电池(电)
电气工程
人工神经网络
荷电状态
国家(计算机科学)
电荷(物理)
物理
估计
计算机科学
工程类
人工智能
算法
量子力学
系统工程
功率(物理)
作者
Xilin Dai,Ruidi Zhou,Jinhao Zhang,Keyi He,Fanfan Lin,Hao Ma
标识
DOI:10.1109/tte.2025.3573618
摘要
For lithium-ion batteries in electric vehicles, ambient temperature variations and sensor noises affect the accurate estimation of the State of Charge (SOC). To achieve both temperature and noise robustness in SOC estimation with an efficient and interpretable approach, the SocNet is proposed in this paper. As a physics-guided neural network, the structure of SocNet is designed and optimized based on physics knowledge, with the Physics-Guided Feature Extraction, SOC Lookback, and Linear Summation Layer. The SocNet was trained and tested at different ambient temperatures, achieving a mean absolute error (MAE) of 0.40%. Furthermore, SocNet was tested with four different types of noise added to the input, and the MAE increased by only 0.28%. Compared with 8 current methods, SocNet reduced the number of parameters by 68.06% and runtime by 49.12%, while improving temperature robustness and noise robustness by 43.66% and 76.87%.
科研通智能强力驱动
Strongly Powered by AbleSci AI