Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Raimondas Pomarnacki has a total of 53 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Advanced Condition Monitoring and Fault Analysis in Industrial Electronics

    by Raimondas Pomarnacki

    Modern industrial electronic and electrical systems—converters, controllers, and electric motor drives among them—are exposed to electrical, mechanical, and thermal stresses that can lead to unexpected failures, production losses, and, in the worst cases, safety and environmental incidents

  • Open Access

    Antenna and Spectrum Sensing Techniques for Fault Detection in Electrical and Electronic Equipment: A Structured Review

    by Žygimantas Lingė, Raimondas Pomarnacki

    This paper presents a structured review of antenna and electromagnetic spectrum monitoring techniques for non-invasive fault detection in electrical and electronic equipment. Electromagnetic emissions from partial discharges, arc faults, insulation degradation, and component ageing carry diagnostic signatures detectable through remote radio-frequency sensing. We review (1) antenna technologies spanning magnetic-field loops to ultra-high-frequency electric-field sensors, including fractal, Vivaldi, spiral, and bio-inspired designs; (2) data acquisition platforms ranging from laboratory oscilloscopes to software-defined radio receivers and IoT edge nodes; (3) signal processing methods including time–frequency analysis, adaptive decomposition, and statistical techniques; and (4) machine learning approaches from classical classifiers to deep learning architectures such as convolutional neural networks, recurrent neural networks, and Transformer-based models. Unlike prior surveys focusing on individual fault types or specific equipment classes, this review connects all five layers of the sensing pipeline—from electromagnetic emission physics through antenna selection, signal acquisition, processing, and intelligent classification—for partial-discharge, arc, and insulation faults and analyses the cross-layer constraints that couple them. Design optimisation techniques based on computational electromagnetic methods (FDTD, FEM) and sensitivity calibration challenges are discussed. Open challenges, including the lack of standardised UHF calibration, cross-equipment generalisation, and the scarcity of open electromagnetic fault datasets, are identified, along with emerging directions in flexible antennas, edge AI, and digital twin integration.

  • Open Access

    Signal Processing Optimization in Resource-Limited IoT for Fault Prediction in Rotating Machinery

    by Robertas Ūselis, Artūras Serackis, Raimondas Pomarnacki

    Traditional fault detection methods, often designed for centralized or cloud-based systems, are ill-suited for the edge. The deployment of predictive maintenance solutions on ultra-low-cost embedded platforms remains a significant challenge due to strict limitations in memory, processing capacity, and energy availability. To address these challenges, vibration and motor current signals were analyzed using an ultra-low-cost RP2040 microcontroller. For fault detection, this study uses statistical time-domain features and principal component analysis (PCA), followed by classification with eXtreme Gradient Boosting (XGBoost) models distilled for resource-constrained deployment. Experimental evaluation demonstrated that vibration-based features achieved a diagnostic accuracy of 94.1%, while current-based representations obtained 95.5% accuracy when using principal components, compared to 83.2% with handcrafted statistical features. Model distillation reduced memory footprint by up to 2.5× (from 0.42 MB to 0.15 MB) without compromising diagnostic fidelity, enabling deployment within the 264 KB RAM and 2 MB Flash constraints of the RP2040 microcontroller. This study proposes a modular framework that systematically evaluates statistical features, dimensionality reduction, sensor synchronization, and model distillation, thereby identifying the most cost-efficient combination of techniques that balances diagnostic accuracy with strict memory and processing constraints. The findings establish that accurate fault detection can be realized directly on severely resource-limited hardware, thereby extending the practical applicability of condition monitoring to cost-sensitive industrial environments.


  • Open Access

    Unmanned Aerial Vehicles for the Monitoring of Telecommunication Towers from the Engineering Approach

    by Raimondas Pomarnacki, Domantas Bručas, Tomas Jačionis, Darius Plonis

    In this article, the authors conducted electromagnetic radiation research on telecommunication base stations using Unmanned Aerial Vehicles (UAVs). Until now, UAVs have only been capable of performing visual inspections, without investigating electrical parameters. The authors suggest a method that involves using a spectrum analyzer and an automated flight with a predefined trajectory around the base stations to conduct electromagnetic radiation research, which is used by telecommunication regulatory organizations. Two different types of UAVs were used in this work: a drone and a fixed-wing aircraft, each with distinct characteristics. The authors successfully designed and tested both types of UAVs under real conditions and performed measurements. A specialized algorithm with software was developed for processing measurement results, which accurately presents the data in a graphical format. Experiments were performed, and the results, at distances of 200 m or further from the telecommunication base tower by changing the altitude by 5 m, were collected.


  • Open Access

    The Impact of the Weather Forecast Model on Improving AI-Based Power Generation Predictions through BiLSTM Networks

    by Mindaugas Jankauskas, Artūras Serackis, Nerijus Paulauskas, Raimondas Pomarnacki, Van Khang Hyunh

    This study aims to comprehensively analyze five weather forecasting models obtained from the Open-Meteo historical data repository, with a specific emphasis on evaluating their impact in predicting wind power generation. Given the increasing focus on renewable energy, namely, wind power, accurate weather forecasting plays a crucial role in optimizing energy generation and ensuring the stability of the power system. The analysis conducted in this study incorporates a range of models, namely, ICOsahedral Nonhydrostatic (ICON), the Global Environmental Multiscale Model (GEM Global), Meteo France, the Global Forecast System (GSF Global), and the Best Match technique. The Best Match approach is a distinctive solution available from the weather forecast provider that combines the data from all available models to generate the most precise forecast for a particular area. The performance of these models was evaluated using various important metrics, including the mean squared error, the root mean squared error, the mean absolute error, the mean absolute percentage error, the coefficient of determination, and the normalized mean absolute error. The weather forecast model output was used as an essential input for the power generation prediction models during the evaluation process. This method was confirmed by comparing the predictions of these models with actual data on wind power generation. The ICON model, for example, outscored others with a root mean squared error of 1.7565, which is a tiny but essential improvement over Best Match, which had a root mean squared error of 1.7604. GEM Global and Gsf Global showed more dramatic changes, with root mean squared errors (RMSEs) of 2.0086 and 2.0242, respectively, indicating a loss in prediction accuracy of around 24% to 31% compared to ICON. Our findings reveal significant disparities in the precision of the various models used, and certain models exhibited significantly higher predictive precision.


  • Research of the WIFI/WIMAX patch type antenna on varying embedded material’s dimensions

    by Darius Plonis, Raimondas Pomarnacki, Diana Belova-Plonienė, Andrius Katkevičius, Vaiva Rusen

    The microstrip patch antenna with the feeder gap is improved with nematic liquid crystal of type E7 embedded material, which has replaced the part of dielectric substrate. The investigation is focused on the impact of the geometrical parameters of the fragment of embedded material to the S parameters of the microstrip patch antenna. Authors presents initial simulation results to investigate how embedded material influences and changes typical antenna electrical characteristics. The computer-based modeling is performed with Ansys HFSS®. The embedded material has allowed to control the resonance frequencies and directivity and also to improve the gain of the antenna. The best case is obtained with –21.76 dB return loss at 2.4 GHz frequency when the length and width of the fragment of embedded material were equal to 1 mm and 20 mm respectfully. The designed antenna is characterized by good directivity when all energy is concentrated in main lobe.

  • Open Access

    Integrated Multiport DC-DC and Multilevel Converters for Multiple Renewable Energy Source Integration

    by Immanuel N. Jiya, Ahmed Salem, Huynh Van Khang, Raimondas Pomarnacki

    This research introduces an innovative converter system which has been developed to seamlessly incorporate multiple sources of renewable energy into both DC and AC grids. The integration of multiple energy sources is made possible through the utilization of a unique converter system that combines a multiport DC converter topology with a multilevel inverter topology, while maintaining a low component count and hence increased overall power density and efficiency for the proposed converter system. Unlike previous literature, where each energy source needs a separate DC converter and a two-level converter is used for DC to AC conversion, this converter system features buck-boost operation, superior power quality characteristics, and fewer components. The system suggests the implementation of a DC link voltage balancing technique that relies on an auxiliary circuit to achieve equilibrium in the voltage on the DC link, as a possible substitute to the more complicated control-based balancing scheme. The operational integrity of the converter system is assessed through rigorous numerical simulations and experimentally validated using OPAL-RT’s OP5700 hardware-in-the-loop (HIL) implementation platform as well as an in-house experimental test setup.


  • Open Access

    Improved Fault Classification and Localization in Power Transmission Networks Using VAE-Generated Synthetic Data and Machine Learning Algorithms

    by Muhammad Amir Khan, Bilal Asad, Toomas Vaimann, Ants Kallaste, Raimondas Pomarnacki, Van Khang Hyunh

    The reliable operation of power transmission networks depends on the timely detection and localization of faults. Fault classification and localization in electricity transmission networks can be challenging because of the complicated and dynamic nature of the system. In recent years, a variety of machine learning (ML) and deep learning algorithms (DL) have found applications in the enhancement of fault identification and classification within power transmission networks. Yet, the efficacy of these ML architectures is profoundly dependent upon the abundance and quality of the training data. This intellectual explanation introduces an innovative strategy for the classification and pinpointing of faults within power transmission networks. This is achieved through the utilization of variational autoencoders (VAEs) to generate synthetic data, which in turn is harnessed in conjunction with ML algorithms. This approach encompasses the augmentation of the available dataset by infusing it with synthetically generated instances, contributing to a more robust and proficient fault recognition and categorization system. Specifically, we train the VAE on a set of real-world power transmission data and generate synthetic fault data that capture the statistical properties of real-world data. To overcome the difficulty of fault diagnosis methodology in three-phase high voltage transmission networks, a categorical boosting (Cat-Boost) algorithm is proposed in this work. The other standard machine learning algorithms recommended for this study, including Support Vector Machine (SVM), Decision Trees (DT), Random Forest (RF), and K-Nearest Neighbors (KNN), utilizing the customized version of forward feature selection (FFS), were trained using synthetic data generated by a VAE. The results indicate exceptional performance, surpassing current state-of-the-art techniques, in the tasks of fault classification and localization. Notably, our approach achieves a remarkable 99% accuracy in fault classification and an extremely low mean absolute error (MAE) of 0.2 in fault localization. These outcomes represent a notable advancement compared to the most effective existing baseline methods.


  • Open Access

    Improved Fault Classification and Localization in Power Transmission Networks using VAE-generated Synthetic Data and Machine Learning Algorithms

    by Muhammad Amir Khan, Bilal Asad, Toomas Vaimann, Ants Kallaste, Raimondas Pomarnacki, Van Khang Hyunh

    Keywords: Electrical power systems, Support vector machines, Random Forest, Machine learning, Wavelet transform, Transmission lines fault, Electrical power quality, Short circuit, Classification of faults, Localization of faults, Decision trees, Ensemble learning, K-nearest neighbors.


  • Open Access

    Digital Twin as a Virtual Sensor for Wind Turbine Applications

    by Mahmoud Ibrahim, Anton Rassõlkin, Toomas Vaimann, Ants Kallaste, Janis Zakis, Van Khang Hyunh, Raimondas Pomarnacki

    Digital twins (DTs) have been implemented in various applications, including wind turbine generators (WTGs). They are used to create virtual replicas of physical turbines, which can be used to monitor and optimize their performance. By simulating the behavior of physical turbines in real time, DTs enable operators to predict potential failures and optimize maintenance schedules, resulting in increased reliability, safety, and efficiency. WTGs rely on accurate wind speed measurements for safe and efficient operation. However, physical wind speed sensors are prone to inaccuracies and failures due to environmental factors or inherent issues, resulting in partial or missing measurements that can affect the turbine’s performance. This paper proposes a DT-based sensing methodology to overcome these limitations by augmenting the physical sensor platform with virtual sensor arrays. A test bench of a direct drive WTG based on a permanent magnet synchronous generator (PMSG) was prepared, and its mathematical model was derived. MATLAB/Simulink was used to develop the WTG virtual model based on its mathematical model. A data acquisition system (DAS) equipped with an ActiveX server was used to facilitate real-time data exchange between the virtual and physical models. The virtual sensor was then validated and tuned using real sensory data from the physical turbine model. The results from the developed DT model showed the power of the DT as a virtual sensor in estimating wind speed according to the generated power.