Knowledge-Based Digital Twin Engineering for Plant Monitoring Scale-Up
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing approaches for building digital twins for industrial plants require extensive collaboration among domain experts, process modeling engineers, and data scientists, making the process time-consuming and not scalable, as each type of industry and specific plant necessitates a new design and development process from scratch.
Innovation Solution
A processor-implemented method and system that uses knowledge-based engineering to identify high-level problem statements, derive detailed technical problem definitions, and build digital twins by executing knowledge-guided workflows, combining physics-based and data-based models to create an integrated digital twin for solving plant monitoring and optimization issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing approaches for building digital twins are used, then domain expertise and customization are achieved, but development time and effort increase significantly
Solution Approach 1:
The patent pre-configures multiple problem type specific workflows with predefined tasks, parameters, and logic before actual digital twin development begins. These workflows include problem definition workflows, data collection workflows, model selection workflows, and validation workflows that are prepared in advance and can be automatically executed when a new digital twin project is initiated, eliminating the need to start from scratch for each project
Solution Approach 2:
The patent divides the digital twin development process into discrete, modular problem types (e.g., fault detection, predictive maintenance, process optimization) with dedicated workflows for each. Each workflow is further segmented into independent tasks that can be executed separately and combined, allowing selective application of workflows based on specific project requirements while maintaining overall process structure
2Adaptability or versatility
If custom digital twin solutions are developed for each plant, then specific plant requirements are met, but scalability is reduced
Solution Approach 1:
The patent creates a universal digital twin development platform that handles multiple problem types and plant configurations through a single integrated system. The platform includes a repository of reusable workflows, parameters, and logic that can be applied across different plants and industry types, allowing the same infrastructure to serve diverse customization needs without requiring separate development processes for each plant
3Reliability
If comprehensive workflows are implemented, then problem solving capability is enhanced, but system complexity increases
Solution Approach 1:
The patent introduces an intermediary layer of problem type specific workflows that act as mediators between high-level problem statements and detailed digital twin implementation. These workflows contain predefined logic, parameters, and task sequences that automatically handle the complexity of problem solving, allowing users to initiate solutions with simple inputs while the intermediary workflows manage the sophisticated processing in the background
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Existing approaches for building digital twins specific to industrial plants require industry domain experts, process modeling engineers, data scientists, and solution developers to spend considerable time and effort to build the right solution. This is not an easily reproducible process. For each type of industry and for each specific plant, the design, and development process must start all over, more or less from scratch and the effort needs to be reinvested. Hence this is not a scalable proposition. Method and system disclosed herein provide a knowledge-based plant monitoring and optimization approach. In this approach, for a given high-level problem statement, a detailed problem definition is derived, a plant view of interest is identified using the knowledge based approach, and in turn plant data of interest is identified. Further, a digital twin is generated using the plant data of interest, which is then used for the plant monitoring and optimization.