Abstract: This proposal presents the creation of a framework that combines deep learning-based anomaly detection with ontology-driven knowledge representation to improve fault diagnosis in oil and gas production plants. The framework aims to leverage the strength of both techniques to reduce false alarm rates and to provide operators with more comprehensive information for decision-making.

Keywords: Anomaly Detection, Ontology, Oil and Gas, Time-Series, Framework

Authors: Gustavo Alexsandro de Lima and Mara Abel

Journal/Conference:  Doctoral and Masters Consortium on Ontologies – Ontology Research in Brazil (ONTOBRAS)

Publication: https://ceur-ws.org/Vol-3905/master6.pdf