<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T04:29:09Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/33062" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/33062</identifier><datestamp>2026-09-24T04:12:49Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Emadi, Ali</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Navega Vieira, Romulo</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-04-17T18:20:55Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2026</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/11375/33062</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/7717</dim:field>
   <dim:field mdschema="dc" element="description">This research was undertaken, in part, thanks to funding from the Natural Sciences and Engineering Research Council of Canada (NSERC), Stellantis, and Canada Research Chair in Transportation Electrification and Smart Mobility.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">This thesis investigates and improves state of charge (SoC) estimation for lithium-ion batteries, a core function of battery management systems (BMSs) in electric vehicles (EVs). The research begins with a review of state-of-the-art BMSs, focusing on battery monitoring and balancing, state estimation, thermal management, fault diagnosis, contactor drive control, and battery communication. The review highlights key challenges in EV applications, particularly the reduced accuracy and robustness of SoC estimators across operating conditions. The potential to improve SoC estimation is initially explored using two deep neural networks combined with low-pass filters. The results indicate a 40% improvement in SoC estimation accuracy compared to non-filtered counterparts, highlighting the benefits of capturing temporal patterns in EV applications.

Based on this review and initial analyses, a more comprehensive investigation of deep neural networks and Kalman-filter SoC estimators for lithium-ion batteries is conducted, along with the development of a hybrid approach that integrates the predictive capabilities of deep neural networks with the recursive state-estimation properties of Kalman filters. The methodology considers diverse operating conditions, including vehicle payloads, temperatures, drive cycles, and sensor offset errors introduced to emulate real-world inaccuracies. Computational efficiency and memory requirements are also explored to assess deployment feasibility on automotive microprocessors. The results indicate that the hybrid Kalman-filter neural network architecture consistently outperforms the baseline models, achieving 35% lower error compared to optimized deep neural networks and Kalman filters. The hybrid approach effectively handles sensor offset errors, high-power drive cycles, and low-temperature conditions.

Finally, the memory demands of the hybrid SoC estimator are investigated together with other BMS algorithms to assess feasibility on an automotive-grade microprocessor. Overall, this thesis provides a comprehensive study of SoC estimators and proposes a hybrid SoC design methodology that considers accuracy, robustness, and computational feasibility for EV applications.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree">Doctor of Philosophy (PhD)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="rights" lang="en">Attribution-NonCommercial-NoDerivatives 4.0 International</dim:field>
   <dim:field mdschema="dc" element="rights" qualifier="uri">http://creativecommons.org/licenses/by-nc-nd/4.0/</dim:field>
   <dim:field mdschema="dc" element="subject">Deep Neural Networks</dim:field>
   <dim:field mdschema="dc" element="subject">Electric Vehicles</dim:field>
   <dim:field mdschema="dc" element="subject">Kalman Filters</dim:field>
   <dim:field mdschema="dc" element="subject">Hybrid Model</dim:field>
   <dim:field mdschema="dc" element="subject">Lithium-ion</dim:field>
   <dim:field mdschema="dc" element="subject">Low-Pass Filtering</dim:field>
   <dim:field mdschema="dc" element="subject">State of Charge</dim:field>
   <dim:field mdschema="dc" element="title">Hybrid State of Charge Estimation For Batteries in Electric Vehicles: An Integrated Deep Neural Network and Kalman Filter Methodology</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">embargo</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>