Wyniki wyszukiwania - BazTech

1

Selection of an algorithm for classifying data quoted on the Day Ahead Market of TGE S.A. in MATLAB and Simulink using Deep Learning Toolbox

Tchórzewski Jerzy, Mielcarz Tomasz

Studia Informatica : systems and information technology

|

2023

|

Vol. 1(28)

83--108

EN

The article contains an analysis leading to the selection of an algorithm for classifying data listed on the Day-Ahead Market of TGE S.A. in MATLAB and Simulink using Deep Learning Toolbox. In this regard, an introduction to deep learning methods, classification methods, and classification algorithms is provided first. Particular attention was paid to the essence of three important deep learning methods in the classification, i.e. the methods called: Stochastic Gradient Descent Momentum, Root Mean Square Prop and Adaptive Moment Estimation. Then, three architectures of artificial neural networks used in deep learning were characterized, i.e.: Deep Belief Network, Convolutional Neural Network and Recurrent Neural Network. Attention was paid to the selection parameters of algorithms for learning deep artificial neural networks that can be used in classification, such as: accuracy, information losses and learning time. Practical aspects of research experiments were also shown, including selected results of research conducted on volume and fixing 1 data quoted on the TGE S.A. Day-Ahead Market. After analyzing the obtained test results for the hourly system, it was noted that the least suitable algorithm for classification purposes was the Stochastic Gradient Descent Momentum algorithm, which in each case had worse results than the other two algorithms, i.e. the Adaptive Moment Estimation algorithm and the Root Mean algorithm Square Prop. However, the best algorithm turned out to be the Adaptive Moment Estimation algorithm, which obtained the highest accuracy, which was at a level comparable to the Root Mean Square Prop algorithm, with the latter algorithm having larger losses.

2

Prediction capabilities of the LSTM and Perceptron models based on the Day-Ahead Market on the Polish Power Exchange S.A.

Ruciński Dariusz

Studia Informatica : systems and information technology

|

2023

|

Vol. 1(28)

69--82

EN

The main purpose of the research was to examine the properties of models for two kinds of neural networks, a deep learning models in which the Long Short-Term Memory was chosen and shallow neural model in which the Perceptron Neural Network was chosen. The subject of the examination was the Day-Ahead Market system of PPE S.A. The article presents the learning results of both networks and the results of the predictive abilities of the models. The research was conducted based on data published on the Polish Stock Exchange for the 2018 year. The MATLAB environment was chosen as a tool for providing the examinations. The determination index (R2) and the mean square error (MSE) was adopted as the network evaluation criterion for the learning ability and for the prediction ability of both networks.

3

Analysis of a web application supporting gym management in terms of control and systems theory

Tchórzewski Jerzy, Nabiałek Wojciech, Księżopolski Artur

Studia Informatica : systems and information technology

|

2023

|

Vol. 1(28)

47--68

EN

An analysis of the web application supporting the management of the gym was carried out, which was designed in terms of the theory of control and systems. The obtained results of measurements of input and output quantities of selected subsystems were used to carry out the identification, as a result of which models of web application subsystems were obtained. On the basis of the obtained subsystem models, appropriate models were then designed in Simulink for the purposes of simulation and comparative studies of the behavior of subsystem models in relation to real systems that are web applications, including an appropriate analysis of the web application system model was carried out under the name of the gym on its selected subsystems, including in particular the subsystem called Generating a diet. In addition, testing and simulation studies were carried out to check the correct functioning of the web application management system model and the introduction of appropriate changes to the model was proposed, and the obtained research results were discussed, indicating the high accuracy of the obtained web application models.

4

The impact of the size of the training set on the predictive abilities of neural models on the example of the Day-Ahead Market System of TGE S.A.

Ruciński Dariusz

Studia Informatica : systems and information technology

|

2022

|

Vol. 1(26)

5--22

EN

The main object of the research was to examine the acceptable time horizon that could be predicted by previously learned models of the Day-Ahead Market (DAM) TGE S.A. system. The article contains the results of research on the predicting ability of different ANN models of the DAM TGE S.A. The research was conducted based on data covering the operation of the Polish stock exchange in the period from 2002 to 2019 (the first half of the year). The research was carried out based on the learned ANN models of the DAM system. Data were taken for examination covering the time from 2002 to 2019 (1st half of the year) and was divided into a different period, i.e., a month, a quarter, and a half-year., year, etc. The MSE, MAE, MAPE, and R2 were adopted as the criteria for assessing the ability of individual models to predict electricity prices. The research was carried out by successively expanding forecasting periods in a rolling manner. For example, for a half-year, prediction time intervals were increased from one week to month, two months, quarter, half-year, etc. results for a model representing a given period. A lot of interesting research results were obtained.

5

Neural model of the vehicle control system in a racing game. Part 2, Research experiments

Bolesta Arkadiusz, Tchórzewski Jerzy

Studia Informatica : systems and information technology

|

2022

|

Vol. 1(26)

45--60

EN

This article, which is a continuation of the article under the same main title and subtitle: part 1 Design and its implementation, includes the obtained results of research experiments with the use of a designed and implemented racing game. It uses a neural model of the vehicle motion control system on the racetrack in the form of a Perceptron Artificial Neural Network (ANN). In designing the movement of vehicles on the racetrack, the following were used, inter alia, Godot Engine and MATLAB and Simulink programming environment. The numerical data (14 input quantities and two output quantities) for ANN training were prepared with the use of semi-automatic measurement of the race track control points. This article shows, among others, the results of 10 selected research experiments, testing and simulation, confirming the correct functioning of both the computer game and the model of the neural control system. As a result of simulation tests, it turned out that the longest lap of the track in the conducted experiments lasted 4 minutes and 55 seconds, and the shortest - 10.47 seconds. In five minutes, the highest number of laps was 34, while the lowest numbers of laps were 1 and 5. In the course of the experiments it was noticed that under the same conditions the ANN learning outcomes are sometimes different.

6

Neural model of the vehicle control system in a racing game. Part 1, Design and its implementation

Tchórzewski Jerzy, Bolesta Arkadiusz

Studia Informatica : systems and information technology

|

2022

|

Vol. 1(26)

23--44

EN

The publication consist of two parts. Part 1 contains the results of research on the design, learning and implementation of the Perceptron Artificial Neural Network as a model of neural control of car movement on the racetrack. This part 1 presents the results of studies, including review of the methods used in video racing games from the point of view of the selection of a method that can be used in the own research experiment, selection of the Artificial Neural Network architecture, its teaching method and parameters for the intended research experiment, selection of the data measurement method to be used in ANN training, as well as development design of a car game, its implementation and conducting simulation tests. In designing the game of vehicle traffic on the racetrack, among others, Godot Engine game engine and MATLAB and Simulink programming environment. The numerical data (14 input quantities and two output quantities) for ANN training were prepared with the use of semi-automatic measurement of the race track control points. Part 2 shows i.a. the results of the testing and simulation experiments that confirm the correct functioning of both the game and the model of the neural control system. There were also shown, among others, the possibility of continuing research in the field of increasing the flexibility of the racing game, in particular the flexibility of the vehicle traffic control system through the use of other artificial intelligence methods, such as ant algorithms or evolutionary algorithms.

7

Neural model of human gait and its implementation in MATLAB and Simulink Environment using Deep Learning Toolbox

Tchórzewski Jerzy, Wielgo Arkadiusz

Studia Informatica : systems and information technology

|

2021

|

Vol. 1-2(25)

39--65

EN

The article presents selected results of research on the modeling of humanoid robots, including the results of neural modeling of human gait and its implementation in the environment MATLAB and Simulink with the use of Deep Learning Toolbox. The subject of the research was placed within the scope of the available literature on the subject. Then, appropriate research experiments on human movement along a given trajectory were developed. First, the method of measuring the parameters present in the experiment was established, i.e. input quantities (displacement of the left heel, displacement of the right heel) and output quantities (displacement of the measurement point of the human body in space). Then, research experiments were carried out, as a result of which numerical data were measured in order to use them for teaching and testing the Artificial Neural Network. The Perceptron Artificial Neural Network architecture was used to build a model of a neural human walk along a given trajectory. The obtained results were discussed and interpreted, drawing a number of important conclusions.

8

State-space model and implementation Polish Power Exchange in Matlab and Simulnk environments

Marlęga R.

Information Systems in Management

|

2017

|

Vol. 6, No. 4

294--308

EN

This work contains selected results of research on modelling identification of Polish Power Exchange (TGEE) on the example of the figures quoted on the Day Ahead Market (DAM) on TGEE in Poland. In order to obtain a model of the TGEE system on the beginning it was conducted to identify the figures for the period 01.01.2013-31.12.2015 obtaining discrete parametric model arx in MATLAB and Simulink environments using System Identification Toolbox (SIT). The resultant model was converted to a continuous parametric model, and that one on a continuous model in the state space. On the basis of obtained equations of state and outputs, there was interpreted a state variables and parameters of the selected model, i.e. selected elements of the matrix A and matrix B. Research continues.

9

Neural modeling of the electric power stock market in usage of MATLAB and Simulink tools for the day ahead market data

Ruciński D., Tchórzewski J.

Information Systems in Management

|

2016

|

Vol. 5, No. 2

215--226

EN

The work contains selected results of the modelling of neural Electric Power Exchange (EPE) in Poland. For modelling EPE system, artificial neural network (ANN) was constructed. ANN was learned and tested using of the next day market data. Generated neural model was used for simulation tests and susceptibility tests. Suitable model was implemented in Simulink. As a result of simulation tests and susceptibility testing a lot of interesting research results were obtained.

10

Identification modeling of Polish electric power exchange

Marlęga R., Tchórzewski J.

Information Systems in Management

|

2016

|

Vol. 5, No. 2

195--204

EN

This paper contains selected results of identification modeling of Polish Electric Power Exchange (EPE). In order to obtain EPE system model it was performed identification based on figures of EPEís Day-Ahead Market. During performing identification process, parametric arx model in System Identification Toolbox environment was utilized. Generated EPE parametric model has been further used for performing simulation tests and realization of susceptibility testing. Suitable models were implemented in Simulink software. As a result of simulation and susceptibility testing, many interesting findings has been delivered.

11

Modelowanie neuronalne rozwoju systemu elektroenergetycznego na bazie danych testowych IEEE RTS

Tchórzewski J., Roman P., Żurawski T.

Wiadomości Elektrotechniczne

|

2014

|

R. 82, nr 2

17--23

PL

Przedstawiono wybrane wyniki badań projektowania rozwoju systemu elektroenergetycznego za pomocą sztucznych sieci neuronowych.

EN

The paper presents selected results of research on designing the power electric system development using artificial neural networks.

12

Autopilot do śmigłowca bezzałogowego - program w środowisku Simulink

Janiec T., Romicki M., Butkiewicz B.

Prace Instytutu Lotnictwa

|

2008

|

Nr 3-4 (194-195)

117-123

PL

Badania i rozwój nad śmigłowcami autonomicznymi są obecnie szeroko zakrojone. Yamaha Motors dysponuje modelem, który jest używany komercyjnie głównie w spryskiwaniu obszarów rolnych. Celem niniejszej pracy wykonanej na Wydziale Elektroniki i Technik Informacyjnych Politechniki Warszawskiej w lnstytucie Systemów Elektronicznych, bylo opracowanie w środowisku Matlab-Simulink koncepcji autopilota dla śmigłowca bezzałogowego. Stanowila ona wstęp do obecnie rozpoczętej sprzętowej realizacji układu z mikroprocesorem. Zaprojektowano układ sterowania - kontroli lotu, mający za zadanie utrzymywanie śmigłowca w zawisie oraz wykonywanie prostych zadań, takich jak lot na zadaną wysokość i odległość oraz lądowanie. Autopilot zawiera układ sterowania i model śmigłowca zamknięte w pętlę sprzężenia zwrotnego. Układ sterowania zrealizowano w oparciu o logikę rozmytą, stosujac 6 regulatorów typu FPID. Układ sterowania jest typu regałowego, wykorzystujący bazę wiedzy opisującej działania konieczne do uzyskania poprawnego ruchu śmigłowca. Zalety takiego rozwiązania uwidaczniają się szczególnie w procesach słabo poznanych, w których opis matematyczny jest trudny, bądź skomplikowany lib niemożliwy do uzyskania. Matematyczny model śmigłowca musi uwzględniać dostatecznie dużo zjawisk tak, aby nie odbiegał on zbytnio od rzeczywistego zachowania obiektu. Model ten nie może być jednak zbyt skomplikowany ze względu na skończone możliwości obliczeniowe i konieczność spełnienia warunku pracy w czasie rzeczywistym. Wiarygodny model nieliniowy opracowano w NASA (Complexity Helicopter Math Model). Został on użyty do budowy autopilota śmigłowca Yamaha R-50, w prezentowanej pracy również skorzystano z modelu tego typu. Jako środowisko najbardziej odpowiednie ze wzgledu na możliwość realizacji i późniejsze testowanie wybrano oprogramowanie Matlab-Simulink. Przeprowadzono wiele testów weryfikujacych poprawność rozwiązania. Szczególnie badano zachowanie i stabilność śmigłowca po przyłożeniu skoków prędkości i skoku kątów Eulera, zarówno każdy oddzielnie, jak i równoczenie. Badano typowe zadania, jak wznoszenie na zadaną wysokość, zawis, ruch na zadaną wysokośc i odległość, lądowanie. Zarejestrowano wykresy położenia, predkości, kątów orientacji oraz sygnałów sterujących. Ponadto, specjalny program pozwala na wizualizację ruchu śmigłowca. Uzyskane rezultaty można uznać za dobre i spełniajace załozenia. Ze względu na tematykę pracy konieczne było nawiązanie współpracy z Wydziałem MEiL Politechniki Warszawskiej oraz Wojskową Akademią Techniczną.

EN

Research and development on autonomous helicopters are now a wide-ranging. Yamaha Motors has a model that is used commercially mainly in the areas of agricultural spraying. The purpose of this work done at the Department of Electronics and Information Technology of Warsaw University of Technology at the Institute of Electronic Systems, was to develop concepts for unmanned helicopter autopilot in Matlab-Simulink environment. It was the introduction to the current hardware implementation of the system working with a microprocessor. The flight control system was designed, with the task of maintaining the helicopter in hover and performing simple tasks, such as the flight to the given altitude and distance and landing. Autopilot contains the control system and a helicopter model in the closed loop feedback. A control system was implemented on the basis of fuzzy logic, using 6 regulators of FPID type. A control system is a rack type, using a knowledge base describing the actions necessary to obtain the correct helicopter movement. The advantages of such solution are particularly apparent in the weakly known processes, in which the mathematical description is difficult or complicated or impossible to obtain. Helicopter mathematical model must take into account sufficiently so much phenomena, that it has not diverged too much from the actual behavior of the object. The model can not be too complicated because of the finite computing possibilities and the necessery condition to perform in real time. Credible nonlinear model was developed at NASA (Complexity Helicopter Math Model). It has been used to build a Yamaha R-50 helicopter autopilot, in presented work the model of this type was also used. Matlab-Simulink software was selected as the most suitable for the task, because of the implementation possibility and subsequent testing. Numerous tests were performed for verifying the correctness of solution. In particular, were studied the helicopter behavior and stability after applying step of speed and step of Euler angles, both each separately and simultaneously. The typical tasks were studied, such as climb to the given altitude, hover, movement to given altitude and distance, landing. Were recorded graphs for position, velocity, orientation angles and the control signals. In addition, a special program allowed visualization of helicopter movement. The obtained results can be considered as good and satisfying the assumptions made. Given the themes of work, it was necessary to establish cooperation with the MEiL Department of Warsaw University of Technology and Military University of Technology.

13

Symulacja oddziaływania pieca łukowego na system energetyczny

Wciślik M., Kazała R.

Zeszyty Naukowe. Elektryka / Politechnika Łódzka

|

2001

|

z. 97

151--158

PL

W czasie pracy pieca łukowego występują szybkie zmiany obciążenia, powodujące powstawanie zakłóceń w sieci zasilającej. W efekcie występują zjawiska takie jak zmiany częstotliwości, migotanie napięcia w sieci zasilającej oraz generowanie wyższych harmonicznych. Mechanizmy powstawania tych zjawisk nie są w pełni określone. Na ich charakter może mieć wpływ praca układów regulacji urządzeń wytwarzających energię elektryczną oraz regulatorów posuwu elektrod pieca łukowego. Przy projektowaniu tych regulatorów powinno się uwzględniać interakcję między układami regulacji. Celem pracy jest określenie mechanizmów oddziaływania pieca na system zasilający. W tym celu zamodelowany został fragment systemu energetycznego wraz z piecem lukowym. Dla przedstawionego modelu przeprowadzone zostały badania symulacyjne w środowisku Matlab i Simulink, w których analizowano zachowanie systemu zasilania w trakcie pracy pieca.

EN

Fast changes of power of load during exploitation of an arc furnace cause formation of disturbances in power supply system. The phenomena such as frequency changes, voltage flickers and generating of higher harmonics appear in result. The formation mechanisms of the phenomena is not cleared. They may depend on work of automatic control devices of the energy electric generating units and elektrode position controllers of arc furnaces. The interactions between the control devices ought to be taken into account in designing of the electrode controlers. The explonation of the mechanisms of influence of arc furnace on supply system is the main purpose of the paper. The part of the power supply system with the arc furnace was modeled in the Matlab and Simulink environment. The simulation and investigation of behaviour of power supply system during electric steelmaking process were developed using the model.