Fourier and laplace transform used in pretreatment for neural network battery modeling

To solve the large storage capacity in neural network battery modeling, an input pretreatment, based on Fourier or Laplace transform, is proposed. As simulation shows, the improved battery model gets a better precision and consumes a smaller storage capacity. This method can also be used in SOC estimation if farther experiments are conducted.

[1]  Mohammad Farrokhi,et al.  State-of-Charge Estimation for Lithium-Ion Batteries Using Neural Networks and EKF , 2010, IEEE Transactions on Industrial Electronics.

[2]  M.A.S. Masoum,et al.  A neural network model for Ni-Cd batteries , 2008, 2008 43rd International Universities Power Engineering Conference.

[3]  Lijun Gao,et al.  Incremental Battery Model Using Wavelet-Based Neural Networks , 2011, IEEE Transactions on Components, Packaging and Manufacturing Technology.

[4]  Cairo Lucio Nascimento,et al.  Modeling and simulation of nickel-cadmium batteries during discharge , 2011, 2011 Aerospace Conference.