20.500.12556/DiRROS-28093 Uporaba umetne inteligence pri končni kontroli kvalitete elektromotorjev The paper presents modern approaches to end-of-line (EoL) quality inspection, i.e. the final inspection stage in the manufacturing process of electric motors, based on artificial intelligence. Traditional EoL systems rely on extensive signal processing and expert-defined features and thresholds, which limits their adaptability and increases dependence on specialist knowledge. To address these limitations, several machine learning approaches are discussed, including ensemble-based classification models, transfer learning, and deep neural networks. The application of ensemble models enables automatic feature selection and implicit threshold determination, resulting in a significant reduction of model complexity while maintaining or improving classification accuracy. Transfer learning is shown to be particularly effective in pre-production scenarios, where only limited training data are available, allowing faster commissioning of quality inspection systems and improved fault detection reliability. Furthermore, deep learning methods based on convolutional and recurrent neural networks, trained directly on vibration and acoustic signals represented as Mel-frequency spectrograms, eliminate the need for manual feature engineering and achieve high classification accuracy even in highly imbalanced industrial datasets. The presented results demonstrate that artificial intelligence-based EoL systems can simplify diagnostic procedures, reduce reliance on expert knowledge, improve robustness to product variations, and enhance the overall adaptability and efficiency of industrial quality inspection processes. Članek obravnava sodobne pristope h končni kontroli kakovosti (angl. End of Line – EoL) elektromotorjev z uporabo umetne inteligence. EoL predstavlja zadnjo stopnjo preverjanja izdelka v proizvodnem procesu. Predstavljene so metode strojnega učenja (angl. Machine Learning), ansambelski modeli (angl. Ensembles), prenos znanja (angl. Transfer Learning) in nevronske mreže za analizo vibracijskih in zvočnih signalov, ki poenostavijo diagnostične postopke, zmanjšajo odvisnost od ekspertnega znanja ter izboljšajo prilagodljivost industrijskih EoL-sistemov. Rezultati uporabe opisanih metod kažejo na večjo robustnost diagnostike in krajši čas uvajanja novih tipov elektromotorjev v proizvodnjo. transfer learning end-of-line quality inspection končna kontrola kakovosti prenos znanja true false true Univerza v Ljubljani, Fakulteta za strojništvo Slovenija Angleški jezik Slovenski jezik © The Authors 2026. Neznano 2026-03-10 09:14:19 2026-03-10 09:14:20 2026-03-11 03:59:10 0000-00-00 00:00:00 2026 0 0 Nasl. z nasl. zaslona; Opis vira z dne 9. 3. 2026; str. 44-48 [št. ]ǂ1 Vol. 32 Feb. 2026 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 2026-02-23 004.8 2630-4090 10.5545/Ventil-32-2026-1.19 270934787 https://revija-ventil.si/uporaba-umetne-inteligence-pri-koncni-kontroli-kvalitete-elektromotorjev/ 1 274542a0-1c59-11f1-acf8-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=41509 RAZ_Mlinaric_Jernej_2026.pdf RAZ_Mlinaric_Jernej_2026.pdf 1 361E8C4FF9026C48C0CEC963B1291AB5 e4ee7c8fbcc284bfff3ec4c147bdd051ae5e04c6e91fbdd2c6160c8773cdb67f 77cc2204-1c59-11f1-acf8-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=41510 Institut Jožef Stefan 0 0 0