Health assessment of LFP automotive batteries using a fractional-order neural network

Abstract A recurrent neural network with fractional order dynamics is used for assessing the health of LFP rechargeable automotive batteries through incremental capacity analysis. The proposed algorithm learns a dynamical model of the battery voltage from samples of current and voltage taken on a vehicle. The output of this dynamical model is the sum of two terms: the over-potential and the open circuit voltage. The over-potential model includes an element with fractional order dynamics. The open circuit voltage model is designed to depend on the same parameters as the incremental capacity curve, so the expression of the learnt model can be directly related to the health of the battery. The performance of the new method is assessed in three different batteries with varying states of health. A usable estimation of the incremental capacity curve was attained for low to moderate discharge currents. The state of health estimation produced by the fractional order network was consistently better than statistical and fuzzy models, LSTM and Echo State Networks for all the batteries under study.

[1]  Inés Couso,et al.  A Model-Based Virtual Sensor for Condition Monitoring of Li-Ion Batteries in Cyber-Physical Vehicle Systems , 2017, J. Sensors.

[2]  Petre Stoica,et al.  Decentralized Control , 2018, The Control Systems Handbook.

[3]  J. Randles.  Kinetics of rapid electrode reactions , 1947 .

[4]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[5]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[6]  János Abonyi,et al.  Identification and Control of Nonlinear Systems Using Fuzzy Hammerstein Models , 2000 .

[7]  YangQuan Chen,et al.  A Survey of Fractional-Order Neural Networks , 2017 .

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Chunbo Zhu,et al.  Development of a voltage relaxation model for rapid open-circuit voltage prediction in lithium-ion batteries , 2014 .

[10]  Bogdan Gabrys,et al.  Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

[11]  P. Bruce,et al.  Degradation diagnostics for lithium ion cells , 2017 .

[12]  MengChu Zhou,et al.  Virtual sensing techniques and their applications , 2009, 2009 International Conference on Networking, Sensing and Control.

[13]  Zoubin Ghahramani,et al.  A Theoretically Grounded Application of Dropout in Recurrent Neural Networks , 2015, NIPS.

[14]  Ying Xiao,et al.  Model-Based Virtual Thermal Sensors for Lithium-Ion Battery in EV Applications , 2015, IEEE Transactions on Industrial Electronics.

[15]  Lukasz Bartczuk,et al.  A new approach to nonlinear modelling of dynamic systems based on fuzzy rules , 2016, Int. J. Appl. Math. Comput. Sci..

[16]  Suleiman Abu-Sharkh,et al.  Rapid test and non-linear model characterisation of solid-state lithium-ion batteries , 2004 .

[17]  J. D. Kozlowski.  Electrochemical cell prognostics using online impedance measurements and model-based data fusion techniques , 2003, 2003 IEEE Aerospace Conference Proceedings (Cat. No.03TH8652).

[18]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[19]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[20]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[21]  Inés Couso,et al.  Assessing the Health of LiFePO4 Traction Batteries through Monotonic Echo State Networks , 2017, Sensors.

[22]  Luciano Sánchez,et al.  A Variable Effective Capacity Model for $\hbox{LiFePO}_{4}$ Traction Batteries Using Computational Intelligence Techniques , 2015, IEEE Transactions on Industrial Electronics.

[23]  Alain Oustaloup,et al.  Frequency-band complex noninteger differentiator: characterization and synthesis , 2000 .

[24]  Robert Babuska,et al.  Neuro-fuzzy methods for nonlinear system identification , 2003, Annu. Rev. Control..

[25]  Dexian Huang,et al.  Data-driven soft sensor development based on deep learning technique , 2014 .

[26]  Inés Couso,et al.  Health Assessment of Automotive Batteries Through Computational Intelligence-Based Soft Sensors: An Empirical Study , 2017, SOCO-CISIS-ICEUTE.

[27]  Matthieu Dubarry,et al.  Synthesize battery degradation modes via a diagnostic and prognostic model , 2012 .

[28]  Rui Xiong,et al.  Fractional-Order Model-Based Incremental Capacity Analysis for Degradation State Recognition of Lithium-Ion Batteries , 2019, IEEE Transactions on Industrial Electronics.

[29]  A. Jansen,et al.  A Volume Averaged Approach to the Numerical Modeling of Phase-Transition Intercalation Electrodes Presented for LixC6 , 2012 .

[30]  Jie Zhang,et al.  Recurrent neuro-fuzzy networks for nonlinear process modeling , 1999, IEEE Trans. Neural Networks.

[31]  Claudio Gallicchio,et al.  Architectural and Markovian factors of echo state networks , 2011, Neural Networks.

[32]  Xiaojun Zhang,et al.  Global asymptotic synchronization of nonidentical fractional-order neural networks , 2018, Neurocomputing.

[33]  Inés Couso,et al.  A class of Monotone Fuzzy rule-based Wiener systems with an application to Li-ion battery modelling , 2017, Eng. Appl. Artif. Intell..

[34]  Michael Pecht,et al.  A review of fractional-order techniques applied to lithium-ion batteries, lead-acid batteries, and supercapacitors , 2018, Journal of Power Sources.

[35]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[36]  José Luís Casteleiro-Roca,et al.  Power Cell SOC Modelling for Intelligent Virtual Sensor Implementation , 2017, J. Sensors.

[37]  Zheng Chen,et al.  An online state of charge estimation method with reduced prior battery testing information , 2014 .

[38]  Luigi Fortuna,et al.  Soft Sensors for Monitoring and Control of Industrial Processes (Advances in Industrial Control) , 2006 .

[39]  J. Dahn,et al.  Explicit conversion between different equivalent circuit models for electrochemical impedance analysis of lithium-ion cells , 2018 .

[40]  M. Wohlfahrt‐Mehrens,et al.  Ageing mechanisms in lithium-ion batteries , 2005 .