|
|
Reservoir Computing for Industrial Applications
Brhel, Jakub ; Bražina, Jakub (referee) ; Kovář, Jiří (advisor)
In this bachelor thesis, the field of reservoir computing and its application in the industrial sector is investigated. The main objective of the thesis is to verify the effectiveness and accuracy of the echo state network method in time series prediction. To achieve this objective, a dataset from a manufacturing machine is used and the echo state network algorithm is implemented. The results are analysed and are also compared with the results of previous studies in the field of reservoir computing.
|
|
|
Development of Customized Signal Processing SW for dynamic analysis of engineering systems
Witassek, Tomáš ; Kovář, Jiří (referee) ; Lošák, Petr (advisor)
Aim of this thesis is to create a user interface for signal processing mostly in the area of dynamics. First part of this thesis describes the theory of acceleration and force sensors, A/D conversion and corresponding issues such as sampling, quantization and types of convertors. Following part provides a brief summary of National Instruments products for vibration measurement. Next part of this thesis deals with methods of signal processing such as Fourier transform, frequency response functions and experimental modal analysis. Software described in the last part of this thesis is created in LabVIEW enviroment.
|
|
| |
|
|
Character of Luboš Fišer's Work and Style of Composing, Taking into Account the Nature of Solo Piano Pieces
Kovár, Jiří ; Gregor, Vít (advisor) ; Tichá, Libuše (referee)
Title : The character of Lubos Fiser's work and his style of composing, taking into account the nature of solo piano pieces. Abstract : This paper "The character of Lubos Fiser's work and his style of composing, taking into account the nature of solo piano pieces", is focused on all of his pieces. The first part of Fiser's work falls within the artificial character and the second part focuses on the film, hence the incidental music. The main purpose of this thesis is to update and clarify Fiser's review of his complete achievements and composition style into the typological classification and the individual development throughout various creative stages. Consideration will be also given to the creation of solo piano pieces that illustrate and highlight specific features of Fiser's creative development. Characteristics of these pieces will be linked to their structure in the form and tectonics, with regard to the styling tools and related interpretive issues.
|
|
|
Magnetické pole v jádru Galaxie
Hamerský, Jaroslav ; Karas, Vladimír (advisor) ; Kovář, Jiří (referee)
In the present work we study the properties of accretion tori orbiting black hole. Our approach to this problem comes from the solving of general relativistic magnetohydrodynamic equations, which follow from conservation of the energy-momentum tensor, the particle number and from Maxwell's equations. We solve these equations by numerical methods which are described in Chapter 1. The formalism of tori which we consider here is described in Chapter 2. We are interested in tori with constant density of angular momentum and Fishbone-Moncrief tori mainly. We study accretion rates in these tori when the mass of black hole is increased suddenly and so the equilibrium in the torus is corrupted. For tori with constant density of angular momentum we study the influence of the presence of toroidal magnetic field on accretion rates.
|
|
| |
|
|
Artificial Intelligence and Industry 4.0
Kotas, Filip ; Kroupa, Jiří (referee) ; Kovář, Jiří (advisor)
This bachelor thesis deals with search for artificial intelligence methods used in the diagnostics of technical systems. The first part of the work is devoted to the search of used methods in the field of diagnostics of technical systems. The second part summarizes the characteristics and applications of these methods. The conclusion of the thesis deals with the application of the artifical neural network method and the hybrid method „adaptive neuro-fuzzy inference systém“, which is based on the neural network. This part deals with a detailed description and use of these methods in real technical systems.
|
|
|
Illustrative Example of Model-Based Design for Complex Aircraft Systems
Sopoušek, Radek ; Kovář, Jiří (referee) ; Janák, Luděk (advisor)
This bachelor's thesis is on the development of aviation systems, in particular their software, using model-based design (MBD) methods while maintaining recommended practices developed by the aviation industry and certification authorities (in particular RTCA DO-178C/331). The general MBD deployment options given by current aviation regulators and standards are described in the theoretical part of the work. Furthermore, this work describes what the process of developing software for a sub-segment of an aircraft system (altitude hold mode of autopilot software) could look like using the model-based design method. The overlap to the system development level (SAE ARP 4754A) is also partially addressed. The work includes an illustrative example in which system requirements were specified, software development through "Design model" and ensuring traceability between system requirements and model design.
|
|
| |
|
|
Using artificial intelligence to monitor the state of the machine
Popara, Nikola ; Bražina, Jakub (referee) ; Kovář, Jiří (advisor)
This thesis is focus on monitoring state of machine parts that are under the most stress. Type of artificial intelligence used in this work is recurrent neural network and its modifications. Chosen type of neural network was used because of the sequential character of used data. This thesis is solving three problems. In first problem algorithm is trying to determine state of mill tool wear using recurrent neural network. Used method for monitoring state is indirect. Second Problem was focused on detecting fault of a bearing and classifying it to specific category. In third problem RNN is used to predict RUL of monitored bearing.
|
guest ::
