Paper presented at Model-Based Safety and Assessment

Project partner University of Hull has presented a technical paper at the 8th International Symposium on Model-Based Safety and Assessment (IMBSA) held in Munich, Germany. The paper titled: A Deep Learning Framework for Wind Turbine Repair Action Prediction Using Alarm Sequences and Long Short Term Memory Algorithms addresses the use of Deep Learning (DL) to the domain of offshore energy generation, and in particular the use of Condition-based monitoring (CBM) for developing alarm-based systems and data-driven decision making. The paper provides insights into research being conducted in this area, with a specific focus on alarm sequence modelling and the associated challenges faced in its implementation. The paper proposes a novel idea to predict a set of relevant repair actions from an input sequence of alarm sequences, comparing Long Short-term Memory and Bidirectional LSTM models, along with the training accuracy results achieved providing a strong indication of the potential benefits of the proposed approach based on technologies developed in the SESAME project.