Device-Level Data Modeling for Industrial Data Contextualization
Find Innovative SolutionsGenerate 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
Engineering 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
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.
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.
2Productivity
If centralized data processing is used without device-level models, then system architecture is simple, but data contextualization efficiency is low
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.
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.
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
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.
Data Source
Figure 1
Figure 2a
Figure 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.