An ontology-based approach for decentralized monitoring and diagnostics

Modern decentralized industrial applications demand the design of application-independent solutions for monitoring and diagnostics systems (MDSs) that exhibit a high degree of flexibility and re-utilization. To achieve this, we propose an ontology-based approach that adheres to the Meta Object Facility (MOF) paradigm for engineering and maintenance of MDSs. The key of our approach is to built a decentralized system architecture implemented on a semantic technology stack. Our architecture allows for storing plant engineering expert knowledge and the monitoring and diagnosis rules in formalized OWL models. The plant models can then be processed by the rules to compute monitoring states and diagnose causes of faults. This paper specifically focuses on a system implementation in alignment to requirements of the industrial domain. Based on these requirements, alternative knowledge-based tools and techniques are compared to evaluate the effectiveness of our approach.