Semantically-Enhanced Rule-Based Diagnostics for Industrial Internet of Things: The SDRL Language and Case Study for Siemens Trains and Turbines

SemML: Facilitating Development of ML Models for Condition Monitoring with Semantics

“…The quality indicators of welding systems provided by Bosch are monitored by analytic methods [31] or destructive methods [29,30]. For machinery monitoring examples include data-driven monitoring of trains [21] and turbines [15] in Siemens. In the Oil and Gas industry [36], examples includes equipment and process monitoring in off-shore platforms and oil reservoirs at Equinor [14].…”

“…In this work we address the C1-C3 challenges by enhancing machine learning development for condition monitoring with semantic technologies. Note that semantics has recently gained a considerable attention in industry in a wide range of applications and automation tasks such as modelling of industrial assets [12] industrial analytics [13], integration [14][15][16] and querying [17][18][19] of production data, process monitoring [20] and equipment diagnostics [21], moreover, semantic technologies have been adopted or evaluated in a number of large high tech production companies such as Equinor [22], Siemens [23], Festo [24], and Bosch [25,26].…”

Temporal Ontology-Mediated Queries and First-Order Rewritability: A Short Course

“…The technique considered above does not seem to work for (two-sorted) conjunctive queries in place of instance queries; on the other hand, the methods of [7] OMAQs. On the practical side, more real-world use cases are needed to understand which temporal constructs are required to specify relevant temporal events and evaluate the performance of OMQ rewritings; for some activities in this direction we refer the reader to [17,58,25,24].…”

A Framework for Evaluating Snippet Generation for Dataset Search

“…Existing evaluation metrics used in related fields such as snippet generation for ontologies [28] and documents [16] are mainly based on a human-created ground truth. However, an RDF dataset may contain millions of RDF triples, e.g., when it wrapped from a large database [23,18,19,33], or streaming data [25,24], or comes from a manufacturing environment [37,22,26] being much larger than an ontology schema or a document. It would be difficult, if not impossible, to manually identify the optimum snippet as the ground truth.…”