New energy battery sampling circuit picture

Can a random sampling method affect battery training and evaluation results?

However, for the battery dataset, a simple random sampling method may lead to an imbalance of information regarding some aging stages of batteries in either the training or testing set, which may affect the training and evaluation results of the model.

Can partial segment battery data be converted into IC curves?

5.4. Comparison results of different segmented data and generalization performance Due to the randomness of the working conditions, the collected data may be partially segmented. Therefore, this paper uses the partial segment battery data to convert into IC curves to meet the needs of practical applications.

Can a random sampling method reduce battery performance degradation?

Subsequently, we present a stratified random sampling method to address the issue of imbalanced sample distributions in battery dataset partitioning, and employ residual neural networks to mitigate performance degradation caused by stacking multiple network layers.

Which RF model should be used for battery capacity estimation?

The choice of RF, MLP, XGBoost, CNN, and CNN-LSTM models for comparison is because these models are widely used in the field of battery capacity estimation, and using them as performance benchmarks can provide a good evaluation of the effectiveness of the proposed method.

How to convert partial segment battery data into incremental capacity curves?

The partial segment battery data are converted into incremental capacity (IC) curves denoised using wavelet transform, and the soft dynamic time warping (Soft-DTW) algorithm is used to calculate the similarity matrices between the initial IC curve and the aged IC curves.

Which battery is based on LFP and NMC data?

Among them, the LFP data is based on the commercial ANR26650M battery with a capacity of 2300 mAh, which has a voltage range of 2.0V–3.6V (Anseán et al., 2017). The NMC data is based on the commercial INR18650-35E battery with a capacity of 3500 mAh, which has a voltage range of 2.65V–4.2V (Anseán et al., 2020).