Iskanje po katalogu digitalne knjižnice

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: 7
Celotno besedilo (3,54 MB)

Opis: This article has presented a technical concept for producing precisely desired Additive Manufactured (AM) metallic products using Artificial Intelligence (AI). Due to the stochastic nature of the metallic AM process, which causes a greater variance in product properties compared to traditional manufacturing processes, significant inaccuracies in metallurgical properties, as well as geometry, occur. The physics behind these phenomena are related to the melting process, bonding, cooling rate, shrinkage, support condition, part orientation. However, by controlling these phenomena, a wide range of product features can be achieved using the fabricating parameters. A variety of fabricating parameters are involved in the metal AM process, but an appropriate combination of these parameters for a given material is required to obtain an accurate and desired product. Zero defect product can be achieved by controlling these parameters by implementing Knowledge-Based System (KBS). A suitable combination of manufacturing parameters can be determined using mathematical tools with AI, considering the manufacturing time and cost. The knowledge required to integrate AM manufacturing characteristics and constraints into the design and fabricating process is beyond the capabilities of any single engineer. Concurrent Engineering enables the integration of design and manufacturing to enable trades based not only on product performance, but also on other criteria that are not easily evaluated, such as production capability and support. A decision support system or KBS that can guide manufacturing issues during the preliminary design process would be an invaluable tool for system designers. The main objective of this paper is to clearly describe the metal AM manufacturing process problem and show how to develop a KBS for manufacturing process determination.
Ključne besede: metallurgical properties, geometry, additive manufacturing, artificial intelligence, knowledge-based system
Objavljeno v DKUM: 25.09.2024; Ogledov: 0; Prenosov: 9
Celotno besedilo (1,46 MB)
Gradivo ima več datotek! Več...

Opis: Orbifold singularities of M-theory constitute the building blocks of a broad class of supersymmetric quantum field theories (SQFTs). In this paper we show how the local data of these geometries determine global data on the resulting higher symmetries of these systems. In particular, via a process of cutting and gluing, we show how local orbifold singularities encode the 0-form, 1-form, and 2-group symmetries of the resulting SQFTs. Geometrically, this is obtained from the possible singularities that extend to the boundary of the noncompact geometry. The resulting category of boundary conditions then captures these symmetries and is equivalently specified by the orbifold homology of the boundary geometry. We illustrate these general points in the context of a number of examples, including five-dimensional (5D) superconformal field theories engineered via orbifold singularities, 5D gauge theories engineered via singular elliptically fibered Calabi-Yau threefolds, as well as four-dimensional supersymmetric quantum chromodynamics-like theories engineered via M-theory on noncompact G2 spaces.
Ključne besede: F-theory, compactifications, classification, singularities, instantons, geometry
Objavljeno v DKUM: 06.06.2024; Ogledov: 159; Prenosov: 10
Celotno besedilo (863,93 KB)
Gradivo ima več datotek! Več...

Opis: The heating, ventilation and air-conditioning (HVAC) system represents the main auxiliary load for any type of bus. Being the most significant energy-consuming auxiliary load for the electric bus, it must be given special attention in an electric bus system design. To study the heat transfer and thermal optimization for passenger comfort in the electric bus computer-aided design (CAD) is used. The geometry of an electric bus interior is designed considering the main components of the vehicle: passenger cabin, driver’s cabin, windows, walls, and seats. Materials of the same type as those used in the real bus are considered for the geometry model. Based on the heat transfer theory, a thermal model and simulations are made for the heat transfer inside the electric bus. The simulated data are compared with measurement data, and based on these, it can be concluded that the thermal model of the electric bus can be validated and used further for a wide variety of thermal simulation types.
Ključne besede: heat transfer, electric bus, passenger comfort, geometry design, thermal modelling
Objavljeno v DKUM: 13.11.2023; Ogledov: 274; Prenosov: 6
Celotno besedilo (1,04 MB)
Gradivo ima več datotek! Več...

Opis: In the largest, currently known, class of one quadrillion globally consistent F-theory Standard Models with gauge coupling unification and no chiral exotics, the vectorlike spectra are counted by cohomologies of root bundles. In this work, we apply a previously proposed method to identify toric base threefolds, which are promising to establish F-theory Standard Models with exactly three quark doublets and no vectorlike exotics in this representation. The base spaces in question are obtained from triangulations of 708 polytopes. By studying root bundles on the quark-doublet curve Cð3;2Þ1=6 and employing well-known results about desingularizations of toric K3 surfaces, we derive a triangulation independent lower bound Nˇ ð3Þ P for the number Nð3Þ P of root bundles on Cð3;2Þ1=6 with exactly three sections. The ratio Nˇ ð3Þ P =NP, where NP is the total number of roots on Cð3;2Þ1=6 , is largest for base spaces associated with triangulations of the eighth three-dimensional polytope Δ∘ 8 in the Kreuzer-Skarke list. For each of these Oð1015Þ threefolds, we expect that many root bundles on Cð3;2Þ1=6 are induced from F-theory gauge potentials and that at least every 3000th root on Cð3;2Þ1=6 has exactly three global sections and thus no exotic vectorlike quark-doublet modes.
Ključne besede: astrophysics, compactification, string theory models, geometry, higher-dimensional field theories, mathematical physics, quantum fields in curved spacetime, string phenomenology, supersymmetric models, topology
Objavljeno v DKUM: 16.10.2023; Ogledov: 317; Prenosov: 33
Celotno besedilo (444,13 KB)
Gradivo ima več datotek! Več...