Economic factors along with legislation and policies to counter harmful pollution apply specifically to maritime drive research for improved power generation and energy storage.Proton exchange membrane fuel cells are ...Economic factors along with legislation and policies to counter harmful pollution apply specifically to maritime drive research for improved power generation and energy storage.Proton exchange membrane fuel cells are considered among the most promising options for marine applications.Switching converters are the most common interfaces between fuel cells and all types of load in order to provide a stable regulated voltage.In this paper,a method using artificial neural networks(ANNs)is developed to control the dynamics and response of a fuel cell connected with a DC boost converter.Its capability to adapt to different loading conditions is established.Furthermore,a cycle-mean,black-box model for the switching device is also proposed.The model is centred about an ANN,too,and can achieve considerably faster simulation times making it much more suitable for power management applications.展开更多
基金This work has been funded by the Helmholtz Alliance ROBEX–Robotic Exploration of Extreme Environments.The authors would also like to thank the National Science Foundation(NSF)and specifically the Energy,Power,Control and Networks(EPCN)program for their valuable ongoing support in this research within the framework of grant ECCS-1809182‘Collaborative Research:Design and Control of Networked Offshore Hydrokinetic Power-Plants with Energy Storage’.
文摘Economic factors along with legislation and policies to counter harmful pollution apply specifically to maritime drive research for improved power generation and energy storage.Proton exchange membrane fuel cells are considered among the most promising options for marine applications.Switching converters are the most common interfaces between fuel cells and all types of load in order to provide a stable regulated voltage.In this paper,a method using artificial neural networks(ANNs)is developed to control the dynamics and response of a fuel cell connected with a DC boost converter.Its capability to adapt to different loading conditions is established.Furthermore,a cycle-mean,black-box model for the switching device is also proposed.The model is centred about an ANN,too,and can achieve considerably faster simulation times making it much more suitable for power management applications.
