Adaptive Digital Twin Modeling for Continuous Industrial Processes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing industrial processes face challenges in creating a digital twin that effectively monitors and optimizes large-scale, dynamically changing processes due to integration complexities and the inability to leverage data for comprehensive insights, leading to conflicting operational strategies and lack of holistic process understanding.
Innovation Solution
A method and system for generating an adaptive simulation model that integrates processing station layouts and data interfaces, using exporters to create an information metamodel that aggregates and structures data from various stations, enabling a digital twin for dynamic monitoring and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a digital twin is created to monitor industrial processes, then connectivity of assets and homogenization of data is improved, but integration of non-static industrial processes becomes challenging and device complexity increases
Solution Approach 1:
The patent segments the digital twin into multiple hierarchical levels (process level, asset level, component level) to manage complexity. Each level handles specific data types and integration requirements, allowing non-static processes to be monitored without overwhelming integration complexity at any single level.
Solution Approach 2:
The patent introduces an information model as an intermediary layer between the physical industrial process and the digital twin representation. This information model standardizes data exchange formats and interfaces, enabling homogeneous data integration while reducing the complexity of direct integration between diverse process components.
2Productivity
If separate processing stations are optimized individually, then operational efficiency at each station is improved, but conflicting operational strategies arise and holistic process understanding is lost
Solution Approach 1:
The patent merges individual processing station models into a unified digital twin that represents the entire industrial process. This allows optimization at the station level to be coordinated with overall process goals, preventing conflicting strategies while maintaining local efficiency improvements.
Solution Approach 2:
The patent implements feedback loops where the digital twin continuously monitors process data and provides insights back to operational decisions. This enables holistic process understanding to inform individual station optimizations, ensuring that local efficiency improvements align with global process objectives.
3Productivity
If digital twin data is leveraged for comprehensive insights, then process optimization is improved, but the ability to adequately leverage data related to material flow is currently insufficient
Solution Approach 1:
The patent performs preliminary actions by establishing a comprehensive information model structure that anticipates future data needs for material flow analysis. The digital twin is designed with pre-configured data collection points and processing capabilities for material flow tracking, enabling comprehensive insights when material flow data becomes available.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
According to an aspect, a method for monitoring a continuous industrial process is described. The industrial process includes a number of processing stations for processing: material and a material flow between the number of processing stations. Each processing station dynamically provides data, representing a state of the processing station. The method includes providing, for each processing station, a processing station layout of the processing station. The method further includes providing, for each processing station,.an interface model of the processing station. The method, further includes generating an information metamodel from the processing station layout and the interface model of the number of processing stations. The method further includes generating an adaptive simulation model of the industrial process by importing the data representing· the state of the processing station provided by the number of processing stations into the adaptive simulation model via the information metamodel.