The cold start property is one of the main factors restricting the fuel cell application in the automotive field. The constant voltage cold start method of the fuel cell works under low start voltage and produces high heat, which can shorten the start-up time of the fuel cell at low temperature and has the opportunity to be applied to fuel cell vehicles. Meanwhile, in the constant voltage cold start mode, the fuel cell needs to operate under a large current, and more water is generated during the start-up process. Thus, the optimization of operating conditions for the constant voltage cold start is particularly important. However, there are relatively few studies on the optimization of operating conditions for the constant voltage cold start with a single-cell voltage less than 0.3 V. In this work, the cold start experiment of the fuel cell with constant voltage is carried out. According to the cold start experiment, the different cold start voltage, back-pressure, and the inlet flow rate are examined. Based on the experiment data, the operating conditions have a great influence on the cold start property of the fuel cell and the optimized operating conditions of the constant voltage cold start are obtained.

The durability of automotive fuel cells is one of the main factors restricting their commercial application. Therefore, establishing a remaining useful life (RUL) prediction model and developing an online operational method to apply it to the RUL optimization of fuel cell vehicles is an urgent academic problem. In this work, a short-term RUL prediction model and an online operation scheme for fuel cell vehicles are proposed. Firstly, based on historical data of a fuel cell bus under multiple conditions, the daily mode of stack voltage under a 75 A operation condition was selected as a health indicator that could better reflect the health status of a fuel cell stack. Then, an adaptive locally weighted scatterplot smoothing (LOWESS) algorithm was developed to adjust the most appropriate step size to smooth the original data automatically. Furthermore, for better prediction accuracy and stronger adaptability, a short-term RUL prediction model consisting of the adaptive LOWESS and bi-directional long short-term memory was established. Finally, an online operation scheme of the RUL prediction model based on a cloud system gave the model a strong powerful practicability. After validation, this work demonstrated good application prospects in the prognostic and health management of automotive fuel cells.

Reliability and durability are the main factors that hinder the large-scale commercialization of proton exchange membrane fuel cell (PEMFC). Water management is the key to solve such problems, and water content is the measurement standard of water management. But it is very difficult to measure water content inside the fuel cell directly. Thus, water fault diagnosis is a basic technology to monitor the water content indirectly based on the measurable parameters. In this paper, the water fault diagnosis of the PEMFC system has been summarized in three sections including the theoretical model-based method, knowledge-based method, and signal processing method from practical application, and part of them is from the perspective of vehicle application.