Two-phase early prediction method for remaining useful life of lithium-ion batteries based on a neural network and Gaussian process regression

doi:10.1007/s11708-023-0906-4

2024, Vol. 18

Issue (4) : 447-462 https://doi.org/10.1007/s11708-023-0906-4

Two-phase early prediction method for remaining useful life of lithium-ion batteries based on a neural network and Gaussian process regression

Zhiyuan WEI¹, Changying LIU¹, Xiaowen SUN¹, Yiduo LI¹, Haiyan LU²(

)

¹. College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130021, China
². College of Chemistry, Jilin University, Changchun 130012, China; Changsha Automobile Innovation Research Institute of Jilin University, Changsha 410006, China

Download: PDF(8318 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Lithium-ion batteries (LIBs) are widely used in transportation, energy storage, and other fields. The prediction of the remaining useful life (RUL) of lithium batteries not only provides a reference for health management but also serves as a basis for assessing the residual value of the battery. In order to improve the prediction accuracy of the RUL of LIBs, a two-phase RUL early prediction method combining neural network and Gaussian process regression (GPR) is proposed. In the initial phase, the features related to the capacity degradation of LIBs are utilized to train the neural network model, which is used to predict the initial cycle lifetime of 124 LIBs. The Pearson coefficient’s two most significant characteristic factors and the predicted normalized lifetime form a 3D space. The Euclidean distance between the test dataset and each cell in the training dataset and validation dataset is calculated, and the shortest distance is considered to have a similar degradation pattern, which is used to determine the initial Dual Exponential Model (DEM). In the second phase, GPR uses the DEM as the initial parameter to predict each test set’s early RUL (ERUL). By testing four batteries under different working conditions, the RMSE of all capacity estimation is less than 1.2%, and the accuracy percentage (AP) of remaining life prediction is more than 98%. Experiments show that the method does not need human intervention and has high prediction accuracy.

Keywords lithium-ion batteries RUL prediction double exponential model neural network Gaussian process regression (GPR)

Corresponding Author(s): Haiyan LU

About author:

Chunqi Yang contributed equally to this work.

Online First Date: 01 December 2023 Issue Date: 31 July 2024

Cite this article:

Zhiyuan WEI,Changying LIU,Xiaowen SUN, et al. Two-phase early prediction method for remaining useful life of lithium-ion batteries based on a neural network and Gaussian process regression[J]. Front. Energy, 2024, 18(4): 447-462.

URL:

https://academic.hep.com.cn/fie/EN/10.1007/s11708-023-0906-4
https://academic.hep.com.cn/fie/EN/Y2024/V18/I4/447

Fig.1 Capacity degradation of 124 LFP/graphite cells.

Fig.2 Results of feature factor extraction.

Notation	Feature name	Details of extracted features
F1	DeltaYmax	dQ/dV, the maximum value of the y-axis on the IC curve between the 2nd and 100th cycles
F2	DeltaXmax	dQ/dV max (V), the maximum value of the x-axis on the IC curve between the 2nd and 100th cycles
F3	DeltaQvar	Variance = $log ? (\| 1 p − 1 ∑ i = 1 p (Δ Q (V) − Δ Q ¯ (V)) 2 \|)$
F4	DeltaQmin	log(\|min(?Q(V))\|)
F5	CapFadeCycle2Slope	Slope of discharge curve, cycles 2 to 100 = first value in vector b* as in Eq. (5), where d = 99
F6	AvgChargeTime	Average charge time = $15 ∑ i = 2 6 Ch arg ? e Tim e i$
F7	MinIR	Minimum internal resistance = $min n ? IR (n)$
F8	IRDiff2And100	Internal resistance, cycle 100 – cycle 2 = $IR (n = 100) − IR (n = 2)$
F9	IntegralTemp	Temperature integral, cycles 2 to 100 = $∫ t 2 t 100 T (t) d t$

Tab.1 Extraction of feature factors

Fig.3 Distribution of feature factors.

Fig.4 Structure of neural network.

Fig.5 Flowchart of proposed methodology.

Tab.2 RMSE and MAPE results

Fig.6 Comparison of actual cycle life of training, validation, and test data sets with predicted cycle life.

Fig.7 Capacity degradation data of overall test data set.

Tab.3 DEM parameters

Fig.8 Fitting curves of four chosen LIBs.

Fig.9 Predicted capacities.

Tab.4 Evaluation index of EOM cycle

Tab.5 Comparison of Cell1 statistical error and prediction results

Fig.10 Comparison of algorithm results.

1	F Sun. Green energy and intelligent transportation—Promoting green and intelligent mobility. Green Energy and Intelligent Transportation, 2022, 1(1): 100017 https://doi.org/10.1016/j.geits.2022.100017
2	R XiongJ KimW Shen, et al.. Key technologies for electric vehicles. Green Energy and Intelligent Transportation, 2022, 1(2): 100041
3	H He, F Sun, Z Wang. et al.. China’s battery electric vehicles lead the world: Achievements in technology system architecture and technological breakthroughs. Green Energy and Intelligent Transportation, 2022, 1(1): 100020 https://doi.org/10.1016/j.geits.2022.100020
4	M S H Lipu, M A Hannan, A Hussain. et al.. A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations. Journal of Cleaner Production, 2018, 205: 115–133 https://doi.org/10.1016/j.jclepro.2018.09.065
5	H Meng, Y F Li. A review on prognostics and health management (PHM) methods of lithium-ion batteries. Renewable & Sustainable Energy Reviews, 2019, 116: 109405 https://doi.org/10.1016/j.rser.2019.109405
6	M F Ge, Y B Liu, X X Jiang. et al.. A review on state of health estimations and remaining useful life prognostics of lithium-ion batteries. Measurement, 2021, 174: 109057 https://doi.org/10.1016/j.measurement.2021.109057
7	S M Rezvanizaniani, Z Liu, Y Chen. et al.. Review and recent advances in battery health monitoring and prognostics technologies for electric vehicle (EV) safety and mobility. Journal of Power Sources, 2014, 256: 110–124 https://doi.org/10.1016/j.jpowsour.2014.01.085
8	X S Xiong, R Sun, W Q Yan. et al.. A lithiophilic AlN-modified copper layer for high-performance lithium metal anodes. Journal of Materials Chemistry. A, Materials for Energy and Sustainability, 2022, 10(26): 13814–13820 https://doi.org/10.1039/D2TA02138B
9	T Wang, J R He, X B Cheng. et al.. Strategies toward high-loading lithium-sulfur batteries. ACS Energy Letters, 2022, 8(1): 116–150
10	M Ates, A Chebil. Supercapacitor and battery performances of multi-component nanocomposites: Real circuit and equivalent circuit model analysis. Journal of Energy Storage, 2022, 53: 105093 https://doi.org/10.1016/j.est.2022.105093
11	D Z Li, D F Yang, L W Li. et al.. Electrochemical impedance spectroscopy based on the state of health estimation for lithium-ion batteries. Energies, 2022, 15(18): 6665 https://doi.org/10.3390/en15186665
12	J B Son, S Y Zhou, C Sankavaram. et al.. Remaining useful life prediction based on noisy condition monitoring signals using constrained Kalman filter. Reliability Engineering & System Safety, 2016, 152: 38–50 https://doi.org/10.1016/j.ress.2016.02.006
13	Q Xia, Z L Wang, Y Ren. et al.. A modified reliability model for lithium-ion battery packs based on the stochastic capacity degradation and dynamic response impedance. Journal of Power Sources, 2019, 423: 40–51 https://doi.org/10.1016/j.jpowsour.2019.03.042
14	Mo B H, Yu J S, Tang D Y, et al. A remaining useful life prediction approach for lithium-ion batteries using Kalman filter and an improved particle filter. In: 2016 IEEE International Conference on Prognostics and Health Management, Ottawa, Canada, 2016
15	D Wang, F F Yang, K L Tsui. et al.. Remaining useful life prediction of lithium-ion batteries based on spherical cubature particle filter. IEEE Transactions on Instrumentation and Measurement, 2016, 65(6): 1282–1291 https://doi.org/10.1109/TIM.2016.2534258
16	G Xie, X Peng, X Li. et al.. Remaining useful life prediction of lithium-ion battery based on an improved particle filter algorithm. Canadian Journal of Chemical Engineering, 2020, 98(6): 1365–1376 https://doi.org/10.1002/cjce.23675
17	L Ren, L Zhao, S Hong. et al.. Remaining useful life prediction for lithium-ion battery: A deep learning approach. IEEE Access: Practical Innovations, Open Solutions, 2018, 6: 50587–50598 https://doi.org/10.1109/ACCESS.2018.2858856
18	G Z Dong, F F Yang, Z B Wei. et al.. Data-driven battery health prognosis using adaptive Brownian motion model. IEEE Transactions on Industrial Informatics, 2020, 16(7): 4736–4746 https://doi.org/10.1109/TII.2019.2948018
19	Y Li, K L Liu, A M Foley. et al.. Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review. Renewable & Sustainable Energy Reviews, 2019, 113: 109254 https://doi.org/10.1016/j.rser.2019.109254
20	K A Severson, P M Attia, N Jin. et al.. Data-driven prediction of battery cycle life before capacity degradation. Nature Energy, 2019, 4(5): 383–391 https://doi.org/10.1038/s41560-019-0356-8
21	J T He, Z B Wei, X L Bian. et al.. State-of-health estimation of lithium-ion batteries using incremental capacity analysis based on voltage-capacity model. IEEE Transactions on Transportation Electrification, 2020, 6(2): 417–426 https://doi.org/10.1109/TTE.2020.2994543
22	Y X Yang. A machine-learning prediction method of lithium-ion battery life based on charge process for different applications. Applied Energy, 2021, 292: 116897 https://doi.org/10.1016/j.apenergy.2021.116897
23	J G Wang, S D Zhang, C Y Li. et al.. A data-driven method with mode decomposition mechanism for remaining useful life prediction of lithium-ion batteries. IEEE Transactions on Power Electronics, 2022, 37(11): 13684–13695 https://doi.org/10.1109/TPEL.2022.3183886
24	W Zhang, X Li, X Li. Deep learning-based prognostic approach for lithium-ion batteries with adaptive time-series prediction and online validation. Measurement, 2020, 164: 108052 https://doi.org/10.1016/j.measurement.2020.108052
25	C H Weng, J Sun, H Peng. Model parametrization and adaptation based on the invariance of support vectors with applications to battery state-of-health monitoring. IEEE Transactions on Vehicular Technology, 2015, 64(9): 3908–3917 https://doi.org/10.1109/TVT.2014.2364554
26	Y H ShiY R YangJ Wen, et al.. Remaining useful life Prediction for lithium-ion battery based on CEEMDAN and SVR. In: 18th IEEE International Conference on Industrial Informatics, Warwick, UK, 2020, 888–893
27	H C Dong, X N Jin, Y B Lou. et al.. Lithium-ion battery state of health monitoring and remaining useful life prediction based on support vector regression-particle filter. Journal of Power Sources, 2014, 271: 114–123 https://doi.org/10.1016/j.jpowsour.2014.07.176
28	G Q ZhaoG H ZhangY F Liu, et al.. Lithium-ion battery remaining useful life prediction with deep belief network and relevance vector machine. In: IEEE International Conference on Prognostics and Health Management, Dallas, TX, USA, 2017, 7–13
29	X Y Li, Z P Wang, J Y Yan. Prognostic health condition for lithium battery using the partial incremental capacity and Gaussian process regression. Journal of Power Sources, 2019, 421: 56–67 https://doi.org/10.1016/j.jpowsour.2019.03.008
30	X Q Pang, R Huang, J Wen. et al.. A lithium-ion battery RUL prediction method considering the capacity regeneration phenomenon. Energies, 2019, 12(12): 2247 https://doi.org/10.3390/en12122247
31	M F Niri, T M N Bui, T Q Dinh. et al.. Remaining energy estimation for lithium-ion batteries via Gaussian mixture and Markov models for future load prediction. Journal of Energy Storage, 2020, 28: 101271 https://doi.org/10.1016/j.est.2020.101271
32	X Y Li, L Zhang, Z P Wang. et al.. Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks. Journal of Energy Storage, 2019, 21: 510–518 https://doi.org/10.1016/j.est.2018.12.011
33	H Karami, M F Mousavi, M Shamsipur. et al.. New dry and wet Zn-polyaniline bipolar batteries and prediction of voltage and capacity by ANN. Journal of Power Sources, 2006, 154(1): 298–307 https://doi.org/10.1016/j.jpowsour.2005.04.002
34	C C Chan, E W C Lo, W X Shen. The available capacity computation model based on artificial neural network for lead-acid batteries in electric vehicles. Journal of Power Sources, 2000, 87(1–2): 201–204 https://doi.org/10.1016/S0378-7753(99)00502-9
35	D Mazzeo, M S Herdem, N Matera. et al.. Artificial intelligence application for the performance prediction of a clean energy community. Energy, 2021, 232: 120999 https://doi.org/10.1016/j.energy.2021.120999
36	M Y Wang, W F Hu, Y F Jiang. et al.. Internal temperature prediction of ternary polymer lithium-ion battery pack based on CNN and virtual thermal sensor technology. International Journal of Energy Research, 2021, 45(9): 13681–13691 https://doi.org/10.1002/er.6699
37	J T Qu, F Liu, Y X Ma. et al.. A neural-network-based method for RUL prediction and SOH monitoring of lithium-ion battery. IEEE Access: Practical Innovations, Open Solutions, 2019, 7: 87178–87191 https://doi.org/10.1109/ACCESS.2019.2925468
38	M Catelani, L Ciani, R Fantacci. et al.. Remaining useful life estimation for prognostics of lithium-ion batteries based on recurrent neural network. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1 https://doi.org/10.1109/TIM.2021.3111009
39	X Feng, J X Chen, Z W Zhang. et al.. State-of-charge estimation of lithium-ion battery based on clockwork recurrent neural network. Energy, 2021, 236: 121360 https://doi.org/10.1016/j.energy.2021.121360
40	X J Zheng, H J Fang. An integrated unscented Kalman filter and relevance vector regression approach for lithium-ion battery remaining useful life and short-term capacity prediction. Reliability Engineering & System Safety, 2015, 144: 74–82 https://doi.org/10.1016/j.ress.2015.07.013
41	Z W Xue, Y Zhang, C Cheng. et al.. Remaining useful life prediction of lithium-ion batteries with adaptive unscented Kalman filter and optimized support vector regression. Neurocomputing, 2020, 376: 95–102 https://doi.org/10.1016/j.neucom.2019.09.074
42	Z W Deng, L Xu, H A Liu. et al.. Prognostics of battery capacity based on charging data and data-driven methods for on-road vehicles. Applied Energy, 2023, 339: 120954 https://doi.org/10.1016/j.apenergy.2023.120954
43	Z W Deng, X K Lin, J W Cai. et al.. Battery health estimation with degradation pattern recognition and transfer learning. Journal of Power Sources, 2022, 525: 231027 https://doi.org/10.1016/j.jpowsour.2022.231027
44	S S Zhao, C L Zhang, Y Z Wang. Lithium-ion battery capacity and remaining useful life prediction using board learning system and long short-term memory neural network. Journal of Energy Storage, 2022, 52: 104901 https://doi.org/10.1016/j.est.2022.104901
45	C L Zhang, S S Zhao, Y G He. An integrated method of the future capacity and RUL prediction for lithium-ion battery pack. IEEE Transactions on Vehicular Technology, 2022, 71(3): 2601–2613 https://doi.org/10.1109/TVT.2021.3138959
46	C L Zhang, S S Zhao, Z Yang. et al.. A reliable data-driven state-of-health estimation model for lithium-ion batteries in electric vehicles. Frontiers in Energy Research, 2022, 10: 1013800 https://doi.org/10.3389/fenrg.2022.1013800
47	Z Zhou, Y Liu, M You. et al.. Two-stage aging trajectory prediction of LFP lithium-ion battery based on transfer learning with the cycle life prediction. Green Energy and Intelligent Transportation, 2022, 1(1): 100008 https://doi.org/10.1016/j.geits.2022.100008
48	G J Ma, Z D Wang, W B Liu. et al.. A two-stage integrated method for early prediction of remaining useful life of lithium-ion batteries?. Knowledge-based Systems, 2023, 259: 110012 https://doi.org/10.1016/j.knosys.2022.110012
49	L J Zhang, Z Q Mu, C Y Sun. Remaining useful life prediction for lithium-ion batteries based on exponential model and particle filter. IEEE Access: Practical Innovations, Open Solutions, 2018, 6: 17729–17740 https://doi.org/10.1109/ACCESS.2018.2816684
50	Z L Huang, F Xu, F F Yang. State of health prediction of lithium-ion batteries based on autoregression with exogenous variables model. Energy, 2023, 262: 125497 https://doi.org/10.1016/j.energy.2022.125497
51	Q S Zhang, L Yang, W C Guo. et al.. A deep learning method for lithium-ion battery remaining useful life prediction based on sparse segment data via cloud computing system. Energy, 2022, 241: 122716 https://doi.org/10.1016/j.energy.2021.122716

[1]	Nan QI, Kang YAN, Yajuan YU, Rui LI, Rong HUANG, Lai CHEN, Yuefeng SU. Machine learning and neural network supported state of health simulation and forecasting model for lithium-ion battery[J]. Front. Energy, 2024, 18(2): 223-240.
[2]	Pardeep SINGLA, Manoj DUHAN, Sumit SAROHA. A comprehensive review and analysis of solar forecasting techniques[J]. Front. Energy, 2022, 16(2): 187-223.
[3]	Yaolin LIN, Wei YANG. An ANN-exhaustive-listing method for optimization of multiple building shapes and envelope properties with maximum thermal performance[J]. Front. Energy, 2021, 15(2): 550-563.
[4]	Rashmi P. SHETTY, A. SATHYABHAMA, P. Srinivasa PAI. Comparison of modeling methods for wind power prediction: a critical study[J]. Front. Energy, 2020, 14(2): 347-358.
[5]	Shifeng YANG, Wenfeng REN, Jian CHEN. Li₄SiO₄-coated LiNi_0.5Mn_1.5O₄ as the high performance cathode materials for lithium-ion batteries[J]. Front. Energy, 2017, 11(3): 374-382.
[6]	S. Surender REDDY, Chan-Mook JUNG, Ko Jun SEOG. Day-ahead electricity price forecasting using back propagation neural networks and weighted least square technique[J]. Front. Energy, 2016, 10(1): 105-113.
[7]	Arunachalam VELMURUGAN,Marimuthu LOGANATHAN,E. James GUNASEKARAN. Prediction of performance, combustion and emission characteristics of diesel-thermal cracked cashew nut shell liquid blends using artificial neural network[J]. Front. Energy, 2016, 10(1): 114-124.
[8]	Solomon O. GIWA,Sunday O. ADEKOMAYA,Kayode O. ADAMA,Moruf O. MUKAILA. Prediction of selected biodiesel fuel properties using artificial neural network[J]. Front. Energy, 2015, 9(4): 433-445.
[9]	J. JAYACHANDRAN, R. MURALI SACHITHANANDAM. Performance investigation of artificial intelligence based controller for three phase four leg shunt active filter[J]. Front. Energy, 2015, 9(4): 446-460.
[10]	A. CHITRA,S. HIMAVATHI. A modified neural learning algorithm for online rotor resistance estimation in vector controlled induction motor drives[J]. Front. Energy, 2015, 9(1): 22-30.
[11]	Chang CHEN,Danmei XIE,Yangheng XIONG,Hengliang ZHANG. Optimization of turbine cold-end system based on BP neural network and genetic algorithm[J]. Front. Energy, 2014, 8(4): 459-463.
[12]	Moulay Rachid DOUIRI, Mohamed CHERKAOUI. Comparative study of various artificial intelligence approaches applied to direct torque control of induction motor drives[J]. Front Energ, 2013, 7(4): 456-467.
[13]	Srinivasan CHANDRASEKARAN, Arunachalam AMARKARTHIK, Karuppan SIVAKUMAR, Dhanasekaran SELVAMUTHUKUMARAN, Shaji SIDNEY. Experimental investigation and ANN modeling on improved performance of an innovative method of using heave response of a non-floating object for ocean wave energy conversion[J]. Front Energ, 2013, 7(3): 279-287.
[14]	ZHANG Xinhai, XI Guang, ZHANG Xinhai. New experimental technique to determine coal self-ignition duration[J]. Front. Energy, 2008, 2(4): 479-483.
[15]	ZHAO Honglei, WANG Songtao, HAN Wanjin, FENG Guotai. Aerodynamic design by jointly applying S2 flow surface calculation and modern optimization methods on multistage axial turbine[J]. Front. Energy, 2008, 2(1): 93-98.

Viewed

Full text

Abstract

Cited

Shared

Discussed