1. Repositório Aberto da Universidade do Porto
2. FEUP - Faculdade de Engenharia
3. FEUP - Dissertação

Author(s):	Pedro Gabriel Araújo Monteiro
Title:	Data-Driven State Estimation Algorithms for a 48V Battery Management System
Issue Date:	2021-07-23
Description:	Li-ion battery State-of-Charge (SOC), State-of-Health (SOH) and cell parameter estimation are a complex challenge for battery management systems designers, due to the battery's non-linear behaviour at different operating conditions and ageing levels. As a possible solution, multiple machine learning models have been proposed for states estimation throughout the years. These provide an advantage over more common model based methods, as they do not require a deep knowledge and study of the battery's internal behaviour. However, many of these proposed models could not be considered due to their complexity. The high number of required stored parameters and/or elevated memory consumption during estimation may pose challenges to the application of these methods. Therefore, in this thesis, feedforward neural network models are proposed for online SOC and SOH estimation, with an efficient method for online input preprocessing and low parameter requirement in storage, using solely voltage, current and temperature measurements taken during normal operation of the Battery Management System (BMS). For cell parameter estimation, an online Recursive Least Squares (RLS) algorithm with forgetting factor is used, resulting in low online voltage prediction error. As a practical validation method, a hardware setup was designed and developed to emulate the voltage and current behaviour of a Li-ion 48V battery pack. The proposed algorithms were then implemented in a 48V BMS and validated using the hardware setup developed.
Subject:	Engenharia electrotécnica, electrónica e informática Electrical engineering, Electronic engineering, Information engineering
Scientific areas:	Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática Engineering and technology::Electrical engineering, Electronic engineering, Information engineering
DOI:	10.34626/nr1t-6h51
TID identifier:	202824527
URI:	https://hdl.handle.net/10216/138001
Document Type:	Dissertação
Rights:	openAccess
Appears in Collections:	FEUP - Dissertação

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.