| | SLO | ENG | Piškotki in zasebnost

Večja pisava | Manjša pisava

Iskanje po katalogu digitalne knjižnice Pomoč

Iskalni niz: išči po
išči po
išči po
išči po
* po starem in bolonjskem študiju

Opcije:
  Ponastavi


1 - 10 / 126
Na začetekNa prejšnjo stran12345678910Na naslednjo stranNa konec
1.
Controllable speech-driven gesture generation with selective activation of weakly supervised controls
Karlo Crnek, Matej Rojc, 2025, izvirni znanstveni članek

Opis: Generating realistic and contextually appropriate gestures is crucial for creating engaging embodied conversational agents. Although speech is the primary input for gesture generation, adding controls like gesture velocity, hand height, and emotion is essential for generating more natural, human-like gestures. However, current approaches to controllable gesture generation often utilize a limited number of control parameters and lack the ability to activate/deactivate them selectively. Therefore, in this work, we propose the Cont-Gest model, a Transformer-based gesture generation model that enables selective control activation through masked training and a control fusion strategy. Furthermore, to better support the development of such models, we propose a novel evaluation-driven development (EDD) workflow, which combines several iterative tasks: automatic control signal extraction, control specification, visual (subjective) feedback, and objective evaluation. This workflow enables continuous monitoring of model performance and facilitates iterative refinement through feedback-driven development cycles. For objective evaluation, we are using the validated Kinetic–Hellinger distance, an objective metric that correlates strongly with the human perception of gesture quality. We evaluated multiple model configurations and control dynamics strategies within the proposed workflow. Experimental results show that Feature-wise Linear Modulation (FiLM) conditioning, combined with single-mask training and voice activity scaling, achieves the best balance between gesture quality and adherence to control inputs.
Ključne besede: gesture generation, objective evaluation, selective control activation, transformers, weakly supervised learning
Objavljeno v DKUM: 09.09.2025; Ogledov: 0; Prenosov: 3
.pdf Celotno besedilo (1,63 MB)

2.
Possible enhancing of spraying management by evaluating automated control in different training systems
Jurij Rakun, Peter Lepej, Rajko Bernik, Jelisaveta Seka Cvijanović, Miljan Cvetković, Erik Rihter, 2024, izvirni znanstveni članek

Opis: This study explores the feasibility of an automated sensor system for precise plant protection product application in plum orchards, aiming to address issues related to inefficient spraying practices, environmental pollution, and reduced crop quality associated with traditional training systems. The research focuses on detecting tree canopy presence, evaluating electromagnetic valve actuation in different plum training systems, and optimizing plant protection product usage. Sensor-based spraying demonstrates its potential to improve operational efficiency, reduce product losses, and foster environmentally responsible agricultural practices, contributing to the broader field of precision agriculture. For the selected scene, the results show the possibility of a substantial savings of 71.37%, 47.17%, 58.59%, and 55.06% for the One-axis, Bi-axis, UFO, and Combine systems, respectively. Implementing this technology can potentially lead to significant improvements in plum orchard operations while minimizing the industry’s ecological impact on the environment.
Ključne besede: sensors, spraying application control, target-oriented spray, plum orchard, training systems
Objavljeno v DKUM: 08.08.2025; Ogledov: 0; Prenosov: 0
URL Povezava na datoteko

3.
Evaluation of the simultaneous operation of the mechanisms for cross-border interchange and activation of the regulating reserves
Marcel Topler, Boštjan Polajžer, 2021, izvirni znanstveni članek

Opis: This article examines the mechanisms for cross-border interchange of the regulating reserves (RRs), i.e., the imbalance-netting process (INP) and the cross-border activation of the RRs (CBRR). Both mechanisms are an additional service of frequency restoration reserves in the power system and connect different control areas (CAs) via virtual tie-lines to release RRs and reduce balancing energy. The primary objective of the INP is to net the demand for RRs between the cooperating CAs with different signs of interchange power variation. In contrast, the primary objective of the CBRR is to activate the RRs in the cooperating CAs with matching signs of interchange power variation. In this way, the ancillary services market and the European balancing system should be improved. However, both the INP and CBRR include a frequency term and thus impact the frequency response of the cooperating CAs. Therefore, the impact of the simultaneous operation of the INP and CBRR on the load-frequency control (LFC) and performance is comprehensively evaluated with dynamic simulations of a three-CA testing system, which no previous studies investigated before. In addition, a function for correction power adjustment is proposed to prevent the undesirable simultaneous activation of the INP and CBRR. In this way, area control error (ACE) and scheduled control power are decreased since undesired correction is prevented. The dynamic simulations confirmed that the simultaneous operation of the INP and CBRR reduced the balancing energy and decreased the unintended exchange of energy. Consequently, the LFC and performance were improved in this way. However, the impact of the INP and CBRR on the frequency quality has no unambiguous conclusions.
Ključne besede: frequency quality, load-frequency control, regulating reserves, cross-border interchange, cross-border activation
Objavljeno v DKUM: 16.06.2025; Ogledov: 0; Prenosov: 9
.pdf Celotno besedilo (3,17 MB)
Gradivo ima več datotek! Več...

4.
Use of a heating system to control the probiotic beverage production in batch bioreactor
Jožef Ritonja, Andreja Goršek, Darja Pečar, 2021, izvirni znanstveni članek

Opis: Fermentation is a crucial bioengineering process, existentially important for modern society. The most commonly used production unit for this process is the batch bioreactor. Its main advantage is unsophisticated construction, which unfortunately results in its incapability of controlling the transient state of the fermentation process. Control of the fermentation can significantly improve the quality of the product and the economy of the process; therefore, it is useful for bioreactors to be equipped with a control system. Based on the experimental results, we used an optimization method to identify a mathematical model that describes the impact of the bioreactor’s temperature on the fermentation’s transient process. The obtained model was applied for the design and synthesis of the closed-loop control system. Simulations and experiments confirmed the effectiveness of the proposed control system. In this way, we can ensure the consistent quality of the produced probiotic product, increase the amount of the product, and shorten the fermentation time. The original results display the feasibility of the closed-loop control of the batch bioreactor’s fermentation process by changing the temperature. So far, the process has been carried without a closed-loop control system. The problem is current and has not yet been solved sufficiently. There are many attempts published; one of the last shows the possibility of controlling the fermentation process by changing the oxygen supply, which is more complex and expensive for realization than the solution from our study.
Ključne besede: probiotic bewerages, fermentation, modelling, identification, control implementation
Objavljeno v DKUM: 16.06.2025; Ogledov: 0; Prenosov: 7
.pdf Celotno besedilo (2,79 MB)
Gradivo ima več datotek! Več...

5.
Integrating Multi-Physics Modeling within Multi-Objective Optimization to Enhance the Performance and Efficiency of Permanent Magnet Synchronous Machines : doktorska disertacija
Mitja Garmut, 2025, doktorska disertacija

Opis: This Dissertation focuses on the optimization of an Interior Permanent Magnet (IPM) machine for handheld battery-powered tools, aiming to enhance performance and efficiency. The research integrates multi-physics modeling, including electromagnetic Finite Element Method (FEM) and thermal models, to evaluate machine performance under various operating conditions. The performance is evaluated according to selected Key Performance Indicators (KPIs). Further, different control methods, such as Field Oriented Control and Square-Wave Control, impact the performance significantly and are incorporated into the optimization process. Due to the computational challenges of FEM-based performance evaluations in Multi-Objective Optimization (MOO), this work utilizes Artificial Neural Network (ANN)-based meta-models, to accelerate the optimization process while preserving accuracy. The developed meta-models capture nonlinear machine characteristics from the FEM model. These meta-models are then used to evaluate machine performance through a combination of analytical and numerical post-processing methods. Four MOO scenarios are presented, each aimed at optimizing the cross-sectional design of IPM machines, to enhance performance and efficiency while reducing mass and cost. Additionally, these scenarios modify the machine’s electromagnetic behavior, to ensure better alignment with the selected control method. By comparing the optimization process of Scenario 1, which uses direct FEM-based evaluation without time reduction measures, to the approach incorporating Artificial Neural Network based meta-models, the total number of individual FEM evaluations decreased from 2.35×10^9 to 2.03×10^5, without almost any loss of accuracy. This reduced the computation time from 297 years to 9.07 days on our standard desktop computer. The obtained ANN-base meta-models can be used further for other optimizations without the need for additional FEM evaluations. In all four optimization scenarios, the use of meta-models enabled the generation of a Pareto front of the optimal solutions, leading to improved KPIs compared to the reference design. The highest relative improvement occurred in Scenario 1, where the selected optimized machine design achieved a 30% increase in power density compared to the reference design.
Ključne besede: Interior Permanent Magnet (IPM) Machine, Artificial Neural Network (ANN), Meta-Modeling, Multi-Objective Optimization (MOO), Finite Element Method (FEM), Multi-Physics Modeling, Field Oriented Control (FOC), Square-Wave Control (SWC)
Objavljeno v DKUM: 15.05.2025; Ogledov: 0; Prenosov: 138
.pdf Celotno besedilo (17,79 MB)

6.
Toward embedded system resources relaxation based on the event-triggered feedback control approach
Andrej Sarjaš, Dušan Gleich, 2022, izvirni znanstveni članek

Opis: The paper describes an event-triggered nonlinear feedback controller design. Event triggering is a real-time controller implementation technique which reduces embedded system utilization and relaxes task scheduling of the real-time system. In contrast to classic time implementation techniques, the event-triggered execution is validated regarding the introduced triggering policy. The triggering rule is a boundary, where the last task value is preserved until the rule is violated. In the given paper, two different event-triggered strategies are designed for the class of dynamic systems with integral behavior. Both methods are based on sliding mode controller design, where the triggering rule of the first design involves only a partial state vector, which is a direct consequence of the triggering rule derivation throughout the Lyapunov stability analysis. In the second approach, the sliding mode controller is designed upon prior stabilized systems with the additional term, which enables derivation of the triggering rule based on the whole state vector. The second approach offers better closed-loop performance and higher relaxation of the system utilization. The selection of triggering boundary is related closely to the derived minimal inter-event time, which impacts the computational burden of the real-time system and closed-loop performance directly. The derived controllers are compared with the classic sample and hold implementation techniques. The real-time results are presented, and system performances are confirmed regarding embedded system task relaxation, lowering the computational intensity and preserving closed-loop dynamics.
Ključne besede: sliding mode control, event-triggered control, lowering computational intensity, task relaxation
Objavljeno v DKUM: 28.03.2025; Ogledov: 0; Prenosov: 13
.pdf Celotno besedilo (18,67 MB)
Gradivo ima več datotek! Več...

7.
Control of an inductive power transfer system using a double coil structure
Nataša Prosen, Mitja Truntič, Jure Domajnko, 2022, izvirni znanstveni članek

Opis: This paper presents the design of the control of the system using a double DD coil structure. The double DD coil is a layered coil structure that consists of two single DD coils, rotated to each other by 90◦. A large-signal and small-signal model of the proposed IPT system are designed for control synthesis. The small-signal model is derived from the large-signal using harmonic approximation and the extended describing functions (EDF). For the small-signal model, voltage and current control schemes were proposed for the purpose of wireless battery charging. The robustness of the control is tested on a small-scale IPT system using double DD coils and resistive load. The results are evaluated at different reference voltages, currents, loads and coupling coefficients.
Ključne besede: wireless power transfer, double DD coil structure, voltage control, IPT with multiple coils
Objavljeno v DKUM: 28.03.2025; Ogledov: 0; Prenosov: 7
.pdf Celotno besedilo (9,50 MB)
Gradivo ima več datotek! Več...

8.
Control of a modified switched-capacitor boost converter
Benjamin Ošlaj, Mitja Truntič, 2022, izvirni znanstveni članek

Opis: Switched-capacitor converters and their alternatives have been shown to provide high efficiency with high power densities on smaller volumes, and can thereby be a suitable choice for energy harvesting. This paper proposes a hybrid power architecture based on a switched-capacitor topology and a boost converter that can be used for such purposes. A switching capacitor circuit can achieve any voltage ratio, allowing a boost converter to increase the input voltage to higher voltage levels. The first stage is unregulated with high-efficiency voltage conversion. The boost stage provides a regulated voltage output on such a converter. Rather than cascading two converters, their operation is integrated for the output voltage regulation. One major problem of switched-capacitor converters is output voltage regulation, which is solved by the interconnection of the power stages. The simplicity and robustness of the solution provide the possibility to achieve higher voltage ratios than cascading boost converters and provide higher efficiency. The converter’s size and cost can be improved with the integration of switching capacitors in DC-DC converter structures. A converter prototype has been designed, modelled, and built for the input voltage level of 2 V and power level of 5 W.
Ključne besede: SC-BC, cascade control, low power, low voltage
Objavljeno v DKUM: 28.03.2025; Ogledov: 0; Prenosov: 10
.pdf Celotno besedilo (8,68 MB)
Gradivo ima več datotek! Več...

9.
Evolution of domain-specific modeling language: an example of an industrial case study on an RT-sequencer
Tomaž Kos, Marjan Mernik, Tomaž Kosar, 2022, izvirni znanstveni članek

Opis: Model-driven engineering is a well-established software development methodology that uses models to develop applications where the end-users with visual elements model abstractions from a specific domain. These models are based on domain-specific modeling language (DSML), which is particular to the problem domain. During DSML use, new ideas emerge and DSMLs evolve. However, reports on DSML evolution are rare. This study presents a new DSML called RT-Sequencer that evolved from our DSML Sequencer to support, in addition to the Data Acquisition domain, also a new domain—Real-Time Control (RTC) systems. The process of defining models with a new language RT-Sequencer has changed in a way that new end-users were introduced—advanced endusers, which use general-purpose language (GPL) and advanced programming concepts to define modeling environments for the RT-Sequencer end-users. More specifically, an industrial experience with the RT-Sequencer is presented, where DSML was opened for extension so that a GPL code could be inserted into the model to create new visual blocks for the end-user, and the possibility to adapt and optimize the execution code for a particular task. Our experience shows the specific case of DSML evolution supporting another problem domain, and the implementation effort needed to extend domain-specific modeling language with GPL support.
Ključne besede: model-driven engineering, domain-specific modeling languages, measurement systems, Real-Time Control systems, data acquisition, language evolution, experience report
Objavljeno v DKUM: 27.03.2025; Ogledov: 0; Prenosov: 15
.pdf Celotno besedilo (1,70 MB)
Gradivo ima več datotek! Več...

10.
Is the Hitchcock story really true? Public opinion on Hooded crows in cities as input to management
László Kövér, Petra Paládi, Isma Benmazouz, Andrej Šorgo, Natalija Špur, Lajos Juhász, Peter Czine, Péter Balogh, Szabolcs Lengyel, 2022, izvirni znanstveni članek

Opis: In recent years, the Hooded crow (Corvus cornix) has become one of the most successful wild bird species in urban environments across Europe. Hooded crows can cause several problems in cities, including trash scattering, noise disturbance, and aggressive behavior toward humans or pets, and they can be potential vectors of pathogens. To find effective solutions, the public has to be involved in the decision-making process in urban planning management, managed by the city administration. In this study, we surveyed the attitude of people in Hungary towards crows and crow management by collecting information using an online questionnaire containing 65 questions published in 14 Facebook groups. We found that many people were familiar with corvid species and had personal experience with them. In most cases, these experiences were not negative, so the crows were not or only rarely perceived to cause problems to people, such as aggressive behavior, damage to cars or stealing something. Most respondents recognized that the presence of large numbers of hooded crows is a problem to be solved and acknowledged that they do not know how to resolve it. The majority of people expressed their interest in raising public awareness of crows but not in their management actions, which they believe should be implemented by experts. Most respondents preferred passive, harmless methods. More direct methods such as egg/chick removal from the nest, control by trapping, poisoned baits or firearms, or oral contraceptives were the least acceptable. These results express the difficulty in identifying a control method for managing hooded crow populations that is both acceptable to most people and effective at the same time. This study demonstrates the importance of involving public opinion in wildlife management and providing more information to citizens to reduce human-crow conflicts.
Ključne besede: attitude, control, corvids, human-wildlife conflict, urban wildlife management
Objavljeno v DKUM: 27.03.2025; Ogledov: 0; Prenosov: 6
.pdf Celotno besedilo (1,25 MB)
Gradivo ima več datotek! Več...

Iskanje izvedeno v 0.11 sek.
Na vrh
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici