PEMFC Aging Prediction Based on Improved Whale Optimization Algorithm Optimized GRU
To improve the controllability and prediction accuracy of aging prediction for proton exchange membrane fuel cells(PEMFC),this paper proposes a PEMFC voltage prediction method based on improved whale optimization algorithm(IWOA)optimized gated recurrent unit(GRU)neural network.The optimal hyperparameters of GRU are obtained by IWOA,and then GRU is used to accurately predict the PEMFC voltage.Three sets of aging experimental data under static,quasi-dynamic and dynamic conditions are used to compare the proposed method with six methods:back propagation neural network,extreme learning machine,recurrent neural network,long short-term memory neural network,GRU and whale algorithm optimized gated recurrent unit.The proposed method has the highest aging prediction and remaining useful life(RUL)estimation accuracy.Under static,quasi-dynamic and dynamic conditions,when the training set ratio is 50%,compared with GRU,the root mean square error of the prediction results of the proposed method is reduced by 56.99%,35.12%and 9.95%,respectively.Therefore,this method can achieve high-precision PEMFC aging trend and RUL prediction.
万方数据
维普
