摘要
利用三维质子交换膜燃料电池数学模型模拟研究了电池流道进、出口高度对电池性能的影响,然后将数值模拟结果作为神经网络模型的训练数据.以流道进、出口高度和电池电压值作为输入变量,以电池电流密度作为输出变量,建立了3层反向传播神经网络模型;然后利用Bagging集成学习方法对神经网络模型进行集成,构建了燃料电池性能预测方法.研究发现:与单一神经网络模型相比, Bagging神经网络集成模型预测精度更高,且所需模型训练数据量更少.此外对于超出训练数据以外的情形, Bagging神经网络集成模型仍然能够准确地预测燃料电池的性能,且精度良好,表明Bagging神经网络集成模型的鲁棒性较好,可用于更宽工况范围内燃料电池性能的快速预测.
The influence of the inlet and outlet heights of the flow channel on the performance of a proton exchange membrane fuel cell was studied with a three-dimensional fuel cell mathematical model. The numerical results were used as the basic training data of a threelayer back-propagation artificial neural network(ANN) model in which the inlet and outlet heights of the flow channel as well as the cell voltage were set to be the input variables while cell current density is the output variable. Then, applying the Bagging ensemble learning method to integrate the neural network model, a fuel cell performance prediction method is constructed. It was shown that as compared with the ANN model, the Bagging neural network model exhibited higher prediction accuracy and less requirements of model training data. It also can be applied for rapid prediction of fuel cell performance in a wide range of conditions beyond the training data, showing the robustness of the proposed Bagging neural network ensemble model.
引文
1 Frano B.PEM Fuel Cells:Theory and Practice.Cambridge,USA:Elsevier/Academic Press,2013
2 Larminie J,Dicks A.Fuel Cell System Explained.Hoboken:John Wiley&Sons Ltd,2003
3 Bawazeer K,Zilouchian A.Prediction of products quality parameters of a crude fractionation section of an oil refinery using neural networks.In:International Conference on Neural Networks.Houston:IEEE,1997.157-162
4 Jemei S,Hissel D,Pera M C,et al.Black-box modeling of proton exchange membrane fuel cell generators.In:IEEE 2002 28th Annual Conference of the Industrial Electronics Society.IECON 02.Sevilla:IEEE,2002.1474-1478
5 Ou S,Achenie L E K.A hybrid neural network model for PEM fuel cells.J Power Sources,2005,140:319-330
6 Zilouchian A,Jamshidi M.Intelligent Control Systems Using Soft Computing Methodologies.Boca Raton:CRC Press,Inc.,2001
7 Lee W.Empirical modeling of polymer electrolyte membrane fuel cell performance using artificial neural networks.Int J Hydrogen Energy,2004,29:961-966
8 Saengrung A,Abtahi A,Zilouchian A.Neural network model for a commercial PEM fuel cell system.J Power Sources,2007,172:749-759
9 Puranik S V,Keyhani A,Khorrami F.Neural network modeling of proton exchange membrane fuel cell.IEEE Trans Energy Convers,2010,25:474-483
10 Han I S,Chung C B.Performance prediction and analysis of a PEM fuel cell operating on pure oxygen using data-driven models:A comparison of artificial neural network and support vector machine.Int J Hydrogen Energy,2016,41:10202-10211
11 Seyhan M,Akansu Y E,Murat M,et al.Performance prediction of PEM fuel cell with wavy serpentine flow channel by using artificial neural network.Int J Hydrogen Energy,2017,42:25619-25629
12 Chávez-Ramírez A U,Mu?oz-Guerrero R,Durón-Torres S M,et al.High power fuel cell simulator based on artificial neural network.Int JHydrogen Energy,2010,35:12125-12133
13 Jeme?Jemei S,Hissel D,PéraPera M C,et al.A new modeling approach of embedded fuel-cell power generators based on artificial neural network.IEEE Trans Ind Electron,2008,55:437-447
14 Kalogirou S A.Artificial neural networks in renewable energy systems applications:A review.Renew Sust Energy Rev,2001,5:373-401
15 Wang L.A parametric study of PEM fuel cell performances.Int J Hydrogen Energy,2003,28:1263-1272
16 Liu Z,Zeng X,Ge Y,et al.Multi-objective optimization of operating conditions and channel structure for a proton exchange membrane fuel cell.Int J Heat Mass Transfer,2017,111:289-298
17 Kohonen T.An introduction to neural computing.Neural Netw,1988,1:3-16
18周志华.机器学习.北京:清华大学出版社,2016
19 Breiman L.Bagging predictors.Mach Learn,1996,24:123-140