|
|
Extension of Centrifugal Compressor Operational Stability
Růžička, Miroslav ; Třetina, Karel (referee) ; Kmoch, Petr (referee) ; Klement, Josef (advisor)
Centrifugal compressors with high pressure ratio are widely used in small aircraft turbine engines and turbocharges. At high rotational speeds they have narrow stable operating region and commonly used impellers with back swept blades are not able to ensure requested stability. In order to achieve wider stable operating region, some other anti-surge measures can be used, such as an Internal Recirculation Channel (IRC) located in compressor impeller inlet. This thesis deals with an investigation of IRC influence on centrifugal compressor operational parameters. As a first, the various recirculation channel geometry was studied by using of CFD analysis on simplified computational models. Those geometry, which indicated best results in terms of mass flow and looses in channel were used for testing on a model test device. Subsequently the same geometry was tested on real centrifugal compressor in experimental turbine engine to verify influence of IRC on compressor performance map – pressure ratio and efficiency. Simultaneously the CFD analyses of IRC with a 3D model of compressor impeller were performed and results compared with those, gained from measurement on model and compressor. In addition the measurement of flow field downstream the recirculation channel outlet slot with using of 3-hole pressure probe was performed and compared with flow velocity profiles evaluated from numerical simulations.
|
|
|
Analysis of Classification Methods
Juríček, Jakub ; Zendulka, Jaroslav (referee) ; Burgetová, Ivana (advisor)
This work deals with the classification methods used in the knowledge discovery from data process and discusses the possibilities of their validation and comparison. Through experiments, the work focuses on the analysis of four selected methods: Naive Bayes classificator, decision tree, neural network and SVM. Factors influencing basic characteristics such as training speed, classification speed, accuracy are examined. A part of the thesis is a desktop application, which is a tool for training, testing and validation of individual methods. Eleven reference data sets are selected for experimental purposes. At the end of this work experimental results of comparison and observed characteristics of classification methods are summarized.
|
|
|
Automatic Photography Categorization
Veľas, Martin ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This thesis deals with content based automatic photo categorization. The aim of the work is to create an application, which is would be able to achieve sufficient precision and computation speed of categorization. Basic solution involves detection of interesting points, extraction of feature vectors, creation of visual codebook by clustering, using k-means algorithm and representing visual codebook by k-dimensional tree. Photography is represented by bag of words - histogram of presence of visual words in a particular photo. Support vector machines (SVM) was used in role of classifier. Afterwards the basic solution is enhanced by dividing picture into cells, which are processed separately, computing color correlograms for advanced image description, extraction of feature vectors in opponent color space and soft assignment of visual words to extracted feature vectors. The end of this thesis concerns to experiments of of above mentioned techniques and evaluation of the results of image categorization on their usage.
|
|
|
Mobila Application Supporting Time Orientation for People with Autism
Deák, Jaromír ; Chrápek, David (referee) ; Beran, Vítězslav (advisor)
The aim of the project is to design graphical user interface, which helps autistic people with time orientation. The devised user interface follows the rules of Structured education. The main components of the mobile application are mobile schedule and digital clock accompanied by a story. Final user interface was tested by real users, who used the experimental application. Developed experimental application has been used for testing by real users. The tests offer important result: under the supervision, the autistic users are able to utilize the application. The utilisation of clock accompanied by a story is partly verified so far. The important finding is, that after some training, the designed and developed application is exploitable for autistic people.
|
|
|
Automatic Photography Categorization
Veľas, Martin ; Řezníček, Ivo (referee) ; Španěl, Michal (advisor)
This thesis deals with content based automatic photo categorization. The aim of the work is to experiment with advanced techniques of image represenatation and to create a classifier which is able to process large image dataset with sufficient accuracy and computation speed. A traditional solution based on using visual codebooks is enhanced by computing color features, soft assignment of visual words to extracted feature vectors, usage of image segmentation in process of visual codebook creation and dividing picture into cells. These cells are processed separately. Linear SVM classifier with explicit data embeding is used for its efficiency. Finally, results of experiments with above mentioned techniques of the image categorization are discussed.
|
|
|
Monitoring equipment for fermentation processes using the thermodynamic sensors
Jáneš, Pavel ; Búran, Martin (referee) ; Adámek, Martin (advisor)
The bachelor's thesis is focused on the design and implementation of a prototype device that is to be used to monitor fermentation processes in the food industry using thermodynamic sensors. The work contains a brief description of fermentation processes in the food industry and also possible methods of their monitoring. It also deals with the principle of the thermodynamic sensor and the description of the ESP32 microcontroller, which is the core of the prototype. Subsequently, it deals with the design of a prototype, including a program for ESP32, which is able to monitor the fermentation process using a pair of thermodynamic sensors and send the measured data to the cloud service ThingSpeak, to a personal computer or store them in Flash memory. Furthermore, the work deals with testing in experimental measurements, in which fermentation processes were monitored with the prototype.
|
|
|
Analysis of training dataset influence on the efficiency of segmentation
Benešovská, Veronika ; Vičar, Tomáš (referee) ; Jakubíček, Roman (advisor)
Microbial structures are present in every living organism, so it is important to classify them for subsequent research of their origin and function. Bruker, s.r.o is developing the MBT Pathfinder for this purpose, which automates the transfer of colonies to MALDI plates, where the subsequent analysis of the sample takes place. Transferred colonies can be selected manually or using an algorithm that ensures automatic colony segmentation. This algorithm must be learned on a training set, which has huge influence on its accuracy. This work deals with measuring the influence of a dataset on the accuracy of this learning algorithm.
|
|
|
Inquiry-based science club for children
Šulcová, Alena ; Čapek Adamec, Martin (advisor) ; Blažková, Veronika (referee)
This Bachelor thesis is dealing with the use of research-oriented teaching during hobbies as part of leisure activities in the field of natural sciences, especially chemistry. Nowadays is noticeable trend to start with research activities and building relation to natural and technical sciences at very young age of students. In the theoretical part the thesis describe principles and forms of research-oriented teaching and their realization, lecturer qualification conditions and work safety during the experiments in the hobby, development of students potential during younger school age, specifics of this students period and characterizes leisure activities in detail and their delineation in relation to formal education. Part of the practical part is a local survey of the accessibility of research-oriented clubs in the Polepy and Libochovice districts. The empirical part contains verified proposals for five meetings of the science-oriented research group for students of younger school age. The preparation allows both: face-to-face and distance form and indicates the availability and price budget of the material, the risks and the safety of working with tools, the clearly stated goal of each meeting and a detailed description of the students research-oriented activities, including questions and...
|
|
|
Classification with Use of Neural Networks in the Keras Environment
Pyšík, Michal ; Burgetová, Ivana (referee) ; Bartík, Vladimír (advisor)
Tato práce zkoumá problematiku klasifikace pomocí umělých neuronových sítí s využitím knihovny Keras, poskytující vysokoúrovňové rozhraní pro práci s umělými neuronovými sítěmi v programovacím jazyce Python. Cílem práce je prozkoumat rozsáhlé možnosti této knihovny v oblasti klasifikace a porovnat různé typy a topologie umělých neuronových sítí formou experimentů na vybraných datasetech, což je doplněno jednoduchou experimentální aplikací sloužící především jako rozhraní pro tyto experimenty.
|
|
|
Allelopathy of aquatic plants and its possible application to control cyanobacterial blooms
Kolářová, Anna ; Jandová, Kateřina (advisor) ; Kučerová, Andrea (referee)
The excessive growth of phytoplankton and the development of water bloom leading to the damage to aquatic ecosystems are becoming a more and more frequent problem. There are many methods to control the water bloom from which mainly those that use interactions of living organisms have been developing lately, with the utilisation of aquatic plant allelopathy being one of them. Allelopathy is a type of relationship between two organisms when one of them influences the other by secreting allelopathically active compounds in the environment. However, the effect of these secondary metabolites depends on many biotic and abiotic factors, which also has consequences for their potential use to control the water bloom. Although the results of many studies suggest that allelopathy can affect the community of phytoplankton, its role in aquatic ecosystems is still unclear. This thesis summarizes the knowledge about the occurrence of allelopathy among aquatic organisms, the modes of action of allelochemicals and the impacts of the key factors influencing the allelopathic effect. At the same time, it evaluates the prospects of using the allelopathy of aquatic plants to control water bloom and reviews experimental approaches to studying allelopathic interactions.
|
guest ::
