Method and system for estimating state of health of a proton exchange membrane fuel cell

Abstract

The invention relates to a method and system for estimating the state of health of a proton exchange membrane fuel cell. The invention includes determining the polarization curve of the fuel cell; determining the relationship between the output voltage, current density and film thickness of the fuel cell according to the control parameters within the set control range and the basic parameters of the fuel cell; The relationship and polarization curve, the reverse fitting method is used to determine the mapping relationship between the film thickness and the running time; the Fourier fitting method is used to fit the mapping relationship, and the functional relationship between the film thickness and the running time is determined; According to the functional relationship and the running time of the fuel cell, determine the current film thickness, and substitute it back into the relationship between the output voltage, current density and film thickness, and then determine the real-time quantized polarization curve according to the current film thickness; The degree of degradation of the fuel cell determined by the degradation curve determines the corresponding state of health. The invention can improve the real-time performance and quantitative certainty of the estimation of the state of health of the proton exchange membrane fuel cell.

Description

technical field [0001] The invention relates to the field of proton exchange membrane fuel cells, in particular to a method and system for estimating the state of health of a proton exchange membrane fuel cell. Background technique [0002] Proton exchange membrane fuel cells are widely used in transportation and other fields represented by fuel cell vehicles due to their many advantages such as no pollution, high energy conversion rate, low operating temperature, and low noise. As a typical multi-scale, multi-physics, multi-component, multi-factor coupled complex nonlinear system, the state of health estimation and life prediction of proton exchange membrane fuel cells are full of many unknown challenges. [0003] Currently, state-of-health estimation or lifetime prediction for PEMFCs is generally divided into three categories: ① model-based methods; ② data-driven methods; ③ hybrid methods of the two. The model-based method has high requirements on the accuracy of the mode...

AI Technical Summary

Problems solved by technology

The model-based method has high requirements on the accuracy of the model, the parameter calibration in the model is complicated, and it is difficult to apply in real time; the data-driven method needs to rely on a large amount of data, data training is time-consuming, takes up a lot of computing resources, and the cost of parameter adjustment is high. Poor migration ability; although the mixed method of the two can avoid the obvious shortcomings of the two types of methods to a certain extent, it often has shortcomings such as complicated adjustment of empirical parameters and time-consuming data training in practical applications, especially in the case of fuel cell vehicles. The real-time quantification of the battery health status represented by the transportation field is full of many uncertainties

Images