Data-efficient parameter identification of electrochemical lithium-ion battery model using deep Bayesian harmony search

Abstract Lithium-ion batteries have been used in many applications owing to their high energy density and rechargeability. It is very important to monitor the internal physical parameters of the lithium-ion battery for safe and efficient usage, because this can help estimate the state of the battery, develop battery aging models, and schedule optimal operation of batteries. Parameter optimization methods using an accurate electrochemical battery model are much less expensive than direct parameter measurement methods, such as post-mortem methods. Thus, many model-based parameter optimization methods have been developed so far. However, most of these methods are random search methods that are based on heuristic rules, which leads to data-inefficient parameter identification. This means that they require many time-consuming battery model simulation runs to identify optimal parameters. Herein, a novel learning-based method is proposed for data-efficient parameter identification of lithium-ion batteries. A deep Bayesian neural network is used to efficiently identify optimal parameters. The simulations and experimental data validation show that the proposed method requires much fewer battery model simulation runs to identify optimal parameters than existing methods such as genetic algorithms, particle swarm optimization, and the Levenberg-Marquardt algorithm. The parameter estimation error of the proposed method is about 10 times lower than that of the second-best algorithm.

[1]  Yoshinori Kida,et al.  Study on capacity fade factors of lithium secondary batteries using LiNi0.7Co0.3O2 and graphite–coke hybrid carbon , 2002 .

[2]  Jun Zheng,et al.  Multi-objective optimization of lithium-ion battery model using genetic algorithm approach , 2014 .

[3]  D. Aurbach,et al.  Studies of cycling behavior, ageing, and interfacial reactions of LiNi0.5Mn1.5O4 and carbon electrodes for lithium-ion 5-V cells , 2006 .

[4]  Michael Pecht,et al.  Evaluation of Present Accelerated Temperature Testing and Modeling of Batteries , 2018, Applied Sciences.

[5]  Krishna R. Pattipati,et al.  A robust approach to battery fuel gauging, part I: Real time model identification , 2014 .

[6]  Hosam K. Fathy,et al.  Genetic parameter identification of the Doyle-Fuller-Newman model from experimental cycling of a LiFePO4 battery , 2011, Proceedings of the 2011 American Control Conference.

[7]  Linlin Li,et al.  An electrochemical model based degradation state identification method of Lithium-ion battery for all-climate electric vehicles application , 2018, Applied Energy.

[8]  David Lindley,et al.  Smart grids: The energy storage problem , 2010, Nature.

[9]  Wei He,et al.  State of charge estimation of lithium-ion batteries using the open-circuit voltage at various ambient temperatures , 2014 .

[10]  Ahmet T. Alpas,et al.  In-situ observations of lithiation/de-lithiation induced graphite damage during electrochemical cycling , 2011 .

[11]  Mandava Rajeswari,et al.  The variants of the harmony search algorithm: an overview , 2011, Artificial Intelligence Review.

[12]  Richard D. Braatz,et al.  Parameter Estimation and Capacity Fade Analysis of Lithium-Ion Batteries Using First-Principles-Based Efficient Reformulated Models , 2009 .

[13]  Richard D. Braatz,et al.  Parameter Estimation and Capacity Fade Analysis of Lithium-Ion Batteries Using Reformulated Models , 2011 .

[14]  Gregory L. Plett,et al.  Controls oriented reduced order modeling of lithium deposition on overcharge , 2012 .

[15]  M. Doyle,et al.  Simulation and Optimization of the Dual Lithium Ion Insertion Cell , 1994 .

[16]  M. Safari,et al.  Multimodal Physics-Based Aging Model for Life Prediction of Li-Ion Batteries , 2009 .

[17]  A. Izadian,et al.  Electrochemical model parameter identification of a lithium-ion battery using particle swarm optimization method , 2016 .

[18]  King-Jet Tseng,et al.  Energy efficiency of lithium-ion battery used as energy storage devices in micro-grid , 2015, IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society.

[19]  M. Doyle,et al.  Modeling of Galvanostatic Charge and Discharge of the Lithium/Polymer/Insertion Cell , 1993 .

[20]  Lin Yang,et al.  Online identification of lithium-ion battery parameters based on an improved equivalent-circuit model and its implementation on battery state-of-power prediction , 2015 .

[21]  Ralph E. White,et al.  Maximizing the Life of a Lithium-Ion Cell by Optimization of Charging Rates , 2010 .

[22]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[23]  Michael Pecht,et al.  A parameter estimation method for a simplified electrochemical model for Li-ion batteries , 2018, Electrochimica Acta.

[24]  Xianke Lin,et al.  A Comprehensive Capacity Fade Model and Analysis for Li-Ion Batteries , 2013 .

[25]  Afshin Izadian,et al.  Model based condition monitoring in lithium-ion batteries , 2014 .

[26]  Andreas Jossen,et al.  A SEI Modeling Approach Distinguishing between Capacity and Power Fade , 2017 .

[27]  M. Fesanghary,et al.  An improved harmony search algorithm for solving optimization problems , 2007, Appl. Math. Comput..

[28]  V. Subramanian,et al.  Mathematical Model Reformulation for Lithium-Ion Battery Simulations: Galvanostatic Boundary Conditions , 2009 .

[29]  Sudhakar Inguva,et al.  A Phenomenological Degradation Model for Cyclic Aging of Lithium Ion Cell Materials , 2013 .

[30]  Ralph E. White,et al.  Development of First Principles Capacity Fade Model for Li-Ion Cells , 2004 .

[31]  Stephen Duncan,et al.  Lithium-ion battery thermal-electrochemical model-based state estimation using orthogonal collocation and a modified extended Kalman filter , 2015, ArXiv.

[32]  Boucar Diouf,et al.  Potential of lithium-ion batteries in renewable energy , 2015 .

[33]  Ralph E. White,et al.  Parameter Estimation and Model Discrimination for a Lithium-Ion Cell , 2007 .

[34]  Hosam K. Fathy,et al.  Genetic identification and fisher identifiability analysis of the Doyle–Fuller–Newman model from experimental cycling of a LiFePO4 cell , 2012 .

[35]  R. Spotnitz.  Simulation of capacity fade in lithium-ion batteries , 2003 .

[36]  Diana Golodnitsky,et al.  The sei model—application to lithium-polymer electrolyte batteries , 1995 .

[37]  Christian Fleischer,et al.  On-line adaptive battery impedance parameter and state estimation considering physical principles in reduced order equivalent circuit battery models part 2. Parameter and state estimation , 2014 .

[38]  Michael Pecht,et al.  State of charge estimation for Li-ion batteries using neural network modeling and unscented Kalman filter-based error cancellation , 2014 .

[39]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[40]  V. Subramanian,et al.  Towards real-time (milliseconds) parameter estimation of lithium-ion batteries using reformulated physics-based models , 2008 .

[41]  Zhenpo Wang,et al.  A mechanism identification model based state-of-health diagnosis of lithium-ion batteries for energy storage applications , 2018, Journal of Cleaner Production.

[42]  Zhongwei Deng,et al.  Implementation of reduced-order physics-based model and multi parameters identification strategy for lithium-ion battery , 2017 .

[43]  Tian Feng,et al.  Parameter Identification of Lithium-Ion Batteries Model to Predict Discharge Behaviors Using Heuristic Algorithm , 2016 .

[44]  Ralph E. White,et al.  Calendar life study of Li-ion pouch cells , 2007 .

[45]  Ralph E. White,et al.  Capacity fade analysis of a lithium ion cell , 2008 .

[46]  Jonghoon Kim,et al.  Influence of different open circuit voltage tests on state of charge online estimation for lithium-ion batteries , 2016 .

[47]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[48]  Xiaosong Hu,et al.  An electrochemistry-based impedance model for lithium-ion batteries , 2014 .