Primjena umjetne inteligencije u inženjerstvu materijala

undergraduate thesis

• Title (english): AI applications in materials science
• Author: Tea Miškulin
• Mentor: Miroslav Jerković (mentor)
• Committee member: Miroslav Jerković (predsjednik povjerenstva)
• Committee member: Nenad Bolf (član povjerenstva)
• Committee member: Iva Movre Šapić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Chemical Engineering and Technology; Zagreb
• Defense date and country: 2022-09-14, Croatia
• Scientific / art field, discipline and subdiscipline: NATURAL SCIENCES; Mathematics

Abstract

Beton je jedan od najstarijih materijala kojeg ljudi koriste, a danas je najvažniji materijal u građevinskom inženjerstvu. Kroz godine razvijali su se novi načini proizvodnje betona koji su pomogli stvaranju snažnijeg i izdržljivijeg betona. Beton je mješavina različitih sastojaka, a njegova čvrstoća određuje sveukupnu kvalitetu mješavine. Za ocjenu kvalitete betona najčešće se koristi tlačna čvrstoća. Na čvrstoću, osim cementa, utjecaj imaju i mnogi drugi sastojci poput šljake, letećeg pepela, vode, superplastifikatora, krupnih agregata, finih agregata, ali i starost. Tlačna čvrstoća betona funkcija je starosti i sastojaka betona. Kako bi analiza utjecaja ovih parametara na čvrstoću bila što jednostavnija primjenjuju se različiti algoritmi umjetne inteligencije koji procjenjuju vrijednost čvrstoće. Za primjenu algoritama koristi se programski jezik R, kao jedan od najčešće korištenih programskih jezika za rješavanje problema zbog svoje jednostavnosti i pristupačnosti. Cilj ovog rada je implementacijom algoritama umjetne inteligencije pronaći model koji najbolje procjenjuje tlačnu čvrstoću betona.

Abstract (english)

Concrete is one of the oldest materials that people use, and today is the most important material used in civil engineering. Throughout the years, new methods of concrete production have been developed that have helped to create stronger and more durable concrete. Concrete is a mixture of many different ingredients, and its strength determines the overall quality of the mixture. Compressive strength is most often used to evaluate the quality of concrete. In addition to cement, strength is also influenced by many other ingredients such as slag, fly ash, water, superplasticizers, coarse aggregate, fine aggregate, and also age. The compressive strength of concrete is a function of age and its ingredients. In order to make the analysis of the impact of these parameters on the compressive strength as simple as possible, various artificial intelligence algorithms are applied to estimate the strength value. To apply the algorithms, the R programming language is used, as it is on of the most commonly used programming languages for solving problems due to its simplicity and accesibility. The goal of this work is to find a model that best estimates the compressive strength of concrete by implementing artificial intelligence algorithms.

• Keywords: beton; tlačna čvrstoća; umjetna inteligencija; strojno učenje; programski jezik R
• Keywords (english): concrete; compressive strength; artificial intelligence; machine learning; R
• Language: croatian
• URN:NBN: urn:nbn:hr:149:027593
• Study programme: Title: Chemical Engineering - Undergraduate study; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka kemijskog inženjerstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka kemijskog inženjerstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-03-08 13:26:18