Abstract
Lithium-ion batteries (LIBs) are currently the standard for energy storage in portable consumer electronic devices. They are also used in electric vehicles and in some large industrial settings and for grid power storage. The adverse consequences of a dramatic battery failure can be significant compared with the cost of timely replacement or maintenance. Consequently, accurate state-of-health (SOH) prediction is important to inform maintenance or replacement decisions. In this work, we address current challenges related to accuracy and interpretability in data-driven SOH prediction for LIBs by devising a novel physics-informed machine learning prognostic model, termed PIDDA. PIDDA includes three elements: an autoencoder, a physics-informed model training, and a physics-based prediction adjustment. We examine and benchmark our model against alternative data-driven SOH prediction models using the NASA battery prognostic dataset. The computational experiments demonstrate that PIDDA (1) provides significantly higher prediction accuracy; (2) requires less prior data for its predictions; (3) produces more informative and interpretable predictions than alternative models. We conclude with an ablation study of PIDDA to analyze the relative effectiveness of two of its elements, the physics equations in the model training and the physics-based prediction adjustment. The results show that the former (training) provides the heavy lifting in accuracy improvement, roughly two-thirds, and the latter (adjustment) the remaining incremental improvement.
Similar content being viewed by others
References
Ng KS, Moo CS, Chen YP, Hsieh YC (2009) Enhanced coulomb counting method for estimating state-of-charge and state-of-health of lithium-ion batteries. Appl Energy 86(9):1506–1511
Huet F (1998) A review of impedance measurements for determination of the state-of-charge or state-of-health of secondary batteries. J Power Sources 70(1):59–69
Berecibar M, Gandiaga I, Villarreal I, Omar N, Van Mierlo J, Van den Bossche P (2016) Critical review of state of health estimation methods of Li-ion batteries for real applications. Renew Sustain Energy Rev 56:572–587
Venugopal P (2019) State-of-Health estimation of li-ion batteries in electric vehicle using IndRNN under variable load condition. Energies 12(22):4338
Pistoia G (2013) Lithium-ion batteries. Elsevier, Amsterdam
Horiba T (2014) Lithium-ion battery systems. Proc IEEE 102(6):939–950
Lu L, Han X, Li J, Hua J, Ouyang M (2013) A review on the key issues for lithium-ion battery management in electric vehicles. J Power Sources 226:272–288
Mi C, Li B, Buck D, Ota N (2007) Advanced electro-thermal modeling of lithium-ion battery system for hybrid electric vehicle applications. In: 2007 IEEE vehicle power and propulsion conference. IEEE, pp 107–111
Zhang J, Lee J (2011) A review on prognostics and health monitoring of Li-ion battery. J Power Sources 196(15):6007–6014
Cabrera-Castillo E, Niedermeier F, Jossen A (2016) Calculation of the state of safety (SOS) for lithium ion batteries. J Power Sources 324:509–520
Hong J, Lee D, Jeong ER, Yi Y (2020) Towards the swift prediction of the remaining useful life of lithium-ion batteries with end-to-end deep learning. Appl Energy 278:115646
Zhang Z, Wang YX, He H, Sun F (2021) A short-and long-term prognostic associating with remaining useful life estimation for proton exchange membrane fuel cell. Appl Energy 304:117841
Lin CP, Cabrera J, Yang F, Ling MH, Tsui KL, Bae SJ (2020) Battery state of health modeling and remaining useful life prediction through time series model. Appl Energy 275:115338
Eleftheroglou N, Mansouri SS, Loutas T, Karvelis P, Georgoulas G, Nikolakopoulos G, Zarouchas D (2019) Intelligent data-driven prognostic methodologies for the real-time remaining useful life until the end-of-discharge estimation of the Lithium-Polymer batteries of unmanned aerial vehicles with uncertainty quantification. Appl Energy 254:113677
Ma G, Zhang Y, Cheng C, Zhou B, Hu P, Yuan Y (2019) Remaining useful life prediction of lithium-ion batteries based on false nearest neighbors and a hybrid neural network. Appl Energy 253:113626
Yang D, Zhang X, Pan R, Wang Y, Chen Z (2018) A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve. J Power Sources 384:387–395
Richardson RR, Osborne MA, Howey DA (2017) Gaussian process regression for forecasting battery state of health. J Power Sources 357:209–219
Liu D, Luo Y, Liu J, Peng Y, Guo L, Pecht M (2014) Lithium-ion battery remaining useful life estimation based on fusion nonlinear degradation AR model and RPF algorithm. Neural Comput Appl 25(3):557–572
Liu D, Pang J, Zhou J, Peng Y, Pecht M (2013) Prognostics for state of health estimation of lithium-ion batteries based on combination Gaussian process functional regression. Microelectron Reliab 53(6):832–839
Patil MA, Tagade P, Hariharan KS, Kolake SM, Song T, Yeo T, Doo S (2015) A novel multistage support vector machine based approach for Li ion battery remaining useful life estimation. Appl Energy 159:285–297
Saha B, Goebel K (2008) Uncertainty management for diagnostics and prognostics of batteries using Bayesian techniques. In: 2008 IEEE aerospace conference. IEEE, pp 1–8
Saha B, Goebel K (2007) Battery data set. NASA AMES prognostics data repository
Saha B, Goebel K, Christophersen J (2009) Comparison of prognostic algorithms for estimating remaining useful life of batteries. Trans Inst Meas Control 31(3–4):293–308
Ren L, Zhao L, Hong S, Zhao S, Wang H, Zhang L (2018) Remaining useful life prediction for lithium-ion battery: a deep learning approach. IEEE Access 6:50587–50598
Ren L, Dong J, Wang X, Meng Z, Zhao L, Deen MJ (2020) A data-driven auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life. IEEE Trans Industr Inf 17(5):3478–3487
Guo P, Cheng Z, Yang L (2019) A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction. J Power Sources 412:442–450
Tagade P, Hariharan KS, Ramachandran S, Khandelwal A, Naha A, Kolake SM, Han SH (2020) Deep Gaussian process regression for lithium-ion battery health prognosis and degradation mode diagnosis. J Power Sources 445:227281
Severson KA, Attia PM, Jin N, Perkins N, Jiang B, Yang Z, Chen MH, Aykol M, Herring PK, Fraggedakis D, Bazant MZ (2019) Data-driven prediction of battery cycle life before capacity degradation. Nat Energy 4(5):383–391
Lea C, Vidal R, Reiter A, Hager GD (2016) Temporal convolutional networks: a unified approach to action segmentation. In: European conference on computer vision. Springer, Cham, pp 47–54
Kara A (2021) A data-driven approach based on deep neural networks for lithium-ion battery prognostics. Neural Comput Appl 1–14
Widodo A, Shim MC, Caesarendra W, Yang BS (2011) Intelligent prognostics for battery health monitoring based on sample entropy. Expert Syst Appl 38(9):11763–11769
Van der Aalst WM, Rubin V, Verbeek HMW, van Dongen BF, Kindler E, Günther CW (2010) Process mining: a two-step approach to balance between underfitting and overfitting. Softw Syst Model 9(1):87–111
Koehrsen W (2018) Overfitting vs. underfitting: a complete example. Towards Data Science
Gavrilov AD, Jordache A, Vasdani M, Deng J (2018) Preventing model overfitting and underfitting in convolutional neural networks. Int J Softw Sci Comput Intell (IJSSCI) 10(4):19–28
Karniadakis GE, Kevrekidis IG, Lu L, Perdikaris P, Wang S, Yang L (2021) Physics-informed machine learning. Nat Rev Phys 3(6):422–440
Aykol M, Gopal CB, Anapolsky A, Herring PK, van Vlijmen B, Berliner MD, Bazant MZ, Braatz RD, Chueh WC, Storey BD (2021) Perspective—combining physics and machine learning to predict battery lifetime. J Electrochem Soc 168(3):030525
Doyle M, Fuller TF, Newman J (1993) Modeling of galvanostatic charge and discharge of the lithium/polymer/insertion cell. J Electrochem Soc 140(6):1526
Reniers JM, Mulder G, Howey DA (2019) Review and performance comparison of mechanical-chemical degradation models for lithium-ion batteries. J Electrochem Soc 166(14):A3189
Jokar A, Rajabloo B, Désilets M, Lacroix M (2016) Review of simplified pseudo-two-dimensional models of lithium-ion batteries. J Power Sources 327:44–55
Northrop PW, Suthar B, Ramadesigan V, Santhanagopalan S, Braatz RD, Subramanian VR (2014) Efficient simulation and reformulation of lithium-ion battery models for enabling electric transportation. J Electrochem Soc 161(8):E3149
Single F, Horstmann B, Latz A (2017) Revealing SEI morphology: in-depth analysis of a modeling approach. J Electrochem Soc 164(11):E3132
Das S, Attia PM, Chueh WC, Bazant MZ (2019) Electrochemical kinetics of SEI growth on carbon black: part II. Model J Electrochem Soc 166(4):E107
Pinson MB, Bazant MZ (2012) Theory of SEI formation in rechargeable batteries: capacity fade, accelerated aging and lifetime prediction. J Electrochem Soc 160(2):A243
Yang XG, Leng Y, Zhang G, Ge S, Wang CY (2017) Modeling of lithium plating induced aging of lithium-ion batteries: transition from linear to nonlinear aging. J Power Sources 360:28–40
Waldmann T, Hogg BI, Wohlfahrt-Mehrens M (2018) Li plating as unwanted side reaction in commercial Li-ion cells—a review. J Power Sources 384:107–124
Baker DR, Verbrugge MW (2019) Modeling overcharge at graphite electrodes: plating and dissolution of lithium. J Electrochem Soc 167(1):013504
Krewer U, Röder F, Harinath E, Braatz RD, Bedürftig B, Findeisen R (2018) Dynamic models of Li-ion batteries for diagnosis and operation: a review and perspective. J Electrochem Soc 165(16):A3656
You GW, Park S, Oh D (2016) Real-time state-of-health estimation for electric vehicle batteries: a data-driven approach. Appl Energy 176:92–103
Nuhic A, Terzimehic T, Soczka-Guth T, Buchholz M, Dietmayer K (2013) Health diagnosis and remaining useful life prognostics of lithium-ion batteries using data-driven methods. J Power Sources 239:680–688
Li Y, Liu K, Foley AM, Zülke A, Berecibar M, Nanini-Maury E, Van Mierlo J, Hoster HE (2019) Data-driven health estimation and lifetime prediction of lithium-ion batteries: a review. Renew Sustain Energy Rev 113:109254
Aykol M, Herring P, Anapolsky A (2020) Machine learning for continuous innovation in battery technologies. Nat Rev Mater 5(10):725–727
Richardson RR, Osborne MA, Howey DA (2019) Battery health prediction under generalized conditions using a Gaussian process transition model. J Energy Storage 23:320–328
Willard J, Jia X, Xu S, Steinbach M, Kumar V (2020) Integrating physics-based modeling with machine learning: a survey, vol 1, no 1, pp 1–34. arXiv:2003.04919
Xie T, Grossman JC (2018) Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys Rev Lett 120(14):145301
Peng GC, Alber M, Tepole AB, Cannon WR, De S, Dura-Bernal S, Garikipati K, Karniadakis G, Lytton WW, Perdikaris P, Petzold L (2021) Multiscale modeling meets machine learning: what can we learn? Arch Comput Methods Eng 28(3):1017–1037
Zhang Y, Zhang C, Cui N (2013) An adaptive estimation scheme for open-circuit voltage of power Lithium-Ion battery. In: Abstract and applied analysis, vol 2013. Hindawi
Tian S, Hong M, Ouyang M (2009) An experimental study and nonlinear modeling of discharge I-V behavior of valve-regulated lead–acid batteries. IEEE Trans Energy Convers 24(2):452–458
Ma S, Jiang M, Tao P, Song C, Wu J, Wang J, Deng T, Shang W (2018) Temperature effect and thermal impact in lithium-ion batteries: a review. Progr Nat Sci Mater Int 28(6):653–666
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Wu C, Jiang P, Ding C, Feng F, Chen T (2019) Intelligent fault diagnosis of rotating machinery based on one-dimensional convolutional neural network. Comput Ind 108:53–61
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980
Sarasketa-Zabala E, Aguesse F, Villarreal I, Rodriguez-Martinez LM, López CM, Kubiak P (2015) Understanding lithium inventory loss and sudden performance fade in cylindrical cells during cycling with deep-discharge steps. J Phys Chem C 119(2):896–906
Meyes R, Lu M, de Puiseau CW, Meisen T (2019) Ablation studies in artificial neural networks. arXiv:1901.08644
Acknowledgements
This work was supported in part by a Space Technology Research Institute grant from NASA’s Space Technology Research Grants Program.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work; there is no professional or other personal interest of any nature or kind in any product, service, and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix 1: Regression analysis of state equation coefficients
In this appendix, we build a regression model regarding state coefficients \(\theta_{1}\) and \(\theta_{2}\) to the state temperature to the LIB dataset. We take 100 samples of the \(\theta_{1}\) and \(\theta_{2}\) values across the entire temperature range of the battery prognostic dataset and conducted polynomial regression with different orders. We randomly split the dataset into 80% training and 20% testing. In order to prevent the overfitting of the regression, we use the \(l_{2}\) regularization. The coefficient of determination \(R^{2}\) results for different orders of polynomial regression is shown in Fig.
13.
From Fig. 13, first, the \(\theta_{1}\) and \(\theta_{2}\) model \(R^{2}\) values are high that the polynomial regression model can accurately model the relationship between state coefficients to temperature. Second, \(R^{2}\) value of testing is significantly smaller compared with that of training without \(l_{2}\) regularization. This problem is mitigated and solved by applying \(l_{2}\) regularization to the regression. Finally, we identify the most accurate model with the highest \(R^{2}\) value as the fourth polynomial model with \(l_{2}\) regularization. The regression results of the fourth-order polynomial for \(\theta_{1}\) and \(\theta_{2}\) are shown in Fig.
14.
Appendix 2: Structure and weight parameters of the En-ResNet
Here, we introduce the details of the output size, memory requirement per image, and the number of weights of En-ResNet as shown in Table 6. We use 32-bit floating numbers for variables in the data processing that one variable takes \(\frac{32}{8}=4\) bytes. According to Table 6, the number of weights is 0.100 M. The memory usage is the hard requirement of the hardware and weight size indicates the training requirement of the model.
Appendix 3: Structure and weight parameters of the De-ResNet
Here, we introduce the details of the output size, memory requirement per image, and the number of weights of De-ResNet as shown in Table 7. We use 32-bit floating numbers for variables in the data processing that one variable takes \(\frac{32}{8}=4\) bytes. According to Table 7, the number of weights is 15.04 M. The memory usage is the hard requirement of the hardware, and weight size indicates the training requirement of the model.
Appendix 4: PIDDA and pure data-driven predictions for battery No. 6
In this appendix, we discuss the PIDDA and pure data-driven approach prediction on battery No. 6. The comparison of the capacity and SOH predictions of PIDDA, no adjustment, and pure data-driven model is shown in Fig.
15. The RMSE of the capacity and SOH of the PIDDA, no adjustment, and pure data-driven approach is provided in Table
8.
The results of battery No. 6 are similar to those of battery No. 7, and the PIDDA can significantly improve the prediction accuracy compared with the pure data-driven model.
Rights and permissions
About this article
Cite this article
Xu, Z., Guo, Y. & Saleh, J.H. A physics-informed dynamic deep autoencoder for accurate state-of-health prediction of lithium-ion battery. Neural Comput & Applic 34, 15997–16017 (2022). https://doi.org/10.1007/s00521-022-07291-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-07291-5