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

Automated summary

This study proposes a SOC estimation method for batteries based on VMD technique and TCN model. The voltage values are decomposed into different frequency domains using time-frequency analysis, and the features obtained from VMD technique are used as input for the TCN model. Experimental results show that the proposed method outperforms existing methods in terms of mean absolute error and root mean square error, and the error between the estimated and actual values is bounded by 2%.