1. Analiza dinamičnega odziva sistemov z eno prostostno stopnjo na časovno spremenljive zunanje obtežbe z uporabo spektrov odzivaGregor Romih, 2025, diplomsko delo Opis: Diplomsko delo obravnava osnovne principe in metode dinamike gradbenih konstrukcij na
enostavnih sistemih z eno prostostno stopnjo. Predstavljena je izpeljava osnovne enačbe
gibanja in njena posplošitev na primer potresne obtežbe, ki ustreza gibanju podpor. V
osrednjem delu so podane analitične rešitve enačbe gibanja za različne vrste časovno
odvisnih obtežb, pri čemer je poudarek na primeru resonančnega odziva pri harmonični
obtežbi. Za te iste obtežbe je prikazan tudi izračun (maksimalnih) dinamičnih faktorjev, ki
omogočajo enostavno analizo dinamičnih vplivov v gradbeniški praksi. Za primere gibanja
podpor so definirani spektri odziva, ki so nato izračunani za nekaj izbranih primerov gibanja
tal. Izračun je bil narejen z uporabo Newmarkove metode z linearnimi pospeški,
implementirane v programskem okolju Wolfram Mathematica. Z računskima primeroma je
ilustrirana uporaba dinamičnih faktorjev in spektrov odziva na dveh primerih stavb. Dobljeni
rezultati kažejo na enostavnost uporabe uporabljenih konceptov in postopkov, kljub
kompleksnosti dinamičnih pojavov pri gradbenih konstrukcijah. Še več, uporabljene
poenostavitve kažejo, da je mogoče s primernim razumevanjem problematike dobiti
rezultate, ki so dovolj natančni za inženirsko uporabo in/ali oceno velikostnega reda
dinamičnih vplivov v gradbeniški praksi.
Ključne besede: dinamični faktor, dinamična analiza, spekter odziva, gibanje tal, časovni odziv
Objavljeno v DKUM: 25.09.2025; Ogledov: 0; Prenosov: 32
 Celotno besedilo (2,64 MB) |
2. Umetne nevronske mreže z bazo znanja kolektivne inteligence stroke in uporabo v mostogradnjiTomaž Goričan, 2025, doktorska disertacija Opis: Doktorska disertacija se osredotoča na uporabo metod umetne inteligence in podatkov kolektivne inteligence strokovnjakov za napovedovanje parametrov mostov, grajenih po tehnologiji postopnega narivanja. Podatki kolektivne inteligence omogočajo zajem izkušenj strokovnjakov, metode umetne inteligence pa njihovo uporabo in prenos tega znanja. Pri tem podatki kolektivne inteligence izhajajo iz različnih virov - od zakonskih predpisov do parametrov mostov, grajenih po tehnologiji postopnega narivanja. Majhne zbirke podatkov, ki so običajno stalnica pri specifičnih inženirskih problemih, smo ustrezno obdelali z uporabo primernih statističnih metod in jih razširili za uporabo pri metodah umetne inteligence. S tem smo izboljšali pokritost problemskega prostora. Za razširitev zbirke podatkov je bila uporabljena metoda stratificiranega vzorčenja, pri tem pa so bile upoštevane aleatorne in epistemične nezanesljivosti. Analizirane so bile različne metode umetnih nevronskih mrež v namen doseganja optimalnih rezultatov obravnavanega problema. Razvit je bil empirični matematični model, ki omogoča napoved parametrov mostov, grajenih po tehnologiji postopnega narivanja, ter napoved prečnega prereza mostne konstrukcije ob upoštevanju zakonskih predpisov. Pri napovedi parametrov mostov smo izračunali tudi informacije o relativni zanesljivosti rezultatov in lokalnih napakah. Pri evaluaciji izdelanih modelov smo upoštevali tako napako napovedi kot tudi pripadajoče podatke o relativni zanesljivosti rezultatov. Izdelani so bili dvo- in večdimenzionalni grafi za razlago rezultatov in analizo medsebojnih vplivov različnih parametrov. Uporabili smo strogo matematični pristop ter pristop, ki temelji na interpretaciji rezultatov s pomočjo velikih jezikovnih modelov. Za namen aplikacije rezultatov v gospodarstvu je bila izdelana aplikacija Asistent za načrtovanje mostov z uporabo umetnih nevronskih mrež, ki predstavlja pomoč inženirjem pri projektiranju in gradnji mostov, grajenih po tehnologiji postopnega narivanja. Aplikacija omogoča dinamično spreminjanje vhodnih in izhodnih parametrov. Doktorska disertacija dokazuje uporabo podatkov kolektivne stroke v metodah umetne inteligence pri gradnji mostov, grajenih po tehnologiji postopnega narivanja in podaja splošni okvir uporabe metod umetne inteligence v gradbeništvu.
Ključne besede: umetna inteligenca, kolektivna inteligenca, zanesljivost napovedi, pravila stroke, armiranobetonski most, tehnologija postopnega narivanja
Objavljeno v DKUM: 29.05.2025; Ogledov: 0; Prenosov: 38
Celotno besedilo (11,01 MB) |
3. Ranking as a procedure for selecting a replacement variable in the score predicting the survival of patients treated with curative intent for colorectal liver metastasesIrena Plahuta, Matej Mencinger, Iztok Peruš, Tomislav Magdalenić, Špela Turk, Aleks Brumec, Stojan Potrč, Arpad Ivanecz, 2023, izvirni znanstveni članek Opis: Background and Objectives: The issue of a missing variable precludes the external validation of many prognostic models. For example, the Liverpool score predicts the survival of patients undergoing surgical therapy for colorectal liver metastases, but it includes the neutrophil–lymphocyte ratio, which cannot be measured retrospectively.
Materials and Methods: We aimed to find the most appropriate replacement for the neutrophil–lymphocyte ratio. Survival analysis was performed on data representing 632 liver resections for colorectal liver metastases from 2000 to 2020. Variables associated with the Liverpool score, C-reactive protein, albumins, and fibrinogen were ranked. The rankings were performed in four ways: The first two were based on the Kaplan-Meier method (log-rank statistics and the definite integral ��
between two survival curves). The next method of ranking was based on univariate and multivariate Cox regression analyses.
Results: The ranks were as follows: the radicality of liver resection (rank 1), lymph node infiltration of primary colorectal cancer (rank 2), elevated C-reactive protein (rank 3), the American Society of Anesthesiologists Classification grade (rank 4), the right-sidedness of primary colorectal cancer (rank 5), the multiplicity of colorectal liver metastases (rank 6), the size of colorectal liver metastases (rank 7), albumins (rank 8), and fibrinogen (rank 9).
Conclusions: The ranking methodologies resulted in almost the same ranking order of the variables. Elevated C-reactive protein was ranked highly and can be considered a relevant replacement for the neutrophil–lymphocyte ratio in the Liverpool score. These methods are suitable for ranking variables in similar models for medical research.
Ključne besede: colorectal cancer, liver metastases, inflammation, ranking, survival
Objavljeno v DKUM: 07.04.2025; Ogledov: 0; Prenosov: 9
Celotno besedilo (1,15 MB)
Gradivo ima več datotek! Več... |
4. The learning curve of laparoscopic liver resection utilising a difficulty scoreArpad Ivanecz, Irena Plahuta, Matej Mencinger, Iztok Peruš, Tomislav Magdalenić, Špela Turk, Stojan Potrč, 2022, izvirni znanstveni članek Opis: Background: This study aimed to quantitatively evaluate the learning curve of laparoscopic liver resection (LLR) of a single surgeon.
Patients and methods: A retrospective review of a prospectively maintained database of liver resections was conducted. 171 patients undergoing pure LLRs between April 2008 and April 2021 were analysed. The Halls difficulty score (HDS) for theoretical predictions of intraoperative complications (IOC) during LLR was applied. IOC was defined as blood loss over 775 mL, unintentional damage to the surrounding structures, and conversion to an open approach. Theoretical association between HDS and the predicted probability of IOC was utilised to objectify the shape of the learning curve.
Results: The obtained learning curve has resulted from thirteen years of surgical effort of a single surgeon. It consists of an absolute and a relative part in the mathematical description of the additive function described by the logarithmic function (absolute complexity) and fifth-degree regression curve (relative complexity). The obtained learning curve determines the functional dependency of the learning outcome versus time and indicates several local extreme values (peaks and valleys) in the learning process until proficiency is achieved.
Conclusions: This learning curve indicates an ongoing learning process for LLR. The proposed mathematical model can be applied for any surgical procedure with an existing difficulty score and a known theoretically predicted association between the difficulty score and given outcome (for example, IOC).
Ključne besede: difficulty score, learning curve, laparoscopy, hepatectomy, intraoperative complications, surgical procedures
Objavljeno v DKUM: 07.04.2025; Ogledov: 0; Prenosov: 258
 Povezava na celotno besedilo
Gradivo ima več datotek! Več... |
5. Contour maps for simultaneous increase in yield strength and elongation of hot extruded aluminum alloy 6082Iztok Peruš, Goran Kugler, Simon Malej, Milan Terčelj, 2022, izvirni znanstveni članek Opis: In this paper, the Conditional Average Estimator artificial neural network (CAE ANN) was used to analyze the influence of chemical composition in conjunction with selected process parameters on the yield strength and elongation of an extruded 6082 aluminum alloy (AA6082) profile. Analysis focused on the optimization of mechanical properties as a function of casting temperature, casting speed, addition rate of alloy wire, ram speed, extrusion ratio, and number of extrusion strands on one side, and different contents of chemical elements, i.e., Si, Mn, Mg, and Fe, on the other side. The obtained results revealed very complex non-linear relationships between all of these parameters. Using the proposed approach, it was possible to identify the combinations of chemical composition and process parameters as well as their values for a simultaneous increase of yield strength and elongation of extruded profiles. These results are a contribution of the presented study in comparison with published research results of similar studies in this field. Application of the proposed approach, either in the research and/or in industrial aluminum production, suggests a further increase in the relevant mechanical properties.
Ključne besede: AA6082, hot extrusion, mechanical properties, yield strength, elongation, artificial neural networks, analysis
Objavljeno v DKUM: 12.03.2025; Ogledov: 0; Prenosov: 12
Celotno besedilo (4,40 MB)
Gradivo ima več datotek! Več... |
6. CAE artificial neural network applied to the design of incrementally launched prestressed concrete bridgesTomaž Goričan, Milan Kuhta, Iztok Peruš, 2025, izvirni znanstveni članek Opis: Bridges are typically designed by reputable, specialized engineering and design companies with years of experience. In these firms, experienced engineers share and pass on their knowledge to younger colleagues. However, when these experts retire, some of the knowledge is lost forever. As a subset of artificial intelligence methods, artificial neural networks (ANNs) can solve the problem of acquiring, transferring, and preserving specialized expert knowledge. This article describes the possible application of CAE ANN to acquire knowledge and to assist in the design of incrementally launched prestressed concrete bridges. Therefore, multidimensional graphs in the form of iso-curves of equal values were created, allowing practicing engineers to understand complex relationships between design parameters. The graphs also contain information about the reliability of the results, which is defined by an estimated parameter. The general rule is that results based on a larger number of actual data points are more reliable. Finally, an ANN BD assistant is proposed as an application that assists engineers and designers in the early stages of design and/or established engineers and designers in variant studies and design parameter optimization.
Ključne besede: artificial neural networks, bridge design, incremental launching method, expert knowledge, reliability of predictions, prestressed concrete bridges
Objavljeno v DKUM: 10.03.2025; Ogledov: 0; Prenosov: 18
Celotno besedilo (5,54 MB)
Gradivo ima več datotek! Več... |
7. New approach for automated explanation of material phenomena (AA6082) using artificial neural networks and ChatGPTTomaž Goričan, Milan Terčelj, Iztok Peruš, 2024, izvirni znanstveni članek Opis: Artificial intelligence methods, especially artificial neural networks (ANNs), have increasingly been utilized for the mathematical description of physical phenomena in (metallic) material
processing. Traditional methods often fall short in explaining the complex, real-world data observed
in production. While ANN models, typically functioning as “black boxes”, improve production
efficiency, a deeper understanding of the phenomena, akin to that provided by explicit mathematical
formulas, could enhance this efficiency further. This article proposes a general framework that
leverages ANNs (i.e., Conditional Average Estimator—CAE) to explain predicted results alongside
their graphical presentation, marking a significant improvement over previous approaches and those
relying on expert assessments. Unlike existing Explainable AI (XAI) methods, the proposed framework mimics the standard scientific methodology, utilizing minimal parameters for the mathematical
representation of physical phenomena and their derivatives. Additionally, it analyzes the reliability
and accuracy of the predictions using well-known statistical metrics, transitioning from deterministic
to probabilistic descriptions for better handling of real-world phenomena. The proposed approach
addresses both aleatory and epistemic uncertainties inherent in the data. The concept is demonstrated through the hot extrusion of aluminum alloy 6082, where CAE ANN models and predicts
key parameters, and ChatGPT explains the results, enabling researchers and/or engineers to better
understand the phenomena and outcomes obtained by ANNs.
Ključne besede: artificial neural networks, automatic explanation, hot extrusion, aluminum alloy, large language models, ChatGPT
Objavljeno v DKUM: 27.02.2025; Ogledov: 0; Prenosov: 6
Celotno besedilo (3,18 MB)
Gradivo ima več datotek! Več... |
8. Flexible assignment of loading bays for efficient vehicle routing in urban last mile deliveryTomislav Letnik, Matej Mencinger, Iztok Peruš, 2020, izvirni znanstveni članek Opis: Urban freight deliveries are often subject to many access restrictions which creates the need to establish a system of loading bays and to split the last mile delivery into driving and walking parts. A new model based on hard and soft clustering approach is developed to solve the loading bay assignment problem for efficient vehicle routing and walking in last mile delivery. The flexibility of the model is provided by the soft clustering approach based on different membership degrees of customers to loading bays. Especially for instances with large numbers of loading bays, soft clustering seems to give better results, it leads to higher flexibility of city logistics systems, minimal driving distances, and adequately short walking paths, which contribute to the goal of reaching sustainable urban freight deliveries.
Ključne besede: city logistics, last-mile delivery, loading bay, facility location, fuzzy clustering, two-echelon routing problem, location-routing problem
Objavljeno v DKUM: 28.01.2025; Ogledov: 0; Prenosov: 11
Celotno besedilo (14,10 MB)
Gradivo ima več datotek! Več... |
9. Mathematical modeling of the floating sleeper phenomenon supported by field measurements : Mojmir Uranjek, Denis Imamović and Iztok PerušMojmir Uranjek, Denis Imamović, Iztok Peruš, 2024, izvirni znanstveni članek Opis: This article aims to provide an accurate mathematical model with the minimum number of degrees of freedom for describing the floating sleeper phenomenon. This was accomplished using mathematical modeling supported by extensive field measurements of the railway track. Although the observed phenomenon is very complex, the simplified single degree of freedom (SDOF) mathematical model proved accurate enough for its characterization. The progression of the deterioration of the railway track was successfully correlated to changes in the maximal dynamic factor for different types of pulse loading. The results of the presented study might enable the enhanced construction and maintenance of railroads, particularly in karst areas.
Ključne besede: floating sleepers, dynamic factor, pulse loading, field measurements, SDOF mathematical model
Objavljeno v DKUM: 28.11.2024; Ogledov: 0; Prenosov: 23
Celotno besedilo (6,27 MB)
Gradivo ima več datotek! Več... |
10. SAP2000 : priročnik za začetno uporabo pri linearni statični analizi ravninskih linijskih konstrukcijDenis Imamović, 2023 Opis: Program SAP2000 je izredno zmogljivo orodje za mehanske preračune in projektiranje konstrukcij v praksi. Kot odličen se je izkazal tudi v študijske namene pri opravljanju seminarskih nalog in zaključnih del, kot tudi za kontrolo rezultatov “peš” mehanskih analiz, s katerimi se študenti seznanijo v času večletnega študija na Fakulteti za gradbeništvo, prometno inženirstvo in arhitekturo (FGPA) v Mariboru. S tem namenom je bil za vse študente FGPA, ki jih zanima delo v programu SAP2000, izdelan priročnik z naslovom “SAP2000: Priročnik za začetno uporabo pri linearni statični analizi ravninskih linijskih konstrukcij”. V tem delu so za najosnovnejšo mehansko -linearno statično- analizo na treh enostavnih primerih obširno in slikovito predstavljeni vsi vmesni koraki od začetnega modeliranja do končne predstavitve rezultatov. Priročnik je kot takšen namenjen za uporabnika z osnovnim znanjem mehanike brez kakršnihkoli predhodnih izkušenj v programu SAP2000.
Ključne besede: metoda končnih elementov, ravninske linijske konstrukcije, računalniška analiza konstrukcij, analiza statičnega odziva, modeliranje, grafična predstavitev rezultatov
Objavljeno v DKUM: 09.08.2023; Ogledov: 516; Prenosov: 130
Celotno besedilo (19,63 MB)
Gradivo ima več datotek! Več... |
