1. Optimization of an IPMSM for constant-angle square-wave control of a BLDC driveMitja Garmut, Simon Steentjes, Martin Petrun, 2024, original scientific article Abstract: Interior permanent magnet synchronous machines (IPMSMs) driven with a square-wave
control (i.e., six-step, block, or 120◦ control), known commonly as brushless direct current (BLDC)
drives, are used widely due to their high power density and control simplicity. The advance firing
(AF) angle is employed to achieve improved operation characteristics of the drive. The AF angle is,
in general, applied to compensate for the commutation effects. In the case of an IPMSM, the AF angle
can also be adjusted to exploit reluctance torque. In this paper, a detailed study was performed to
understand its effect on the drive’s performance in regard to reluctance torque. Furthermore, a multiobjective optimization of the machine’s cross-section using neural network models was conducted to
enhance performance at a constant AF angle. The reference and improved machine designs were
evaluated in a system-level simulation, where the impact was considered of the commutation of
currents. A significant improvement in the machine performance was achieved after optimizing the
geometry and implementing a fixed AF angle of 10◦.
Keywords: MTPA, maximum torque per ampere, IPM SM, interior permanent magnet synchronous machine, BLDC, brushless direct current drive, rotor optimization, square-wave control, advance firing angle, neural network
Published in DKUM: 13.01.2026; Views: 0; Downloads: 1
 Full text (2,87 MB)
This document has many files! More... |
2. A multi-task deep learning approach for landslide displacement prediction with applications in early warning systemsDamjan Strnad, Domen Mongus, Štefan Horvat, Ela Šegina, 2025, original scientific article Abstract: Accurate landslide displacement prediction is important for the construction of reliable landslide early warning systems (LEWS). Recently, deep neural networks have become the dominant approach for landslide displacement modeling. However, we show that focusing solely on low prediction residuals is not perfectly aligned with the goals of LEWS, where the emphasis is on precise forecasts near the warning threshold. This can result in poor efficiency of threshold-based warning prediction. We propose a multi-task approach to model training, where auxiliary targets are used to optimize the model towards the performance relevant for LEWS. The methodology is validated using the data from the deep-seated Urbas landslide in north-western Slovenia, which has been monitored by GNSS since 2019. Developing a displacement prediction model for Urbas is a step towards extending the existing wire-based mechanical alarm system. We employ a convolutional neural network for day-ahead displacement prediction using recent landslide activity, hydrometeorological measurements and seismological data. The proposed multi-task model retains a competitive score for warning prediction while achieving a significantly lower mean absolute error compared to the reference models. The proposed methodology is generally applicable and has the potential to improve the efficiency of landslide modeling in the context of LEWS.
Keywords: landslide displacement prediction, neural network, multitask learning, landslide early warning system, remote sensing, GNSS
Published in DKUM: 12.12.2025; Views: 0; Downloads: 2
Full text (2,63 MB) |
3. A novel data-driven surrogate approach for fast evaluation of the dynamics of soft ellipsoidal micro-particles in dilute viscous flowJana Wedel, Ivan Dominik Horvat, Nejc Vovk, Matjaž Hriberšek, Jure Ravnik, Paul Steinmann, 2026, original scientific article Abstract: We present a novel data-driven surrogate approach for fast evaluation of the deformation dynamics of soft particles, both initially spherical and ellipsoidal, suspended in external flows, specifically predicting the hydrodynamic tractions on the particle surface. The core of the approach relies on expressing the required force dyad as a linear combination of velocity gradient components, modulated by form coefficients. These coefficients scale shear, rotational, and extensional flow contributions to the velocity gradient. Two training strategies are proposed: one utilizing analytical data, which enables a computational speedup, and another based on data obtained with 3D direct numerical simulations (DNS) using the boundary element method (BEM), with the latter demonstrating the feasibility of this approach even in the absence of analytical solutions. Validation against established literature benchmarks confirms the model’s accuracy in three scenarios: (i) ellipsoidal particles in the quasi-rigid limit in pipe flow, (ii) initially spherical particles in shear flow, and (iii) initially ellipsoidal particles in shear flow. In all cases, the data-driven surrogate approach achieves excellent agreement with reference results. This work establishes a foundation for extending our data-driven approach to flow-induced deformations of soft particles of more complex particle shapes, such as superellipsoids and other non-ellipsoidal geometries, where no analytical traction expression is available.
Keywords: neural network, pseudo-rigid bodies, Barycenter and shape dynamics, Lagrangian particle tracking
Published in DKUM: 27.11.2025; Views: 0; Downloads: 2
Full text (7,16 MB)
This document has many files! More... |
4. The impact of ESG on business performance : anǂempirical analysis of NASDAQ–NYSE-Listed companiesAljaž Herman, Žan Oplotnik, Timotej Jagrič, 2025, original scientific article Abstract: This study investigates the relationship between ESG ratings and a firm’s financial performance, focusing on Return on Assets (ROA) and Return on Equity (ROE). Using a combination of stepwise linear regression and feedforward neural networks (FFNN), we assess both the linear and nonlinear effects of ESG on financial performance. The regression models identify ESG as a significant, positively correlated factor in explaining financial performance, alongside firm demographics, sector affiliation, and financial indicators. Neural networks reveal nonlinear dynamics, particularly for ROA, suggesting threshold effects in the ESG–performance relationship. Sensitivity analysis confirms that ESG’s influence strengthens at higher values. Our findings highlight that ESG is not only statistically relevant but also interacts with firm characteristics in complex ways. These results contribute to the ongoing discourse on sustainable finance by showing that ESG can be a meaningful driver of financial outcomes, especially when modeled through nonlinear approaches.
Keywords: ESG, financial performance, ROA, ROE, regression, neural network
Published in DKUM: 06.11.2025; Views: 0; Downloads: 7
Full text (411,40 KB)
This document has many files! More... |
5. Research on the modelling and analysis of the penetration of renewable sources and storage into electrical networksEva Simonič, Sebastijan Seme, Klemen Sredenšek, 2025, original scientific article Abstract: To address the growing integration of renewable energy sources and storage systems into distribution networks, there is a need for effective tools that can assess the impact of these technologies on grid performance. This paper investigates the impact of integrating residential rooftop photovoltaic (PV) systems and battery energy storage systems (BESSs) into low-voltage (LV) distribution networks. A stochastic approach, using the Monte Carlo method, is applied to randomly place PV systems across the network, generating multiple scenarios for power flow simulations in MATLAB Simulink R2024b. The method incorporates real-world consumer load data and grid topology, representing a novel approach in simulating distribution network behaviour accurately. The novelty of this paper lies in its ability to combine stochastic PV placement with real-world load data, providing a more realistic representation of network conditions. The simulation results revealed that widespread PV deployment can lead to overvoltage issues, but the integration of BESSs alongside PV systems mitigates these problems significantly. The findings of this paper offer valuable insights for Distribution Network Operators, aiding in the development of strategies for optimal PV and BESS integration to enhance grid performance.
Keywords: photovoltaic system, battery energy storage system, low-voltage distribution network, Monte Carlo method, power flow
Published in DKUM: 03.11.2025; Views: 0; Downloads: 10
Full text (3,19 MB)
This document has many files! More... |
6. OpenHENS: an open-source tool for heat exchanger network synthesisKeegan Keysers Hall, Andreja Nemet, Zdravko Kravanja, Timothy Gordon Walmsley, 2026, original scientific article Abstract: The synthesis of heat exchanger networks (HENs) is an NP hard problem, made even more difficult by the requirement of commercial software licenses and coding ability. This paper introduces OpenHENS, a first-of-itskind open-source tool for HEN synthesis. In the literature, HEN synthesis based on mathematical programming almost exclusively relies on commercial MINLP (mixed-integer non-linear programming) solvers (e.g., BARON, Gurobi, etc.). Open source MINLP solvers, in contrast, lack the robustness, scalability and quality that are the hallmarks of commercial solvers. To overcome this challenge, OpenHENS embeds a novel three-step synthesis method that gradually increases the complexity of the model. The first two steps identify economically viable and thermodynamically feasible heat exchanger matches, removing the non-viable matches and reducing the problem size. In the third step, numerous HEN designs are obtained by evolving promising networks to obtain families of near-optimal solutions. OpenHENS was tested on thirteen benchmark problems and seven of the solutions were within 2 % of the total annualised cost (TAC) best-known solutions from literature. In eleven of the benchmark problems, OpenHENS returned more than 10 unique networks within 2 % of the best solution, enabling the engineer to select the most practical design with minimal cost difference. OpenHENS demonstrates that open-source software, when developed correctly, offers comparable performance to commercial software while promoting greater accessibility in industry.
Keywords: heat exchanger network, process integration, optimization, mathematical programming, open source, Phyton
Published in DKUM: 03.11.2025; Views: 0; Downloads: 2
Full text (17,21 MB) |
7. Drivers and constraints of employee satisfaction with remote work : an empirical analysisThabit Atobishi, Saeed Nosratabadi, 2023 Abstract: Background/Purpose: The Covid 19 epidemic has forced many organizations to move to remote work (RW), and this trend is expected to continue even later in the post-epidemic period. Employees of the organization are at the heart of this transi-tion to RW, so identifying the factors that affect employee satisfaction with RW is very important for organizations to increase employee commitment and motivation. Therefore, the main objective of this study was to identify and prioritize the factors affecting employee satisfaction with RW using an innovative method. Method: In the first phase of this study, a conceptual research model was designed inspired by literature. In the next phase, the proposed conceptual model of this re-search was tested using structural equation modeling (SEM). Then, using the artifi-cial neural network model, the importance of each of the model variables in pre-dicting employee satisfaction with RW was identified. Results: The findings of this article ultimately disclosed that work-life balance, in-stitutional and technological support, job satisfaction, and perceived limited com-munication are, respectively, are elements that affect employee satisfaction with RW. The first three factors are drivers of employee satisfaction and the last factor (i.e., perceived limited communication) is the constraint of employee satisfaction with RW because it had a statistically significant negative effect on employee satis-faction with RW. Conclusion: This study revealed that organizations should focus on the processes and strategies to improve employees’ work-life balance, provide institutional and technological support during remote work, and increase job satisfaction in order to increase the satisfaction level of their employees in the remote work. On the other hand, it was found that perceived limited communication is an effective factor that causes a decrease in the level of satisfaction of employees in remote work.
Keywords: remote work, employee satisfaction, structural equation modeling, multilayer per-ceptron, artificial intelligence, artificial neurol network, Covid 19 pandemic
Published in DKUM: 08.10.2025; Views: 0; Downloads: 1
Full text (995,12 KB)
This document has many files! More... |
8. |
9. Prunability of multi-layer perceptrons trained with the forward-forward algorithmMitko Nikov, Damjan Strnad, David Podgorelec, 2025, original scientific article Abstract: We explore the sparsity and prunability of multi-layer perceptrons (MLPs) trained using the Forward-Forward (FF) algorithm, an alternative to backpropagation (BP) that replaces the backward pass with local, contrastive updates at each layer. We analyze the sparsity of the weight matrices during training using multiple metrics, and test the prunability of FF networks on the MNIST, FashionMNIST and CIFAR-10 datasets. We also propose FFLib—a novel, modular PyTorch-based library for developing, training and analyzing FF models along with a suite of FF-based architectures, including FFNN, FFNN+C and FFRNN. In addition to structural sparsity, we describe and apply a new method for visualizing the functional sparsity of neural activations across different architectures using the HSV color space. Moreover, we conduct a sensitivity analysis to assess the impact of hyperparameters on model performance and sparsity. Finally, we perform pruning experiments, showing that simple FF-based MLPs exhibit significantly greater robustness to one-shot neuron pruning than traditional BP-trained networks, and a possible 8-fold increase in compression ratios while maintaining comparable accuracy on the MNIST dataset.
Keywords: Forward-Forward, sparsity, pruning, model compression, machine learning, neural network
Published in DKUM: 20.08.2025; Views: 0; Downloads: 4
Full text (7,01 MB) |
10. Hardened workpiece shape prediction using acoustic responses and deep neural networkJernej Hernavs, Tadej Peršak, Miran Brezočnik, Simon Klančnik, 2025, original scientific article Abstract: This study proposes a novel approach to predict the shape of hardened metal workpieces using acoustic responses processed by a deep convolutional neural network (CNN), aiming to advance automated straightening in manufacturing. Tool steel 1.2379 workpieces of varying widths (24 mm, 90 mm, 200 mm) were struck using a custom-built device, with acoustic responses captured and transformed into scalograms via Continuous Wavelet Transform (CWT). A 40-layer CNN predicted 5×9 shape matrices, validated by 3D scans. The dataset (219 shape states, 3396 recordings) was evaluated using leaveone-workpiece-out cross-validation, comparing the CNN against baseline models (linear regression, random forest, shallow CNN, XGBoost). CNN achieved competitive accuracy, demonstrating the feasibility of acoustic-based shape prediction. As a non-invasive, cost-efective complement to 3D scanning, this method ofers innovative potential for multi-modal quality control systems in manufacturing.
Keywords: metal workpiece, hardened, deep neural network, acoustic respons, shape prediction
Published in DKUM: 14.08.2025; Views: 0; Downloads: 11
Full text (1,10 MB)
This document has many files! More... |
