Coupled Digital Twins for Resource Allocation Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional digital twin (DT) systems are limited in capturing interaction flows between multiple DTs and business flows, leading to inefficiencies in optimization and control of resource allocation in complex business and physical systems.
Innovation Solution
A system and method that utilize a plurality of digital twins interconnected through an asset optimizer module and a system optimizer module, selecting DTs based on accuracy, time coverage, computation time, or contribution to variance, to optimize key process indicators and generate operation protocols for real-world asset systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a monolithic representation approach is used to aggregate all facets and data from different lifecycle stages, then a comprehensive digital representation is achieved, but the resulting object becomes bloated and inefficient
Solution Approach 1:
The patent segments the monolithic digital twin into multiple specialized digital twins, each representing specific facets or lifecycle stages of the physical object. This segmentation allows each digital twin to focus on particular aspects (e.g., operational, maintenance, financial) without aggregating all data, thereby reducing bloat while maintaining comprehensive coverage through the collection of specialized twins.
2Productivity
If conventional DT systems focus only on object-level behaviors, then object efficiency is improved, but interaction flows between multiple DTs and business flows are not captured
Solution Approach 1:
The patent merges multiple digital twins representing different objects, lifecycle stages, and business aspects into an integrated system. This merging enables the capture of interaction flows between digital twins and business flows that would be invisible in isolated object-level models, while each individual digital twin maintains its focus on specific object efficiency metrics.
Solution Approach 2:
The patent introduces business flows as intermediary elements that connect multiple digital twins and facilitate the representation of interaction flows. These business flows act as mediators that capture the relationships and dependencies between different digital twins and the broader business context, enabling comprehensive tracking of interactions without compromising object-level efficiency analysis.
3Reliability
If all digital twins are optimized simultaneously, then comprehensive optimization is achieved, but computation time increases significantly
Solution Approach 1:
The patent segments the optimization process into multiple independent or semi-independent optimization tasks, each corresponding to a specific digital twin or group of related digital twins. This segmentation allows parallel processing and reduces the computational burden of simultaneous optimization, while the coordinated optimization of all digital twins ensures comprehensive system-wide optimization is still achieved.
Solution Approach 2:
The patent performs preliminary optimization of individual digital twins or subsets of digital twins before conducting integrated system optimization. This preliminary action reduces the search space and computational complexity for subsequent comprehensive optimization, enabling faster convergence to optimal solutions while maintaining optimization completeness.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
Optimization systems and methods for optimizing business operations and asset systems are disclosed. A system (100) includes digital twins corresponding to asset systems; business models (138b) corresponding to business operations; and an electronic control unit (ECU). The ECU is programmed to: implement an asset optimizer module (144a), where implementing the asset optimizer module (144a) interconnects the digital twins for optimization, execute the asset optimizer module (144a), where the asset optimizer module (144a) optimizes the digital twins to obtain one or more optimization parameters (138c) for the asset systems, implement a system optimizer module (144b), where the system optimizer module (144b) receives the one or more optimization parameters (138c) and the business models (138b), execute the system optimizer module (144b), where the system optimizer module (144b) generates operation protocols (138d) for the business models (138b), and output, to a user, the operation protocols (138d) for implementation in a real-world asset system (100).