State-of-Charge Estimation of Lithium-Ion Batteries Based on the CNN-Bi-LSTM-AM Model Under Low-Temperature...

Area of Science:

• Electrical Engineering
• Computer Science
• Materials Science

Background:

• Accurate state-of-charge (SOC) estimation is critical for lithium-ion battery management.
• Traditional SOC estimation methods face challenges with noise and nonlinear dynamics at low temperatures.

Purpose of the Study:

• To develop an advanced deep learning model for precise SOC estimation in low-temperature environments.
• To overcome the limitations of existing methods in handling noisy data and complex battery behaviors.

Main Methods:

• A hybrid deep learning model combining a one-dimensional convolutional neural network (1D-CNN), bidirectional long short-term memory (Bi-LSTM), and an attention mechanism (AM) was developed.
• The 1D-CNN extracts local features, Bi-LSTM captures temporal dependencies, and the AM prioritizes crucial time steps.
• The model was evaluated on the Panasonic 18650PF dataset under various driving cycles at temperatures between -20 and 0°C.

Main Results:

• The proposed CNN-Bi-LSTM-AM model achieved a mean absolute error (MAE) of 0.17-0.77% and a root mean square error (RMSE) of 0.33-0.94%.
• The model demonstrated superior performance compared to CNN-LSTM and CNN-Bi-LSTM benchmarks.
• Effective handling of voltage distortion and nonlinearities at low temperatures was observed.

Conclusions:

• The CNN-Bi-LSTM-AM model offers a robust and accurate solution for SOC estimation in challenging low-temperature conditions.
• This approach enhances the reliability of battery management systems operating under extreme environmental factors.
• The findings contribute to the advancement of electric vehicle battery technology and energy storage systems.