荷电状态
学习迁移
计算机科学
人工神经网络
稳健性(进化)
电池(电)
超参数
依赖关系(UML)
期限(时间)
人工智能
机器学习
算法
功率(物理)
生物化学
量子力学
基因
物理
化学
作者
Yu Liu,Xing Shu,Hanzhengnan Yu,Jiangwei Shen,Yuanjian Zhang,Yonggang Liu,Zheng Chen
标识
DOI:10.1016/j.est.2021.102494
摘要
• Long short-term memory network is employed for state of charge estimation. • Transfer learning is exploited to accelerate the training of network model. • A rolling learning method is developed to tackle the battery aging influence. • The framework highlights precise estimation capacity under different conditions. • The well-trained model can be easily transplanted to similar batteries. This study investigates accurate state of charge estimation algorithms for lithium-ion batteries based on the long short-term memory recurrent neural network and transfer learning. The long short-term memory network with the five typical layer topology is firstly constructed to learn the dependency of state of charge on measured variables. The transfer learning algorithm with fine-tuning strategy is then exploited to regulate the parameters of fully connected layer and share the knowledge of other layers. By this manner, the information from the source data can be applied to predict state of charge of other batteries with less training data. Additionally, a rolling learning method is developed to update the model parameters when the battery capacity is degraded. The precision and robustness of the proposed framework are comprehensively validated through comparative analysis of multitudinous sets of hyperparameters and methods. The experimental results manifest that the developed framework highlights precise estimation capability of state of charge at different aging states and time-varying temperature conditions. In addition, the proposed algorithm is verified feasible when transferred to different batteries based on only 30% training data.
科研通智能强力驱动
Strongly Powered by AbleSci AI