Digital Twin Smart Tags for AI Model Validation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Industrial automation systems face challenges in collecting and formatting data from distributed industrial devices into a unified, meaningful presentation, particularly due to the highly distributed nature of data across various industrial machines or systems, leading to uncontextualized and unstructured data that requires significant effort to render meaningful to users.

Innovation Solution

The implementation of a system that supports structured data types, referred to as Basic Information Data Types (BIDTs), which include state, rate, odometer, and event data types, allowing for the definition of data tags with user-configurable metadata, enabling contextualized presentations of industrial data through hierarchical asset models and gateway devices that aggregate and visualize this data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If data is collected from distributed industrial devices without structured formatting, then data collection coverage is improved, but data usability and contextualization deteriorate

Engineering Contradiction:
Improvedata collection coverageVSAvoiddata contextualization
Core Design Contradiction:
Quantity of substanceVSLoss of information

Solution Approach 1:

The patent segments data into structured Basic Information Data Types (BIDTs) including state, rate, odometer, and event types. Each data point from distributed devices is categorized into specific segments with defined metadata schemas, transforming unstructured data streams into organized, contextualized information units that maintain meaning while enabling comprehensive collection.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary layer of data normalization and contextualization services between distributed industrial devices and the digital twin system. This intermediary processes raw data, applies BIDT schemas, and enriches data with contextual metadata, preventing information loss while maintaining broad data collection capabilities across heterogeneous devices.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If a unified data presentation system is implemented, then data usability is improved, but system complexity increases

Engineering Contradiction:
Improvedata usabilityVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent implements a universal BIDT framework that serves multiple functions simultaneously: data collection, validation, contextualization, storage, and presentation. This single unified schema system handles diverse data types from various industrial devices through a common interface, improving usability without proportionally increasing complexity through standardized multi-functional components.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent applies parameter changes by transforming raw industrial data into standardized BIDT parameters with defined properties and metadata. This parameterization approach creates a consistent data representation layer that simplifies presentation while the underlying standardization reduces the complexity burden of handling diverse data sources.

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If AI analysis is applied to identify key variables and relationships, then predictive analytics capability is improved, but computational requirements increase

Engineering Contradiction:
Improvepredictive analytics capabilityVSAvoidcomputational requirements
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The patent performs preliminary action by pre-processing and structuring data into BIDTs with embedded metadata and relationships before AI analysis. Key variables and their relationships are pre-identified and organized during data collection and normalization phases, reducing the computational burden on AI algorithms by presenting pre-curated, context-rich data structures rather than raw unprocessed data.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The BIDT framework enables self-service by embedding contextual metadata, data relationships, and validation rules directly within data structures. This self-describing data format allows AI systems to autonomously understand data meaning and relationships without requiring extensive preprocessing or feature engineering, reducing computational requirements while enhancing predictive analytics capability.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3696622B1Ai extensions and intelligent model validation for an industrial digital twin
Publication Date: 2024.07.31 ROCKWELL AUTOMATION TECH INC
  • EP3696622B1 patent drawingFigure 1
  • EP3696622B1 patent drawingFigure 2
  • EP3696622B1 patent drawingFigure 3

AI summary

Industrial smart data tags conforming to structured data types serve as the basis for creating a digital twin of an industrial asset. The digital twin can comprise an automation model and a mechanical model or other type of non-automation model, both of which reference the smart tags in connection with digitally modeling the industrial asset. The structured data topology offered by the smart tags allows the digital twin to be readily interfaced with artificial intelligence (AI) systems. AI analysis can leverage the smart tags to discover new relationships between key performance indicators and other variables of the asset and encode these relationships in the smart tags themselves. These enhanced smart tags can also be leveraged to perform Al-based validation the digital twin. Additional contextualization provided by the enhanced smart tags can simplify AI analysis and assist in quickly converging on desired analytic results.