Journal
ENERGIES
Volume 10, Issue 5, Pages -Publisher
MDPI
DOI: 10.3390/en10050691
Keywords
mean square error (MSE); remaining useful life (RUL); support vector machine (SVM); voltage derivative (DV)
Categories
Funding
- project of Research and Development of Test Cycles for Chinese New Energy Vehicles-Data Acquisition in Kunming [CF2016-0163]
- High-Level Overseas Talents Program of Yunnan province [10978196]
- Innovation Team Program of Kunming University of Science and Technology [14078368]
- Scientific Research Start-up Funding of Kunming University of Science and Technology [14078337]
Ask authors/readers for more resources
Battery remaining useful life (RUL) estimation is critical to battery management and performance optimization of electric vehicles (EVs). In this paper, we present an effective way to estimate RUL online by using the support vector machine (SVM) algorithm. By studying the characteristics of the battery degradation process, the rising of the terminal voltage and changing characteristics of the voltage derivative (DV) during the charging process are introduced as the training variables of the SVM algorithm to determine the battery RUL. The SVM is then applied to build the battery degradation model and predict the battery real cycle numbers. Experimental results prove that the built battery degradation model shows higher accuracy and less computation time compared with those of the neural network (NN) method, thereby making it a potential candidate for realizing online RUL estimation in a battery management system (BMS).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available
Share Paper
