Comparative study of a structured neural network and an extended Kalman filter for state of health determination of lithium-ion batteries in hybrid electricvehicles

State of health (SOH) determination becomes an increasingly important issue for a safe and reliable operation of lithium-ion batteries in hybrid electric vehicles (HEVs). Characteristic performance parameters as capacity and resistance change over lifetime and have to be determined precisely. This work deduces two different parameter estimation methods to identify the SOH of battery resistance and investigates the feasibility of an application in HEVs. First, a knowledge-based algorithm of a developed structured neural network (SNN). Thereby, the structure of the network is adopted from the mathematical description of the electrical equivalent circuit model. Two main advantages expected from a SNN compared to a regular neural network are: first a reduced structure and complexity of the network through predefined functions and thus faster computation, second the possibility to get access to internal parameters of the model. In order to verify a proper operation and performance of the developed SNN, a model-based second parameter estimation method is used with the well established the extended Kalman filter (EKF) algorithm. Furthermore, the developed algorithms are applied on real-vehicle data of a HEV battery at begin of life and after 170,000km. A verification of the identified states against reference data based on electro-chemical impedance spectroscopy shows nearby identical results for SNN and EKF. Additionally, a comparison of implementation effort and computation time isgiven.

[1]  Cao Binggang,et al.  State of charge estimation based on evolutionary neural network , 2008 .

[2]  M Brill.  Erweiterte Onboard-Diagnose von Lithium-Ionen-Batterien in Fahrzeugen mit alternativem Antriebskonzept. Entwicklung eines auf Fahrzeugsteuergeraete optimierten Batteriemodells zur Erkennung und Prognose des aktuellen Alterungszustands von Lithium-Ionen Antriebsbatterien , 2010 .

[3]  Jay Lee,et al.  A review on prognostics and health monitoring of Li-ion battery , 2011 .

[4]  M. Broussely,et al.  Main aging mechanisms in Li ion batteries , 2005 .

[5]  Terry Hansen,et al.  Support vector based battery state of charge estimator , 2005 .

[6]  Yiran Hu,et al.  Battery state of charge estimation in automotive applications using LPV techniques , 2010, Proceedings of the 2010 American Control Conference.

[7]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[8]  Guangjun Liu,et al.  A battery State of Charge estimation method with extended Kalman filter , 2008, 2008 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.

[9]  Michael Pecht,et al.  A comparative review of prognostics-based reliability methods for Lithium batteries , 2011, 2011 Prognostics and System Health Managment Confernece.

[10]  Mark A. Fanty,et al.  Computing with structured connectionist networks , 1988, CACM.

[11]  Michael Buchholz,et al.  State-of-health monitoring of lithium-ion batteries in electric vehicles by on-board internal resistance estimation , 2011 .

[12]  Christian Mohrdieck,et al.  Lithium-Ionen-Batterie: Erster Serieneinsatz im S 400 Hybrid , 2009 .

[13]  Gregory L. Plett,et al.  Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs: Part 2. Modeling and identification , 2004 .

[14]  Jorge Moreno,et al.  Energy-management system for a hybrid electric vehicle, using ultracapacitors and neural networks , 2006, IEEE Transactions on Industrial Electronics.

[15]  Joerg Thielen,et al.  Lithium-Ionen-Batterie , 2010 .

[16]  D. Sauer,et al.  Characterization of high-power lithium-ion batteries by electrochemical impedance spectroscopy. I. Experimental investigation , 2011 .

[17]  Gregory L. Plett,et al.  Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs Part 1. Background , 2004 .

[18]  Bo-Suk Yang,et al.  Intelligent prognostics for battery health monitoring based on sample entropy , 2011, Expert Syst. Appl..

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

[20]  P. Garcia,et al.  Saliency tracking-based, sensorless control of AC machines using structured neural networks , 2005, Fourtieth IAS Annual Meeting. Conference Record of the 2005 Industry Applications Conference, 2005..

[21]  Heinz Wenzl,et al.  BATTERIES | Lifetime Prediction , 2009 .

[22]  Aleksei M. Zheltikov,et al.  Impedance Spectroscopy: Theory, Experiment, and Applications Second Edition. Evgenij Barsoukov and J. Ross Macdonald (eds). John Wiley & Sons, Inc., Hoboken, New Jersey, 2005, pp. 595 , 2007 .

[23]  Lin Ma,et al.  Prognostic modelling options for remaining useful life estimation by industry , 2011 .

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

[25]  Souradip Malkhandi,et al.  Fuzzy logic-based learning system and estimation of state-of-charge of lead-acid battery , 2006, Eng. Appl. Artif. Intell..

[26]  Danil V. Prokhorov,et al.  Neural Networks in Automotive Applications , 2008, Computational Intelligence in Automotive Applications.

[27]  A. Lasia.  Electrochemical Impedance Spectroscopy and its Applications , 2014 .

[28]  Bo-Hyung Cho,et al.  Li-Ion Battery SOC Estimation Method Based on the Reduced Order Extended Kalman Filtering , 2006 .

[29]  Bhaskar Saha,et al.  Prognostics Methods for Battery Health Monitoring Using a Bayesian Framework , 2009, IEEE Transactions on Instrumentation and Measurement.

[30]  K. T. Chau,et al.  A new battery available capacity indicator for electric vehicles using neural network , 2002 .

[31]  Mohammad Farrokhi,et al.  State-of-Charge Estimation for Lithium-Ion Batteries Using Neural Networks and EKF , 2010, IEEE Transactions on Industrial Electronics.

[32]  T. Weigert,et al.  State-of-charge prediction of batteries and battery–supercapacitor hybrids using artificial neural networks , 2011 .

[33]  W. B. Johnson,et al.  Fundamentals of Impedance Spectroscopy , 2005 .

[34]  Tetsuro Matsui,et al.  Development of remaining life assessment for oil-immersed transformer using structured neural networks , 2009, 2009 ICCAS-SICE.

[35]  Chenglin Liao,et al.  Research on Improved EKF Algorithm Applied on Estimate EV Battery SOC , 2010, 2010 Asia-Pacific Power and Energy Engineering Conference.

[36]  Thomas J. Weigert,et al.  State-of-charge prediction of batteries and batterysupercapacitor hybrids using artificial neural n , 2011 .

[37]  Danil V. Prokhorov,et al.  Toyota Prius HEV neurocontrol and diagnostics , 2008, Neural Networks.

[38]  Bo-Hyung Cho,et al.  Li-Ion Battery SOC Estimation Method based on the Reduced Order Extended Kalman Filtering , 2006 .

[39]  Dan Cornford,et al.  Structured neural network modelling of multi-valued functions for wind vector retrieval from satellite scatterometer measurements , 2000, Neurocomputing.

[40]  Sandrine Bourlot,et al.  Investigation of aging mechanisms of high power Li-ion cells used for hybrid electric vehicles , 2011 .

[41]  Greg Welch,et al.  An Introduction to Kalman Filter , 1995, SIGGRAPH 2001.

[42]  D. Sauer,et al.  Characterization of high-power lithium-ion batteries by electrochemical impedance spectroscopy. II: Modelling , 2011 .

[43]  E. Barsoukov,et al.  Impedance spectroscopy : theory, experiment, and applications , 2005 .