-State-of-charge (SOC) plays a fundamental role in guiding battery management strategies. Recently, a variety of deep learning methods have been successfully applied in SOC estimation with impressive estimation accuracy. Nevertheless, the pros and cons of deep-learning estimators remain unexplored. This work investigates the performance of four state-of-the-art deep learning algorithms in the context of SOC estimation, including the fully connected neural network (FCNN), long short-term memory (LSTM), gate recurrent unit (GRU) and temporal convolutional network (TCN). Two kinds of lithium-ion batteries are tested by using specific devices programmed with dynamic drive cycles. The four methods are then evaluated regarding the accuracy by using experimental data collected at 25 °C. Afterwards, their robustness is evaluated at various temperatures with noise-polluted input data. The battery chemistries are also taken into consideration to assess their generalization performance. Finally,
State-of-charge (SOC) is a crucial battery quantity that needs constant monitoring to ensure cell longevity and safe operation. However, SOC is not an observable quantity and cannot be practically measured outside of laboratory environments. Hence, machine learning (ML) has been employed to map correlated observable signals such as voltage, current and temperature to SOC values. In recent studies, deep learning (DL) has been a prominent ML approach outperforming many existing methods for SOC estimation. However, yielding optimal performance from DL models relies heavily on appropriate selection of hyperparameters. At present, researchers relied on established heuristics to select hyperparameters through manual tuning or exhaustive search methods such as grid search (GS) and random search (RS). This results in lengthy development time in addition to less accurate and inefficient models. This study proposes a systematic and automated approach to hyperparameter selection with a Bayesian o
Deep learning has gained much traction in application to state-of-charge (SOC) estimation for Li-ion batteries in electric vehicle applications. However, with the vast selection of architectures and hyperparameter combinations, it remains challenging to design an accurate and robust SOC estimation model with a sufficiently low computation cost. Therefore, this study provides a comparative evaluation among commonly used deep learning models from the recurrent, convolutional and feedforward architecture benchmarked on an openly available Li-ion battery dataset. To evaluate model robustness and generalization capability, we train and test models on different drive cycles at various temperatures and compute the RMSE and MAE error metric. To evaluate model computation costs, we run models in real-time and record the model size, floating point operations per second (FLOPS), and run-time duration per datapoint. This study proposes a two-hidden layer stacked gated recurrent unit (GRU) model tr