Publication
Agent-Based Communication for Fault Diagnosis in Skill-Based Production Environments Using Messages Based on I4.0 Language and Asset Administration Shells
Pascal Rübel; William Motsch; Alexis T. Bernhard; Simon Jungbluth; Martin Ruskowski
In: Kosmas Alexopoulos; Sotiris Makris; Panagiotis Stavropoulos (Hrsg.). Advances in Artificial Intelligence in Manufacturing II. European Symposium on Artificial Intelligence in Manufacturing (ESAIM-2024), Cham, Pages 157-170, ISBN 978-3-031-86489-6, Springer Nature Switzerland, 2025.
Abstract
Small batch sizes and individualized products are managed with the concept of Cyber-Physical Production Systems (CPPS), enabling flexibility through interchangeable constellations, but increases complexity, especially when dealing with dependencies between decentralized subsystems. To increase the resilience and self-healing capabilities, greater automation of fault detection and diagnosis (FDD) is a key factor. It is a challenge to gather knowledge about faults, as these rarely occur compared to normal behavior. The flexibility in skill-based production systems makes this situation even more difficult. To overcome this challenge, data and knowledge about faults and their context from several Cyber-Physical Production Modules is used, which leads to federated knowledge databases. The knowledge databases are modeled in the Capability-Skill-Service-Fault-Symptom model (CSSFS model). To achieve the goal of high availability, resilience and autonomy of CPPS, automated decision-making for FDD using CSSFS applications is required. Therefore, automatic communication between FDD components is necessary. Therefore, focus of this paper is on the development of a communication scheme, which models participants using Asset Administration Shells and the I4.0 Language to model their interactions to enable automated communication and makes distributed knowledge accessible. To ensure decentralized control of these services, functionalities from several factory levels are encapsulated by Multi-Agent Systems (MAS) that follow a holonic structure.