Battery health prediction under generalized conditions using a Gaussian process transition model

Accurately predicting the future health of batteries is necessary to ensure reliable operation, minimise maintenance costs, and calculate the value of energy storage investments. The complex nature of degradation renders data-driven approaches a promising alternative to mechanistic modelling. This study predicts the changes in battery capacity over time using a Bayesian non-parametric approach based on Gaussian process regression. These changes can be integrated against an arbitrary input sequence to predict capacity fade in a variety of usage scenarios, forming a generalised health model. The approach naturally incorporates varying current, voltage and temperature inputs, crucial for enabling real world application. A key innovation is the feature selection step, where arbitrary length current, voltage and temperature measurement vectors are mapped to fixed size feature vectors, enabling them to be efficiently used as exogenous variables. The approach is demonstrated on the open-source NASA Randomised Battery Usage Dataset, with data of 26 cells aged under randomized operational conditions. Using half of the cells for training, and half for validation, the method is shown to accurately predict non-linear capacity fade, with a best case normalised root mean square error of 4.3%, including accurate estimation of prediction uncertainty.

[1]  Kevin G. Gallagher,et al.  Impact of battery degradation on energy arbitrage revenue of grid-level energy storage , 2017 .

[2]  Dongpu Cao,et al.  Battery Health Prognosis for Electric Vehicles Using Sample Entropy and Sparse Bayesian Predictive Modeling , 2016, IEEE Transactions on Industrial Electronics.

[3]  Chaoyang Wang,et al.  Modeling of lithium plating induced aging of lithium-ion batteries: Transition from linear to nonlinear aging , 2017 .

[4]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[5]  Xin Zhang,et al.  An improved unscented particle filter approach for lithium-ion battery remaining useful life prediction , 2018, Microelectron. Reliab..

[6]  Dirk Uwe Sauer,et al.  Development of a lifetime prediction model for lithium-ion batteries based on extended accelerated aging test data , 2012 .

[7]  Rutooj D. Deshpande,et al.  Modeling Solid-Electrolyte Interphase (SEI) Fracture: Coupled Mechanical/Chemical Degradation of the Lithium Ion Battery , 2017 .

[8]  K. Goebel,et al.  Prognostics in Battery Health Management , 2008, IEEE Instrumentation & Measurement Magazine.

[9]  M. Verbrugge,et al.  Cycle-life model for graphite-LiFePO 4 cells , 2011 .

[10]  Michael A. Osborne,et al.  Gaussian process regression for forecasting battery state of health , 2017, 1703.05687.

[11]  Andreas Jossen,et al.  Comprehensive Modeling of Temperature-Dependent Degradation Mechanisms in Lithium Iron Phosphate Batteries , 2017 .

[12]  Xiaofeng Wang,et al.  A Battery Management System With a Lebesgue-Sampling-Based Extended Kalman Filter , 2019, IEEE Transactions on Industrial Electronics.

[13]  Matthew B. Pinson,et al.  Theory of SEI Formation in Rechargeable Batteries: Capacity Fade, Accelerated Aging and Lifetime Prediction , 2012, 1210.3672.

[14]  Christoph R. Birkl,et al.  Oxford Battery Degradation Dataset 1 , 2017 .

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

[16]  R. Weron,et al.  Recent advances in electricity price forecasting: A review of probabilistic forecasting , 2016 .

[17]  B. Saha,et al.  Uncertainty Management for Diagnostics and Prognostics of Batteries using Bayesian Techniques , 2008, 2008 IEEE Aerospace Conference.

[18]  Michael A. Osborne,et al.  Blitzkriging: Kronecker-structured Stochastic Gaussian Processes , 2015, 1510.07965.

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

[20]  Andrea Marongiu,et al.  Critical review of on-board capacity estimation techniques for lithium-ion batteries in electric and hybrid electric vehicles , 2015 .

[21]  Taejung Yeo,et al.  A novel multistage Support Vector Machine based approach for Li ion battery remaining useful life estimation , 2015 .

[22]  Wolfgang G. Bessler,et al.  Multi-Scale Thermo-Electrochemical Modeling of Performance and Aging of a LiFePO4/Graphite Lithium-Ion Cell , 2017 .

[23]  Jay F. Whitacre,et al.  An intertemporal decision framework for electrochemical energy storage management , 2018 .

[24]  Chen Li,et al.  Failure statistics for commercial lithium ion batteries: A study of 24 pouch cells , 2017 .

[25]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[26]  Yu Peng,et al.  Data-driven prognostics for lithium-ion battery based on Gaussian Process Regression , 2012, Proceedings of the IEEE 2012 Prognostics and System Health Management Conference (PHM-2012 Beijing).

[27]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[28]  P. Ruetschi Aging mechanisms and service life of lead–acid batteries , 2004 .

[29]  Michael Osterman,et al.  Prognostics of lithium-ion batteries based on DempsterShafer theory and the Bayesian Monte Carlo me , 2011 .

[30]  Michael Buchholz,et al.  Health diagnosis and remaining useful life prognostics of lithium-ion batteries using data-driven methods , 2013 .

[31]  José L. Bernal-Agustín,et al.  Comparison of different lead–acid battery lifetime prediction models for use in simulation of stand-alone photovoltaic systems , 2014 .

[32]  Qiang Miao,et al.  Prognostics of lithium-ion batteries based on relevance vectors and a conditional three-parameter capacity degradation model , 2013 .

[33]  Dirk Uwe Sauer,et al.  A holistic aging model for Li(NiMnCo)O2 based 18650 lithium-ion batteries , 2014 .

[34]  Souhaib Ben Taieb,et al.  A gradient boosting approach to the Kaggle load forecasting competition , 2014 .

[35]  Andrew Gordon Wilson,et al.  Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP) , 2015, ICML.

[36]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[37]  Matthew Daigle,et al.  Adaptation of an Electrochemistry-based Li-Ion Battery Model to Account for Deterioration Observed Under Randomized Use , 2014, Annual Conference of the PHM Society.