HomeAbstract of 3rd-retconfA Novel Convolutional Neural Network Approach for Accurate Battery State-of-Charge Estimation

A Novel Convolutional Neural Network Approach for Accurate Battery State-of-Charge Estimation

Proceedings of The 3rd International Academic Conference on Research in Engineering and Technology

Year: 2024

DOI:

[PDF]

 

A Novel Convolutional Neural Network Approach for Accurate Battery State-of-Charge Estimation

Anant Oonsivilai, Alethea Oonsivilai, Kakanang Posridee, Ratchadaporn Oonsivilai

 

 

ABSTRACT:

This research introduces an innovative methodology for precisely determining the state-of-charge (SOC) of a battery utilizing a convolutional neural network (CNN). The proposed CNN architecture is meticulously designed to proficiently extract pertinent features from a battery’s sensor data, encompassing voltage, current, and temperature measurements. The CNN model’s ability to capture intricate patterns and dependencies within the sensor data significantly enhances its accuracy and robustness compared to conventional SOC estimation techniques. Through rigorous experimental evaluations, this study conclusively demonstrates the superior performance of the proposed CNN approach in accurately estimating battery SOC, making it a promising solution for various battery-powered applications.

keywords: convolutional neural network, battery, state of charge, estimation