【Applied Energy 最新原创论文】一种用于锂离子电池退化轨迹预测的合成数据生成方法与进化Transformer模型

(1) 使用条件生成对抗网络（CGAN）对电池容量退化曲线进行生成.

(2) 设计了最大多样性筛选方法和数据评估方法，保证了生成曲线的合理性和可靠性.

(3) 使用进化方法自动优化模型架构及其超参数，以提高预测精度和效率.

(4) 将进化 Transformer-CNN 模型应用于电池退化轨迹预测.

    Identifying the long-term degradation of lithium-ion batteries in their early usage phase is crucial for the battery management system (BMS) to properly maintain the battery for practical use. Nevertheless, this procedure is challenging due to variations in the production and operating conditions of the battery. In recent years, it has been empirically proven that the data-driven method is a promising solution for handling the prediction of degradation. However, the lack of appropriate data remains the main obstacle that impacts the ultimate performance of the prediction. Furthermore, the prediction is also influenced by the setup of the predictor, which covers the structure of neural networks and their hyperparameters. The challenge of automating this process remains unresolved. In this study, we propose a novel degradation trajectory prediction framework. First, synthetic data is generated via a conditional generative adversarial network (CGAN), providing the characterization of the battery’s degradation at an early stage and utilizing the argument data to alleviate the issue of insufficient data. Second, an evaluation method to evaluate the quality of the synthetic data is also provided. In addition, a selection method is proposed based on the diversity mechanism to further filter out the redundancy of synthetic data. These two sub-processes aim to promote the quality of the synthetic data. Finally, the synthetic data hybrid with real values is used for the training of a transformer model, whose architecture and hyper-parameters are automatically configured via an evolutionary framework. The experimental results show that the proposed method can achieve accurate predictions compared to its rivals, and its best configuration can be automatically configured without hand-crafted efforts.

Keywords

Lithium-ion battery 锂离子电池

Degradation trajectory prediction 退化轨迹预测

Transformer model Transformer模型

Evolutionary framework 进化框架

Fig. 1. The main procedure of the proposed degradation trajectory prediction method.

Fig. 2. The conditional-GAN for data synthesis.

Fig. 4. Overall structure of the evolutionary transformer-CNN model.

Fig. 7. The results of degradation trajectory prediction for our private dataset. (a)–(d) demonstrate the prediction results for Cell 4, 5, 7 and 8, respectively.

Fig. 8. The results of degradation trajectory prediction for the Maryland dataset. (a)–(b) demonstrate the prediction results for CS2-35 and CS2-37, respectively.

Fig. 9. The results of degradation trajectory prediction on-road vehicle dataset. (a)–(d) demonstrate the prediction results for Cell 2, 4, 6 and 8, respectively.

Fig. 10. The prediction results of RMSE and MAE for the degradation trajectory prediction. (a)–(c) represents the prediction results for cluster 1 to cluster 3, respectively.

       本研究由西安理工大学，西安交通大学，南京工程学院等单位的研究人员共同完成。

通信作者简介：

       蔡磊，博士，西安理工大学计算机科学与工程学院副教授，主要研究方向包括进化计算、锂离子电池健康诊断与预测等。蔡磊老师在科研方面取得了多项成果，包括发表多篇国际期刊、主持并参与多个科研项目。

第一作者简介：

       金海燕，教授，西安理工大学博士生导师，第十四届陕西省青年科技奖获得者，陕西省优秀共产党员，陕西省科技创新团队带头人，陕西高校青年创新团队带头人，陕西省网络计算与安全技术重点实验室副主任，陕西省计算机教育学会理事。主要研究方向为计算机视觉、图象处理、智能信息处理及优化等，主持国家自然科学基金项目、陕西省科技计划项目等20余项；获中国发明协会创新奖、陕西省科学技术奖等省部级科研奖励3项；授权国家发明专利36项，在TP、AAAI等国际期刊和会议上发表论文80余篇。

关于Applied Energy

点击“阅读原文”

喜欢我们的内容？

点个“赞”或者“再看”支持下吧！