The two power sources of a fuel cell electric vehicle (FCEV) are proton electrolyte membrane fuel cell (PEMFC) and Liion battery (LIB). The health status of PEMFC and LIB decreases with the use of FCEV, so the energy management strategy (EMS) needs to give an optimal power distribution based on the health status of power sources throughout the lifetime. However, rule-based control strategies cannot achieve this. To prolong the service lifetime of two power sources by optimizing power distribution, this article proposes a long-term energy management strategy (LTEMS) for FCEV, which contains a reinforcement learning module and an improved thermostat controller. By designing a reward function, the reinforcement learning module outputted various LIB state of charge (SOC) boundary which changes with power source attenuation. Based on SOC boundary, the improved thermostat controller will control the fuel cell current under specific driving conditions. Simulation was carried out based on different LIB state of health (SOH) and external temperature, and the simulation results were compared with the data collected from FCEV under rule-based (RB) strategies. It can be found that the proposed LTEMS can effectively reduce fuel cell and LIB attenuation, and meet the FCEV power demand.
The problem of low accuracy and low convenience in the existing state of health (SOH) estimation method for vehicle lithium-ion batteries has become one of the important problems in the electric vehicle field. This paper proposes an improved cuckoo search particle filter (ICS-PF) algorithm based on a charging time segment from equal voltage data to estimate battery health status. Appropriate voltage ranges of charging time segments are selected according to the battery charging law, and in the meantime, the charging time segments are collected as a health indicator to establish the corresponding relationship with battery capacity attenuation value. An improved cuckoo search particle filter algorithm based on the traditional particle filter (PF) and cuckoo search (CS) algorithm is proposed by enhancing the search step size and discovery probability to estimate the capacity attenuation. The estimation result shows that this method is superior to the traditional particle filter and cuckoo search particle filter (CS-PF) method, as the maximum estimation error is less than 2%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.