| Abstract | Energy efficiency, emissions and vessel generated noise data from the field trials of more than 20 workboats spanning over a six years period were collected and analyzed. Results suggest that GHGs as well as local air and water pollution produced by the operations of smaller coastal vessels, can be significant. Operational profiles or duty cycle data indicate that vessel efficiencies vary considerably throughout a typical trip. Understanding under which operational conditions offer higher efficiencies and inefficiencies can enable operators to make operational changes to improve energy efficiency and reduce emissions. The Glas Ocean Electric (GOE) team in collaboration with the National Research Council of Canada (NRC), Cranfield University (CU) and Deep Sense at Dalhousie University, and with funding support from Transport Canada (TC), the Defense Advanced Research Projects Agency (DARPA), the Royal Canadian Navy IDEaS program, have been developing a system using machine learning techniques that enables the prediction of operational conditions for vessels. This system, operating at a granular level and responding in real-time, can be integrated with a broad range of sensors under the Internet of Things (IoT) framework to provide a comprehensive understanding of operations, offer optimised efficiency and enable reduced emissions.This paper presents:•a subset of data collected during;•the process followed to develop a prototype system that has the potential to–reduce emissions;–act as a third party emissions monitor;–provide duty cycles to be used in the development of alternative propulsion systems such as battery electric and hybrid and;–optimize operations in real-time. |
|---|
