Theoretical Framework for Health Estimation Using Machine Learning

Krishnan S. Hariharan

doi:10.1007/978-3-319-03527-7_8

Theoretical Framework for Health Estimation Using Machine Learning

2017-12-29

0

PRE

AI

K

Krishnan S. Hariharan *

DOI：10.1007/978-3-319-03527-7_8

原文链接

原文求助

摘要

En 中文

Real-time prediction of Remaining Useful Life (RUL) is an essential feature of a robust battery management system (BMS). However, due to the complex nature of the battery degradation, physics-based degradation modeling is often infeasible. Data-driven approaches provide an alternative when physics-based modeling is infeasible. In this chapter, we investigate some of the most popular machine learning-based data-driven approaches used by the Lithium-ion battery community. The chapter first introduces basic concepts of classification and regression, followed by a generic framework for its solution. Finally, we introduce some machine learning algorithms for the solution of this generic framework.

Theoretical Framework for Health Estimation Using Machine Learning

摘要

AI总结

期刊

机构