Life prediction of battery based on random forest optimized by genetic algorithm

When the random forest algorithm is used for battery life prediction, the prediction result is unstable, and it is difficult to ensure the accuracy of the model. In view of the above problems, this study proposes to use genetic algorithms to optimize the random forest prediction model. While ensurin...

Full description

Saved in:
Bibliographic Details
Published in2020 IEEE International Conference on Prognostics and Health Management (ICPHM) pp. 1 - 6
Main Authors Cailian, LI, chun, ZHANG
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2020
Subjects
Batteries
Decision trees
Discharges (electric)
Forestry
genetic algorithm
Genetic algorithms
life prediction
lithium-ion battery
Prediction algorithms
Predictive models
random forest algorithm
Online AccessGet full text

Cover

More Information
Summary:When the random forest algorithm is used for battery life prediction, the prediction result is unstable, and it is difficult to ensure the accuracy of the model. In view of the above problems, this study proposes to use genetic algorithms to optimize the random forest prediction model. While ensuring the prediction accuracy, the depth and number of decision trees in the random forest are optimized, and the optimal combination of decision tree depth and number is used Life prediction. Using the lithium-ion battery data published by NASA to conduct simulation experiments and evaluate the prediction performance of the model, and then compare with the prediction results of the random forest prediction model and lasso prediction model.
DOI:10.1109/ICPHM49022.2020.9187060