Battery State of Health Estimation with Improved Generalization Using Parallel Layer Extreme Learning Machine
Abstract
:1. Introduction
2. Methodology
2.1. Deterministic Extreme Learning Machine
2.2. Deterministic Parallel Layer Extreme Learning Machine
2.3. Experimental Dataset Description
2.4. State of Health (SOH)
2.5. Characterization and Feature Selection
2.6. Summary of Scheme Setup Procedure
Model Input: [$\Delta $V, $\Delta $SOC, $\Delta $E] $\in {\mathbb{R}}^{\mathbf{3}\times \mathit{N}}$ 
Model Output:SOH $\in {\mathbb{R}}^{\mathbf{1}\times \mathit{N}}$ 

3. Results and Discussion
3.1. PLELM Model Training
3.2. PLELM Model Validation
3.3. Model Comparison with Deterministic ELM and Demonstration of the Drift Problem
4. Summary and Conclusions
Author Contributions
Funding
Conflicts of Interest
References
 Gantenbein, S.; Schönleber, M.; Weiss, M.; IversTiffee, E. Capacity Fade in lithiumIon Batteries and Cyclic Aging over Various StateofCharge Ranges. Sustainability 2019, 11, 6697. [Google Scholar]
 Vetter, J.; Novak, P.; Wagner, M.R.; Veit, C.; Moller, K.C.; Besenhard, J.O.; Winter, M.; WohlfahrtMehrens, M.; Vogler, C.; Hammouche, A. Aging mechanisms in lithiumion batteries. J. Power Sources 2005, 147, 269–281. [Google Scholar] [CrossRef]
 Victor, A.; Jeffrey, F. lithiumion Battery Anode Aging Mechanisms. Materials 2013, 6, 1310–1325. [Google Scholar]
 Groot, J. StateofHealth Estimation of lithiumion Batteries: Cycle Life Test Methods. Master’s Thesis, Chalmers University of Technology, Gothenburg, Sweden, 2012. Available online: http://publications.lib.chalmers.se/records/fulltext/154090/154090.pdf (accessed on 11 April 2021).
 Ramadass, P.; Bala, H.; Ralph, W.; Branko, N.P. Mathematical modelling of the capacity fade of lithiumion cells. J. Power Sources 2003, 123, 230–240. [Google Scholar] [CrossRef]
 Paulo, K.; Shengbo, E.L.; Dongsuk, K. Simplification of pseudo twodimensional battery model using dynamic profile of lithium concentration. J. Power Sources 2015, 286, 510–525. [Google Scholar]
 Linlin, F.; Junqiu, L.; Bo, P. Online Estimation and Error Analysis of both SOC and SOH of Lithiumion Battery based on DEKF Method. ICAE2018—The 10th International Conference on Applied Energy. Energy Procedia 2019, 158, 3008–3013. [Google Scholar]
 Hansen, T.; Wang, C.J. Support vectorbased battery state of charge estimator. J. Power Sources 2005, 141, 351–358. [Google Scholar] [CrossRef]
 Wang, J.; Guo, J.; Ding, L. An adaptive Kalman filtering based State of Charge combined estimator for electric vehicle battery pack. Energy Convers. Manag. 2009, 50, 3182–3186. [Google Scholar]
 He, J.; Wei, Z.; Bian, X.; Yan, F. StateofHealth Estimation of LithiumIon Batteries Using Incremental Capacity Analysis Based on Voltage–Capacity Model. IEEE Trans. Transp. Electrif. 2020, 6, 2. [Google Scholar] [CrossRef]
 Arijit, G.; Amit, P. State of Health Estimation of LithiumIon Batteries Using Capacity Fade and Internal Resistance Growth Models. IEEE Trans. Transp. Electrif. 2018, 4, 1. [Google Scholar]
 Christopher, R.; Osama, A.M. Adaptive Battery Management and Parameter Estimation Through PhysicsBased Modeling and Experimental Verification. IEEE Trans. Transp. Electrif. 2016, 2, 4. [Google Scholar]
 Liu, Z.; Dang, X. A New Method for State of Charge and Capacity Estimation of LithiumIon Battery Based on Dual Strong Tracking Adaptive H Infinity Filter. Math. Probl. Eng. 2018, 5218205, 18. [Google Scholar] [CrossRef] [Green Version]
 Wei, Z.; Zhao, J.; Ji, D.; Tseng, K.J. A multitime scale estimator for battery state of charge and capacity dual estimation based on an online identified model. Appl. Energy 2017, 204, 1264–1274. [Google Scholar] [CrossRef]
 Bonfitto, A.; Ezemobi, E.; Feraco, S.; Tonoli, A.; Amati, N.; Hegde, S. State of Health Estimation of Lithium Batteries for Automotive Applications with Artificial Neural Networks. In Proceedings of the 2019 AEIT International Conference of Electrical and Electronic Technologies for Automotive, AEIT AUTOMOTIVE, Turin, Italy, 2–4 July 2019. [Google Scholar]
 Chang, C.; Liu, Z.; Huang, Y.W.; Wei, D.Q.; Zhang, L. Estimation of Battery State of Health Using Back Propagation Neural Network. Comput. Aided Draft. Des. Manuf. 2014, 24, 60. [Google Scholar]
 Kim, J.; Yu, J.; Kim, M.; Kim, K.; Han, S. Estimation of lithiumion Battery State of Health based on Multilayer Perceptron: As an EV Application. IFAC Pap. 2018, 51, 392–397. [Google Scholar] [CrossRef]
 Wu, J.; Wang, Y.; Zhang, X.; Chen, Z. A novel state of health estimation method of lithiumion battery using group method of data handling. J. Power Sources 2016, 327, 457–464. [Google Scholar] [CrossRef]
 Bowen, J.; Yong, G.; Lifeng, W. A State of Health Estimation Framework for LithiumIon Batteries Using Transfer Components Analysis. Energies 2019, 12, 2524. [Google Scholar]
 Zhang, S.; Zhai, B.; Guo, X.; Wang, K.; Peng, N.; Zhang, X. Synchronous estimation of state of health and remaining useful lifetime for lithiumion battery using the incremental capacity and artificial neural networks. J. Energy Storage 2019, 26, 100951. [Google Scholar] [CrossRef]
 Weng, C.; Sun, J.; Peng, H. A unified opencircuitvoltage model of lithiumion batteries for stateofcharge estimation and stateofhealth monitoring. J. Power Sources 2014, 258, 228–237. [Google Scholar] [CrossRef]
 Bian, X.; Wei, Z.; He, J.; Yan, F.; Liu, L. A Novel Modelbased Voltage Construction Method for Robust Stateofhealth Estimation of Lithiumion Batteries. IEEE Trans. Ind. Electron. 2020. [Google Scholar] [CrossRef]
 Santhanagopalan, S.; White, R.E. Quantifying CelltoCell Variations in lithiumion Batteries. Int. J. Electrochem. 2012, 2012, 395838. [Google Scholar] [CrossRef] [Green Version]
 Pan, S.J.; Tsang, I.W.; Kwok, J.T.; Yang, Q. Domain Adaptation via Transfer Component Analysis. IEEE Trans. Neural Netw. 2011, 22, 199–210. [Google Scholar] [CrossRef] [Green Version]
 Tang, X.; Zou, C.; Yao, K.; Chen, G.; Liu, B.; He, Z.; Gao, F. A fast estimation algorithm for lithiumion battery state of health. J. Power Sources 2018, 396, 453–458. [Google Scholar] [CrossRef]
 Pan, H.; Lü, Z.; Wang, H.; Wei, H.; Chen, L. Novel battery stateofhealth online estimation method using multiple health indicators and an extreme learning machine. Energy 2018, 160, 466–477. [Google Scholar] [CrossRef]
 RazaviFar, R.; Chakrabarti, S.; Saif, M.; Zio, E.; Palade, V. Extreme Learning Machine Based Prognostics of Battery Life. Int. J. Artif. Intell. Tools 2018, 27, 1850036. [Google Scholar] [CrossRef]
 Henríquez, P.A.; Ruz, G.A. Extreme learning machine with a deterministic assignment of hidden weights in two parallel layers. Neurocomputing 2017, 226, 109–116. [Google Scholar] [CrossRef]
 Tavares, L.D.; Saldanha, R.R.; Vieira, D. Extreme learning machine with parallel layer perceptrons. Neurocomputing 2015, 166, 164–171. [Google Scholar] [CrossRef]
 Li, G.; Zou, J. Multiparallel Extreme Learning Machine with Excitatory and Inhibitory Neurons for Regression. Neural Process. Lett. 2019, 51, 1579–1597. [Google Scholar] [CrossRef]
 Qu, B.Y.; Lang, B.F.; Liang, J.J.; Qin, A.K.; Crisalle, O.D. Twohiddenlayer extreme learning machine for regression and classification. Neurocomputing 2016, 175, 826–834. [Google Scholar] [CrossRef]
 Tansel, D.; Ender, S. Evolutionary parallel extreme learning machines for the data classification problem. Comput. Ind. Eng. 2019, 130, 237–249. [Google Scholar]
 Saha, B.; Goebel, K. “Battery dataset”, NASA Ames Prognostics Data Repository; NASA Ames Research Center: Moffett Field, CA, USA, 2007; Available online: http://ti.arc.nasa.gov/project/prognosticdatarepository (accessed on 11 April 2021).
 Huang, G.B.; Zhu, Q.Y.; Siew, C.K. Extreme learning machine: Theory and applications. Neurocomputing 2006, 70, 489–501. [Google Scholar] [CrossRef]
 Huang, G.B.; Zhu, Q.Y.; Siew, C.K. Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks. Proceedings of International Joint Conference on Neural Networks, IJCNN 2004, Budapest, Hungary, 25–29 July 2004. [Google Scholar]
 Ömer, F.E.; Yılmaz, K. A detailed analysis on extreme learning machine and novel approaches based on ELM. Am. J. Comput. Sci. Eng. 2014, 1, 43–50. Available online: https://www.semanticscholar.org/paper/ADetailedAnalysisonExtremeLearningMachineandErtugrulKaya/08e6fcca9745ee3cc5e14b56d7472c068f5d94d8 (accessed on 11 April 2021).
 Krömer, P.; Platoš, J.; Snášel, V. Differential evolution for the optimization of lowdiscrepancy generalized Halton sequences. Swarm Evol. Comput. 2020, 54, 100649. [Google Scholar] [CrossRef]
 Martin, M.; Adel, G.A. Closer Look at State of Charge (SOC) and State of Health (SOH) Estimation Techniques for Batteries; TA1542102/17; Analog Devices Inc.: Norwood, MA, USA, 2017. [Google Scholar]
 Yang, J.; Yu, J.; Tang, D.; Dai, J. A closedloop voltage prognosis for lithiumion batteries under dynamic loads using an improved equivalent circuit model. Microelectron. Reliab. 2019, 100–101, 113459. [Google Scholar] [CrossRef]
 Bonfitto, A.; Feraco, S.; Tonoli, A.; Amati, N.; Monti, F. Estimation accuracy and computational cost analysis of artificial neural networks for state of charge estimation in lithium batteries. Batteries 2019, 5, 47. [Google Scholar] [CrossRef] [Green Version]
Indicator Variable  Model Train Features  Unit 

Training Feature  
Voltage (V)  ΔV  [V] 
State of Charge (SOC)  ΔSOC  [%] 
Energy (E)  ΔE  [Wh] 
Model Output  
State of Health (SOH)  $[\%]$ 
PLELM  ICA Model  

RMSE  MAE  EB  %${\mathit{E}}_{\mathit{OB}}$  RMSE  
Training  B0007  0.046  0.034  (−0.14, 0.14)  1.570  0.66 
Validation  B0005  0.362  0.345  ( 0.02, 0.67)  2.037  0.87 
B0006  0.473  0.355  (−0.62, 1.31)  3.240  2.49  
B0018  0.170  0.158  (−0.04, 0.36)  0.250   
RMSE  MAE  EB  %${\mathit{E}}_{\mathit{OB}}$  

Training  B0007  0.245  0.191  (−0.74, 0.74)  0.615 
Validation  B0005  1.117  0.762  (−1.70, 3.22)  1.24 
B0006  1.563  0.907  (−3.18, 4.82)  0.19  
B0018  0.501  0.361  (−0.79, 1.46 )  0.89 
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. 
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ezemobi, E.; Tonoli, A.; Silvagni, M. Battery State of Health Estimation with Improved Generalization Using Parallel Layer Extreme Learning Machine. Energies 2021, 14, 2243. https://doi.org/10.3390/en14082243
Ezemobi E, Tonoli A, Silvagni M. Battery State of Health Estimation with Improved Generalization Using Parallel Layer Extreme Learning Machine. Energies. 2021; 14(8):2243. https://doi.org/10.3390/en14082243
Chicago/Turabian StyleEzemobi, Ethelbert, Andrea Tonoli, and Mario Silvagni. 2021. "Battery State of Health Estimation with Improved Generalization Using Parallel Layer Extreme Learning Machine" Energies 14, no. 8: 2243. https://doi.org/10.3390/en14082243