Estimating Battery State-of-Charge using Machine Learning and Physics-Based Models University of Wisconsin-Madison

Format:

Book

Conference/Event

Author/Creator:

Sapra, Harsh Darshan, author.

Contributor:

Desorcy, Lukas

Elfimova, Olesia

Kokjohn, Sage

Kweon, Chol-Bum

Shumaker, Justin

Upadhya, Sahana

Venkataraman, Shivaram

Wagner, Michael

Conference Name:

WCX SAE World Congress Experience (2023-04-18 : Detroit, Michigan, United States)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2023

Summary:

Lithium-ion and Lithium polymer batteries are fast becoming ubiquitous in high-discharge rate applications for military and non-military systems. Applications such as small aerial vehicles and energy transfer systems can often function at C-rates greater than 1. To maximize system endurance and battery health, there is a need for models capable of precisely estimating the battery state-of-charge (SoC) under all temperature and loading conditions. However, the ability to perform state estimation consistently and accurately to within 1% error has remained unsolved. Doing so can offer enhanced endurance, safety, reliability, and planning, and additionally, simplify energy management. Therefore, the work presented in this paper aims to study and develop experimentally validated mathematical models capable of high-accuracy battery SoC estimation. In this work, experiments are performed with Lithium Polymer battery cells to measure performance parameters such as current, battery capacity, temperatures, and voltage. Next, physics-based and machine learning modeling approaches are developed to study their ability to predict SoC. Measurements performed at high C-rates (1C 4C) are used for model training and calibration, validation, and testing. The results show that the Pseudo-2D electrochemical model can predict SoC within about 2 % root-mean-squared-error (RMSE) at different C-rates. However, the Feed Forward Neural Network modeling approach with Butterworth and Hampel filters achieved lower than and close to 1 % RMSE for battery SoC estimations

Notes:

Vendor supplied data

Publisher Number:

2023-01-0522

Access Restriction:

Restricted for use by site license