Digital Twin Updating Through Cross-Source Semantic Annotation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating and updating digital twins for complex physical systems is a time and resource-intensive process due to the heterogeneity and disjoint nature of available data from various sources, which often requires manual human-driven data entry and lacks efficient data consolidation.
Innovation Solution
A method and system that repeatedly extracts and semantically annotates data from multiple conjoint data sources, using previously annotated data to enrich and export information into a digital twin system, creating or updating a digital representation of the physical system, while maintaining a modular and expandable structure to accommodate various data sources and formats.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual human-driven data entry is used to import data from multiple conjoint data sources, then data consolidation can be performed, but the process becomes time and resource-intensive
Solution Approach 1:
The patent replaces manual human-driven data entry with an automated computer-based system that extracts and semantically annotates data from multiple conjoint data sources. The processor automatically performs data import, consolidation, and annotation tasks that previously required human operators, thereby eliminating the time and resource constraints while maintaining data consolidation accuracy through systematic automated processing.
Solution Approach 2:
The system enables self-service by allowing the digital twin creation process to autonomously extract data from multiple data sources, perform semantic annotation, and consolidate information without requiring continuous human intervention. The automated processor serves itself by systematically managing the entire data import and consolidation workflow, reducing both time consumption and resource requirements.
2Loss of information
If all available information about a physical system is copied to a digital environment, then a complete digital twin is created, but the process becomes resource straining for complex systems
Solution Approach 1:
The patent extracts only the necessary data from multiple conjoint data sources rather than copying all available information. The systematic extraction process identifies and retrieves relevant data instances from engineering data, runtime data, accounting information, and other sources, filtering out redundant information and reducing the overall data processing complexity while maintaining digital twin completeness.
Solution Approach 2:
The patent segments the data import and consolidation process into distinct automated steps: data extraction from individual sources, semantic annotation of extracted data, and systematic consolidation into the digital twin. This segmentation of the complex process into manageable automated stages reduces device complexity by making each step independent and programmable, while ensuring all necessary information is captured.
3Adaptability or versatility
If data from heterogenous sources with different semantics is imported, then comprehensive data coverage is achieved, but manual data entry efforts increase
Solution Approach 1:
The patent implements a universal automated data import system that can handle multiple heterogenous data sources with different formats and semantics. The processor is designed to systematically extract data from various conjoint data sources including engineering data, runtime data, and accounting information, applying consistent semantic annotation rules across all sources. This multi-functional approach maintains data source compatibility while dramatically improving data import efficiency by eliminating manual entry requirements.
Solution Approach 2:
The patent applies parameter changes by systematically transforming data from different sources into a unified semantic framework. The automated system changes the state of imported data by applying consistent semantic annotations and normalization rules, converting heterogenous data formats into a standardized structure that improves productivity while maintaining adaptability to various data sources.
Data Source
AI summary
To create or update a digital twin modeling a physical system, data from several conjoint data sources are repeatedly extracted and semantically annotated, wherein semantic annotations of data that have been extracted from a first conjoint data source are influenced by previously extracted and semantically annotated data from at least one other conjoint data source. The semantically annotated data are used to create or update the digital twin. This provides a modular and easily expandable solution for enriching a digital twin from a plurality of conjoint data sources with heterogenous data. Processing of different data sources does not happen isolated from one another while the system remains modularly expandable to new data sources. Compared to previous approaches, instead of creating yet another stand-alone digital representation of the physical system that is not compatible with already existing solutions, these solutions are augmented with a modular data management pipeline.