|
|
Data Analysis for Predictive Maintenance of a Robotic Arm
Žitný, Roland ; Rozman, Jaroslav (oponent) ; Janoušek, Vladimír (vedoucí práce)
The Mitsubishi MELFA robotic arms used in modern factories work almost without interruption and produce sensory data about their operation. Various analysis techniques can be applied to such data for predictive maintenance, which provide information on the condition and maintenance needs of such robotic arms. The proposed predictive maintenance process consists of a sensory data acquisition system using the slmpclient and mitsubishi-monitor libraries, an analysis method system with anomaly detection using a convolutional autoencoder, anomaly classification using convolutional neural networks, and data segmentation into segments of individual robot actions using hidden Markov models. Such analysis techniques provide information on the severity, type, and location of emerging faults and abnormalities in behavior, which then determine the time required to perform the required maintenance. This work presents a created chain of predictive maintenance processes, where the obtained findings provide valuable insights into the application of predictive maintenance of Mitsubishi MELFA robotic arms in an industrial environment.
|
|
| |
|
|
Code Generation from Object Oriented Petri Nets
Cibák, Michal ; Janoušek, Vladimír (oponent) ; Kočí, Radek (vedoucí práce)
The goal of this thesis is to analyze the current solution of a code generator from Object oriented Petri nets written in PNtalk language to Java language, propose changes and implement them. First the overall scheme was analyzed and missing parts were specified, then the source code of the compiler was analyzed and errors were found. After implementing the fixes for these errors, it was proposed to modify the compiler and simulator such that the missing functionality was supported. These changes were implemented.
|
|
|
Sequence Diagram Generation from Object-Oriented Petri Nets
Beňo, Adam ; Janoušek, Vladimír (oponent) ; Kočí, Radek (vedoucí práce)
The thesis focuses on the issue of sequence diagram generation from scenarios modelled by object-oriented Petri nets (OOPN). It aims on module implementation into existing OOPN editor which enables showing sequence diagrams from individual simulations and is connected with simulated model. The user thus gets complete overview of the simulation process and is able to detect errors in OOPN models.
|
|
|
City Traffic Simulator for Web
Kováč, Kristián ; Janoušek, Vladimír (oponent) ; Rozman, Jaroslav (vedoucí práce)
The goal of this thesis is to create a city traffic simulator, which visualizes its results on a web interface. Information about the traffic network is obtained from the OpenStreetMap project. The simulation is based on a microscopic model and focuses mainly on the Brno - Střed area. Vehicles are modeled as separate entities that communicate with each other and follow the traffic rules. The thesis describes the basic principles of traffic modeling and simulation. It also deals with some existing microscopic traffic simulators and their properties. The second part of the thesis describes the design and implementation of the created application. It focuses mainly on the description of OpenStreetMap data processing, vehicle model, structure of simulation results and their visualization on a web interface.
|
|
|
UWB Locator
Jančiar, Marek ; Kočí, Radek (oponent) ; Janoušek, Vladimír (vedoucí práce)
The subject of this work is the implementation and evaluation of the parameters of the localization system using UWB technology. This work focuses on two localization methods, namely TWR and TDoA. To compare the capabilities of UWB with other wireless techno- logy, this work also includes an implementation using BLE technology, specifically a method that uses the RSSI value. Parameters such as the accuracy or energy consumption of the implementation of these methods on specific hardware were practically measured and in- corporated into the text of this work. With the help of this work, the reader can create an image of the capabilities of the mentioned technologies and the way of implementing the localization methods.
|
|
|
Vizualizace neuroevoluce při učení neuronových sítí
Bednář, Martin ; Janoušek, Vladimír (oponent) ; Zbořil, František (vedoucí práce)
Tato práce zkoumá možnosti učení neuronových sítí za pomoci neuroevolučních algoritmů, zabývá se obecným fungováním neuroevoluce, návrhem a implementací neuroevolučích algoritmů a okrajově i návrhem a implementací dopředných neuronových sítí s plně propojenými vrstvami. Výsledkem práce je program, který provádí neuroevoluční algoritmus a grafická aplikace, která tento program zapouzdřuje pro snadnější používání a která slouží pro zobrazení grafického výstupu programu vizualizujícího řešení konkrétního problému pomocí vytvořených neuronových sítí učených pomocí neuroevoluce. Závěr práce je věnován experimentům nad vytvořeným programem.
|
|
|
Test Suite of the EAS Framework
Mazáková, Júlia ; Janoušek, Vladimír (oponent) ; Smrčka, Aleš (vedoucí práce)
This work focuses on the software testing of the system with an emphasis on lower layers of testing, which includes unit and integration testing. The primary objective is to showcase the testing process using the EAS (Effective Agenda System) framework, starting with the test plan process followed by the creation of the final test suite that will evaluate the performance of the system's backend microservices. This test suite covers a significant part of the system's functionality. The results are stored and analyzed in the final test report. Performed analysis of the system and the final suite serve as valuable assets in the context of testing.
|
|
|
Nástroj pro editaci a běh řídicích panelů pro IoT aplikace
Ryška, Andrej ; Peringer, Petr (oponent) ; Janoušek, Vladimír (vedoucí práce)
Táto bakalárska práca sa zaoberá rozborom stávajúcich otvorených (open source) riešení systémov pre IoT zariadenia so zameraním na prezentáciu, spracovanie a manipuláciu s dátami cez užívateľské rozhranie webovej aplikácie. Cieľom tejto práce je na základe analýzy vytvoriť vlastné riešenie chytrej domácnosti, preferujúce jednoduchosť konfigurácie a užívateľskú prívetivosť. Vytvorená aplikácia bude prepojiteľná so systémami Node-RED, Domoticz a Home Assistant na základe spoločného MQTT brokera, z ktorého bude aplikácia čerpať dáta a manipulovať so stavmi jednotlivých IoT zariadení.
|
|
|
Deep Learning Methods for Machine Playing the Scotland Yard Board Game
Hrkľová, Zuzana ; Janoušek, Vladimír (oponent) ; Zbořil, František (vedoucí práce)
This theses concerns with deep learning methods applied to machine playing board games containing movement uncertainty. Reinforcement learning principles with main focus on Q-learning algorithms were studied, among which Deep Q--Network had been chosen and applied on simplified rules of the Scotland Yard board game. The final implementation was put to test against Alpha-Beta and Monte Carlo Tree Search. The results have shown that the hider driven by DQN represented the hardest opponent for the other two methods, while the DQN seekers did not manage to surpass past results. Although the implemented method did not reach better results than currently known methods, it proved to be the least demanding when considering computational resources and time needed to perform a given move, making it the most perspective to implement on original version of the game in the future.
|
host ::
RSS.