PLC Semantic Context Models for Reusable Automation Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems for data analytics in automation systems face challenges in contextualizing data effectively, requiring significant effort to specify and formalize contextual information, leading to non-standardized applications that are specific to customers or domains, and are not easily adaptable to changes in automation infrastructure or reusable across different settings.
Innovation Solution
The use of semantic models expressed in standardized, formal, domain-independent languages to add context to data at the point of generation, enabling persistent contextualization for later analysis, and employing technologies like RDF(S) and OWL for knowledge representation, allowing dynamic integration and access to contextualized information using standardized interfaces like SPARQL.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If contextual information is statically defined by application engineers during development, then data analytics algorithms can be implemented, but the effort required to specify and formalize contextual data is huge and the applications are not reusable
Solution Approach 1:
The PLC system automatically generates and maintains contextual information using semantic models and ontologies. The system self-describes its data structures, relationships, and meanings through standardized semantic representations, eliminating the need for manual contextualization by application engineers while maintaining data analytics accuracy
Solution Approach 2:
The patent implements a universal semantic model framework that can represent contextual information across different automation systems and applications. This standardized approach allows the same contextualization mechanisms to serve multiple purposes and systems, making applications reusable without additional customization
2Adaptability or versatility
If contextual data is customized for particular customers or domains, then specific analytics requirements are met, but standardization is lost and applications cannot be reused without additional customization
Solution Approach 1:
The system uses configurable semantic model parameters and ontology properties that can be adjusted to meet specific customer or domain requirements. By changing parameters within the standardized framework rather than redesigning the entire system, the patent achieves both customization and reusability
Solution Approach 2:
The contextual information is segmented into modular semantic models and ontology components that can be independently configured, selected, and combined. This modular approach allows specific portions to be customized for particular applications while maintaining the overall standardized framework for reusability
3Reliability
If manual effort is used to adapt existing applications to changes in automation infrastructure, then applications remain functional, but the adaptation process requires significant manual effort
Solution Approach 1:
The semantic models and contextual information are designed to be dynamic and automatically adaptable to changes in automation infrastructure. When new sensors or actuators are added, the system automatically generates corresponding semantic representations and updates relationships, maintaining application functionality without manual intervention
Solution Approach 2:
The system continuously monitors changes in the automation infrastructure and automatically adjusts contextual information and semantic models in response. This feedback mechanism ensures applications remain functional by detecting infrastructure changes and adapting the semantic representation accordingly
4Quantity of substance
If contextual data is not made available in a standardized format, then data can be stored internally, but service providers and third parties cannot easily access and utilize the data
Solution Approach 1:
The patent introduces standardized semantic models and ontologies as intermediaries between internal data storage and external access requirements. These semantic layers translate internal data representations into standardized, machine-readable formats that service providers and third parties can easily access and utilize while maintaining comprehensive data availability
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of contextualizing automation system data in an intelligent programmable logic controller includes the intelligent programmable logic controller collecting automation system data and creating a structured representation of the automation system data. The intelligent programmable logic controller selects a semantic context model from a plurality of available semantic context models based on relevance to the structured representation of the automation system data and creates semantically contextualized data using the semantic context model and the structured representation of the automation system data. The semantically contextualized data is stored by the intelligent programmable logic controller on a non-volatile computer-readable storage medium operably coupled to the intelligent programmable logic controller.