Robust prediction of lithium-ion battery temperature using wavelet scattering and deep learning

Mohamed M. A. Hassan; Hatem Kayed; Bassam Adel; Mohamed M. A. Hassan; Hatem Kayed; Bassam Adel

doi:10.3934/energy.2026009

AIMS Energy

2026, Volume 14, Issue 1: 212-234. doi: 10.3934/energy.2026009

Previous Article Next Article

Research article Topical Sections

Robust prediction of lithium-ion battery temperature using wavelet scattering and deep learning

Mechanical Power Engineering Department, Faculty of Engineering, Cairo University, Cairo, Egypt

Received: 16 October 2025 Revised: 31 December 2025 Accepted: 26 January 2026 Published: 11 February 2026

Lithium-ion batteries are essential for electric vehicles and energy storage systems; nevertheless, inconsistent temperature distributions jeopardize their safety and reliability, potentially resulting in thermal runaway. Thus, precise temperature forecasting models are crucial for enhancing performance and guaranteeing operational safety. In this research, we present a hybrid framework that combines the Wavelet Scattering Transform (WST) with Long Short-Term Memory (LSTM) neural networks to predict battery temperature distributions. The methodology was validated using datasets from the NASA Ames Prognostics Center of Excellence (PCoE), which included authentic cycle data for voltage, current, and temperature. To guarantee reliability, model predictions were calibrated and assessed using three methods: RAW outputs, bias correction, and Poly2. The proposed WST-LSTM framework showed improved stability and consistency relative to the raw-signal LSTM baseline, supporting its suitability for thermal-safety evaluation and battery-management applications. The proposed framework was implemented in MATLAB/Simulink for an electric-vehicle battery model, thereby validating its applicability to real-world automotive platforms. This study emphasizes forecasting temperature at a specific sensor point rather than reconstructing the temperature field. The suggested WST-LSTM model predicted the temperature trajectory at this location utilizing electrical and environmental signals.
- electric vehicles,
- lithium-ion batteries,
- Wavelet Scattering Transform (WST),
- LSTM,
- temperature prediction
Citation: Mohamed M. A. Hassan, Hatem Kayed, Bassam Adel. Robust prediction of lithium-ion battery temperature using wavelet scattering and deep learning[J]. AIMS Energy, 2026, 14(1): 212-234. doi: 10.3934/energy.2026009

Related Papers:

Abstract

Lithium-ion batteries are essential for electric vehicles and energy storage systems; nevertheless, inconsistent temperature distributions jeopardize their safety and reliability, potentially resulting in thermal runaway. Thus, precise temperature forecasting models are crucial for enhancing performance and guaranteeing operational safety. In this research, we present a hybrid framework that combines the Wavelet Scattering Transform (WST) with Long Short-Term Memory (LSTM) neural networks to predict battery temperature distributions. The methodology was validated using datasets from the NASA Ames Prognostics Center of Excellence (PCoE), which included authentic cycle data for voltage, current, and temperature. To guarantee reliability, model predictions were calibrated and assessed using three methods: RAW outputs, bias correction, and Poly2. The proposed WST-LSTM framework showed improved stability and consistency relative to the raw-signal LSTM baseline, supporting its suitability for thermal-safety evaluation and battery-management applications. The proposed framework was implemented in MATLAB/Simulink for an electric-vehicle battery model, thereby validating its applicability to real-world automotive platforms. This study emphasizes forecasting temperature at a specific sensor point rather than reconstructing the temperature field. The suggested WST-LSTM model predicted the temperature trajectory at this location utilizing electrical and environmental signals.

References

[1]	Han J, Wang F (2023) Design and testing of a small orchard tractor driven by a power battery. Eng Agríc 43: e20220195. https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20220195/2023 doi: 10.1590/1809-4430-eng.agric.v43n2e20220195/2023
[2]	Huang Y, Li J (2022) Key challenges for grid‐scale lithium‐ion battery energy storage. Adv Energy Mater 12: 2202197. https://doi.org/10.1002/aenm.202202197 doi: 10.1002/aenm.202202197
[3]	Yang S, Ling C, Fan Y, et al. (2019) A review of lithium-ion battery thermal management system strategies and the evaluation criteria. Int J Electrochem Sci 14: 6077–6107. https://doi.org/10.20964/2019.07.06 doi: 10.20964/2019.07.06
[4]	Feng X, Zheng S, Ren D, et al. (2019) Investigating the thermal runaway mechanisms of lithium-ion batteries based on thermal analysis database. Appl Energy 246: 53–64. https://doi.org/10.1016/j.apenergy.2019.04.009 doi: 10.1016/j.apenergy.2019.04.009
[5]	Gharebaghi M, Rezaei O, Li C, et al. (2024) A survey on using second-life batteries in stationary energy storage applications. Energies 18: 42. https://doi.org/10.3390/en18010042 doi: 10.3390/en18010042
[6]	Zeng Y, Chalise D, Lubner SD, et al. (2021) A review of thermal physics and management inside lithium-ion batteries for high energy density and fast charging. Energy Storage Mater 41: 264–288. https://doi.org/10.1016/j.ensm.2021.06.008 doi: 10.1016/j.ensm.2021.06.008
[7]	Smith K, Wang CY (2006) Power and thermal characterization of a lithium-ion battery pack for hybrid-electric vehicles. J Power Sources 160: 662–673. https://doi.org/10.1016/j.jpowsour.2006.01.038 doi: 10.1016/j.jpowsour.2006.01.038
[8]	Wang Q, Ping P, Zhao X, et al. (2012) Thermal runaway caused fire and explosion of lithium-ion battery. J Power Sources 208: 210–224. https://doi.org/10.1016/j.jpowsour.2012.02.038 doi: 10.1016/j.jpowsour.2012.02.038
[9]	Feng X, Ouyang M, Liu X, et al. (2018) Thermal runaway mechanism of lithium-ion battery for electric vehicles: A review. Energy Storage Mater 10: 246–267. https://doi.org/10.1016/j.ensm.2017.05.013 doi: 10.1016/j.ensm.2017.05.013
[10]	Tran MK, Mevawalla A, Aziz A, et al. (2022) A review of lithium-ion battery thermal runaway modeling and diagnosis approaches. Processes 10: 1192. https://doi.org/10.3390/pr10061192 doi: 10.3390/pr10061192
[11]	Pal S, Kashyap P, Panda B, et al. (2025) A comprehensive review of thermal runaway for batteries: Experimental, modelling, challenges and proposed framework. Int J Green Energy, 1–24. https://doi.org/10.1080/15435075.2025.2462606 doi: 10.1080/15435075.2025.2462606
[12]	Chalise D, Lu W, Srinivasan V, et al. (2020) Heat of mixing during fast charge/discharge of a Li-ion cell: A study on NMC523 cathode. J Electrochem Soc 167: 090560. https://doi.org/10.1149/1945-7111/abaf71 doi: 10.1149/1945-7111/abaf71
[13]	Goodenough JB, Park KS (2013) The Li-ion rechargeable battery: A perspective. J Am Chem Soc 135: 1167–1176. https://doi.org/10.1021/ja3091438 doi: 10.1021/ja3091438
[14]	Bandhauer TM, Garimella S, Fuller TF (2011) A critical review of thermal issues in lithium-ion batteries. J Electrochem Soc 158: R1. https://doi.org/10.1149/1.3515880 doi: 10.1149/1.3515880
[15]	Spotnitz R (2003) Simulation of capacity fade in lithium-ion batteries. J Power Sources 113: 72–80. https://doi.org/10.1016/S0378-7753(02)00490-1 doi: 10.1016/S0378-7753(02)00490-1
[16]	Pesaran AA (2002) Battery thermal models for hybrid vehicle simulations. J Power Sources 110: 377–382. https://doi.org/10.1016/S0378-7753(02)00200-8 doi: 10.1016/S0378-7753(02)00200-8
[17]	Sheikh SS, Anjum M, Khan MA, et al. (2020) A battery health monitoring method using machine learning: A data-driven approach. Energies 13: 3658. https://doi.org/10.3390/en13143658 doi: 10.3390/en13143658
[18]	Balouji E, Salor O (2017) Classification of power quality events using deep learning on event images. 2017 3^rd International Conference on Pattern Recognition and Image Analysis (IPRIA), Shahrekord, Iran, 216–221. https://doi.org/10.1109/PRIA.2017.7983049
[19]	Graves A, Mohamed AR, Hinton G (2013) Speech recognition with deep recurrent neural networks. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, BC, Canada, 6645–6649. https://doi.org/10.1109/ICASSP.2013.6638947
[20]	Xu K, Zhuang J, Meng X, et al. (2023) Temperature-field prediction for lithium-ion batteries using improved local tangent space alignment. Int J Heat Mass Transfer 209: 124126. https://doi.org/10.1016/j.ijheatmasstransfer.2023.124126 doi: 10.1016/j.ijheatmasstransfer.2023.124126
[21]	Mallat S (2012) Group invariant scattering. Commun Pure Appl Math 65: 1331–1398. https://doi.org/10.1002/cpa.21413 doi: 10.1002/cpa.21413
[22]	Ramamoorthy ML, Selvaperumal S, Nagarajan R (2025) An adaptive battery health monitoring framework using wavelet scattering and spiking graph transformers optimized by arctic wolf algorithm. Iran J Sci Technol, Trans Electr Eng, 1–27. https://doi.org/10.1007/s40998-025-00885-4 doi: 10.1007/s40998-025-00885-4
[23]	NASA (2012) Prognostics Center of Excellence (PCoE) Data Set Repository. Available from: https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/.
[24]	Liu N, Zhang F, Chang L, et al. (2024) Scattering-based hybrid network for facial attribute classification. Front Comput Sci 18: 183313. https://doi.org/10.1007/s11704-023-2570-6 doi: 10.1007/s11704-023-2570-6
[25]	Wang Y, Guo P, Ma N, et al. (2022) Robust wavelet transform neural-network-based short-term load forecasting for power distribution networks. Sustainability 15: 296. https://doi.org/10.3390/su15010296 doi: 10.3390/su15010296
[26]	Khumprom P, Yodo N (2019) A data-driven predictive prognostic model for lithium-ion batteries based on a deep learning algorithm. Energies 12: 660. https://doi.org/10.3390/en12040660 doi: 10.3390/en12040660
[27]	He T, Gong Z (2024) State of health estimation for lithium-ion batteries using a hybrid neural network model with multi-scale convolutional attention mechanism. J Power Sources 609: 234680. https://doi.org/10.1016/j.jpowsour.2024.234680 doi: 10.1016/j.jpowsour.2024.234680
[28]	Mansour NM, Awaad IA, Abdelsalam AA (2024) Performance analysis of wavelet scattering transform-based feature matrix for power system disturbances classification. Int J Electr Comput Eng 14: 6094–6110. https://doi.org/10.11591/ijece.v14i6.pp6094-6110 doi: 10.11591/ijece.v14i6.pp6094-6110
[29]	Mansour NM, Abdelsalam AA, Awaad IA, et al. (2025) A novel long short-term memory-based approach for microgrid fault detection and classification using the wavelet scattering transform. IEEE Access 13: 120905–120916. https://doi.org/10.1109/ACCESS.2025.3584355 doi: 10.1109/ACCESS.2025.3584355
[30]	Wang B, Chen Z, Zhang P, et al. (2025) The lithium-ion battery temperature field prediction model based on CNN-Bi-LSTM-AM. Sustainability 17: 2125. https://doi.org/10.3390/su17052125 doi: 10.3390/su17052125
[31]	Xu K, Zhuang J, Meng X, et al. (2023) Temperature-field prediction for lithium-ion batteries using improved local tangent space alignment. Int J Heat Mass Transfer 209: 124126. https://doi.org/10.1016/j.ijheatmasstransfer.2023.124126 doi: 10.1016/j.ijheatmasstransfer.2023.124126
[32]	Zhou X, Guo W, Shi X, et al. (2024) Machine learning assisted multi-objective design optimization for battery thermal management system. Appl Therm Eng 253: 123826. https://doi.org/10.1016/j.applthermaleng.2024.123826 doi: 10.1016/j.applthermaleng.2024.123826
[33]	Sherkatghanad Z, Ghazanfari A, Makarenkov V, et al. (2024) A self-attention-based CNN-Bi-LSTM model for accurate state-of-charge estimation of lithium-ion batteries. J Energy Storage 88: 111524. https://doi.org/10.1016/j.est.2024.111524 doi: 10.1016/j.est.2024.111524
[34]	Bruna J, Mallat S (2013) Invariant scattering convolution networks. IEEE Trans Pattern Anal Mach Intell 35: 1872–1886. https://doi.org/10.1109/TPAMI.2012.230 doi: 10.1109/TPAMI.2012.230
[35]	Andén J, Mallat S (2011) Multiscale scattering for audio classification. Proc 12th Int Soc Music Information Retrieval Conf (ISMIR), 657–662. https://doi.org/10.5281/zenodo.1415750
[36]	Bruna J, Mallat S (2013) Invariant scattering convolution networks. IEEE Trans Pattern Anal Mach Intell 35: 1872–1886. https://doi.org/10.1109/TPAMI.2012.230 doi: 10.1109/TPAMI.2012.230
[37]	Andén J, Mallat S (2014) Deep Scattering Spectrum. IEEE Trans Signal Process 62: 4114–4128. https://doi.org/10.1109/TSP.2014.2326991 doi: 10.1109/TSP.2014.2326991
[38]	Bruna J, Mallat S (2011) Classification with scattering operators. CVPR 2011, 1561–1566. https://doi.org/10.1109/CVPR.2011.5995635 doi: 10.1109/CVPR.2011.5995635
[39]	Zarka J, Thiry L, Angles T, et al. (2019) Deep network classification by scattering and homotopy dictionary learning. arXiv. https://doi.org/10.48550/arXiv.1910.03561
[40]	AlBader M, Toliyat HA (2020) Wavelet scattering transform based induction motor current signature analysis. 2020 International Conference on Electrical Machines (ICEM), 1452–1457. https://doi.org/10.1109/ICEM49940.2020.9270810
[41]	Al-Itbi AS, Alwahhab ABA, Sahan AM (2022) X-Ray Covid-19 detection based on scatter wavelet transform and dense deep neural network. Comput Syst Sci Eng 41: 3. https://doi.org/10.32604/csse.2022.021980 doi: 10.32604/csse.2022.021980
[42]	Susu AA, Agboola HA, Solebo C, et al. (2020) Wavelet time scattering based classification of interictal and preictal EEG signals. J Brain Res 3: 115. https://doi.org/10.37421/2684-4583.2020.3.115 doi: 10.37421/2684-4583.2020.3.115
[43]	Liu F, Xia S, Wei S, et al. (2022) Wearable electrocardiogram quality assessment using wavelet scattering and LSTM. Front Physiol 13: 905447. https://doi.org/10.3389/fphys.2022.905447 doi: 10.3389/fphys.2022.905447
[44]	Agboola HA, Zaccheus JE (2023) Wavelet image scattering-based glaucoma detection. BMC Biomed Eng 5: 1. https://doi.org/10.1186/s42490-023-00067-5 doi: 10.1186/s42490-023-00067-5
[45]	Hirn M, Mallat S, Poilvert N (2017) Wavelet scattering regression of quantum chemical energies. Multiscale Model Simul 15: 2. https://doi.org/10.1137/16M1075454 doi: 10.1137/16M1075454
[46]	Rohan A (2022) Deep scattering spectrum germaneness for fault detection and diagnosis for component-level Prognostics and Health Management (PHM). Sensors 22: 9064. https://doi.org/10.3390/s22239064 doi: 10.3390/s22239064
[47]	Lai WH, Tsai ST, Cheng DL, et al. (2021) Application of wavelet scattering and machine learning on structural health diagnosis for quadcopter. Appl Sci 11: 10297. https://doi.org/10.3390/app112110297 doi: 10.3390/app112110297
[48]	de Aguiar EL, Lazzaretti AE, Mulinari BM, et al. (2021) Scattering transform for classification in non-intrusive load monitoring. Energies 14: 6796. https://doi.org/10.3390/en14206796 doi: 10.3390/en14206796
[49]	Bourgana T, Brijder R, Ooijevaar T, et al. (2021) Wavelet scattering network based bearing fault detection. Proceedings of the European Conference of the PHM Society 6: 8. https://doi.org/10.36001/phme.2021.v6i1.2875 doi: 10.36001/phme.2021.v6i1.2875
[50]	The MathWorks Inc (2022) MATLAB version: 9.13. 0 (R2022b), Natick, Massachusetts. Available from: https://www.mathworks.com.
[51]	Hochreiter S, Schmidhuber J (1997) Long Short-Term Memory. Neural Comput 9: 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735 doi: 10.1162/neco.1997.9.8.1735
[52]	Abdelsalam AA, Hassanin AM, Hasanien HM (2021) Categorisation of power quality problems using long short‐term memory networks. IET Gener Transm Distrib 15: 1626–1639. https://doi.org/10.1049/gtd2.12122 doi: 10.1049/gtd2.12122
[53]	Liu Y, Wang Y, Yang X, et al. (2017) Short-term travel time prediction by deep learning: A comparison of different LSTM-DNN models. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). https://doi.org/10.1109/ITSC.2017.8317886
[54]	Balouji E, Salor O (2017) Classification of power quality events using deep learning on event images. 2017 3rd International Conference on Pattern Recognition and Image Analysis (IPRIA). https://doi.org/10.1109/PRIA.2017.7983049
[55]	Zhang L, Zhu X, Zhao S, et al. (2017) A novel virtual network fault diagnosis method based on long short-term memory neural networks. 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall). https://doi.org/10.1109/VTCFall.2017.8288236
[56]	Chauhan S, Vig L (2015) Anomaly detection in ECG time signals via deep long short-term memory networks. 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA). https://doi.org/10.1109/DSAA.2015.7344872

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)