20.500.12556/RUL-174500 Sistemi za podporo odločanju pri optimizaciji proizvodnje penicilina magistrsko delo Decision support systems for penicillin production optimisation V skladu s smernicami industrije 5.0 se razvoj tehnoloških rešitev usmerja na podporo ljudem v proizvodnem okolju. Z zadnjimi trendi je večji poudarek namenjen razvoju podpornih sistemov, ki operaterjem proizvodnje olajšajo vodenje njihove dejavnosti s tem, da spremljajo njihove aktivnosti in jim predlagajo, katere korekcijske ukrepe naj v danem trenutku izvedejo. V delu so bili razviti različni sistemi za podporo odločanju, ki so bili testirani na primeru simulacijskega okolja IndPenSim za proizvodnjo penicilina. Za ta namen so bili razviti podporni sistemi, ki ob vnaprej določenih časih (vsakih 24 ur) operaterjem predlagajo korekcijske ukrepe. Predstavljene so bile tri družine sistemov za podporo odločanju, ki temeljijo na optimizaciji napovednega modela, GNN priporočilnih sistemih in hibridnih metodah. Rezultati kažejo, da je mogoče z uporabo različnih podpornih sistemov povečati končni izplen penicilina, pri čemer še posebej izstopa hibridni pristop, ki izkorišča prednosti obeh drugih pristopov. Primerjava z obstoječo literaturo kaže, da predlagane metode dosegajo izplene, primerljive z doslej najzmogljivejšimi modeli za optimizacijo procesa simuliranega z IndPenSim. Pri tem so bili posegi v proces izvedeni bistveno redkeje, kot v prejšnjih delih. Navedene ugotovitve potrjujejo primernost razvitih pristopov za uporabo tudi pri drugih procesih. In accordance with the principles of Industry 5.0, the development of technological solutions is directed toward supporting people in the industrial production environment. Recent trends place greater emphasis on the development of support systems that assist production operators in managing their activities by monitoring their performance and suggesting which corrective measures should be taken at a given moment. In this work, various decision support systems were developed and tested in the IndPenSim simulation environment for penicillin production. For this purpose, decision support systems were designed to provide operators with corrective action recommendations at predefined time intervals (every 24 hours). Three families of decision support systems were introduced, based on predictive model optimization, GNN-based recommendation systems, and hybrid methods. The results demonstrate that the application of different decision support systems can increase the final yield of penicillin, with the hybrid approach standing out in particular, as it exploits the advantages of the other two approaches. A comparison with prior studies confirms that the proposed methods reach yields equivalent to those of the strongest IndPenSim-based optimization models reported so far. Moreover, interventions in the process were required significantly less frequently than in previous studies. These findings confirm the suitability of the developed approaches for application to other processes as well. sistemi za podporo odločanju priporočilni sistemi optimizacija penicilin proizvodni proces nadzor in vodenje operater industrija 5.0 GNN nevronske mreže XGBoost decision support systems recommender systems optimization penicillin production process monitoring and control operator Industry 5.0 GNN neural networks XGBoost true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2025-10-03 08:15:05 2025-10-03 08:15:11 2025-11-23 03:46:58 0000-00-00 00:00:00 2025 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004 155150 251233027 19787.pdf 19787.pdf 1 74D34F5F84A35D816384738E9AD2E166 86244cfb56f6276b34d3379bf04ab2b6d7782e56a124d957f78961620eaf6bc6 1c49b3b1-a020-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=219320 Fakulteta za matematiko in fiziko 0 0 0