Identification of lithium-ion battery parameter variations across cells using artificial intelligence

master's thesis

Tine Lubej (Author), Mitja Truntič (Mentor), Dirk Uwe Sauer (Co-mentor)

Abstract

This thesis focuses on improving the simulation, estimation, and accuracy of parameter identification in lithium-ion battery models. The key objective was to enhance a previously developed program by transitioning it to an object-oriented design, making it more efficient, user-friendly, and modular. Additionally, efforts were made to optimize the parameter estimation process by upgrading the cost function used during simulations and integrating real-world battery measurement data, specifically for the LGM50 battery type. The first step in the thesis involved reworking the codebase to an object-oriented structure, which improved not only the code’s clarity but also its extensibility and efficiency. With this change, the program was better suited for future improvements and became more accessible for other users through simplified installation procedures. This was accompanied by the implementation of unit testing to ensure the reliability of the code. Experiments were conducted across a range of discharge rates (from 0.05C to 1C) to evaluate the performance of the model under different conditions. These tests helped to identify trends in how the model responded to changes in operational parameters. Additionally, a dynamic pulse test was performed, which allowed for more precise estimation of the parameters. The results of these tests demonstrated the robustness of the methodology, especially under dynamic conditions. A major innovation introduced in this thesis was the development of a new cost function, which led to noticeable improvements in parameter estimation accuracy, particularly under high discharge rates and when estimating multiple parameters simultaneously. This new cost function proved especially effective in more complex scenarios, where the original cost function struggled to maintain the same level of accuracy. The program’s capabilities were further extended by incorporating real experimental data. Using a constant discharge profile for the LGM50 battery, the results showed some challenges when dealing with real-world data, particularly due to issues in measurement or data preprocessing. Nonetheless, the model consistently produced solutions, although the accuracy was influenced by the quality of the input data. The thesis concludes by highlighting the success of the improvements made, both in terms of the program’s structure and the precision of its estimations. However, it also emphasizes the importance of improving the quality of real-world data to fully leverage the model’s potential in practical applications. This work lays a foundation for future developments in battery modeling, providing a framework that is adaptable for further research and practical use.

Keywords

machine learning;lithium-ion batteries;parameter estimation;uncertainty quantification;real-experimental data;master's theses;

Data

Language:	English
Year of publishing:	2024
Typology:	2.09 - Master's Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[T. Lubej]
UDC:	681.5.015:621.354(043.2)
COBISS:	229492227
Views:	0
Downloads:	25
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	Slovenian
Secondary title:	Identifikacija variacij parametrov litij-ionskih baterij med celicami z uporabo umetne inteligence
Secondary abstract:	To zaključno delo se osredotoča na izboljšanje simulacije, ocenjevanja in natančnosti identifikacije parametrov v modelih litij-ionskih baterij. Ključni cilj je bil izboljšati predhodno razvit program s prehodom na objektno usmerjeno zasnovo, s čimer je postal učinkovitejši, uporabniku prijaznejši in modularen. Poleg tega smo si prizadevali za optimizacijo postopka ocenjevanja parametrov z nadgradnjo stroškovne funkcije, ki se uporablja med simulacijami, in vključitvijo podatkov o meritvah realnih baterij, zlasti za tip baterije LGM50. Prvi korak v magistrski nalogi je vključeval preoblikovanje baze kode v objektno usmerjeno strukturo, kar je izboljšalo ne le jasnost kode, temveč tudi njeno razširljivost in učinkovitost. S to spremembo je bil program primernejši za prihodnje izboljšave in je s poenostavljenimi postopki namestitve postal dostopnejši drugim uporabnikom. To je spremljalo izvajanje testiranja enot, da bi zagotovili zanesljivost kode. Izvedeni so bili poskusi z različnimi hitrostmi praznjenja (od 0,05C do 1C), da bi ocenili učinkovitost modela v različnih pogojih. Ti preskusi so pomagali ugotoviti trende v odzivanju modela na spremembe operativnih parametrov. Poleg tega je bil izveden dinamični impulzni preskus, ki je omogočil natančnejšo oceno parametrov. Rezultati teh preskusov so pokazali zanesljivost metodologije, zlasti v dinamičnih pogojih. Glavna inovacija, uvedena v tej disertaciji, je bil razvoj nove stroškovne funkcije, ki je omogočila opazno izboljšanje natančnosti ocenjevanja parametrov, zlasti pri visokih stopnjah praznjenja in pri hkratnem ocenjevanju več parametrov. Ta nova stroškovna funkcija se je izkazala za še posebej učinkovito v kompleksnejših scenarijih, kjer je prvotna stroškovna funkcija s težavo ohranjala enako raven natančnosti. Zmogljivosti programa so bile dodatno razširjene z vključitvijo resničnih eksperimentalnih podatkov. Pri uporabi konstantnega profila praznjenja za baterijo LGM50 so rezultati pokazali nekaj izzivov pri obravnavi dejanskih podatkov, zlasti zaradi težav pri merjenju ali predobdelavi podatkov. Kljub temu je model dosledno zagotavljal rešitve, čeprav je na natančnost vplivala kakovost vhodnih podatkov. V zaključku magistrskega dela je poudarjen uspeh izvedenih izboljšav, tako v smislu strukture programa kot natančnosti njegovih ocen. Poudarja pa tudi pomen izboljšanja kakovosti realnih podatkov, da bi v celoti izkoristili potencial modela v praktičnih aplikacijah. To delo postavlja temelje za prihodnji razvoj na področju modeliranja baterij in zagotavlja okvir, ki ga je mogoče prilagoditi za nadaljnje raziskave in praktično uporabo.
Secondary keywords:	strojno učenje;litij-ionske baterije;ocenjevanje parametrov;kvantifikacija negotovosti;realni eksperimentalni podatki;magistrske naloge;
Type (COBISS):	Master's thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Elektrotehnika
Pages:	1 spletni vir (1 datoteka PDF ([VII], 79 f.))
ID:	25173189