3D Digital Twin Synchronization for Automated As-Built Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current digital twin synchronization methods are manually driven and error-prone, leading to delays in factory design and simulation processes due to the lack of an automated method for updating as-built representations of factory assets.
Innovation Solution
An automated model-based guided digital twin synchronization system using visual sensors, machine learning, and graph-based tools to generate and maintain an as-built digital twin, compare it with an as-planned twin, and automatically update changes in the digital twin based on spatio-temporal differences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual synchronization methods are used to update digital twin representations, then human workers can perform routine inspection jobs, but the process is highly error-prone and causes delays in work cell design and simulation processes
Solution Approach 1:
The patent replaces manual mechanical inspection processes with an automated computer-based system that uses visual sensors, machine learning models, and automated comparison algorithms to detect and synchronize changes between physical work cells and digital twin representations, eliminating human error and accelerating the synchronization process
Solution Approach 2:
The system enables self-service automation where the digital twin synchronization process performs its own verification and validation through automated comparison of as-built representations with design models, eliminating the need for manual verification steps and reducing errors
2Productivity
If automated digital twin synchronization is implemented, then round-trip time in reconfiguration is reduced and productivity increases, but the system complexity and device complexity increase
Solution Approach 1:
The patent implements a multi-functional automated system that performs visual data capture, machine learning-based change detection, automated comparison with design models, verification, validation, and digital twin synchronization all through a single integrated system, enabling high productivity while managing complexity through functional consolidation
Solution Approach 2:
The system creates and maintains digital copies (digital twins) of physical work cells that can be automatically updated and compared, allowing rapid reconfiguration analysis and simulation without physically reconfiguring the actual production line, thereby increasing productivity while keeping the physical system simple
3Measurement precision
If manual spatio-temporal difference analysis is performed, then detailed verification can be done, but the process is slow and delays incremental updates
Solution Approach 1:
The patent replaces manual visual inspection and comparison methods with automated computer-based image processing and machine learning algorithms that can rapidly analyze spatio-temporal differences between as-built and design representations with high precision, simultaneously improving both accuracy and speed of update detection
Solution Approach 2:
The system introduces an automated machine learning-based comparison engine as an intermediary between visual sensor data and digital twin updates, enabling rapid and precise detection of changes without requiring manual analysis, thus accelerating the update process while maintaining measurement precision
Data Source
AI summary
An automated model based guided digital twin synchronization system is described. The system comprises visual sensors configured to acquire raw visual data of a physical 3D scene content from a real site, a database to provide a 3D model of the physical 3D scene content, a processor and a memory for storing computer-executable instructions executed by the processor. The instructions comprise an automated machine learning model based logic to: generate and maintain an as-built digital twin of the assets and large-scale infrastructures present in the physical 3D scene by ingesting the raw visual data to a common and binding structured representation, compare the as-built digital twin representation obtained from the real site against corresponding an as-planned digital twin to determine spatio-temporal differences between the as-built and the as-planned digital twins, and update automatically the as-planned digital twin to reflect any changes to the physical 3D scene based on the spatio-temporal differences.