| 초록 |
Lithium-ion batteries have been widely used in electric vehicles due to their high energy density and ease of recharging. To safely and efficiently use a battery, it is important to accurately estimate the State of Charge(SoC) of the battery. It is difficult to directly measure the SoC, so it is indirectly estimated through the coulomb counting method or open-circuit voltage(OCV) based method. The coulomb counting method has a limitation in that a difference from an actual value increases when errors accumulate, and the OCV method has a limitation in that the battery must be in an equilibrium state to measure the OCV. To overcome these limitations, this study proposed a model to estimate the SoC based on artificial neural network algorithms Multi-Layer Perceptron(MLP), Long Short-Term Memory(LSTM), and Gated Recurrent Units(GRU). The current, voltage, and temperature datasets are used as the model input. The models are trained under conditions that the window size of the training dataset is 10, 50, and 100, respectively. The accuracy and computation time of the models trained in each case are compared and analyzed. |
