Filters
total: 7860
-
Catalog
- Publications 6447 available results
- Journals 252 available results
- Conferences 126 available results
- Publishing Houses 1 available results
- People 183 available results
- Inventions 4 available results
- Projects 15 available results
- Research Equipment 8 available results
- e-Learning Courses 121 available results
- Events 32 available results
- Offers 1 available results
- Open Research Data 670 available results
displaying 1000 best results Help
Search results for: THERMOELECTRIC GENERATOR (TEG) MAXIMUM POWER POINT TRACKING (MPPT) SWARM INTELLIGENCE (SI) FEED-FORWARD NEURAL NETWORK (FFNN)
-
Designing of an effective structure of system for the maintenance of a technical object with the using information from an artificial neural network
Publication -
Design of a Shape-Memory-Alloy-Based Carangiform Robotic Fishtail with Improved Forward Thrust
PublicationShape memory alloys (SMAs) have become the most common choice for the development of mini- and micro-type soft bio-inspired robots due to their high power-to-weight ratio, ability to be installed and operated in limited space, silent and vibration-free operation, biocompatibility, and corrosion resistance properties. Moreover, SMA spring-type actuators are used for developing different continuum robots, exhibiting high degrees...
-
Application capabilities of the maximum distributed generation estimate methodology
PublicationThe paper presents application capabilities of the maximum distributed generation estimate methodology. This subject is an example of solutions to the problem that today face the transmission system operator and distribution system operators, which is related to the high saturation with wind power generation predicted for the near future.
-
Servo tracking of targets at sea
PublicationW artykule przedstawiono propozycje systemu sterowania układem śledzącym umieszczonym na okręcie. Przedstawiono dynamikę błędów śledzenia obiektu we współrzędnych LOS (ang., Line - Of - Sight). Zostało wykazane, że regulacja błędów śledzenia LOS jest możliwa przy pomocy sprzężenia feed-forward od prędkości śledzonego obiektu. Ponieważ prędkość ta nie jest mierzalna zastosowano filtr Kalmana w celu jej estymacji. Ponieważ problem...
-
Employing flowgraphs for forward route reconstruction in video surveillance system
PublicationPawlak’s flowgraphs were utilized as a base idea and knowledge container for prediction and decision making algorithms applied to experimental video surveillance system. The system is used for tracking people inside buildings in order to obtain information about their appearance and movement. The fields of view of the cameras did not overlap. Therefore, when an object was moving through unsupervised areas, prediction was needed...
-
Performance analysis of an rfid-based 3d indoor positioning system combining scene analysis and neural network methods
PublicationThe main purpose of this research is to improve localization accuracy of an active Radio Frequency Identification, RFID tag, in 3D indoor space. The paper presents a new RFID based 3D Indoor Positioning System which shows performance improvement. The proposed positioning system combines two methods: the Scene Analysis technique and Artificial Neural Network. The results of both simulation using Log-Distance Path Loss Model and...
-
Preliminary studies on the effect of feed speed on the colour change of wood
PublicationThis paper presents the results of preliminary analyses of the effect of cutting parameters on changes in the colour of wood. Beech wood cut with use circular saw was analysed. The cutting parameter tested was the feed speed, represented by the feed per tooth. Sawing processes with different feed per tooth ranging from 0.0008 mm to 0.09 mm were analysed. It was observed that over the entire range of feed rate per tooth analysed,...
-
Biotrickling filtration of n-butanol vapors: process monitoring using electronic nose and artificial neural network
PublicationBiotrickling filtration is one of the techniques used to reduce odorants in the air. It is based on the aerobic degradation of pollutants by microorganisms located in the filter bed. The research presents the possibility of using the electronic nose prototype combined with artificial neural network for biofiltration process monitoring in terms of reduction in n-butanol concentration and odour intensity of treated air. The study...
-
Adjusting the Stiffness of Supports during Milling of a Large-Size Workpiece Using the Salp Swarm Algorithm
PublicationThis paper concerns the problem of vibration reduction during milling. For this purpose, it is proposed that the standard supports of the workpiece be replaced with adjustable stiffness supports. This affects the modal parameters of the whole system, i.e., object and its supports, which is essential from the point of view of the relative tool–workpiece vibrations. To reduce the vibration level during milling, it is necessary to...
-
Computational Intelligence - 2023
e-Learning CoursesWidening the students knowledge about the selected methods of artificial intelligence
-
Computational Intelligence 2022
e-Learning CoursesWidening the students knowledge about the selected methods of artificial intelligence
-
Efficient uncertainty quantification using sequential sampling-based neural networks
PublicationUncertainty quantification (UQ) of an engineered system involves the identification of uncertainties, modeling of the uncertainties, and the forward propagation of the uncertainties through a system analysis model. In this work, a novel surrogate-based forward propagation algorithm for UQ is proposed. The proposed algorithm is a new and unique extension of the recent efficient global optimization using neural network (NN)-based...
-
Multisensor Tracking of Marine Targets - Decentralized Fusion of Kalman and Neural Filters
Publication -
Spectrum-based modal parameters identification with Particle Swarm Optimization
PublicationThe paper presents the new method of the natural frequencies and damping identification based on the Artificial Intelligence (AI) Particle Swarm Optimization (PSO) algorithm. The identification is performed in the frequency domain. The algorithm performs two PSO-based steps and introduces some modifications in order to achieve quick convergence and low estimation error of the identified parameters’ values for multi-mode systems....
-
GaAs-Si interfacial energy determination
PublicationBazując na półempirycznym modelu wiązań kowalencyjnych w krzemie wyznaczono energie międzypowierzchni GaAs-Si. Obliczona energia międzypowierzchni GaAs-Si zależna jest od orientacji podłoża Si. Minimalna energia międzypowierzchniowa wyznacza odpowiednią konfigurację atomów w pobliżu powierzchni, która określa optymalne warunki heteroepitaksji GaAs na podłożach Si.
-
Jarosław Chojnacki prof. dr hab. inż.
PeopleBorn in 1961 in Bydgoszcz, professional education started at the Chemical Technical Highschool (I. Łukasiewicz). He graduated from the Faculty of Chemistry at the Gdańsk University of Technology in 1986, defending the work on ion-selective electrodes. Subsequent studies were related to organic and siliconorganic synthesis and, from 2002 year on, to crystallography. The doctoral thesis concerned the Silanotiolanes of coinage metals...
-
Structure and thermoelectric properties of nickel-doped copper selenide synthesised in a hydrogen atmosphere
PublicationNickel-doped copper selenide—Cu2-xNixSe (x = 0; 0.01; 0.02; 0.03)—materials with high thermoelectric properties were synthesised through reduction of reagents in hydrogen. The impact of the nickel content on both the microstructure and thermoelectric properties was examined. The nickel-doped samples’ microstructure differed significantly from pristine copper selenide. Besides Cu2Se, copper precipitations were present in the materials....
-
Artificial neural network based fatigue life assessment of friction stir welding AA2024-T351 aluminum alloy and multi-objective optimization of welding parameters
PublicationIn this paper, the fracture behavior and fatigue crack growth rate of the 2024-T351 aluminum alloy has been investigated. At first, the 2024-T351 aluminum alloys have been welded using friction stir welding procedure and the fracture toughness and fatigue crack growth rate of the CT specimens have been studied experimentally based on ASTM standards. After that, in order to predict fatigue crack growth rate and fracture toughness,...
-
Low cost microwave X-band generator
PublicationA low cost microwave X-band generator for educational purposes was designed and built. Its simple construction and user's interface makes it suitable for a student laboratory.The generator is based on a single frequency conversion concept. It uses a digitally tunable PLL chip for intermediate frequency generation and an active frequency multiplier for frequency conversion. The generator covers 9,7 - 11 GHz part of the X frequency...
-
Iterative Global Sensitivity Analysis Algorithm with Neural Network Surrogate Modeling
PublicationGlobal sensitivity analysis (GSA) is a method to quantify the effect of the input parameters on outputs of physics-based systems. Performing GSA can be challenging due to the combined effect of the high computational cost of each individual physics-based model, a large number of input parameters, and the need to perform repetitive model evaluations. To reduce this cost, neural networks (NNs) are used to replace the expensive physics-based...
-
Automatic Image and Speech Recognition Based on Neural Network
Publication -
Neural-Network-Based Parameter Estimations of Induction Motors
Publication -
Cellular neural network application to moire pattern filtering
Publication -
Neural Network - Based Parameters Estimations Of Induction Motors
PublicationW artykule przedstwaiono algorytmy estymacji rezystancji wirnika i indukcyjności wzajemnej w zamkniętym układzie sterowania prędkości silnika indukcyjnego klatkowego. Do wyznaczenia rezystancji wykorzystano algorytm oparty na porównaniu modelu napięciowego i prądowego silnika. Do wyznaczania indukcyjności wykorzystano, znaną z literatury, zależność modelu multiskalarnego. Wyznaczane w stanie ustalonym parametry zapisywane są w...
-
Comparative study of methods for artificial neural network training.
PublicationPrzedstawiono wyniki badań porównawczych następujących metod uczenia sieci neuronowych: propagacji wstecznej błędów, rekursywnej metody najmniejszych kwadratów, metody Zangwill'a i algorytmów ewolucyjnych. Badania dotyczyły projektowania adaptacyjnego regulatora neuronowego napięcia generatora synchronicznego.
-
Neural network breast cancer relapse time prognosis
PublicationPrzedstawiono architekturę i wyniki testowania sztucznej sieci neuronowej w prognozowaniu czasu nawrotu choroby u kobiet chorych na raka piersi. Sieć neuronowa uczona była na danych zgromadzonych przez 20 lat. Dane opisują grupę 439 pacjentów za pomocą 40 parametrów. Spośród tych parametrów wybrano 6 najistotniejszych: liczbę przerzutowych węzłów chłonnych, wielkość guza, wiek, skalę według Blooma oraz stan receptorów estrogenowych...
-
Zbigniew Lubośny prof. dr hab. inż.
People -
An in-depth study of the Barkhausen emission signal properties of the plastically deformed Fe-2%Si alloy
PublicationZbadana została korelacja między natężeniem emisji magnetoakustycznej a natężeniem mechanicznego efektu Barkhausena dla próbek ze stali P91 mających różną mikrostrukturę na skutek plastycznego płynięcia w temperaturze pokojowej lub na skutek przyspieszonego pełzania w temperaturze 773K pod naprężeniem 290 KPa. Zakres deformacji plastycznej dla pierwszego zestawu próbek wynosił od 2% do 10,5% a dla drugiego od 0,85% do 10%. Oba...
-
A Novel Speed Observer for Doubly-Fed Induction Generator
PublicationThe purpose of this paper is to show a new state observer for doubly-fed generator. A proposed z-type observer algorithm based on mathematical model of doubly fed generator with additional variables treated as a disturbances has been used. A nonlinear multiscalar control method has been used to control active and reactive power of the generator. All analyses were verified by simulations and experiments tests.
-
Rafał Leszczyna dr hab. inż.
PeopleDr hab. Rafal Leszczyna is an associate professor at Gdansk University of Technology, Faculty of Management and Economics. He holds the M.Sc. degrees of Computer Science and Business Management. In December, 2006 he earned a Ph.D. in Computer Science, specialisation - Computer Security at the Faculty of Electronics, Telecommunications and Informatics of Gdansk University of Technology. Between 2004 and 2008 he worked in the European...
-
Virtual spring damper method for nonholonomic robotic swarm self-organization and leader following
PublicationIn this paper, we demonstrate a method for self-organization and leader following of nonholonomic robotic swarm based on spring damper mesh. By self-organization of swarm robots we mean the emergence of order in a swarm as the result of interactions among the single robots. In other words the self-organization of swarm robots mimics some natural behavior of social animals like ants among others. The dynamics of two-wheel robot...
-
GPU Power Capping for Energy-Performance Trade-Offs in Training of Deep Convolutional Neural Networks for Image Recognition
PublicationIn the paper we present performance-energy trade-off investigation of training Deep Convolutional Neural Networks for image recognition. Several representative and widely adopted network models, such as Alexnet, VGG-19, Inception V3, Inception V4, Resnet50 and Resnet152 were tested using systems with Nvidia Quadro RTX 6000 as well as Nvidia V100 GPUs. Using GPU power capping we found other than default configurations minimizing...
-
Structure and thermoelectric properties of bismuth telluride—Carbon composites
PublicationCarbon nanotubes and amorphous carbon have been introduced into a bismuth telluride matrix (0.15 and 0.30 wt.% ratio) to investigate the influence of the carbon on the composite’s thermoelectric properties. Composites with well-dispersed additives have been obtained by sonication and ball-milling methodology. Carbon nanotubes and an amorphous carbon addition led to a decrease in electric conductivity from 1120 S/cm to 77 S/cm....
-
Neural network simulator's application to reference performance determination of turbine blading in the heat-flow diagnostics.
PublicationIn the paper, the possibility of application of artificial neural networks to perform the fluid flow calculations through both damaged and undamaged turbine blading was investigated. Preliminary results are presented and show the potentiality of further development of the method for the purpose of heat-flow diagnostics.
-
Voltage variations and their reduction in a rural low-voltage network with PV sources of energy
PublicationRenewable sources of energy (RES), especially photovoltaic (PV) micro-sources, are very popular in many countries. This way of clean power production is applied on a wide scale in Poland as well. The Polish legal regulations and tariffs specify that every prosumer in a low-voltage network may feed this network with a power not higher than the maximum declared consumed power. In power networks with RES, the voltage level changes...
-
Event-Triggered Communication in Cooperative, Adaptive Model Predictive Control of a Nuclear Power Plant’s Turbo–Generator Set
PublicationThis paper discusses the issue of optimizing the communication between the components of a cooperating control system formed by a pair of MPC controllers of a nuclear power plant turbine set using online recursive least squares identification. It is proposed to use event-triggered communication, i.e., sending information only at selected time instants, as opposed to the standard approach where communication is triggered by time...
-
Hybrid high-frequency-SiC and line-frequency-Si based PEBB for MV modular power converters
PublicationIzolowane przekształtniki DC-DC o sterowanym kącie przesunięcia napięć strony pierwotnej i wtórnej są kluczowymi elementami współczesnych modułowych przekształtników energoelektronicznych średniego napięcia (SN). W porównaniu do konwencjonalnych przekształtników SN, przekształtniki modułowe z izolowanymi przetwornicami DC-DC nie wymagają izolacji w postaci wielkogabarytowych transformatorów o częstotliwości sieci. Zastosowanie...
-
Toward Mechanosynthesis of Diamondoid Structures: VI. Quantum-Chemical Molecular Dynamics Comparison of Conditions for the STM Tip Driven Mechanosynthesis on Hydrogenated Si(111), Si(110) and Si(100) Surfaces.
Publicationmożliwość prototypowania przejściowych generacji nano-urządzeń otrzymanych drogą pozycjonowanej mechanosyntezy za pomocą stm wyposażonego w ostrze typu swcnt są analizowane metodą kwantowo-chemicznej dynamiki molekularnej. proponowana strategia syntezy polega na insercji atomów si oraz cząsteczek sih2 we wiązania si-h na uwodornionej powierzchni si(111), si(110) oraz si(100) kryształu krzemu. rezultaty modelowania sugerują, że...
-
Threat intelligence platform for the energy sector
PublicationIn recent years, critical infrastructures and power systems in particular have been subjected to sophisticated cyberthreats, including targeted attacks and advanced persistent threats. A promising response to this challenging situation is building up enhanced threat intelligence that interlinks information sharing and fine-grained situation awareness. In this paper a framework which integrates all levels of threat intelligence...
-
Creating neural models using an adaptive algorithm for optimal size of neural network and training set.
PublicationZaprezentowano adaptacyjny algorytm generujący modele neuronowe liniowych układów mikrofalowych, zdolny do oszacowania optymalnego rozmiaru zbiory uczącego i sieci neuronowej. Stworzono kilka modeli nieciągłości falowodowych i mokropaskowych, a następnie zweryfikowano ich poprawność porównując wyniki analiz metodą dopasowania rodzajów i metodą momentów filtrów pasmowo-przepustowych.
-
Diamond surface modification following thermal etching of Si supported hydrogenated diamond films by DBr
PublicationZbadano, wykorzystując spektroskopię oscylacyjną (HREELS - High Resolution Electron Energy Loss Spectroscopy) modyfikacje chemiczne powierzchni wodorowanego diamentu, umieszczonego na podkładzie krzemowym i wystawionego na działanie DBr a następnie podgrzanego do temp. powyżej 600 st.K. Przedstawiona procedura powoduje tworzenie się węglika krzemu SiC na powierzchni warstwy diamentowej, co jest widoczne na widmie HREEL jako dwa...
-
Determination of ionic conductivity in the Bi-Si-O and Pb-Si-O glasses
PublicationImpedance spectroscopy measurements in various gas atmospheres were carried out in order to explain the doubts about the type of carriers and the mechanism of electrical conductivity in Bi-Si-O and Pb-Si-O glasses. In bismuth silicate glass, a typical ionic conductivity with oxygen ions as charge carriers was observed. The level of electrical conductivity of the glass at 400 °C was 5 × 10−8 S·cm−1 , with the activation energy of...
-
Classification of Covid-19 using Differential Evolution Chaotic Whale Optimization based Convolutional Neural Network
PublicationCOVID-19, also known as the Coronavirus disease-2019, is an transferrable disease that spreads rapidly, affecting countless individuals and leading to fatalities in this worldwide pandemic. The precise and swift detection of COVID-19 plays a crucial role in managing the pandemic's dissemination. Additionally, it is necessary to recognize COVID-19 quickly and accurately by investigating chest x-ray images. This paper proposed a...
-
Bilateral power supply of the traction network as a first stage of Smart Grid technology implementation in electric traction
PublicationSince 2001, trolleybus system in Gdynia has been involved in many activities related to the reduction of power consumption, both in terms of implementation and research and development. In PKT, in cooperation with SESTO company, started applications of Smart Grid technologies in supply network: the bilateral supply. The paper presents results of this this novel investment.
-
Piotr Szczuko dr hab. inż.
PeoplePiotr Szczuko received his M.Sc. degree in 2002. His thesis was dedicated to examination of correlation phenomena between perception of sound and vision for surround sound and digital image. He finished Ph.D. studies in 2007 and one year later completed a dissertation "Application of Fuzzy Rules in Computer Character Animation" that received award of Prime Minister of Poland. His interests include: processing of audio and video, computer...
-
Application of Maximum Lenght Sequence in Silent Sonar
PublicationSilent sonars are designed to reduce the distance over which their sounding pulses can be detected by intercept sonars. In order to meet this objective, we can use periodical sounding signals that have low power, a very long duration and wide spectrum. If used in the silent sonar's receiver, matched filtration ensures very good detection of motionless or slow moving targets. However, it is more difficult to detect echo signals...
-
Estimation of Selected Synchronous Generator Parameters Based on the Gradient Method
PublicationThe authors present a method for the estimation of synchronous generator model parameters using a gradient algorithm. The paper shows an example of model parameter estimation for a turbogenerator and hydrogenerator, based on the generator voltage time responses obtained during an active and reactive power rejection test.
-
Koncepcja i symulacja polowa generatora o zmiennej częstotliwości. Zastosowanie w autonomicznych systemach elektroenergetycznych = Conception and field simulations of a variable frequency generator. Application for autonomous power generation system
PublicationStreszczenie angielskie: This paper covers a conception and simulation results for a brushless synchronous generator working with variable speed in an autonomous energy generation system (e.g. airplane power grid, hybrid vehicle, micro-CHP). The papers has two parts: presentation of the generator conception used in modern autonomous energy generation systems, and simulation results using filed model elaborated in Flux2D software....
-
Dataset Related Experimental Investigation of Chess Position Evaluation Using a Deep Neural Network
PublicationThe idea of training Articial Neural Networks to evaluate chess positions has been widely explored in the last ten years. In this paper we investigated dataset impact on chess position evaluation. We created two datasets with over 1.6 million unique chess positions each. In one of those we also included randomly generated positions resulting from consideration of potentially unpredictable chess moves. Each position was evaluated...
-
Comparison of Selected Neural Network Models Used for Automatic Liver Tumor Segmentation
PublicationAutomatic and accurate segmentation of liver tumors is crucial for the diagnosis and treatment of hepatocellular carcinoma or metastases. However, the task remains challenging due to imprecise boundaries and significant variations in the shape, size, and location of tumors. The present study focuses on tumor segmentation as a more critical aspect from a medical perspective, compared to liver parenchyma segmentation, which is the...