Variational mode decomposition enabled temporal convolutional network model for state of charge estimation

Due to the fast growth of electric vehicles (EVs) , estimation for Battery's State-of-charge (SOC) received significant research interests. The reason is that an accurate SOC can significantly contribute reliability EVs. A Variational Mode Decomposition (VMD) technique enabled Temporal Convolutional Network (TCN) model proposed by authors estimation. method first adopts time-frequency analysis techniques decompose voltage values into different frequency domains, each which analysed with VMD obtain its features as input TCN model. Then, combines outputs domains attention module final output Experiments on real battery datasets indicate outperforms existing methods 7.2% in mean absolute error and 6.13% root square error. In addition, between estimated actual using bounded 2%.