Model strojnega učenja za analizo hitrosti propadanja premostitvenih objektov na podlagi realnih podatkov Development of an artificial intelligence model for analysing the deterioration rate of bridges based on real-world data Umetna inteligenca v zadnjih letih pomembno spreminja številna področja, saj omogoča učinkovito analizo velikih količin podatkov, avtomatizacijo procesov in podporo pri sprejemanju odločitev. Čeprav njena uporaba hitro narašča, je v gradbeništvu še vedno manj razširjena kot v številnih drugih gospodarskih panogah. To predstavlja pomembno priložnost za razvoj novih pristopov, ki med drugim lahko izboljšajo načrtovanje, upravljanje in vzdrževanje infrastrukturnih objektov. Premostitveni objekti so med najpomembnejšimi elementi prometne infrastrukture, njihovo stanje pa neposredno vpliva na varnost, zanesljivost in učinkovitost prometnega omrežja. Zaradi staranja konstrukcij, naraščajočih prometnih obremenitev ter omejenih finančnih sredstev postaja pravočasno napovedovanje propadanja vse pomembnejše. Cilj diplomskega dela je bil razviti model umetne inteligence za analizo hitrosti propadanja premostitvenih objektov na podlagi realnih podatkov. Za pripravo in vrednotenje napovednih modelov je bila uporabljena programska oprema Orange Data Mining, kjer smo na podlagi izbranih atributov uporabili različne modele za napovedovanje. Rezultati kažejo, da lahko metode strojnega učenja podpirajo analizo propadanja premostitvenih objektov in predstavljajo pomemben del nove dobe gradbeništva. Artificial intelligence has significantly transformed numerous fields in recent years by enabling the efficient analysis of large amounts of data, process automation, and decision-making support. Although its application is rapidly increasing, it remains less widespread in the construction industry than in many other economic sectors. This presents an important opportunity for the development of new approaches that can improve the planning, management, and maintenance of infrastructure assets. Bridges are among the most important elements of road transport infrastructure, and their condition directly affects the safety, reliability, and efficiency of the transport network. Due to ageing, increasing traffic loads, and limited financial resources, the timely prediction of deterioration is becoming increasingly important. The goal of this thesis was to develop an artificial intelligence model for analysing the deterioration rate of bridges based on real-world data. Orange Data Mining software was used for data preparation and for the development and evaluation of predictive models. Based on selected attributes, different prediction models were developed. The results indicate that machine learning methods can effectively support the analysis of bridge deterioration rate and represent an important component of the emerging digital era in the construction industry. strojno učenje umetna inteligenca Orange Data Mining upravljanje s cestno infrastrukturo premostitveni objekti napovedovanje propadanja machine learning artificial intelligence Orange Data Mining road asset management bridges deterioration rate prediction true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2026-09-19 08:46:08 2026-09-19 08:46:11 2026-09-19 08:46:12 0000-00-00 00:00:00 2026 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 1970-01-01 182687 23309.pdf 23309.pdf 1 bf03a31a-b3f5-11f1-8bc5-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=248264 Fakulteta za gradbeništvo in geodezijo 0 0 0