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. 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) |
6. 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: 9
Full text (1,10 MB)
This document has many files! More... |
7. Computationally efficient multi-objective optimization of an interior permanent magnet synchronous machine using neural networksMitja Garmut, Simon Steentjes, Martin Petrun, 2025, original scientific article Abstract: Improving the power density of an interior permanent magnet synchronous machine requires a complex and comprehensive approach that includes electromagnetic and thermal aspects. To achieve that, a multi-objective optimization of the machine’s geometry was performed according to selected key performance indicators by using numerical and analytical models. The primary objective of this research was to create a computationally efficient and accurate alternative to a direct finite element method-based optimization. By integrating artificial neural networks as meta-models, we aimed to demonstrate their performance in comparison to existing State-of-the-Art approaches. The artificial neural network approach achieved a nearly 20-fold reduction compared with the finite element method-based approach in computation time while maintaining accuracy, demonstrating its effectiveness as a computationally efficient alternative. The obtained artificial neural network can also be reused for different optimization scenarios and for iterative fine-tuning, further reducing the computation time. To highlight the advantages and limitations of the proposed approach, a multi-objective optimization scenario was performed, which increased the power-to-mass ratio by 16.5%.
Keywords: interior permanent magnet synchronous machine, artificial neural network, metamodel, multi-objective optimization, finite element method
Published in DKUM: 08.08.2025; Views: 0; Downloads: 22
Full text (2,87 MB) |
8. Comparative analysis of nonlinear models developed using machine learning algorithmsMaja Rožman, Alen Kišić, Dijana Oreški, 2024, original scientific article Abstract: Machine learning algorithms are increasingly used in a vast spectrum of domains where statistical approaches were previously used. Algorithms such as artificial neural networks, classification, regression trees, or support vector machines provide various advantages over traditional linear regression or discriminant analysis. Advantages such as flexibility, scalability, and improved accuracy in dealing with diverse data types, nonlinear problems, and dimensionality reduction, compared to traditional statistical methods are empirically demonstrated in many previous research papers. In this paper, two machine learning algorithms are compared with one statistical method on highly nonlinear data. Results indicate a high level of effectiveness for machine learning algorithms when dealing with nonlinearity.
Keywords: machine learning, decision tree algorithm, artificial neural network, predictive models, data characteristics, nonlinear data, artificial intelligence
Published in DKUM: 02.07.2025; Views: 0; Downloads: 9
Full text (730,52 KB)
This document has many files! More... |
9. Integrating Multi-Physics Modeling within Multi-Objective Optimization to Enhance the Performance and Efficiency of Permanent Magnet Synchronous Machines : doktorska disertacijaMitja Garmut, 2025, doctoral dissertation Abstract: 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.
Keywords: 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)
Published in DKUM: 15.05.2025; Views: 0; Downloads: 161
Full text (17,79 MB) |
10. Robot for navigation in maize crops for the Field Robot Event 2023David Iván Sánchez-Chávez, Noé Velázquez-López, Guillermo García-Sánchez, Alan Hernández-Mercado, Omar Alexis Avendaño-Lopez, Mónica Elizabeth Berrocal-Aguilar, 2024, original scientific article Abstract: Navigation in a maize crop is a crucial task for the development of autonomous robots in agriculture, with numerous applications such as spraying, monitoring plant growth and health, and detecting weeds and pests. The Field Robot Event 2023 (FRE) continued to challenge universities and other research teams to push the development of algorithms for agricultural robots further. The Universidad Autónoma Chapingo has been developing a robot for various agricultural tasks, aiming to provide a low-cost alternative to work with Mexican farmers in the future. For this edition of the FRE, a navigation algorithm was created using an encoder, an IMU (Inertial Measurement Unit), an RPLIDAR (Rotating Platform Light Detection and Ranging), and cameras to collect data for decision-making. The algorithm was developed in ROS Melodic, dividing the task into steps that were tested to determine the robot's actual movements. The system navigates by using ROIs (regions of interest) and the mass center to guide the robot between maize rows. It calculates the mean of the final orientation values before reaching the end of a row, which is detected using an RPLIDAR. For turns and straight-line movements to reach the next row, the orientation is used as a guide. To detect plants for spraying, lasers located on each side of the vehicle are employed. Obstacle detection relies on a YOLOv5 (You Only Look Once) trained model and a laser, while reverse navigation uses a rear camera. During the competition, the robot faced challenges such as dealing with grass, the small size of the plants, and the need to use a different power source, which affected its performance.
Keywords: machine vision, convolutional neural network (CNN), regions of interest (ROI), autonomous navigation
Published in DKUM: 23.04.2025; Views: 0; Downloads: 2
 Link to file |
