20.500.12556/RUL-186791 Napovedovanje preostanka življenjske dobe baterije s klasičnimi metodami strojnega učenja Prediction of remaining battery life using classical machine learning methods V zaključni nalogi smo obravnavali napovedovanje staranja baterij oziroma preostanka njihove življenjske dobe z metodami strojnega učenja. S pomočjo podatkov o ciklanju baterij so bile izračunane značilke, na podlagi katerih so se modeli klasičnega strojnega učenja po sistemu izpuščanja ene baterije naučili napovedovati staranje baterij. Napovedi so bile ovrednotene s srednjo absolutno napako, korenom srednje kvadratne napake in koeficientom determinacije. Na končnih napovedih je bil uporabljen skriti markovski model. Ugotovili smo, da so za uspešno napoved pomembni dovolj velika množica učnih baterij, podoben potek staranja baterij ter ustrezna izbira značilk in napovednega modela. The thesis presents the prediction of battery ageing and remaining battery life using machine learning methods. Features were calculated from battery cycling data and used to train classical machine learning models to predict battery ageing using a leave one battery out approach. The predictions were evaluated using mean absolute error, root mean square error and the coefficient of determination. A hidden Markov model was applied to the final predictions. The results showed that successful prediction requires a sufficiently large set of training batteries, similar ageing behaviour among the batteries, and an appropriate selection of features and prediction model. litij-ionske baterije degradacija baterij strojno učenje napovedovanje življenjske dobe baterij značilke metrike vrednotenja lithium-ion batteries battery degradation machine learning battery lifetime prediction features evaluation metrics true false false [N. Kosmač] Slovenski jezik Angleški jezik Diplomsko delo/naloga 2026-09-05 08:32:22 2026-09-05 08:32:38 2026-09-07 12:44:52 0000-00-00 00:00:00 2026 0 Ljubljana 0 XI, 20, [29] f. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 621.352:004.85(043.2) 289381 290218243 49277.pdf 49277.pdf 1 4189D1AC7D34EEA7BA83265DF3DC4237 94ff1acb4238b503301ff712f060f47aa6069a714d10d9c3e00bb4af6326062b 9525fc38-a8f3-11f1-8bc5-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=246162 Fakulteta za strojništvo 0 0 0