Nauki Techniczne

Bulletin of the Polish Academy of Sciences Technical Sciences

Zawartość

Bulletin of the Polish Academy of Sciences Technical Sciences | 2025 | 73 | 1

Abstrakt

With a continued strong pace of artificial intelligence, the way of formulating the flight day plan has a significant impact on the efficiency of flight training. However, through extensive research, we find that the scheduling of flight days still relies on manual work in most military aviation academies. This method suffers from several issues, including protracted processing times, elevated error rates, and insufficient degree of optimization. This article provides a comprehensive analysis of automated flight scheduling using a goal programming algorithm and details the implementation of the corresponding algorithm on the LINGO platform. The study enhances the flexibility and robustness of the model by setting bias variables, wherein the flight courses for students and instructors can be automatically and reasonably scheduled.
Przejdź do artykułu

Autorzy i Afiliacje

Pengfei Sun
1
ORCID: ORCID
Jia Liu
1
ORCID: ORCID
Hao Nian
1

  1. Naval Aviation University, 188 Erma Road, Yantai City, Shandong Province, China

Abstrakt

In an extremely broad range of industrial applications, especially in electric vehicles, permanent magnet synchronous motors (PMSMs) play a vital role. Any failure in PMSMs may cause possible safety hazards, a drop in productivity, and expensive downtime. Therefore, their reliable operation is essential. Accurate failure identification and classification allow for addressing problems before they escalate, which helps ensure the seamless operation of PMSMs and reduces the likelihood of equipment failure. Therefore, in this paper, novel failure identification methods based on gated recurrent unit (GRU) and long short-term memory (LSTM) from recurrent neural network (RNN) methods are proposed for early identification of stator inter-turn short circuit failure (ISCF) and demagnetization failure (DF) occurring in PMSMs under multiple operating conditions. The proposed methods use three-phase current signals recorded from the experimental study under multiple operating conditions of the motor as input data. In the proposed methods, both feature extraction and classification are executed within a unified framework. The experimental outcomes obtained demonstrate that the proposed methods can identify a total of six unique motor conditions, including three ISCF variations and two DF variations, with high accuracy. The LSTM and GRU approaches predicted the identification of failures with 98.23% and 98.72% accuracy, respectively. Compared to existing methods, the success of the proposed approaches is satisfactory. In addition, LSTM and GRU-based failure identification methods are also compared in detail for accuracy, precision, sensitivity, specificity, and training time in this study.
Przejdź do artykułu

Autorzy i Afiliacje

Timur Lale
1
ORCID: ORCID
Gökhan Yüksek
1
ORCID: ORCID

  1. Department of Electrical and Electronics Engineering, Faculty of Architecture and Engineering, Batman University,Bati Raman Campus 72000, Batman, Turkey

Abstrakt

The study discusses the results of research on the multiple processing of thermoplastic starch-based polymer compositions. The research subject was two compositions from the envifill® M product line (Grupa Azoty, Poland): M30 and MB173, intended for injection applications. The materials underwent four processing cycles, each consisting of extrusion and injection operations. The research included determining the mass flow rate, mechanical parameters (tensile strength, bending strength, Young’s modulus, impact strength), thermomechanical parameters (storage modulus as a function of temperature), and thermal parameters (thermal resistance, phase transition temperature). The change in these parameters as a function of the processing rate was examined. It was shown that if one wants to reuse waste from the tested compositions, MB173 turns out to be a better material. Even though in the case of the M30 material, the changes obtained do not disqualify this material for re-use, a greater control of the degree of prior processing and the amount of waste used is recommended.
Przejdź do artykułu

Autorzy i Afiliacje

Krzysztof Moraczewski
1
ORCID: ORCID
Cezary Gozdecki
1
Marek Kociszewski
1
Bartłomiej Jagodziński
1
Krzysztof Szabliński
1
Magdalena Stepczyńska
1

  1. Faculty of Materials Engineering, Kazimierz Wielki University, Chodkiewicza 30, 85-064 Bydgoszcz, Poland

Abstrakt

The combustion or co-combustion of biomass or alternative fuels is important in the energy sector because of the need to reduce the share of fossil fuels. This article is a continuation of previous studies on the behaviour of the mineral matter of selected fuels during the sintering processes. The blends of wheat straw biomass from Polish crops (WS) with bituminous coal from the Makoszowa mine (BC) were studied. The study included proximate and ultimate analysis and oxide analysis of ash blends with the following composition: 10wt% WS/90wt%BC, 25wt% WS/75wt%BC, and 50wt% WS/50wt%BC. Based on the oxide content, a prediction (using FactSage 8.0 software) of the sintering process of the mixtures was tested. The following parameters were determined: slag phase content, specific heat at constant pressure, and ash density. The fracture stress tests were carried out using the mechanical test. Pressure tests were also performed using the pressure drop test method. The test results of all test methods used were compared with each other. Based on this comparison, a clear correlation was found between the sintering temperatures determined by the mechanical method and the pressure drop method and the physical properties of the ashes, such as density and heat capacity, as well as the chemical properties, i.e. the content of the slag phase. The results of the presented research are a valuable addition to the previous work of the authors. The goal of this work is to develop a precise and measurably simple method to determine the sintering temperature of ashes. This is an extremely important issue, especially in the case of the need to use a wide range of fuels in the energy industry.
Przejdź do artykułu

Autorzy i Afiliacje

Karol Król
1
Dorota Nowak-Woźny
1
Tomasz Janiczek
2

  1. Department of Energy Conversion Engineering, Faculty of Mechanical and Power Engineering, Wroclaw University of Science and Technology,27 Wybrzeze Wyspia ˙ nskiego Street, 50-370 Wroclaw, Poland
  2. Department of Control Systems and Mechatronics, Faculty of Information and Communication Technology, Wroclaw University of Science andTechnology, 27 Wybrzeze Wyspia ˙ nskiego Street, 50-370 Wroclaw, Poland

Abstrakt

Hard-facing alloys increase the service life of components exposed to abrasive, erosive, or metal-to-metal wear conditions. Hard-facing is a metalworking process in which layers of a harder material are arc-welded onto a base metal. In particular, high-chromium hard-face weld deposit layers form a strong metallurgical bond with the substrate steel plate, enhancing the resistance to abrasive loadings. Metallurgical and microstructural analysis is conducted to improve the performance of such bi-layered metal structures. The discussion of an HC-O hard-face alloy deposited on S235 steel substrate plates is presented here, focusing on the characterization of the coating microstructure. The study establishes the relationship among the chemical composition, ‘as-clad’ microstructure, and hardness properties of the investigated high chromium Fe – 27 wt.% Cr – 5 wt.% C hard-facing alloy.
Przejdź do artykułu

Autorzy i Afiliacje

Teresa Faras
1
ORCID: ORCID
Benjamin Koenig
2
Paul P. Meyer
3
Ibra Diop
4

  1. French-German Research Institute of Saint-Louis (ISL), Saint-Louis, France
  2. ENSTA Bretagne, Brest, France
  3. Department of Mechanical and Process Engineering, ETH Zürich, Switzerland
  4. Welding Alloys France, Holtzwihr, France

Abstrakt

This study aims to analyze the ceramic-metal composite Al2O3/TiO2/TiAl2O5 obtained using the slip-casting method. Samples containing 50% of the solid phase and 2% and 4% fractions of the metallic phase were examined. Rheological investigations were performed. Measurements of shrinkage and density of the composites produced were determined. The phase composition of the obtained composite was investigated using SEM/EDS and XRD techniques. Stereological analysis was performed as well. The slip-casting method enables the production of the proposed composite, reinforced by the presence of TiO2 and TiAl2O5 . With the increase in the content of the metallic phase in the composite, the thialite phase content increases, but relative density and volumetric shrinkage of the obtained composites both decrease. Thialite grains are characterized by a size in the range of 4 µm to 15 µm, which leads to a low density of the samples. The results revealed that no significant effect of changing the metal phase content of the slurries used for the composites being fabricated was observed on the limiting grain growth of alumina during the sintering process of slip-casting composites. This finding is important as it suggests that the increase in metallic phase content does not lead to undesirable grain coarsening, which could degrade mechanical properties.
Przejdź do artykułu

Autorzy i Afiliacje

Marcin Wachowski
1
ORCID: ORCID
Justyna Zygmuntowicz
2
ORCID: ORCID
Robert Kosturek
1
ORCID: ORCID
L. Śnieżek
1
ORCID: ORCID
P. Piotrkiewicz
2
ORCID: ORCID
Radosław Żurowski
3
ORCID: ORCID
Karolina Korycka
3

  1. Faculty of Mechanical Engineering, Military University of Technology, 2 gen. S. Kaliskiego St., 00-908 Warsaw, Poland
  2. Faculty of Materials Science and Engineering, Warsaw University of Technology, 141 Woloska St, 02-507 Warsaw, Poland
  3. Faculty of Chemistry, Warsaw University of Technology, 3 Noakowskiego St, 00-664 Warsaw, Poland

Abstrakt

The application of the Internet of Things (IoT) is increasing exponentially, the dynamic data flow and distributive operation over low-resource devices pose a huge threat to sensitive human data. This paper introduces an artificial immune system (AIS) based approach to intrusion detection in IoT network ecosystems. The proposed approach implements dual-layered AIS; which is robust to zero-day attacks and designed to adapt new types of attack classes in the form of antibodies. In this paper, a hybrid method has been presented which uses hybrid of clonal selection using variational auto-encoders as innate immune layer and apaptive dentritic model for identifying intrusions over IoT specific datasets. Moreover we present extensive empirical analysis over six IoT network benchmark datasets for semi-supervised multi-class classification task and obtain superior performance compared to five state-of-the-art baselines. Finally, VC-ADIS achieves 99.83% accuracy over MQTT-set dataset.
Przejdź do artykułu

Autorzy i Afiliacje

Vineeta Soni
1
ORCID: ORCID
Devershi Pallavi Bhatt
1
Narendra Singh Yadav
1

  1. Manipal University Jaipur, Jaipur, India

Abstrakt

This paper presents a preliminary study delving into the application of machine learning-based methods for optimizing parameter selection in filtering techniques. The authors focus on exploring the efficacy of two prominent filtering methods: smoothing and cascade filters, known for their profound impact on enhancing the quality of brain signals. The study specifically examines signals acquired through functional near-infrared spectroscopy (fNIRS), a noninvasive neuroimaging modality offering valuable insights into brain activity. Through meticulous analysis, the research underscores the potential of machine learning approaches in discerning optimal parameters for filtering, thereby leading to a significant enhancement in the quality and reliability of fNIRS-derived signals. The results demonstrate the effectiveness of machine learning-based methods in optimizing parameter selection for filtering techniques, particularly in the context of fNIRS signals. By leveraging these approaches, the study achieves notable improvements in the quality and reliability of brain signal data. This work sheds light on promising avenues for refining neuroimaging methodologies and advancing the field of signal processing in neuroscience. The successful application of machine learning-based techniques highlights their potential for optimizing neuroimaging data processing, ultimately contributing to a deeper understanding of brain function.
Przejdź do artykułu

Autorzy i Afiliacje

Mariusz Pelc
1 2
ORCID: ORCID
Dariusz Mikolajewski
3 4
ORCID: ORCID
Adrian Luckiewicz
5
ORCID: ORCID
Adam Sudol
6
ORCID: ORCID
Patryk Mendon
7
ORCID: ORCID
Edward Jacek Gorzelańczyk
8 9
ORCID: ORCID
Aleksandra Kawala-Sterniuk
10
ORCID: ORCID

  1. Institute of Computer Science, University of Opole, Opole, Poland
  2. School of Computing and Mathematical Sciences, University of Greenwich, London, UK
  3. Institute of Computer Science, Kazimierz Wielki University in Bydgoszcz, Bydgoszcz, Poland
  4. Neuropsychological Research Unit, 2nd Clinic of the Psychiatry and Psychiatric Rehabilitation, Medical University in Lublin, Lublin, Poland
  5. Faculty of Electrical Engineering, Institute of Theory of Electrical Engineering, Measurement and Information Systems,Warsaw University of Technology, Warszawa, Poland
  6. University of Applied Sciences in Nysa, Department of Technical Sciences, Nysa, Poland
  7. Faculty of Electrical Engineering, Automatic Control and Informatics, Opole University of Technology, Opole, Poland
  8. Kazimierz Wielki University in Bydgoszcz, Institute of Philosophy, Bydgoszcz, Poland
  9. The Society for the Substitution Treatment of Addiction "Medically Assisted Recovery", 85-791 Bydgoszcz, Poland
  10. Department of Artificial Intelligence, Faculty of Information and Communication Technology,Wroclaw University of Science and Technology, Wroclaw, Poland

Abstrakt

The development of automated driving vehicles aims to provide safer, comfortable, and more efficient mobility options. However, the decision-making control of autonomous vehicles still faces limitations of human performance mimicry. These limitations become particularly evident in complex and unfamiliar driving scenarios, where weak decision-making abilities and poor adaptation of vehicle behaviour are prominent issues. This paper proposes a game-theoretic decision-making algorithm for human-like driving in the vehicle lane change scenario. Firstly, an inverse reinforcement learning (IRL) model is used to quantitatively analyze the lane change trajectories of the natural driving dataset, establishing the human-like human cost function. Subsequently, joint safety, and comfort to build the comprehensive decision cost function. The combined decision cost function is used to conduct a noncooperative game of vehicle lane changing decisions to solve the optimal decision of host vehicle lane changing. The host vehicle lane-changing decision problem is formulated as a Stackelberg game optimization problem. To verify the feasibility and effectiveness of the algorithm proposed in this study, a lane change test scenario was established. Firstly, we analyze the human-like decision-making model derived from the maximum entropy inverse reinforcement learning algorithm to verify the effectiveness and robustness of the IRL algorithm. Secondly, the human-like game decision-making algorithm in this paper is validated by conducting an interactive lane-changing experiment with obstacle vehicles of different driving styles. The experimental results prove that the human-like driving decision-making model proposed in this study can make lane-changing behaviours in line with human driving patterns in lane-changing scenarios of the expressway.
Przejdź do artykułu

Autorzy i Afiliacje

Yalan Jiang
1
ORCID: ORCID
Xuncheng Wu
1
Weiwei Zhang
2
Wenfeng Guo
3
Wangpengfei Yu
2
Jun Li

  1. School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai, 201620, China
  2. Shanghai Smart Vehicle Cooperating Innovation Center Co., Ltd., Shanghai, 201805, China
  3. School of Vehicle and Mobility, Tsinghua University, Beijing, 100084, China

Abstrakt

Unmanned aerial vehicles (UAVs) require precise system identification for optimal performance and safety, yet sensor noise and signal distortion frequently compromise data quality. Recent studies have explored various approaches to mitigate these issues. However, this study introduces a novel method that utilizes wavelet transform techniques, distinctively enhancing UAV sensor signal processing. Unlike conventional methods that primarily focus on noise reduction, this approach employs multi-resolution wavelet decomposition to denoise and align signals effectively, crucial for accurate system identification. This systematic exploration of various wavelet bases and the application of the output error method for correlating signals provide a unique combination not extensively covered in current literature. The technique was validated using simulated sensor data at 50 Hz from a small UAV platform, the Multiplex®Fun Cub, specifically targeting longitudinal dynamics response. Results demonstrated substantial improvements in signal quality, with significantly enhanced correlation coefficients, showcasing the potential of our wavelet techniques to refine UAV system analysis. This paper presents a comprehensive framework for applying wavelet-based techniques in UAV system identification, significantly advancing the robustness and reliability of identification processes and distinguishing our work from existing methods by its integration of wavelet decomposition and advanced system identification techniques.
Przejdź do artykułu

Autorzy i Afiliacje

Pedro Jimenez-Soler
1
ORCID: ORCID
Piotr Lichota
1
ORCID: ORCID

  1. Institute of Aeronautics and Applied Mechanics, Warsaw University of Technology, 00-665 Warsaw, Poland

Abstrakt

Gravitational classifiers belong to the supervised machine learning area, and the basic element they process is a data particle. So far, many algorithms have been presented in the world literature. They focus on creating a data particle and determining its two important parameters – a centroid and a mass. Hypergeometrical divide is one of the latest algorithms in this group, which focuses on reducing the amount of processing data and keeping relevant information. The proportion of data to information depends on the data particle divide depth level. Its properties and application potential have been researched, and this article is the next step of the work. The research described in this article aimed to determine the relation of the depth level value of data particle divide to the effectiveness of the hypergeometrical divide algorithm. The research was conducted on 7 real data sets with different characteristics, applying methods and measures of evaluating artificial intelligence algorithms described in the literature. 63 measurements were performed. As a result, the effectiveness of the hypergeometrical divide method was defined at each of the available data particle divide depth levels for each of the used databases.
Przejdź do artykułu

Autorzy i Afiliacje

Łukasz Rybak
1
ORCID: ORCID
Janusz Dudczyk
1
ORCID: ORCID

  1. Military University of Technology, Faculty of Electronics, Warsaw, Poland

Abstrakt

Porous materials are extremely efficient in absorbing mechanical energy in different applications. In the present study, porous materials based on the Ti-6(wt.%)Al-4V alloy were manufactured with the use of two different powder metallurgy methods: i) blended elemental powder approach using titanium hydride (TiH2) as well as V-Al master alloy powders and ii) using hydrogenated Ti-6-4 pre-alloyed powder. The powder compacts were sintered with additions of ammonium bicarbonate as a pore-holding removable agent. The emission of hydrogen from hydrogenated powders on vacuum sintering and the resulting shrinkage of powder particles permitted the control of the sintering process and the creation of anticipated porous structures. Mechanical characteristics were evaluated under quasi-static and dynamic compressive loading conditions. Dynamic compression tests were performed using the direct impact Hopkinson pressure bar technique. All investigations aimed at characterizing the mechanical energy-absorbing ability of the obtained porous structures. The anticipated strength, plasticity, and energyabsorbing characteristics of porous Ti-6-4 material were evaluated, and the possibilities of their application were also discussed. Based on the obtained results, it was found that porous Ti-6-4 material produced with a blended elemental powder approach showed more promising energy absorption properties in comparison with pre-alloyed powder.
Przejdź do artykułu

Autorzy i Afiliacje

Pavlo E. Markovsky
1
ORCID: ORCID
Jacek Janiszewski
2
ORCID: ORCID
Oleksandr O. Stasiuk
1
Dymitro G. Savvakin
1
ORCID: ORCID
Denys V. Oryshych
1
ORCID: ORCID
Piotr Dziewit
2
ORCID: ORCID

  1. 1 G.V. Kurdyumov Institute for Metal Physics of NAS of Ukraine, 36, Vernadsky Blvd., 03142, Kyiv, Ukraine
  2. Military University of Technology, ul. Gen. Sylwestra Kaliskiego 2, 00–908 Warsaw 46, Poland

Abstrakt

The DC-DC converter represents a crucial component in renewable energy sources. The stability and dynamic capability enhancement of the DC/DC converter have emerged as a significant research topic in the current era. Model predictive control (MPC) is particularly prevalent due to its high dynamic response speed, simplicity of the controller design, and capacity for multi-objective optimization. However, the traditional finite control set model predictive control (FCS-MPC) method suffers as a result of variable switching frequency and vast computing. To improve the dynamic performance of the converter, a novel nonlinear control strategy named fixed switching frequency MPC and passivity-based control (PBC), named FSF-PBMPC, are both proposed. They could allow to achieve fixed switching frequency and to enhance the system’s dynamic response speed. Firstly, the Euler-Lagrange (EL) model of the boost converter is established. Secondly, the relationship between duty cycle and MPC is established. Ultimately, the output voltage of PBC is incorporated into the cost function of the FCS-MPC. The characteristics of PBC power shaping and damping injection can enhance the system’s immunity to interference, improve the system’s dynamic response speed, and thus reinforce the system’s stability. Then, depending on MATLAB, the simulation results can prove that the proposed strategy has the effect we expected.
Przejdź do artykułu

Autorzy i Afiliacje

Yajing Zhang
1
ORCID: ORCID
Yuqing Shen
1
BaoYing Huang
2
Jiangchao Zhang
2
Haojing Chang
3

  1. School of Automation, Beijing Information Science & Technology University, Beijing, China
  2. State Grid Economic and Technological Research Institute Co., Ltd, Beijing, China
  3. State Grid Corporation Gansu, Power Grid Construction Division, Gansu, China

Instrukcja dla autorów

Guide for Authors

https://www.editorialsystem.com/bpasts/journal/for_authors/

As of January 1st, 2025, there are changes in the fees for open access publications in Bulletin of the Polish Academy of Sciences Technical Sciences: 2000 PLN (approx. 500 EUR) - up to 8 pages of the journal format and mandatory over-length charges of 250 PLN (approx. 60 EUR) per page (see the above link with instructions for Authors for details)

Guide for Reviewers

https://www.editorialsystem.com/bpasts/journal/for_reviewers/

Call for Papers

https://www.editorialsystem.com/bpasts/journal/call_for_papers/

Guide for Guest Editors

https://www.editorialsystem.com/editor/bpasts/journal/page1/

Dodatkowe informacje

NEW PUBLICATION FEES
Articles submitted by December 31st, 2024: existing fee: 1500 PLN (and mandatory over-length charges of 230 PLN per page)
Articles submitted from January 1st, 2025: new fee: 2000 PLN (approx. 500 EUR- depending on the exchange rate) - a flat fee per paper up to 8 pages of the journal format (each additional page will be charged an additional 250 PLN).

Ta strona wykorzystuje pliki 'cookies'. Więcej informacji