Solid oxide fuel cells for shipping: A machine learning model for early detection of hazardous system deviations

With rising concerns about the amount of pollutant emissions generated by shipping and the consequent pressure to curb the environmental impact of shipping activities, fuel cells are expected to take an important role in ship propulsion. In particular, Solid Oxide Fuel Cells (SOFCs) are envisaged to provide high electrical efficiency and offer the opportunity of combining heat and power production. This work deals with the safety issues related to the safety implications of the use of Fuel Cells in maritime applications. A machine-learning model for identifying and intercepting critical events, based on the early detection of the system weak signals, is developed and applied to a Solid Oxide Fuel Cell (SOFC) system. The model relies on a hybrid approach: a data-driven model based on gradient-boosted decision trees and a computational model of the SOFC system are integrated to enhance the data-driven approach by implementing physics-based knowledge to boost the resulting predictive capabilities. The outlined approach even if it requires further validation at the full scale may be considered a step forward in enabling the prediction of the conditions that may lead to an accident with remarkable accuracy.

Automated summary

With increasing concerns about shipping emissions and the need to reduce the environmental impact, fuel cells are expected to play a vital role in ship propulsion. Specifically, Solid Oxide Fuel Cells (SOFCs) are seen as offering high electrical efficiency and the ability to combine heat and power production. This study focuses on the safety implications of using fuel cells in maritime applications and develops a machine-learning model to detect critical events and enhance predictive capabilities for SOFC systems. This approach, although requiring further validation, represents a significant step towards accurately predicting accident conditions.