Device-Level Data Modeling for Industrial Data Contextualization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing industrial automation systems face challenges in efficiently contextualizing industrial data at the device level, which limits the ability to derive actionable insights from this data.

Innovation Solution

The implementation of an industrial device with a program execution component, smart tag configuration component, and data publishing component, which executes an industrial control program, sets contextualization metadata for smart tags, and sends data values and metadata to an external system for contextualization and analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If industrial data is collected from devices without device-level contextualization, then data collection is simple, but the ability to derive actionable insights is limited

Engineering Contradiction:
Improveloss of contextual informationVSAvoiddevice complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by implementing smart tags with contextualization metadata directly at the device level before data leaves the industrial device. The smart tag configuration component pre-associates metadata describing correlations between data values and business objectives with the relevant data tags, so that contextual information is embedded in advance rather than added later during centralized processing.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements self-service by enabling individual industrial devices to autonomously perform contextualization of their own data through the smart tag configuration component. Each device can independently define and attach contextualization metadata to its data tags without requiring external intervention, allowing devices to serve their own data contextualization needs.

Inventive Principle:
Principle #25Self-service

2Productivity

If centralized data processing is used without device-level models, then system architecture is simple, but data contextualization efficiency is low

Engineering Contradiction:
Improvedata contextualization efficiencyVSAvoidsystem architecture complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent applies segmentation by dividing the data contextualization function from centralized processing and distributing it to individual device levels. Each industrial device maintains its own smart tags with contextualization metadata, creating independent data models at the device level. This segmentation enables parallel processing of contextualization across multiple devices, improving overall efficiency.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces another dimension by adding the device-level data model layer between the raw data collection layer and the centralized processing layer. This intermediate layer operates at a different dimensional level (device level versus enterprise level), allowing contextualization to occur locally before data aggregation, thereby improving efficiency without oversimplifying the overall system architecture.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Loss of information

If all industrial data is transmitted to external systems for analysis, then comprehensive analysis is possible, but data transmission volume and processing overhead increase

Engineering Contradiction:
Improvepreservation of contextual informationVSAvoiddata transmission volume
Core Design Contradiction:
Loss of informationVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential contextualization metadata from the full data set and transmits it along with the data values to external systems. By separating the contextualization information from the raw data and transmitting only the relevant metadata, the system reduces transmission volume while preserving the necessary contextual information for analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP3798947B1Contextualization of industrial data at the device level
Publication Date: 2025.04.23 ROCKWELL AUTOMATION TECH INC
  • EP3798947B1 patent drawingFigure 1
  • EP3798947B1 patent drawingFigure 2a
  • EP3798947B1 patent drawingFigure 2b

AI summary

An industrial device supports device-level data modeling that pre-models data stored in the device with known relationships, correlations, key variable identifiers, and other such metadata to assist higher-level analytic systems to more quickly and accurately converge to actionable insights relative to a defined business or analytic objective. Data at the device level can be modeled according to modeling templates stored on the device that define relationships between items of device data for respective analytic goals (e.g., improvement of product quality, maximizing product throughput, optimizing energy consumption, etc.). This device-level modeling data can be provided to higher level systems together with their corresponding data tag values to high level analytic systems, which discovers insights into an industrial process or machine based on analysis of the data and its modeling data.