Perspective on Automation of Statistical Modeling Process for Battery Lifetime Prediction

Automating the process of statistical modeling would be substantially beneficial for the fields that rely heavily on expert statisticians. In this paper, a perspective is briefly provided on how to automate statistical modeling processes for the prediction of battery lifetime, especially on automating the step of feature engineering, to alleviate the considerable time and human intervention required by the current data-driven lifetime prediction methods. An example related to overpotential concept for early prediction is discussed to show that teach machines concepts the same way as humans are taught may be a promising way to enable the machine to gain anthropomorphic intelligence that is beneficial for automated feature engineering.

[1]  Christian Fleischer,et al.  Critical review of the methods for monitoring of lithium-ion batteries in electric and hybrid vehicles , 2014 .

[2]  Kalyan Veeramachaneni,et al.  Deep feature synthesis: Towards automating data science endeavors , 2015, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[3]  M. Bazant,et al.  Multiphase Porous Electrode Theory , 2017, 1702.08432.

[4]  T. Baumhöfer,et al.  Production caused variation in capacity aging trend and correlation to initial cell performance , 2014 .

[5]  Jun Lu,et al.  Batteries and fuel cells for emerging electric vehicle markets , 2018 .

[6]  Ganesan Nagasubramanian,et al.  Accelerated calendar and pulse life analysis of lithium-ion cells , 2003 .

[7]  M. Pecht,et al.  A Bayesian approach for Li-Ion battery capacity fade modeling and cycles to failure prognostics , 2015 .

[8]  Kristen A. Severson,et al.  Data-driven prediction of battery cycle life before capacity degradation , 2019, Nature Energy.

[9]  M. D. Rooij,et al.  Electrochemical Methods: Fundamentals and Applications , 2003 .

[10]  Jaesik Choi,et al.  The Automatic Statistician: A Relational Perspective , 2015, ArXiv.

[11]  Simon F. Schuster,et al.  Lithium-ion cell-to-cell variation during battery electric vehicle operation , 2015 .

[12]  Simon F. Schuster,et al.  Nonlinear aging characteristics of lithium-ion cells under different operational conditions , 2015 .

[13]  Joshua B. Tenenbaum,et al.  Automatic Construction and Natural-Language Description of Nonparametric Regression Models , 2014, AAAI.

[14]  Yee Whye Teh,et al.  Scaling up the Automatic Statistician: Scalable Structure Discovery using Gaussian Processes , 2017, AISTATS.