Industrial Semantic Model Instantiation for Legacy Data Diagnostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In industrial infrastructures, service engineers face significant time-consuming challenges in diagnosing issues within complex legacy systems due to the need for manual investigation across large, siloed data sets, requiring extensive manpower and technical expertise to maintain proper operation.
Innovation Solution
A method and apparatus that create an instantiated industrial semantic model by receiving data from industrial infrastructure components, deriving types of components based on characteristics, mapping them to context models, and instantiating a knowledge graph for seamless data access and integration, using predefined knowledge models to automate data mapping and connection across unrelated data sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual investigation of siloed data sets is performed, then comprehensive diagnostic results can be obtained, but time consumption and manpower requirements increase significantly
Solution Approach 1:
The patent introduces an intermediary layer (semantic model with context models and instance models) that mediates between raw siloed data and diagnostic queries. This intermediary automatically joins data from multiple sources using predefined semantic relationships, eliminating the need for manual investigation while preserving diagnostic completeness.
Solution Approach 2:
The system performs preliminary action by pre-defining context models and instance models that encode domain knowledge and data relationships in advance. When a diagnostic query is made, the pre-established semantic models automatically retrieve and join relevant data without requiring real-time manual analysis.
2Loss of information
If customized queries are formulated for each legacy system, then comprehensive diagnostic information can be retrieved, but system complexity and query formulation difficulty increase
Solution Approach 1:
The patent creates a universal semantic model framework that can handle multiple legacy systems through a common interface. The context models and instance models provide a unified way to represent data from different sources, allowing a single query approach to work across diverse systems without requiring system-specific customization.
Solution Approach 2:
The semantic model acts as an intermediary that translates diverse legacy system data into a unified representation. This intermediary layer handles the complexity of data joining and integration, presenting a simplified interface to users while maintaining comprehensive information retrieval capabilities.
3Loss of information
If data from multiple siloed sources are integrated manually, then a comprehensive view of industrial infrastructure can be achieved, but automation level and operational efficiency decrease
Solution Approach 1:
The system implements self-service by enabling automatic data integration through predefined semantic models. The context models and instance models automatically join data from multiple siloed sources based on encoded relationships, eliminating manual integration efforts while achieving comprehensive data coverage.
Solution Approach 2:
The patent performs preliminary action by pre-defining the semantic relationships and data models that encode how different data sources should be integrated. This preliminary configuration enables automated, high-level integration operations without requiring manual intervention during actual data retrieval and joining operations.
Data Source
AI summary
Provided is an apparatus and method for providing an instantiated industrial semantic model, iISM, for an industrial infrastructure having data generation components, the apparatus including: an interface unit adapted to receive from an industrial infrastructure data generated by data generation components provided within the industrial infrastructure, a context management unit adapted to derive types of data generation components provided within the industrial infrastructure depending on characteristics of the received data and adapted to map each derived type of data generation component to an associated context model specified in the industrial semantic model, ISM, stored in a repository, and an instantiating unit adapted to instantiate the stored industrial semantic model, ISM, with predefined industrial instance models, IIMs, of data generation components on the basis of the mapped context models to generate the instantiated industrial semantic model, iISM, of the industrial infrastructure.