Fuel cell life prediction method and system

Abstract

The invention relates to a fuel cell life prediction method and system, and the method comprises the steps: obtaining the microstructure parameters of an electric pile material in a fuel cell, inputting the microstructure parameters of the electric pile material into a prediction network model, and outputting to obtain a life prediction result; establishing the prediction network model, including the sub-steps of respectively carrying out durability testing on the fuel cells divided into the test group and the characterization group under the same working condition; obtaining galvanic pile material microstructure parameters of the characterization group and the remaining service life of the corresponding test group at different moments to obtain a data set; and training a neural network model by using the data set to form a mapping relation between the microstructure parameters of the galvanic pile and the residual service life of the galvanic pile. Compared with the prior art, the method has the advantages that the nonlinear relation with the residual life of the galvanic pile is directly established through the measurable galvanic pile microscopic parameters; therefore, the errors generated by predicting the long-term voltage of the galvanic pile through an existing method model are avoided, the requirement for prediction precision is reduced, and guidance is effectively provided for subsequent durability tests.

Description

technical field [0001] The invention relates to the field of fuel cell detection, in particular to a fuel cell life prediction method and system. Background technique [0002] The existing methods for fuel cell stack life prediction are mainly divided into the following two categories: [0003] One of them is fuel cell stack life prediction method driven by fuel cell electrochemical mechanism model. Most fuel cell stack performance prediction methods driven by electrochemical mechanism models combine the material properties of the stack itself, the failure mechanism of the stack, and the electrochemical mechanism to construct a semi-empirical formula to predict the performance degradation of the fuel cell stack. However, if this method needs to accurately predict the operating state of the fuel cell, it needs to establish a complex mathematical model to describe its internal electrochemical and thermal phenomena, and the formula lacks versatility. [0004] The other is a d...

AI Technical Summary

Problems solved by technology

However, the current research data of this method are mainly current density, voltage, etc., and mainly focus on predicting the future voltage of the stack through the current density of the stack. Considering that the voltage values ​​of the stack are relatively small (<1V), this method The demand for prediction accuracy of the model is very high, and slight fluctuations in the prediction value will have a greater impact on the error, and the longer the prediction time is, the larger the prediction error of the model will be

Images