Wyszukiwarka
Katedra Inteligentnych Systemów Sterowania i Wspomagania Decyzji
Publikacje
Filtry
wszystkich: 275
Katalog Publikacji
Rok 2023
-
Decomposition of the induced magnetism degaussing problem for fast determination of currents in demagnetization coils wrapped outside an object under arbitrary external field conditions
PublikacjaSafe passage of ships in the presence of sea mines can be ensured by limiting or reducing the ship’s magnetic footprint. For vessels with plastic hulls, the main component that requires magnetic damping is the engine. Demagnetization of such an object can be achieved by wrapping it with coils and setting the direct current appropriately. For each specific geographic location, the currents in the coils can be determined iteratively...
Rok 2022
-
A robust sliding mode observer for non-linear uncertain biochemical systems
PublikacjaA problem of state estimation for a certain class of non-linear uncertain systems has been addressed in this paper. In particular, a sliding mode observer has been derived to produce robust and stable estimates of the state variables. The stability and robustness of the proposed sliding mode observer have been investigated under parametric and unstructured uncertainty in the system dynamics. In order to ensure an unambiguous non-linear...
-
Power efficient thrust allocation algorithms in design of dynamically positioned ships
PublikacjaAssessment of power consumption on a Dynamically Positioned (DP) ship in the early design stage can assist crucial design choices. The study presents a comparison between two algorithms of optimal thrust allocation in a propulsion system for an over-actuated DP ship. Applied algorithms were Quadratic Programming (QP) and Non- dominated Sorting Genetic Algorithm II (NSGAII). Based on both approaches, tools were developed for ship...
Rok 2021
-
Measurement Campaign and Mathematical Model Construction for the Ship Zodiak Magnetic Signature Reproduction
PublikacjaThe paper presents the partial work done within the framework of the EDA Siramis II project focused on magnetic signature reproduction of ships. Reproduction is understood here as the ability to determine the magnetic anomaly of the local Earth magnetic field in any direction and at any measurement depth due to the presence of the analysed object. The B-91 type hydrographic ship Zodiak was selected as the real case study. The work...
-
Novel hierarchical nonlinear control algorithm to improve dissolved oxygen control in biological WWTP
PublikacjaWastewater treatment is a problem known to humankind for centuries. The quality of treated sewage determines the condition of reservoirs around the world. Control of such a complex and nonlinear system as a wastewater treatment plant requires thorough knowledge of the process. The paper presents a hierarchical control system of a Sequencing Batch Reactor (SBR) in Wastewater Treatment Plant (WWTP) taking into account a model based...
-
TOWARDS EXPLAINABLE CLASSIFIERS USING THE COUNTERFACTUAL APPROACH - GLOBAL EXPLANATIONS FOR DISCOVERING BIAS IN DATA
PublikacjaThe paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data. A global explanation is proposed, and a step-by-step framework on how to detect and test bias is introduced. Since removing unwanted bias is often a complicated and tremendous task, it is automatically inserted, instead. Then, the bias is evaluated with the proposed counterfactual approach. The obtained results...
Rok 2020
-
An Automatic Self-Tuning Control System Design for an Inverted Pendulum
PublikacjaA control problem of an inverted pendulum in the presence of parametric uncertainty has been investigated in this paper. In particular, synthesis and implementation of an automatic self-tuning regulator for a real inverted pendulum have been given. The main cores of the control system are a swing-up control method and a stabilisation regulator. The first one is based on the energy of an inverted pendulum, whereas the second one...
-
Approximation of Fractional Order Dynamic Systems Using Elman, GRU and LSTM Neural Networks
PublikacjaIn the paper, authors explore the possibility of using the recurrent neural networks (RNN) - Elman, GRU and LSTM - for an approximation of the solution of the fractional-orders differential equations. The RNN network parameters are estimated via optimisation with the second order L-BFGS algorithm. It is done based on data from four systems: simple first and second fractional order LTI systems, a system of fractional-order point...
-
Autonomous Ship Utility Model Parameter Estimation Utilising Extended Kalman Filter
PublikacjaIn this paper, a problem of autonomous ship utility model identification for control purposes is considered. In particular, the problem is formulated in terms of model parameter estimation (one-step-ahead prediction). This is a complex task due to lack of measurements of the parameter values, their time-variability and structural uncertainty introduced by the available models. In this work, authors consider and compare two utility...
-
Bezzałogowy kołowy pojazd elektryczny do automatycznego wychodzenia z poślizgów
PublikacjaPojazdy bezzałogowe znajdują zastosowanie w wielu dziedzinach współczesnego świata. Pojazdy autonomiczne wraz z algorytmami wspomagającymi kierowanie pojazdami skupiają uwagę wielu zespołów inżynierskich. Jednym z ważniejszych aspektów bezpieczeństwa na drogach jest wspomaganie zapobiegania i wychodzenia z poślizgów w dynamicznym środowisku. Artykuł przedstawia projekt oraz wykonanie bezzałogowego pojazdu kołowego zdolnego do automatycznego...
-
Control of nonlinear and linearized model of self-balancing electric motorcycle
PublikacjaSelf-Balancing Electric Motorcycle (SBEM) is a dynamic and nonlinear electro-mechanical system. In this paper, the process of mathematical modelling and line-arization of SBEM is presented. The model of the control system in Matlab envi-ronment is implemented. The control system using the PID controller is designed. The operation of particular structures of the PID controller on the simulation model is compared. Due to simulation...
-
Design aspects of a low-cost prosthetic arm for people with severe movement disabilities
PublikacjaIn this paper the main aspects of mechanical design behind the low-cost prosthetic arm are presented. The fundamentals of a proper design has been defined to obtain functional 3D printed 5 degree of freedom (DOF) prosthesis. The designed prosthetic arm is a part of the hybrid interface with eye tracking movement control. The main focus was to create affordable but usable prosthesis which corresponds in size and weights to the human...
-
Design of optimal state feedback controller with observer for multidimensional electrical system
PublikacjaFrom the control point of view, two-input-two-output RC electrical system is a linear and multidimensional system. In this paper, integral control and closed-loop observer are verified whether they can be used and designed. To verify this, Kalman tests are made. These structures are presented and discussed. Integral Control is tested with some base disturbances impact and checked whether it can handle them. The estimated values...
-
Designing control strategies of aeration system in biological WWTP
PublikacjaThe paper presents the complete design processes of a novel aeration control systems in the SBR (Sequencing Batch Reactor) wastewater treatment plant (WWTP). Due to large energy expense and high influence on biological processes, the aeration system plays a key role in WWTP operation. The paper considers the aeration system for a biological WWTP located in the northeast of Poland. This system consists of blowers, the main collector...
-
Explainable AI for Inspecting Adversarial Attacks on Deep Neural Networks
PublikacjaDeep Neural Networks (DNN) are state of the art algorithms for image classification. Although significant achievements and perspectives, deep neural networks and accompanying learning algorithms have some important challenges to tackle. However, it appears that it is relatively easy to attack and fool with well-designed input samples called adversarial examples. Adversarial perturba-tions are unnoticeable for humans. Such attacks...
-
Fuzzy Multi-Regional Fractional PID controller for Pressurized Water nuclear Reactor
PublikacjaThe paper presents the methodology for the synthesis of a Fuzzy Multi-Regional Fractional Order PID controller (FMR-FOPID) used to control the average thermal power of a PWR nuclear reactor in the load following mode. The controller utilizes a set of FOPID controllers and the fuzzy logic Takagi-Sugeno reasoning system. The proposed methodology is based on two optimization parts. The first part is devoted to finding the optimal...
-
Improving the Quality of Magnetic Signature Reproduction by Increasing Flexibility of Multi-Dipole Model Structure and Enriching Measurement Information
PublikacjaThe paper presents the construction of a multi-dipole model that allows reproducing magneticsignatures of ferromagnetic objects. The virtual object used in the paper is an ellipsoid, which is the sourceof synthetic data. To make the situation more realistic, noise is added to the synthetic data. Two significantimprovements compared to previous work are presented. Three-axial magnetometers are introduced insteadof uniaxial magnetometers....
-
Model of aeration system at biological wastewater treatment plant for control design purposes
PublikacjaThe wastewater treatment plant (WWTP) is a dynamic, very complex system, in which the most important control parameter is the dissolved oxygen (DO) con-centration. The air is supplied to biological WWTP by the aeration system. Aera-tion is an important and expensive activity in WWTP. The aeration of sewage ful-fils a twofold role. Firstly, oxygen is provided as the main component for biolog-ical processes. Secondly, it supports...
-
Neural Architecture Search for Skin Lesion Classification
PublikacjaDeep neural networks have achieved great success in many domains. However, successful deployment of such systems is determined by proper manual selection of the neural architecture. This is a tedious and time-consuming process that requires expert knowledge. Different tasks need very different architectures to obtain satisfactory results. The group of methods called the neural architecture search (NAS) helps to find effective architecture...
-
Proces zmiany sprzedawcy energii elektrycznej w Polsce dla odbiorcy w gospodarstwie domowym
PublikacjaW publikacji przedstawiono proces zmiany sprzedawcy energii elektrycznej dla odbiorcy w gospodarstwie domowym, prowadzony w detalicznym segmencie rynku energii. Szczególny nacisk położono na proces bazujący na generalnej umowie dystrybucji dla usługi kompleksowej. Odniesiono się do wszystkich, istotnych regulacji mających zastosowanie do poruszanych kwestii, ze szczególnym uwzględnieniem zapisów instrukcji ruchu i eksploatacji...
-
Realization, programming and controlling of the Stewart-Gough platform
PublikacjaThis paper presents realizaon, programming, and controlling of a low cost Stewart-Gough plaorm (SGP) with rotary actuators. The realized SGP is applied in a ball & plate control system. Developed dedicated software consists of embedded and applicaon soware for both the SGP posioning system and the ball & plate control. system. A ball posion is being obtained using computer vision. The paper contains tests results for both an SGP...
-
Self-Supervised Learning to Increase the Performance of Skin Lesion Classification
PublikacjaTo successfully train a deep neural network, a large amount of human-labeled data is required. Unfortunately, in many areas, collecting and labeling data is a difficult and tedious task. Several ways have been developed to mitigate the problem associated with the shortage of data, the most common of which is transfer learning. However, in many cases, the use of transfer learning as the only remedy is insufficient. In this study,...
-
Skuteczność nowoczesnych algorytmów optymalizacji czerpiących inspirację z procesów naturalnych
PublikacjaZe względu na nieistnienie uniwersalnego algorytmu optymalizacji rozwiązującego wszystkie problemy naukowo techniczne opracowywanie nowych i wydajniejszych obliczeniowo algorytmów optymalizacyjnych wciąż jest popularnym zadaniem. Przeglądając literaturę z dziedziny optymalizacji można zauważyć trend tworzenia „wymyślnych” algorytmów opartych na procesach naturalnych. W artykule sprawdzono skuteczność nowo powstałych algorytmów...
-
Supervisory fuzzy control system for biological processes in sequencing wastewater batch reactor
PublikacjaThe paper proposes the design of the supervisory heuristic fuzzy control system applied to a Sequencing Batch Reactor (SBR) in the Wastewater Treatment Plant (WWTP). Based on real data records and the biological process and aeration system models, a control system for biological processes has been designed. The supervisory control system performs management of the reactor work cycle, determines the phase length, controls the sludge...
Rok 2019
-
A comprehensive approach to double inverted pendulum modelling
PublikacjaThe problem of mathematical modelling and indication of properties of a DIP has been investigated in this paper. The aim of this work is to aggregate the knowledge on a DIP modelling using the Euler-Lagrange formalism in the presence of external forces and friction. To indicate the main properties important for simulation, model parameters identification and control system synthesis, analytical and numerical tools have been used....
-
Deep neural network architecture search using network morphism
PublikacjaThe paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. Moreover, we used the function preserving transformations which enabled the effective operation of the algorithm in a short period of time. The network obtained with the advantage of NAS was validated on skin lesion classification...
-
Design of control algorithms for mobile robots in an environment with static and dynamic obstacles
PublikacjaThis article proposes the construction of autonomous mobile robots and designing of obstacle avoidance algorithms for them. Nowadays, mobile robots are gaining more and more popularity on the customer as well as industrial market, for example as automatic vacuum cleaners or lawnmowers. Obstacle avoidance algorithms play an important role in performance of this types of robots. The proposed algorithms were designed for builds with...
-
DIAGNOSIS OF MALIGNANT MELANOMA BY NEURAL NETWORK ENSEMBLE-BASED SYSTEM UTILISING HAND-CRAFTED SKIN LESION FEATURES
PublikacjaMalignant melanomas are the most deadly type of skin cancer but detected early have high chances for successful treatment. In the last twenty years, the interest of automated melanoma recognition detection and classification dynamically increased partially because of public datasets appearing with dermatoscopic images of skin lesions. Automated computer-aided skin cancer detection in dermatoscopic images is a very challenging task...
-
Improving SBR Performance Alongside with Cost Reduction through Optimizing Biological Processes and Dissolved Oxygen Concentration Trajectory
PublikacjaAuthors of this paper take under investigation the optimization of biological processes during the wastewater treatment in sequencing batch reactor (SBR) plant. A designed optimizing supervisory controller generates the dissolved oxygen (DO) trajectory for the lower level parts of the hierarchical control system. Proper adjustment of this element has an essential impact on the efficiency of the wastewater treatment process as well...
-
MACHINE LEARNING SYSTEM FOR AUTOMATED BLOOD SMEAR ANALYSIS
PublikacjaIn this paper the authors propose a decision support system for automatic blood smear analysis based on microscopic images. The images are pre-processed in order to remove irrelevant elements and to enhance the most important ones - the healthy blood cells (erythrocytes) and the pathologic (echinocytes). The separated blood cells are analyzed in terms of their most important features by the eigenfaces method. The features are the...
-
Marine autonomous surface ship - control system configuration
PublikacjaThis paper addresses the problem of marine autonomous surface ship (MASS) control. The contribution of the paper is the development of a control system configuration, done assuming fully autonomous MASS operation under distinct operational conditions. The overview of hardware and software selection is included.
-
Mechatronics design, modelling and controlling of the Stewart-Gough platform
PublikacjaThis paper presents a mechatronics design of a low cost Stewart-Gough platform (SGP) with rotary actuators. The designed SGP is supposed to be applied in a ball & plate control system. The synthesis of the ball & plate control system is also within the subject of the paper. A mechatronics design process of the SGP was conducted with computer-aided design (CAD) software. Unique analytical solutions of an inverse kinematics problem...
-
Metody strojenia regulatorów typu PID z wykorzystaniem technologii syntezy regulatorów od stanu
PublikacjaUkłady sterujące typu PID są jednymi z najbardziej popularnych regulatorów wykorzystywanych w układach regulacji. W związku z tym znanych jest szereg metod doboru wartości ich parametrów (nastaw). Obok różnych metod inżynierskich czy analitycznych strojenia tego typu regulatorów, dostępne są również podejścia bazujące na optymalizacji. Wskaźnikiem jakości znajdującym w nich zastosowanie jest np. całka z kwadratu uchybu. W artykule...
-
Mixed integer nonlinear optimization of biological processes in wastewater sequencing batch reactor
PublikacjaWastewater treatment plays a key role for humanity. The waste entering lakes, rivers, and seas deteriorates daily quality of life. Therefore, it is very important to improve the efficiency of wastewater treatment. From a control point of view, a biological wastewater treatment plant is a complex, non-linear, multidimensional, hybrid control system. The paper presents the design of the optimizing hierarchical control system applied...
-
Model konstrukcyjny i sterowanie robotami mobilnymi w środowisku z przeszkodami
PublikacjaW dzisiejszych czasach mobilne roboty autonomiczne zyskują coraz większą popularność, zarówno w środowiskach przemysłowych jak i w konsumenckich. Mają one głównie na celu ułatwianie pracy człowieka poprzez przejęcie części jego obowiązków. Z racji różnorodności środowisk, w jakich mogą one pracować, korzystają z algorytmów omijania przeszkód w celu osiągnięcia swobody poruszania się. Artykuł przedstawia model konstrukcyjny oraz...
-
Projekt systemu sterowania dwukołowym robotem balansującym
PublikacjaW niniejszym artykule rozważony został problem sterowania dwukołowym robotem balansującym. Celem zaprezentowanych prac było zaprojektowanie systemu sterowania tego typu obiektem z wykorzystaniem metod nowoczesnej teorii sterowania. W ramach syntezy, bazując na wyprowadzonym w oparciu o zasady dynamiki Newtona modelu, dobrana została struktura systemu sterowania w postaci regulatora wykorzystującego sprzężenie zwrotne od stanu oraz...
-
Quadrotor Flight Controller Design Using Classical Tools
PublikacjaA principal aspect of quadrocopter in-flight operation is to maintain the required attitude of the craft’s frame, which is done either automatically in the so-called supervised flight mode or manually during man-operated flight mode. This paper deals with the problem of flight controller (logical) structure and algorithm design dedicated for the man-operated flight mode. The role of the controller is to stabilise the rotational...
-
Selected Technical Issues of Deep Neural Networks for Image Classification Purposes
PublikacjaIn recent years, deep learning and especially Deep Neural Networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the Convolutional Neural Networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good...
-
Soft Real-Time Communication with WebSocket and WebRTC Protocols Performance Analysis for Web-based Control Loops
PublikacjaThe web browser has become an access window for content and services. The browser is available on almost any device connected to the network, regardless of its intended use: desktop, mobile device, computing server, e-book reader etc. Browsers are used by people to read news, contact the world, to check a bank account, register a visit at the doctor, watching video content, electronic purchases, using web versions of the office...
-
Zaprojektowanie, wykonanie i sterowanie panelem słonecznym
PublikacjaOdnawialne źródła energii stają się coraz bardziej popularne. Rynek fotowoltaiki w ostatnich latach znacznie powiększył swój udział w zaspokajaniu zwiększonego zapotrzebowania na energię wszystkich gałęzi przemysłu oraz gospodarek państw. Obecny etap rozwoju technologicznego dąży do maksymalizowania sprawności przetwarzania energii słonecznej na energię elektryczną. Prężnie rozwijająca się automatyzacja pozwala na budowę układów,...
Rok 2018
-
An optimised placement of the hard quality sensors for a robust monitoring of the chlorine concentration in drinking water distribution systems
PublikacjaThe problem of an optimised placement of the hard quality sensors in drinking water distribution systemsunder several water demand scenarios for a robust monitoring of the chlorine concentration is formulatedin this paper. The optimality is understood as achieving a desired trade off between the sensors and theirmaintenance costs and the accuracy of estimation of the chlorine concentration. The contribution of thiswork is a comprehensive...
-
Analiza istotności cech znamion skórnych dla celów diagnostyki czerniaka złośliwego
PublikacjaPomimo dynamicznego rozwoju metod uczenia maszynowego i ich wdrażania do praktyki lekarskiej, automatyczna analiza znamion skórnych wciąż jest nierozwiązanym problemem. Poniższy artykuł proponuje zastosowanie algorytmu ewolucyjnego do zaprojektowania, wytrenowania i przetestowania całych populacji klasyfikatorów (sztucznych sieci neuronowych) oraz ich iteracyjnego udoskonalania w każdej kolejnej populacji, w celu osiągnięcia jak...
-
Data augmentation for improving deep learning in image classification problem
PublikacjaThese days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neural Networks (CNN) are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this...
-
Decentralized Microgrid Energy Management System with Market-Based Energy Trade System
PublikacjaThis paper presents a decentralized energy management system for a power microgrid, which integrates individual users, who own renewable energy sources and energy storages. The purpose of the system is to make optimal use of available resources to cover the electricity needs of the whole microgrid. Thanks to the energy exchange system, in addition to exchanges with the distribution network, the system also allows trades within...
-
Decision support system for design of long distance heat transportation system
PublikacjaDistrict Heating (DH) systems are commonly supplied using local heat sources. Nowadays, modern insulation materials allow for effective and economically viable heat transportation over long distances (over 20 km). The paper proposes a Decision Support System (DSS) for optimized selection of design and operating parameters of a long distance Heat Transportation System (HTS). The method allows for evaluation of feasibility and effectiveness...
-
Diagnozowanie stanu retinopatii cukrzycowej przy pomocy głębokich sieci neuronowych
PublikacjaW referacie opisano problem wykrywania oraz klasyfikacji stanu retinopatii cukrzycowej ze zdjęć dna oka przy pomocy głębokich sieci neuronowych. Retinopatia cukrzycowa jest chorobą oczu często występującą u osób z cukrzycą. Nieleczona prowadzi do uszkodzenia wzroku, a nawet ślepoty. W pracy badawczej opracowano system wykrywania retinopatii cukrzycowej na podstawie zdjęć dna oka. Opracowana sieć neuronowa przypisuje stan choroby...
-
Estymacja respiracji wykorzystująca pomiar stężenia tlenu w SBR
PublikacjaBiologiczna oczyszczalnia ścieków jest złożonym nieliniowym systemem przemysłowym. Jednym z istotnych i kosztownych procesów tam zachodzących jest napowietrzanie ścieków. Z procesem tym związana jest respiracja, czyli szybkość zużywania tlenu przez bakterie oczyszczające ścieki. Jest to jeden z najważniejszych parametrów, decydujący o efektywności oczyszczania ścieków. Niestety koszt zakupu urządzeń do pomiaru respiracji – respirometrów...
-
Identification of the Contamination Source Location in the Drinking Water Distribution System Based on the Neural Network Classifier
PublikacjaThe contamination ingression to the Water Distribution System (WDS) may have a major impact on the drinking water consumers health. In the case of the WDS contamination the data from the water quality sensors may be efficiently used for the appropriate disaster management. In this paper the methodology based on the Learning Vector Quantization (LVQ) neural network classifier for the identification of the contamination source location...
-
Implementation of the FOPID Algorithm in the PLC Controller - PWR Thermal Power Control Case Study
PublikacjaIn the paper authors describe proposition of design and verification procedures of the discrete Fractional Order PID (FOPID) algorithm for control of the Pressurized Water Reactor (PWR) thermal power near its nominal operating point. The FOPID algorithm synthesis consists of: off-line optimal tunning of its parameters in continuous time-domain with LQ (Linear Quadratic) performance index and simplified models of nuclear reactor...
-
Monocykl elektryczny – projekt i realizacja
PublikacjaW ostatnich czasach zaobserwować można rozwój pojazdów elektrycznych. Czynnikami, które pozytywnie wpływają na to zjawisko jest redukcja emisji spalin oraz hałasu, które emitują standardowe pojazdy. Przy mniejszych, mobilnych konstrukcjach elektrycznych, dodatkową zaletą jest zmniejszenie problemu związanego z zatłoczeniem ulic. Artykuł przedstawia projekt oraz wykonanie monocyklu elektrycznego. Uwzględniając założenia projektowe,...