Optimization of Radial Basis Function Neural Network Model Based on Particle Swarm Algorithm for Prediction of Voltage in Solid Oxide Fuel Cell

Solid Oxide Fuel Cell (SOFC) has good potential as a new energy source, but it is difficult to conduct direct research on SOFC directly due to its high price, hermeticity and high temperature. Therefore, in this paper, we use the method of mechanism modeling to build a SOFC system model in ASPEN PLUS and obtain a large amount of experimental data. A training set and a test set of this data are separated out. And PSO-RBF neural network is used to build the voltage prediction model of SOFC system, and the neural network is trained and tested using these data. To increase the voltage prediction's accuracy, the RBF neural network's parameters are optimized using the PSO algorithm. The results show that the PSO-RBF neural network model has a good prediction of the voltage of the SOFC system with high accuracy. The <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$R^{2}$</tex> of the training and test sets is greater than 0.99, and both MSE and RMSE are close to 0.