Semantic Framework for Industrial Analytics and Diagnostics / 4016
Gulnar Mehdi, Sebastian Brandt, Mikhail Roshchin, Thomas Runkler
Massive data streams from sensors and devices are prominent form of industrial data generated during condition-monitoring and diagnosis of complex systems. Data analytics and reasoning has emerged as a vital tool to harness massive data sets, providing insights into historical and real-time system conditions; enhanced decision support, reliability and cost reduction. However, application of data analytics is mainly challenged by the complexity of data-access, integration, domain-specific query support and contextual reasoning capabilities. The current state-of-the-art only uses dedicated scenarios and sensors, but this limits reuse, scalability and are not sufficient for an integrated solution. Our thesis investigates if semantic technology can be a potential solution to interact and leverage data analytics for operational use. First, we have studied related work and utilized ontology-based data access (OBDA) techniques for semantic interpretation of diagnosis for Siemens Turbine use-case. Secondly, we have extended our solution to support any analytical workflow by means of an ontology.