|
|
Increase of efficiency of a single phase induction machine
Muczka, Vojtěch ; Klíma, Jiří (referee) ; Mach, Martin (advisor)
This thesis is dedicated to efficiency increase of one phase induction machine through material change of induction cage and rotor slot shape optimization under the condition of maintaining the same locked-rotor torque. In the first part of this thesis is the explanation of induction machine principles. Next is the comparison of measured and simulated parameters of small one phase machine from ATAS company. The following part is dedicated to the analysis of rotor slot shape and ring size influence on machine parameters when using pure aluminum instead of resistive alloy. The next chapter deals with slot shape optimization in the program RMxprt, controlled by genetic algorithm written in MATLAB interface. In the final part are the resultant slot shapes simulated in Ansys Maxwell using finite element method and then the measured, simulated and expected parameters are compared.
|
|
|
Recognition of emotions in Czech texts
Červenec, Radek ; Smékal, Zdeněk (referee) ; Burget, Radim (advisor)
With advances in information and communication technologies over the past few years, the amount of information stored in the form of electronic text documents has been rapidly growing. Since the human abilities to effectively process and analyze large amounts of information are limited, there is an increasing demand for tools enabling to automatically analyze these documents and benefit from their emotional content. These kinds of systems have extensive applications. The purpose of this work is to design and implement a system for identifying expression of emotions in Czech texts. The proposed system is based mainly on machine learning methods and therefore design and creation of a training set is described as well. The training set is eventually utilized to create a model of classifier using the SVM. For the purpose of improving classification results, additional components were integrated into the system, such as lexical database, lemmatizer or derived keyword dictionary. The thesis also presents results of text documents classification into defined emotion classes and evaluates various approaches to categorization.
|
|
| |
|
|
Proposal of Traffic Management in Smart Cities
Schimmer, Jiří ; Mašek, Pavel (referee) ; Fujdiak, Radek (advisor)
Thesis deals with parts of telemetry in traffic, functionality of these parts and their effectiveness and improvement. Thesis also includes simulation environment of four crossroads and implemented responsive Dijkstra´s algorithm for searching the shortest path. In simulation environment are setup static values of the intervals on traffic lights. There is also implemented genetic algorithm, which is in part of optimization looking for more accurate timing solution for different amount of cars.
|
|
|
Genetic Algorithm Acceleration Using OpenCL
Hrušovský, Marek ; Šimek, Václav (referee) ; Jaroš, Jiří (advisor)
Tato práce se zabývá problematikou urychlování genetických algoritmů a hned v úvodu nastiňuje možnosti využití genetických algoritmů v praxi. V první kapitole je detailně rozebrán princip fungování genetického algoritmu. Tato kapitola se dále zabývá možnostmi zákódování problému, který je použit pro běh genetického algoritmu. Konkrétně je vzpomenuto binární zakódování jedince, celočíselné zakódování jedince, neceločíselné zakódování jedince a permutační zakódování jedince. Pro každý typ zakódování jsou dále představeny genetické operátory mutace, křížení a selekce. Důraz je kladen na permutační genetické operátory OX a PMX. Další kapitola se zabývá možnostmi paralelizace genetického algoritmu. Další kapitola představuje nový standard jménem OpenCL, který umožňuje snadnou paralelizaci výpočtú s využitím různých typů procesorů v ten samý čas. OpenCL taktéž zjednodušuje programování pro grafické karty. Další kapitola navrhuje možnost, jak urychlit výpočet genetického algoritmu s využitím grafické karty a jazyka OpenCL. Pro urychlení byl zvolen permutační genetický algoritmus "problém N-dam", který je náročný na paměť grafické karty. Tato kapitola rozebírá technické specifikace grafické karty, které jsou nevyhnutelné k určení maximální velikosti šachovnice. V kapitole je analyzována správná práce s pamětí grafické karty, která je nevyhnutelná k dosažení urychlení zvoleného genetického algoritmu. Jsou zde taky nastíněny dva generátory náhodných čísel, které jsou součástí testů. Následující kapitola detailně popisuje fungování navržené paralelizace genetického algoritmu. Jsou zde porovnány dvě metody evaluace jedince a je popsán způsob testování a vyhodnocování výsledků. Předposlední kapitola porovnává časovou náročnost generátorů náhodných čísel. Bylo zjištěno, že generátor HybridTaus je o 20 rychlejší o proti generátoru XORshift na GPU. Na CPU byl naopak rychlejší generátor XORshift. Generátor XORshift je na GPU 20 krát rychlejší a generátor HybridTaus je dokonce až 80 krát rychlejší. Dále byly porovnány evaluační funkce. Bylo zjištěno, že GPU běh je 800 krát rychlejší oproti běhu na CPU. Paměťově náročná evaluační metoda byla schopná dosáhnout jenom dvojnásobné zrychlení. Kapitola dále porovnává funkce křížení. PMX dosáhlo zrychlení maximálně o 100 a i to v případech, které nejsou atraktivní pro řešení problému N-dam (N>20). V případe OX je možné dosáhnout zrychlení až o 1100. Také v tomto případě jsou atraktivní hodnoty pouze do 500. Testy, které vyhodnocují běh celého GA, ukázaly, že GPU verze je zhruba dvojnásobně rychlejší. Malé zrychlení bylo způsobeno operátorem selekce a funkcí křížení.
|
|
|
Evolutionary Optimisation of Analogue Circuits
Mihulka, Tomáš ; Zachariášová, Marcela (referee) ; Bidlo, Michal (advisor)
The aim of this work was to create a system for optimisaton of specific analog circuits by evolution using multiple fitness functions . A set of experiments was run, and the results analyzed to evaluate the feasibility of evolutionary optimisation of analog circuits . A requirement for this goal is the study and choice of certain types of analog circuits and evolutionary algorithms . For the scope of this work , amplifiers and oscillators were chosen as target circuits , and genetic algorithms and evolutionary strategies as evolutionary algorithms . The motivation for this work is the ongoing effort to automate the design and optimisation of analog circuits , where evolutionary optimisation is one of the options .
|
|
|
Evolutionary Design of Collective Communications Accelerated by GPUs
Tyrala, Radek ; Dvořák, Václav (referee) ; Jaroš, Jiří (advisor)
This thesis provides an analysis of the application for evolutionary scheduling of collective communications. It proposes possible ways to accelerate the application using general purpose computing on graphics processing units (GPU). This work offers a theoretical overview of systems on a chip, collective communications scheduling and more detailed description of evolutionary algorithms. Further, the work provides a description of the GPU architecture and its memory hierarchy using the OpenCL memory model. Based on the profiling, the work defines a concept for parallel execution of the fitness function. Furthermore, an estimation of the possible level of acceleration is presented. The process of implementation is described with a closer insight into the optimization process. Another important point consists in comparison of the original CPU-based solution and the massively parallel GPU version. As the final point, the thesis proposes distribution of the computation among different devices supported by OpenCL standard. In the conclusion are discussed further advantages, constraints and possibilities of acceleration using distribution on heterogenous computing systems.
|
|
|
Evolutionary Design of Moving Objects
Baláž, Martin ; Žaloudek, Luděk (referee) ; Bidlo, Michal (advisor)
This thesis deals with the utilization of evolutionary techniques to find such environment characteristics, that allow the object in this environment to perform the movement according to specified parameters. The environment which is utilized in this work is a cellular automaton, whose local transition function is optimized using the genetic algorithm. The principles of computational development are applied. The presented work tends to the area of theoretical biology. Its main objective is to create a simple simulator of life of artificial organisms. In particular, movement as a specific aspect of life is considered. For this purpose the application allows the designer to define an organism at the level of cells of the cellular automaton and apply the genetic algorithm to design the transition function specifying the behavior of the organism according to given parameters.
|
|
|
New Evolutionary Algorithms for Designing Cellular Automata
Ormandy, Adam ; Zachariášová, Marcela (referee) ; Bidlo, Michal (advisor)
This thesis describes an evolutionary design of state-transition functions in cellular auto- mata built on conditionally matching rules. It presents a new algorithm ESP and its com- parison with already existing evolutionary techniques, specifically the evolutionary strategy and genetic algorithm. Chosen Case studies include self-replicating structures, moving ob- jects and development of patterns.
|
|
|
Optimization by means of metaheuristics in Python using the DEAP library
Kesler, René ; Charvát, Pavel (referee) ; Klimeš, Lubomír (advisor)
{This thesis deals with optimization by means of metaheuristics, which are used for complicated engineering problems that cannot be solved by classical methods of mathematical programming. At the beginning, choosed metaheuristics are described: simulated annealing, particle swarm optimization and genetic algorithm; and then they are compared with use of test functions. These algorithms are implemented in Python programming language with use of package called DEAP, which is also described in this thesis. Algorithms are then applied for optimization of design parameters of the heat storage unit.
|
guest ::
