Production Operability Monitoring via Knowledge Graph Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing material flow simulations in production systems face challenges due to cumbersome data generation and synchronization, inconsistencies in data sources, and inefficient validation, leading to erroneous results and increased time and cost in simulation model development.
Innovation Solution
An apparatus and method utilizing a knowledge graph with declarative constraints to validate and integrate production data, generating simulation models, and comparing simulated logs with measured logs to monitor operability, employing SHACL and SPARQL for data consistency and integrity checks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual data integration and validation methods are used for simulation model generation, then data consistency can be checked, but the process becomes time-consuming and requires frequent exchange meetings between experts
Solution Approach 1:
The patent applies preliminary action by performing automated data validation and consistency checks before simulation model generation. The system validates production data against the knowledge graph schema in advance, identifying inconsistencies before they affect simulation results, thereby eliminating the need for time-consuming manual review meetings while ensuring data reliability
Solution Approach 2:
The patent replaces manual mechanical processes (expert review meetings, manual data integration) with an automated computational system. The validation engine automatically compares production data against the knowledge graph schema using computational algorithms, substituting human expert time with automated validation that ensures data consistency without requiring frequent exchange meetings
2Measurement precision
If comprehensive validation of production data is performed, then simulation accuracy improves, but the complexity of the data processing pipeline increases
Solution Approach 1:
The patent introduces a new dimension to data validation by organizing production data into a structured knowledge graph with schemas that define expected data formats, relationships, and constraints. This dimensional organization allows comprehensive validation without increasing processing complexity, as the schema-based approach provides a systematic framework for validating diverse data sources simultaneously
Solution Approach 2:
The patent applies universality through a reusable knowledge graph schema that can validate multiple types of production data (machine data, process data, quality data) using a single unified framework. The schema serves multiple validation functions across different data sources, reducing overall system complexity while maintaining comprehensive validation capabilities that ensure simulation accuracy
3Adaptability or versatility
If heterogeneous data sources are integrated into the simulation model, then the model becomes more comprehensive, but data synchronization becomes cumbersome
Solution Approach 1:
The patent introduces a knowledge graph as an intermediary layer between heterogeneous production data sources and the simulation model. The knowledge graph schema acts as a mediator that standardizes data from various sources (ERP, MES, machine sensors) into a unified structure, enabling comprehensive data integration without direct complex synchronization between all data sources, thereby reducing synchronization complexity while maintaining adaptability
Data Source
AI summary
An apparatus comprising: an input unit to receive production-related data of the production system; a mapping engine to map the production-related data to instance data of a first knowledge graph according to a given mapping definition; a first validation unit to validate a consistency and/or an integrity of the instance data using declarative constraints and to output a first validation result; a simulator to generate a computer-implemented material flow simulation model of the production system based on the instance data and depending on the first validation result; a generator to generate simulated production logs using the material flow simulation model; a second validation unit to validate the simulated production logs against measured production logs of the production system and to output a second validation result; and an output unit to output the second validation result for monitoring the operability of the production system.