QUANTIZED LSTM FOR PREDICTIVE THERMAL MONITORING OF TEMPERATURE OF LITHIUM-ION BATTERY
DOI:
https://doi.org/10.11113/jurnalteknologi.v88.23506Keywords:
Lithium-ion battery, Temperature, Long Short-Term Memory, QuantizationAbstract
The large memory requirements and low inference speed renders the deployment of Long short-term memory (LSTM) impractical for predictive monitoring in battery thermal management system. Thus, this study proposes quantization aware training, where the weights and biases were quantized using ternary quantization scheme and while the activation function were quantized using 8-, 6- and 4-bit level schemes. The various quantization strategies were evaluated with statistical analysis such as mean square error (MSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) and train and validated with oxford battery dataset. In addition, the various bit level schemes were compared in terms of performance.As 4-bit level level offers lowest memory footprint. This space saving is done where 24-bit = 16 values are assigned for the activation unit and unable to cover the whole spectrum compared to full precision, thus results in large mean accuracy loss. On the other hand, 6-bit level quantization proves to be better performance with relatively smaller memory footprint compared to 8-bit level quantization.Thus, 6-bit level quantization is suitable for low power edge application for battery management system.
References
Wang, R., Cui, W., Chu, F. and Wu, F. 2020. Lithium Metal Anodes: Present and Future. Journal of Energy Chemistry. 48: 145159.
Liu, D.H., Bai, Z., Li, M., Yu, A., Luo, D., Liu, W., Yang, L., Lu, J., Amine, K. and Chen, Z. 2020. Developing High Safety Li-metal Anodes for Future High-energy Li-metal Batteries: Strategies and Perspectives. Chemical Society Reviews. 49(15): 54075445.
Chen, K., D. Y. Yang, G. Huang, and X. B. Zhang. 2021. Lithium–Air Batteries: Air-Electrochemistry and Anode Stabilization. Accounts of Chemical Research. 54(3): 632–641.
Zhao, H., N. Deng, J. Yan, W. Kang, J. Ju, Y. Ruan, X. Wang, X. Zhuang, Q. Li, and B. Cheng. 2018. A Review on Anode for Lithium–Sulfur Batteries: Progress and Prospects. Chemical Engineering Journal. 347: 343–365.
Piao, Z., H. R. Ren, G. Lu, K. Jia, J. Tan, X. Wu, Z. Zhuang, Z. Han, C. Li, R. Gao, and X. Tao. 2023. Stable Operation of Lithium Metal Batteries with Aggressive Cathode Chemistries at 4.9 V. Angewandte Chemie International Edition 62 (15): e202300966.
Zhang, Q. K., X. Q. Zhang, H. Yuan, and J. Q. Huang. 2021. Thermally Stable and Nonflammable Electrolytes for Lithium Metal Batteries: Progress and Perspectives. Small Science. 1(10): 2100058.
Zhang, S., Z. Shen, and Y. Lu. 2021. Research Progress of Thermal Runaway and Safety for Lithium Metal Batteries. Acta Physico-Chimica Sinica. 37: 2008065.
Li, M., K. Wang, F. Shen, Y. Bai, C. Yang, J. Liu, J. Yan, Y. Chen, and X. Han. 2023. An Electrolyte-Locked Thermally Stable Composite Separator for Safe Lithium-Ion Batteries. Journal of Alloys and Compounds. 938: 168543.
l’Abee, R., F. DaRosa, M. J. Armstrong, M. M. Hantel, and D. Mourzagh. 2017. High-Temperature Stable Li-Ion Battery Separators Based on Polyetherimides with Improved Electrolyte Compatibility. Journal of Power Sources. 345: 202–211.
Zhu, S., C. He, N. Zhao, and J. Sha. 2021. Data-Driven Analysis on Thermal Effects and Temperature Changes of Lithium-Ion Battery. Journal of Power Sources. 482: 228983.
Al Miaari, A., and H. M. Ali. 2023. Batteries Temperature Prediction and Thermal Management Using Machine Learning: An Overview. Energy Reports. 10: 2277–2305.
Li, M., C. Dong, B. Xiong, Y. Mu, X. Yu, Q. Xiao, and H. Jia. 2022. STTEWS: A Sequential-Transformer Thermal Early Warning System for Lithium-Ion Battery Safety. Applied Energy. 328: 119965.
Li, M., C. Dong, X. Yu, Q. Xiao, and H. Jia. 2021. Multi-Step Ahead Thermal Warning Network for Energy Storage System Based on the Core Temperature Detection. Scientific Reports. 11(1): 15332.
Ma, Y., C. Shan, J. Gao, and H. Chen. 2022. A Novel Method for State of Health Estimation of Lithium-Ion Batteries Based on Improved LSTM and Health Indicators Extraction. Energy. 251: 123973.
Van, C. N., and D. T. Quang. 2023. Estimation of State of Health and Internal Resistances of Lithium-Ion Battery Based on LSTM Network. International Journal of Electrochemical Science. 18(6): 100166.
Yayan, U., A. T. Arslan, and H. Yucel. 2021. A Novel Method for State of Health Prediction of Batteries Based on Stacked LSTM with Quick Charge Data. Applied Artificial Intelligence. 35(6): 421–439.
Kaur, K., A. Garg, X. Cui, S. Singh, and B. K. Panigrahi. 2021. Deep Learning Networks for Capacity Estimation for Monitoring State of Health of Li-Ion Batteries for Electric Vehicles. International Journal of Energy Research. 45(2): 3113–3128.
Jiang, Y., Y. Yu, J. Huang, W. Cai, and J. Marco. 2021. Li-Ion Battery Temperature Estimation Based on Recurrent Neural Networks. Science China Technological Sciences. 64(6): 1335–1344.
Zhu, S., C. He, N. Zhao, and J. Sha. 2021. Data-Driven Analysis on Thermal Effects and Temperature Changes of Lithium-Ion Battery. Journal of Power Sources. 482: 228983.
Yao, Q., D. D. C. Lu, and G. Lei. 2022. A Surface Temperature Estimation Method for Lithium-Ion Battery Using Enhanced GRU-RNN. IEEE Transactions on Transportation Electrification. 9(1): 1103–1112.
Mirsalari, S. A., N. Nazari, S. A. Ansarmohammadi, S. Sinaei, M. E. Salehi, and M. Daneshtalab. 2021. ELC-ECG: Efficient LSTM Cell for ECG Classification Based on Quantized Architecture. In Proceedings of the 2021 IEEE International Symposium on Circuits and Systems (ISCAS). 1–5.
Rocha, L. G., D. Biswas, B. E. Verhoef, S. Bampi, C. Van Hoof, M. Konijnenburg, M. Verhelst, and N. Van Helleputte. 2020. Binary CorNET: Accelerator for HR Estimation from Wrist-PPG. IEEE Transactions on Biomedical Circuits and Systems. 14(4): 715–726.
Zhao, S., J. Yang, and M. Sawan. 2021. Energy-Efficient Neural Network for Epileptic Seizure Prediction. IEEE Transactions on Biomedical Engineering. 69(1): 401–411.
Li, F., B. Liu, X. Wang, B. Zhang, and J. Yan. 2016. Ternary Weight Networks. arXiv Preprint. arXiv:1605.04711.
Birkl, C. 2017. Oxford Battery Degradation Dataset 1. Oxford: University of Oxford.
Nagel, M., M. Fournarakis, Y. Bondarenko, and T. Blankevoort. 2022. Overcoming Oscillations in Quantization-Aware Training. In Proceedings of the International Conference on Machine Learning (ICML). 16318–16330. PMLR.
Gupta, K., and A. Asthana. 2024. Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2452–2461.
Birkl, C. 2017. Oxford Battery Degradation Dataset 1. Oxford: University of Oxford.
Kumar, P., G. Rankin, K. R. Pattipati, and B. Balasingam. 2022. Model-Based Approach to Long-Term Prediction of Battery Surface Temperature. IEEE Journal of Emerging and Selected Topics in Industrial Electronics. 4(1): 389–399.
Raijmakers, L. H. J., D. L. Danilov, R. A. Eichel, and P. H. L. Notten. 2019. A Review on Various Temperature-Indication Methods for Li-Ion Batteries. Applied Energy. 240: 918–945.
Tang, X., K. Yao, B. Liu, W. Hu, and F. Gao. 2018. Long-Term Battery Voltage, Power, and Surface Temperature Prediction Using a Model-Based Extreme Learning Machine. Energies. 11(1): 86
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
