1. Predictive modelling of weld bead geometry in wire arc additive manufacturingKristijan Šket, Miran Brezočnik, Timi Karner, Rok Belšak, Mirko Ficko, Tomaž Vuherer, Janez Gotlih, 2025, izvirni znanstveni članek Opis: This study investigates the predictive modelling of weld bead geometry in wire arc additive manufacturing (WAAM) through advanced machine learning methods. While WAAM is valued for its ability to produce large, complex metal parts with high deposition rates, precise control of the weld bead remains a critical challenge due to its influence on mechanical properties and dimensional accuracy. To address this problem, this study utilized machine learning approaches—Ridge regression, Lasso regression and Bayesian ridge regression, Random Forest and XGBoost—to predict the key weld bead characteristics, namely height, width and cross-sectional area. A Design of experiments (DOE) was used to systematically vary the welding current and travelling speed, with 3D weld bead geometries captured by laser scanning. Robust data pre-processing, including outlier detection and feature engineering, improved modelling accuracy. Among the models tested, XGBoost provided the highest prediction accuracy, emphasizing its potential for real-time control of WAAM processes. Overall, this study presents a comprehensive framework for predictive modelling and provides valuable insights for process optimization and the further development of intelligent manufacturing systems. Ključne besede: wire arc additive manufacturing, WA AM, predictive modelling, machine learning, weld bead geometry, XGBoost Objavljeno v DKUM: 13.03.2025; Ogledov: 0; Prenosov: 8
Celotno besedilo (3,54 MB) |
2. Enhancing manufacturing precision: Leveraging motor currents data of computer numerical control machines for geometrical accuracy prediction through machine learningLucijano Berus, Jernej Hernavs, David Potočnik, Kristijan Šket, Mirko Ficko, 2024, izvirni znanstveni članek Opis: Direct verification of the geometric accuracy of machined parts cannot be performed simultaneously with active machining operations, as it usually requires subsequent inspection with measuring devices such as coordinate measuring machines (CMMs) or optical 3D scanners. This sequential approach increases production time and costs. In this study, we propose a novel indirect measurement method that utilizes motor current data from the controller of a Computer Numerical Control (CNC) machine in combination with machine learning algorithms to predict the geometric accuracy of machined parts in real-time. Different machine learning algorithms, such as Random Forest (RF), k-nearest neighbors (k-NN), and Decision Trees (DT), were used for predictive modeling. Feature extraction was performed using Tsfresh and ROCKET, which allowed us to capture the patterns in the motor current data corresponding to the geometric features of the machined parts. Our predictive models were trained and validated on a dataset that included motor current readings and corresponding geometric measurements of a mounting rail later used in an engine block. The results showed that the proposed approach enabled the prediction of three geometric features of the mounting rail with an accuracy (MAPE) below 0.61% during the learning phase and 0.64% during the testing phase. These results suggest that our method could reduce the need for post-machining inspections and measurements, thereby reducing production time and costs while maintaining required quality standards Ključne besede: smart production machines, data-driven manufacturing, machine learning algorithms, CNC controller data, geometrical accuracy Objavljeno v DKUM: 10.03.2025; Ogledov: 0; Prenosov: 8
Celotno besedilo (4,44 MB) Gradivo ima več datotek! Več... |
3. Study of environmental impacts on overhead transmission lines using genetic algorithmsKristijan Šket, Mirko Ficko, Nenad Gubeljak, Miran Brezočnik, 2023, izvirni znanstveni članek Opis: In our study, we explored the complexities of overhead transmission line (OTL) engineering, specifically focusing on their responses to varying atmospheric conditions (ambient temperature, ambient humidity, solar irradiance, ambient pressure, wind speed, wind direction), and electric current usage. Our goal was to comprehend how these independent variables impact critical responses (dependent variables) such as conductor temperature, conductor sag, tower leg stress, and vibrations – parameters crucial for electric distribution. We modelled the target output variable as a polynomial of a certain degree of the input variables. The precise forms of the polynomial were determined using the genetic algorithms (GA). Developed models are essential for quantifying the influence of each input parameter, enriching our understanding of essential system elements. They provide long-term predictions for assessing transmission line lifespan and structural stability, with particularly high precision in forecasting temperature and sag angle. It is important to note that certain engineering parameters, such as material properties and load considerations, were not included in our research, potentially influencing accuracy. Ključne besede: Overhead Transmission Lines (OTL), machine learning, modelling, optimization, genetic algorithms (GA) Objavljeno v DKUM: 10.03.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (417,77 KB) Gradivo ima več datotek! Več... |
4. Optimizing laser cutting of stainless steel using latin hypercube sampling and neural networksKristijan Šket, David Potočnik, Lucijano Berus, Jernej Hernavs, Mirko Ficko, 2025, izvirni znanstveni članek Opis: Optimizing cutting parameters in fiber laser cutting of austenitic stainless steel is challenging due to the complex interplay of multiple variables and quality metrics. To solve this problem, Latin hypercube sampling was used to ensure a comprehensive and efficient exploration of the parameter space with a smaller number of trials (185), coupled with feedforward neural networks for predictive modeling. The networks were trained with a leave-oneout cross-validation strategy to mitigate overfitting. Different configurations of hidden layers, neurons, and training functions were used. The approach was focused on minimizing dross and roughness on both the top and bottom areas of the cut surfaces. During the testing phase, an average MSE of 0.063 and an average MAPE of 4.68% were achieved by the models. Additionally, an experimental test was performed on the best parameter settings predicted by the models. Initial modelling was conducted for each quality metric individually, resulting in an average percentage difference of 1.37% between predicted and actual results. Grid search was also per formed to determine an optimal input parameter set for all outputs, with predictions achieving an average ac curacy of 98.34%. Experimental validation confirmed the accuracy and robustness of the model predictions, demonstrating the effectiveness of the methodology in optimizing multiple parameters of complex laser cutting processes. Ključne besede: laser cutting optimization, cut surface quality, dross formation, Latin hypercube sampling, feedforward neural network Objavljeno v DKUM: 10.01.2025; Ogledov: 0; Prenosov: 23
Celotno besedilo (3,38 MB) Gradivo ima več datotek! Več... |
5. Uporaba evolucijskih metod za napovedovanje stroškov inženirskih projektov : magistrsko deloKristijan Šket, 2023, magistrsko delo Opis: Magistrsko delo obsega napovedovanje stroškov inženirskih projektov v orodjarstvu, katerih cilj so transferna orodja za preoblikovanje pločevine. Cilj dela je s pomočjo genetskega programiranja in programskega okolja BricsCAD na podlagi stroškovne analize že izdelanih transfernih orodij ustvariti napovedne matematične modele za napovedovanje stroškov vsebinsko podobnih projektov v prihodnosti. Za zadostno genetsko raznovrstnost v začetnih generacijah smo organizme ustvarili s polnim, rastočim in delno polnim, delno rastočim načinom. Kot najbolj točen napovedni model v fazi testiranja se je izkazal model z delno polnim, delno rastočim načinom stvarjenja, ki je dosegel povprečno točnost 97,59 %. Ustvarjeni napovedni model je funkcijske gene izbiral iz osnovnih matematičnih operacij: seštevanja, odštevanja, množenja in deljenja. Za uporabo priporočamo model, pridobljen z rastočim načinom in naborom funkcijskih genov iz osnovnih računskih operacij brez operacije deljenja. Model je zgolj 0,25 % manj točen, vendar je enostavnejši za uporabo in za delovanje zahteva poznavanje le trinajstih in ne sedemnajstih spremenljivk. Ključne besede: evolucijske metode, genetsko programiranje, modeliranje in optimizacija, projektno vodenje v orodjarstvu, obvladovanje stroškov Objavljeno v DKUM: 24.04.2023; Ogledov: 675; Prenosov: 156
Celotno besedilo (2,01 MB) |
6. Napovedovanje temperature vodnikov in obremenitev na stebrih daljnovodov s pomočjo genetskih algoritmov : diplomsko deloKristijan Šket, 2020, diplomsko delo Opis: Diplomsko delo zajema reševanje problema v sistemu prenosa in distribucije električne energije. Proučevali smo atmosferske vplive in vplive odvzema električne energije iz sistema na temperaturo in poves električnih vodnikov ter napetosti in vibracije v podporni konstrukciji. Za modeliranje smo uporabili metodo genetskih algoritmov, ki temeljijo na darvinističnih izsledkih o razvoju vrst in posnemajo principe naravne selekcije. Razviti modeli omogočajo študij teže posameznega vpliva. Namen dobljenih modelov je določanje najmočnejših vplivov in možnost napovedovanja vrednosti odzivov za daljše časovno obdobje in s tem ocenjevanje življenjske dobe daljnovodov. Rezultat našega dela so napovedni modeli z visoko stopnjo prilagojenosti na učni in testni množici. Modeli podajajo natančne napovedi, predvsem za temperaturo električnih vodnikov in njihov poves. Nižjo stopnjo natančnosti napovedi pri napetostih in vibracijah v stebrih pripisujemo dejstvu, da na te odzive vplivajo tudi obremenitve na konstrukciji in lastnosti materiala. Ključne besede: električni vodniki, stebri, napetosti, vibracije, genetski algoritmi, modeliranje in optimizacija. Objavljeno v DKUM: 10.09.2020; Ogledov: 1267; Prenosov: 402
Celotno besedilo (1,20 MB) |