|
| |
|
| |
|
|
Computational modelling of thermal behavior of DC motor
Grepl, Robert ; Wierciak, J. ; Vlach, R.
The paper deals with computational modelling of thermal behavior ofdrive system with DC motor. Motivation to built dynamical thermal model is toincrease utility value performance of electrical motor in particular roboticapplication. There is mathematical model presented in the paper, describedidentification of parameters process and shown results for two kind ofidentification approaches. Usage of neural networks approximators ismentioned.
|
|
|
Thermal modelling of DC motor for controled torque overloading
Grepl, Robert ; Vlach, R. ; Kratochvíl, Ctirad
The paper deals with the application of the thermal nets theory for thermalmodelling of DC motor. There is considered particular drive system -electromechanical servo for quadruped robot. Mathematical model is described,methodology of experiment came up and results are discussed. Parameters ofmodel are identified and possible applications of resultant model are given.Computer analysis are performed in Matlab.
|
|
| |
|
| |
|
|
Comparison of approaches to creating credit scoring models
Hofman, Elena ; Šedivý, Jan (advisor)
This work is focused on the management of a credit risk related to the traditional bank lending business to individuals. The paper deals with a theory of measuring risk with help of PD (Probability of Default) parameter when different scoring models are used. The goal is to outline an issue with the credit risk and its management in general, attention is paid to details of a process of creating scoring models. There are three specific modeling techniques listed, namely logistic regression, decision trees and neural networks. Methods are explained in detail and are given possibilities of mutual comparison. The application part is devoted to the evaluation and comparison of credit scoring models based on these methods.
|
|
|
History and Development of Artificial Inteligence
Kraitz, Petr ; Jirků, Petr (advisor) ; Berka, Petr (referee)
This work describes relatively short history of the field of Artificial Intelligence. It contains main obstacles and challenges, which scientists in the past and present solved and still have to solve, as well as a description of methods how to deal with those challenges and which possibilities are there for the future development of the field. The main focus of the work was not to present a full picture of the field of Artificial Intelligence, but to introduce this interesting field, its founders and nowadays scientists, main problems and related disciplines of science. The work is divided into chapters describing the history of the field artificial intelligence in the last century and related fields of informatics, biology, psychology, economy and hardware technology. Next chapter presents to the reader the main problems of the field, which were and still are being solved in the top research and development laboratories in the world. Next two chapters introduce two approaches to dealing with said problems, namely neural networks and evolutional algorithms and expert systems as an example of the oldest application of Artificial Intelligence in "Good Old-fashioned Artificial Intelligence" way as defined by John Haugeland. The last chapter is just an outline how the next few years in the filed may look like and what can we await in the next years.
|
|
|
Economical models realized by neural network GMDH type
Beneš, Vratislav ; Jablonský, Josef (advisor) ; Hrabčák, Petr (referee)
This diploma thesis is about design and realization of neural network MIA GMDH for ekonomical modelling by inductive method. Models are compared with statistical methods by quallity and usebility degree. An application was developed for verification of functionality on experiments. The same experiments were run in econometrical software. The results were compared. The MIA GMDH is suitable for economic modelling.
|
|
|
Cluster analysis of more dimensional data by a neural network
Helcl, Zbyněk ; Křivan, Miloš (advisor) ; Berka, Petr (referee)
The topic of the present thesis is an analysis of a sample data archive containing measured values of real and reactive power. The measurement in question took place in late 2006 and early 2007 using MEg40 recording measurement devices disposed in a station for transforming high voltage to low voltage in the Pražská energetika distribution network. The procedure of processing measured values, the preparation thereof for a subsequent processing by a neural network, and a final statistical evaluation of determined individual clusters -- typical daily take-off diagrams -- will be described. The results of the present thesis may be applied in the making of predictions of electrical energy consumption at a particular transformer station.
|
guest ::
