Aviation lead-acid battery state-of-health assessment using PSO-SVM technique

Author

Jiayu Xie ; Weiqing Li ; Yan Hu

Author_Institution

Aviation Eng. Inst., Civil Aviation Flight Univ. of China, Guanghan, China

fYear

2014

fDate

27-29 June 2014

Firstpage

344

Lastpage

347

Abstract

It is an important issue to assess the state-of-health (SOH) of battery, including aircraft. There are several methods on the assessment of SOH of battery having been reported in recent years. Herein, we proposed a hybrid PSO+SVM model, which employed particle swarm optimization (PSO) algorithm to search the best parameters of support vector machine (SVM) to estimate SOH of aviation lead-acid battery. Results showed that the proposed PSO-SVM model achieved 98.75% classification accuracy using a real dataset provided by Civil Aviation Flight University of China. Hence, the hybrid PSO+SVM model is very promising compared to the previous reports.

Keywords

aerospace computing; aircraft power systems; lead acid batteries; particle swarm optimisation; support vector machines; China; Civil Aviation Flight University; PSO-SVM technique; aircraft; aviation lead-acid battery SOH assessment; aviation lead-acid battery state-of-health assessment; particle swarm optimization algorithm; support vector machine; Accuracy; Aircraft; Batteries; Kernel; Lead; Mathematical model; Support vector machines; aviation lead-acid battery; particle swarm optimization; state-of-health assessment; support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Software Engineering and Service Science (ICSESS), 2014 5th IEEE International Conference on

Conference_Location

Beijing

ISSN

2327-0586

Print_ISBN

978-1-4799-3278-8

Type

conf

DOI

10.1109/ICSESS.2014.6933578

Filename

6933578