Mitigating Undesired Conditions in Flexible Production with Product-Process-Resource Asset Knowledge Graphs

TL;DR

This paper introduces a semantic knowledge graph model for flexible industrial production systems that enhances analysis and mitigation of undesired conditions, integrating semantic tech with large language models for intuitive human interaction.

Contribution

The paper presents a comprehensive PPR-AKG model based on industry standards and combines it with LLMs, enabling improved analysis and human interaction in flexible CPPS.

Findings

Efficient support for resource allocation based on explicit capabilities.

Effective identification and mitigation of undesired conditions.

Enhanced human interaction through LLM-based chatbots.

Abstract

Contemporary industrial cyber-physical production systems (CPPS) composed of robotic workcells face significant challenges in the analysis of undesired conditions due to the flexibility of Industry 4.0 that disrupts traditional quality assurance mechanisms. This paper presents a novel industry-oriented semantic model called Product-Process-Resource Asset Knowledge Graph (PPR-AKG), which is designed to analyze and mitigate undesired conditions in flexible CPPS. Built on top of the well-proven Product-Process-Resource (PPR) model originating from ISA-95 and VDI-3682, a comprehensive OWL ontology addresses shortcomings of conventional model-driven engineering for CPPS, particularly inadequate undesired condition and error handling representation. The integration of semantic technologies with large language models (LLMs) provides intuitive interfaces for factory operators, production planners, and engineers to interact with the entire model using natural language. Evaluation with the use case addressing electric vehicle battery remanufacturing demonstrates that the PPR-AKG approach efficiently supports resource allocation based on explicitly represented capabilities as well as identification and mitigation of undesired conditions in production. The key contributions include (1) a holistic PPR-AKG model capturing multi-dimensional production knowledge, and (2) the useful combination of the PPR-AKG with LLM-based chatbots for human interaction.