Prediction method for predicting service life of proton exchange membrane fuel cell

Abstract

The invention discloses a prediction method for predicting the service life of a proton exchange membrane fuel cell. The prediction method comprises the steps of determining input network parameters:according to parameter data of a stack of the proton exchange membrane fuel cell, determining the number of input network types and the number of output network types; performing discrete wavelet transformation: carrying out discrete wavelet transformation on the parameter data, selecting basic wavelet types according to parameter data, and obtaining a denoised training sample through discrete wavelet transformation; and training an extreme learning machine neural network: determining the training sample and a test sample, and by utilizing an extreme learning machine, through randomly selecting an input weight and a deviation of a hidden layer, calculating an output matrix and an output weight of the hidden layer, and performing prediction through an inverse process of calculating the output weight by an evolutionary algorithm to output a prediction result. According to the method, the service life prediction precision of the proton exchange membrane fuel cell is high, and the prediction time is short.

Description

technical field [0001] The invention belongs to the technical field of fuel cells, in particular to a prediction method for life prediction of proton exchange membrane fuel cells. Background technique [0002] The proton exchange membrane fuel cell is not limited by the efficiency of the Carnot cycle, and is an extremely clean and efficient power generation system, but it also has the problem of voltage degradation. Lifespan prediction and health management technology can be seen as a good way to help prolong their lifespan. The current general forecasting methods include data-driven, model-driven, and hybrid-driven. Since a large amount of monitoring data will be generated during the operation of the fuel cell platform, the observed data is a time series with nonlinear and non-Gaussian distribution, so it cannot be predicted by a simple static linear model, but the trend of data changes should be obtained through dynamic training and learning And predict, based on the abo...

AI Technical Summary

Problems solved by technology

However, due to the time-consuming optimization of the existing extreme learning machine parameters, it is more suitable for offline prediction. At present, there is an urgent need for an algorithm that reduces the prediction time and does not affect or improve the prediction accuracy to predict the service life of proton exchange membrane fuel cells.

Images