Developing an Innovative Seq2Seq Model to Predict the Remaining Useful Life of Low-Charged Battery Performance Using High-Speed Degradation Data
Source abstract
Abstract
This study introduces a novel Sequence-to-Sequence (Seq2Seq) deep learning model for predicting lithium-ion batteries’ remaining useful life. We address the challenge of extrapolating battery performance from high-rate to low-rate charging conditions, a significant limitation in previous studies. Experiments were also conducted on commercial cells using charge rates from 1C to 3C. Comparative analysis of fully connected neural networks, convolutional neural networks, and long short-term memory networks revealed their limitations in extrapolating to untrained conditions. Our Seq2Seq model overcomes these limitations, predicting charging profiles and discharge capacity for untrained, low-rate conditions using only high-rate charging data. The Seq2Seq model demonstrated superior performance with low error and high curve-fitting accuracy for 1C and 1.2C untrained data. Unlike traditional models, it predicts complete charging profiles (voltage, current, temperature) for subsequent cycles, offering a comprehensive view of battery degradation. This method significantly reduces battery life testing time while maintaining high prediction accuracy. The findings have important implications for lithium-ion battery development, potentially accelerating advancements in electric vehicle technology and energy storage.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Battery Technologies Research · Advancements in Battery Materials · Reliability and Maintenance Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Energy Systems Engineering, Chung-Ang University, Seoul 06974, Republic of Korea
Funding
Chung-Ang University Research Scholarship Grant in 2023 · National Research Foundation of Korea (NRF) · Ministry of Science and ICT
References (44)
Show source-provided references
1. Advanced Machine Learning Approach for Lithium-Ion Battery State Estimation in Electric Vehicles10.1109/TTE.2015.2512237 ↗
2. Identify capacity fading mechanism in a commercial LiFePO4 cell10.1016/j.jpowsour.2009.05.036 ↗
3. A brief review on key technologies in the battery management system of electric vehicles10.1007/s11465-018-0516-8 ↗
4. Critical Review on the Battery State of Charge Estimation Methods for Electric Vehicles10.1109/ACCESS.2017.2780258 ↗
5. Critical review of state of health estimation methods of Li-ion batteries for real applications10.1016/j.rser.2015.11.042 ↗
6. Data-driven prediction of battery cycle life before capacity degradation10.1038/s41560-019-0356-8 ↗
7. State of Charge Estimation for Lithium-Ion Battery Using Recurrent NARX Neural Network Model Based Lighting Search Algorithm10.1109/ACCESS.2018.2837156 ↗
8. Remaining Useful Life Prediction for Lithium-Ion Battery: A Deep Learning Approach10.1109/ACCESS.2018.2858856 ↗
9. Predicting the state of charge and health of batteries using data-driven machine learning10.1038/s42256-020-0156-7 ↗
10. Long Short-Term Memory10.1162/neco.1997.9.8.1735 ↗
11. Long Short-Term Memory Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries10.1109/TVT.2018.2805189 ↗
12. Sequence to Sequence Learning with Neural Networks
13. Multi-time-scale framework for prognostic health condition of lithium battery using modified Gaussian process regression and nonlinear regression10.1016/j.jpowsour.2020.228358 ↗
14. Prognostics Methods for Battery Health Monitoring Using a Bayesian Framework10.1109/TIM.2008.2005965 ↗
15. State-of-charge estimation for lithium-ion batteries based on attentional sequence-to-sequence architecture10.1016/j.est.2023.106836 ↗
16. State-of-charge estimation of Li-ion batteries using deep neural networks: A machine learning approach10.1016/j.jpowsour.2018.06.104 ↗
17. State of health and remaining useful life prediction of lithium-ion batteries based on a disturbance-free incremental capacity and differential voltage analysis method10.1016/j.est.2023.107161 ↗
18. 18650 vs. 21700 Li-ion cells—A direct comparison of electrochemical, thermal, and geometrical properties10.1016/j.jpowsour.2020.228614 ↗
19. Critical review of the methods for monitoring of lithium-ion batteries in electric and hybrid vehicles10.1016/j.jpowsour.2014.02.064 ↗
20. Ageing mechanisms in lithium-ion batteries10.1016/j.jpowsour.2005.01.006 ↗
21. A comprehensive review of lithium-ion battery state estimation methods: From shallow learning to deep learning
22. Degradation diagnostics for lithium ion cells10.1016/j.jpowsour.2016.12.011 ↗
23. Diagnosis of Current Flow Patterns Inside Fault-Simulated Li-Ion Batteries via Non-Invasive, In Operando Magnetic Field Imaging10.1002/smtd.202300748 ↗
24. Capacity and degradation mode estimation for lithium-ion batteries based on partial charging curves at different current rates10.1016/j.est.2022.106517 ↗
25. Gaussian process regression for forecasting battery state of health10.1016/j.jpowsour.2017.05.004 ↗
26. Remaining useful life prediction of lithium-ion batteries based on attention mechanism and bidirectional long short-term memory network10.1016/j.measurement.2022.112093 ↗
27. CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
28. Novel informed deep learning-based prognostics framework for on-board health monitoring of lithium-ion batteries10.1016/j.apenergy.2022.119011 ↗
29. An LSTM-SA model for SOC estimation of lithium-ion batteries under various temperatures and aging levels10.1016/j.est.2024.110906 ↗
30. Capacity estimation of lithium-ion batteries with automatic feature extraction and graph-enhanced LSTM10.1016/j.est.2024.111131 ↗
31. LSTM-Based Battery Remaining Useful Life Prediction with Multi-Channel Charging Profiles10.1109/ACCESS.2020.2968939 ↗
32. Chen, D., Zhang, W., Zhang, C., Sun, B., Chen, H., Yang, S., and Cong, X. (2023). A Novel Sequence-to-Sequence Prediction Model for Lithium-Ion Battery Capacity Degradation Based on Improved Particle Swarm Optimization. Batteries, 9.10.3390/batteries9080414 ↗
33. Online State-of-Health Estimation for Li-Ion Battery Using Partial Charging Segment Based on Support Vector Machine10.1109/TVT.2019.2927120 ↗
34. Modeling and prediction of lithium-ion battery thermal runaway via multiphysics-informed neural network10.1016/j.est.2023.106654 ↗
35. Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review10.1016/j.rser.2019.109254 ↗
36. An indirect remaining useful life prognosis for Li-ion batteries based on health indicator and novel artificial neural network10.1016/j.est.2022.104701 ↗
37. A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve10.1016/j.jpowsour.2018.03.015 ↗
38. Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning10.1038/s41467-020-15235-7 ↗
39. A critical review on self-adaptive Li-ion battery ageing models10.1016/j.jpowsour.2018.08.064 ↗
40. A review of the state of health for lithium-ion batteries: Research status and suggestions10.1016/j.jclepro.2020.120813 ↗
41. Data-driven designs and multi-scale simulations of enhanced ion transport in low-temperature operation for lithium-ion batteries10.1007/s11814-022-1364-0 ↗
42. Deep-learning based spatio-temporal generative model on assessing state-of-health for Li-ion batteries with partially-cycled profiles10.1039/D3MH00013C ↗
43. Model-free reconstruction of capacity degradation trajectory of lithium-ion batteries using early cycle data10.1016/j.etran.2023.100243 ↗
44. Study on Li-ion battery fast charging strategies: Review, challenges and proposed charging framework10.1016/j.est.2022.105507 ↗