|
|
Modern vibrodiagnostics of machines and evaluation of datasets by neural networks
Koníček, Tomáš ; Holoubek, Tomáš (referee) ; Hammer, Miloš (advisor)
This Master‘s thesis focuses on technical diagnostics with an emphasis on vibrodiagnostics of machines and equipment. The aim is to carry out research on vibration monitoring using modern on-line systems and to investigate the possibilities of processing the acquired data files using neural networks. Vibration monitoring from Siemens SIPLUS CMS is analyzed, including a description of individual hardware and software components. The work also focuses on machine diagnostics using a real model equipped with the SIPLUS CMS system in cooperation with the SIMATIC S7-1200 programmable automaton. The obtained data will be transferred via the FTP protocol for further processing in the Matlab program. Neural network models will be designed and used, which will be trained on the measured data. Convolutional neural network model will be used. The results will be evaluated and a conclusion will be drawn.
|
|
| |
|
|
Modelled pressure pulsations in a fluid with the influence of a second viscosity
Dzjamko, Vladislav ; Pochylý, František (referee) ; Habán, Vladimír (advisor)
The aim of this thesis is to determine the value of the speed of sound and the second dynamic viscosity of the fluid using numerical optimization of analytical model. Theoretically, the speed of sound and the second viscosity can be determined from three measured pressure waveforms in time along the length of the tube, while the speed of sound is traced to determine the correctness of the result. The thesis is divided into seven successive chapters. The first two define all the necessary concepts and the 1D analytical model used. The following chapters deal with the design of the experiment, data evaluation and numerical optimization of the search parameters in the frequency domain.The range of measured frequencies was from 1 kHz to 20,59 kHz. Einstein´s notation is used this this thesis. All graphs associated with the analytical model and the evaluation of the results are created in Matlab. The optimization functions fminsearch and lsqnonlin are used to evaluate the speed of sound and the second viscosity, however the fminsearch function overestimates the magnitude of the second viscosity. The thesis includes the calculation of the problem using Ansys and the subsequent comparison of all results.
|
|
|
Automating the search for abnormalities from tomographic data
Semerák, Petr ; Zemek, Marek (referee) ; Bazala, Jiří (advisor)
Předložená diplomová práce se zabývá automatizací procesu skenování a vyhodnocování abnormalit gascoolerů, které vznikají při jejich výrobě. Nedestruktivní testování využívá technologii CT skenování jejímž výstupem jsou obrazová data. Cílem práce je nahradit zdlouhavý proces ručního procházení dat spolehlivou algoritmizovatelnou metodou a ověřit, zda je tento směr vývoje perspektivní. V teoretické části se práce zabývá chladícími systémy v automobilech, nedestruktivním testování s těžištěm v CT technologii a rešerší softwarů pro prohlížení a analýzu CT dat. Praktická část diplomové práce se zaměřuje na problematiku ucpaných kanálků gascoolerů. Jsou popsány příčiny vzniku této abnormality, dosavadní přístup k jejímu odhalení a nový automatický přístup kontroly. Navržený algoritmus spolu s aplikaci vytvořenou pomocí Matlabu jsou testovány na konkrétních datech. Spolehlivost výsledků je v závěru porovnávána ručním hodnocením CT snímků. Pro hodnocení kvality obrazových dat je trénována hluboká neuronová síť.
|
|
|
Water Surface Visualization
Kliš, Michal ; Vlnas, Michal (referee) ; Starka, Tomáš (advisor)
The aim of this work is to investigate and implement methods for real-time simulation and visualization of large water bodies. The knowledge gained from the research is further exploited in the implementation of a specific application used for ocean simulation. Among the methods discussed is the spectral method. The text will offer the reader, in addition to the actual introduction to this method, various insights to focus on in its implementation.
|
|
|
Automatic detection of ischemia in ECG
Noremberczyk, Adam ; Potočňák, Tomáš (referee) ; Ronzhina, Marina (advisor)
This thesis discusses the utilization of the artificial neural networks (ANN) for detection of coronary artery disease (CAD) in frequency area. The first part of this thesis is orientated towards the theoretical knowledge. Describes the issue of ECG pathological changes. ECQ are converted to frequency area. Described statistical methods and methods for automatic detection of CAD and MI. Explained the issue of the perceptron and ANN. The second deals with use of Neural Network Toolbox MATLAB®. This part focuses on counting and finding suitable parameters and making connection of band. At the end of the thesis UNS is used to detect ischemic parameters and the results are discussed. Average values for the best settings are 100% accuracy.
|
|
|
Dynamic properties of tuned branch
Čepl, Ondřej ; Kůrečka, Jan (referee) ; Habán, Vladimír (advisor)
The main part of the thesis is experimental determination of transmission in side-branch resonator. In first part are described basics of digital signal processing and sound damping in piping systems. A special attention is payed to Fourier transform. The second part deals with experimental measurement of damping in a side-branch resonator for several lengths of the resonator. The collected data were analyzed using Fourier transform with a fulfilled coherence condition. At the end of this section are shown graphs, which describe tuning frequency dependence of side-branch resonator's length. There are seven different lengths. The thesis contains comparison of theoretical and measured tuning frequencies.
|
|
|
Smart Sheet Music Reader for Android
Smejkal, Vojtěch ; Herout, Adam (referee) ; Szőke, Igor (advisor)
Oblasti jako automatické otáčení stránek nebo automatický hudební doprovod jsou studovány již několik desetiletí. Tato práce shrnuje současné metody pro počítačové sledování not v reálném čase. Zabývá se také hudebními příznaky jako jsou chroma třídy a syntetizované spektrální šablony. Dále popisuje klíčové části systému jako krátkodobou Fourierovu transformaci a Dynamické borcení času. V rámci projektu byl navrhnut a vyvinut vlastní systém pro sledování pozice hráče v notách, který byl následně implementován jako mobilní aplikace. Výsledný systém dokáže sledovat i skladby s výrazně odlišným tempem, pauzami během hry nebo drobnými odchylkami od předepsaných not.
|
|
|
The Spectrum analysis of different types of saxophones
Greiplová, Barbora ; Mojdl, Edgar (referee) ; Jirásek, Ondřej (advisor)
The bachelor thesis deals with the sound of three types of Yamaha saxophones, specifically soprano, alto and tenor saxophone. Lists the basic parameters of the instrument, how it forms the tone and how it is typical. It focuses on characteristics in its tone using spectral analysis, LPC analysis and directional characteristics. The work focuses on the common properties of saxophones as instruments, it also looks for differences between selected types of saxophones and between individual tones. The results are compared in graphs, tables and verbal evaluation.
|
|
| |
guest ::
