Hannan M A, How D N T, Lipu M S Hossain, Mansor M, Ker Pin Jern, Dong Z Y, Sahari K S M, Tiong S K, Muttaqi K M, Mahlia T M Indra, Blaabjerg F
Department of Electrical Power Engineering, COE, Universiti Tenaga Nasional, 43000, Kajang, Malaysia.
Department of Electrical, Electronic and Systems Engineering, Universiti Kebangsaan Malaysia, 43600, Bangi, Malaysia.
Sci Rep. 2021 Oct 1;11(1):19541. doi: 10.1038/s41598-021-98915-8.
Accurate state of charge (SOC) estimation of lithium-ion (Li-ion) batteries is crucial in prolonging cell lifespan and ensuring its safe operation for electric vehicle applications. In this article, we propose the deep learning-based transformer model trained with self-supervised learning (SSL) for end-to-end SOC estimation without the requirements of feature engineering or adaptive filtering. We demonstrate that with the SSL framework, the proposed deep learning transformer model achieves the lowest root-mean-square-error (RMSE) of 0.90% and a mean-absolute-error (MAE) of 0.44% at constant ambient temperature, and RMSE of 1.19% and a MAE of 0.7% at varying ambient temperature. With SSL, the proposed model can be trained with as few as 5 epochs using only 20% of the total training data and still achieves less than 1.9% RMSE on the test data. Finally, we also demonstrate that the learning weights during the SSL training can be transferred to a new Li-ion cell with different chemistry and still achieve on-par performance compared to the models trained from scratch on the new cell.
准确估计锂离子电池的荷电状态（SOC）对于延长电池寿命以及确保其在电动汽车应用中的安全运行至关重要。在本文中，我们提出了一种基于深度学习的变压器模型，该模型通过自监督学习（SSL）进行训练，用于端到端的SOC估计，无需特征工程或自适应滤波。我们证明，在SSL框架下，所提出的深度学习变压器模型在恒定环境温度下实现了最低均方根误差（RMSE）为0.90%，平均绝对误差（MAE）为0.44%；在变化的环境温度下，RMSE为1.19%，MAE为0.7%。通过SSL，所提出的模型仅使用20%的总训练数据，只需训练5个epoch就能训练成功，并且在测试数据上的RMSE仍低于1.9%。最后，我们还证明，SSL训练期间的学习权重可以转移到具有不同化学性质的新锂离子电池上，并且与在新电池上从头开始训练的模型相比，仍能实现相当的性能。
