end functional behaviors of industrial systems and do not integrate the impact of environmental factors on asset management, leading to inadequate strategic decision-making.
Innovation Solution
A systemic digital twin manager is developed using a Σ (Sigma) modeling language and associated hardware architecture to model and simulate the lifecycle of industrial assets, incorporating environmental and operational data for predictive simulations and real-time optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing digital twin solutions are used to model industrial systems, then system visualization is achieved, but end-to-end functional behaviors and environmental factor impacts are not captured
Solution Approach 1:
The system is divided into multiple hierarchical levels (system level, subsystem level, component level) with each level having its own digital twin model. This segmentation allows capturing functional behaviors at different granularities while managing complexity through modular representation.
Solution Approach 2:
The patent introduces a new dimension to digital twins by adding environmental context and causal relationship modeling. Instead of traditional geometric or operational digital twins, this approach incorporates environmental factors and causal mechanisms as additional dimensional layers, enabling comprehensive capture of system behaviors.
2Measurement precision
If comprehensive digital twins are created to capture all system behaviors, then modeling accuracy improves, but computational resources and simulation time increase
Solution Approach 1:
Causal models are pre-built and validated before actual simulations are run. These pre-computed causal relationships enable faster predictive simulations by avoiding redundant calculations, as the causal structure is already established from historical data and expert knowledge.
Solution Approach 2:
The system performs simulations selectively based on user queries and critical decision points, rather than continuously running all possible scenarios. This partial execution approach maintains precision for critical analyses while reducing overall computational resource consumption.
3Productivity
If real-time data synchronization is implemented between physical and digital twins, then operational optimization improves, but data processing complexity and latency increase
Solution Approach 1:
The system implements feedback loops where real-time data from physical systems continuously updates digital twins, which then generate predictions and recommendations that feed back to operational systems. This feedback mechanism enables real-time optimization by closing the loop between sensing, modeling, and decision-making.
Solution Approach 2:
An intermediary data processing layer is introduced between physical systems and digital twins, using edge computing nodes to pre-process and filter data locally. This intermediary layer reduces the volume of data needing transmission and processing in real-time, minimizing latency while maintaining synchronization accuracy.
4Reliability
If environmental factors are integrated into digital twin models, then predictive capabilities improve, but model complexity and data requirements increase
Solution Approach 1:
The system applies different levels of environmental factor integration to different parts of the model based on their relevance to specific predictions. Critical components receiving detailed environmental data, while less critical components use simplified models, optimizing the balance between predictive accuracy and data requirements.
Data Source
AI summary
A method for modeling and simulating a system of systems, involving a technical system of interest as well as of a plurality of systems external to the technical system of interest, forming the environment wherein the system of interest evolves.