Digital Twin Generation from Automated Component Data Clustering

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for creating digital twins require pre-existing digital structures and subelements, limiting their applicability to installations or factories without finished digital modules, and necessitate manual compilation of cluster structures from engineering data.

Innovation Solution

A method that identifies and clusters automation engineering data by component types or IDs, allowing for the creation of a digital twin without prior digital models, using data sources like automation engineering, MCAD, ECAD, robotics, and description data, and storing the digital twin in various database formats such as relational or NoSQL databases.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If pre-existing digital structures and subelements are required to create a digital twin, then the digital twin can be constructed from standardized modules, but this limits applicability to installations or factories without finished digital modules

Engineering Contradiction:

Improveease of digital twin creationVSAvoidapplicability to different installations

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The patent segments automation engineering data into component data clusters, where each cluster represents a specific component or subsystem. This segmentation allows the digital twin to be built from discrete, identifiable data groups rather than requiring pre-assembled digital modules, enabling creation for installations without existing digital models.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of starting with pre-existing digital structures and adding details, the patent inverts the approach by starting with raw automation engineering data and automatically generating the digital twin structure through clustering algorithms. This inversion eliminates the requirement for pre-existing digital modules while maintaining systematic organization.

Inventive Principle:

Principle #13The other way round (Inversion)

2Adaptability or versatility

If manual compilation of cluster structures is performed from engineering data, then the digital twin can be customized to specific installations, but this increases the complexity and time required for creation

Engineering Contradiction:

Improvecustomization to specific installationsVSAvoidtime for digital twin creation

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent implements self-service by enabling the automation engineering data to automatically organize itself into meaningful component data clusters through clustering algorithms. The system performs the compilation task that would otherwise require manual intervention, reducing creation time while maintaining the ability to capture installation-specific characteristics.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent changes the parameter of data organization from manual compilation to automated clustering based on data characteristics. By adjusting the clustering parameters and algorithms, the system adapts to different installation types and data formats, maintaining customization capability while eliminating manual labor.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If automated clustering of automation engineering data is performed, then the creation process is simplified and accelerated, but this requires sophisticated algorithms to accurately identify component data clusters

Engineering Contradiction:

Improvespeed of digital twin creationVSAvoidcomplexity of clustering algorithms

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent employs dynamic clustering algorithms that can adapt their parameters and strategies based on the characteristics of the input data. This dynamic approach allows the system to handle diverse automation engineering data efficiently without requiring overly complex fixed algorithms, balancing automation capability with computational efficiency.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20220334572A1Method for Generating a Digital Twin of a System or Device

Publication Date: 2022.10.20 SIEMENS AG

AI summary

A method for generating a digital twin of a system or device includes identifying component data clusters within the first data source, where the component data clusters are assigned or assignable component types or component ID information relating to the system or device, allocating a respective component type designation or a respective component ID information designation to at least one of the identified component data clusters, and generating and storing the digital twin of the system or device.