The study of SOC estimation using incremental learning

MingLong Li; YaWen Dai

doi:10.1117/12.2661020

16 December 2022 The study of SOC estimation using incremental learning

MingLong Li, YaWen Dai

Proceedings Volume 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022); 125006C (2022) https://doi.org/10.1117/12.2661020
Event: 5th International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, Chongqing, China

Abstract

As an energy storage medium, the dynamic changes of current and voltage of power battery in actual vehicle use are fluctuating compared to constant current and voltage tests under laboratory conditions, so the distribution of its training data set is also fluctuating and changing. To address the above problems, this paper proposes a support vector regression algorithm (SVR) using incremental learning to improve the estimation accuracy and adapt to a variety of application scenarios. The details of the study are as follows. State of charge (SOC) - one of the key characteristic quantities of power batteries. To improve the generalizability of the SOC estimation model to complex dynamic operating conditions, an incremental learning approach is incorporated into the support vector machine regression algorithm (SVR) to adapt to changes in the distribution of the data set under dynamic operating conditions by incremental learning of additional data sets. A combination of error-driven and sample-labeling methods is used for accurate samples. Finally, the prediction results of both ISVR and SVR algorithms are compared using data from both DST and FUDS dynamic conditions. The experimental results from offline data show that the average absolute error of the incremental SVR prediction results for complex conditions is less than 0.008, which is about 0.044% lower than that of the general SVR.

Citation Download Citation

MingLong Li and YaWen Dai "The study of SOC estimation using incremental learning", Proc. SPIE 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 125006C (16 December 2022); https://doi.org/10.1117/12.2661020

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

System on a chip

Error analysis

Statistical analysis

Statistical modeling

Data acquisition

Data conversion

Show All Keywords

Keywords/Phrases

Search In:

Publication Years