Application of OWL ontologies and LSTM networks in searching for anomalies of time series

The paper describes the results of the development of an algorithm for detecting anomalies in time series, taking into account the specifics of the subject area. The algorithm involves finding a time series forecast using LSTM networks, detecting anomalies based on the obtained forecast, filtering the found anomalies in accordance with possible deviations of the time series values from the trend reflected in the ontology, and logically deriving search results using a set of SWRL rules. The effectiveness of the proposed approach has been confirmed by a number of experiments conducted on the benchmark of data on the operation of oil rigs.