|
|
State of charge prediction of lead acid batteries
Chochola, Ondřej ; Bača, Petr (referee) ; Křivík, Petr (advisor)
The general aim of the thesis is a detailed examination of battery charging condition possibility of lead-acid accumulator with the help of pulse current method. The methodology consists of experimental cell testing by pulse battery charging and pulse battery discharging during a progressive change of charging and discharging current as well as charging and discharging time change. The testing procedure proceeds at a various battery charging condition. Principal aim of this work is to compare final voltage dependencies and to establish the usability of pulse current method to determine battery charging condition.
|
|
| |
|
| |
|
|
Recursive procedures for detection of changes
Chochola, Ondřej ; Hušková, Marie (advisor) ; Černíková, Alena (referee)
In the thesis we study a sequential monitoring scheme for detecting a change in variance. We assume to have a stable historical period of length m. The goal is to propose tests with asymptotically small probability of type I error and power 1 as m tends to infinity. Two such procedures were proposed. The first uses estimates of variance from the historical period, the second uses recursive estimates. The distribution under the null hypothesis and also under the alternative hypothesis was derived for both test statistics. Furthermore a simulation study for of the finite sample performance of the monitoring schemes was conducted.
|
|
| |
|
|
Robust Monitoring Procedures for Dependent Data
Chochola, Ondřej ; Hušková, Marie (advisor) ; Antoch, Jaromír (referee) ; Černíková, Alena (referee)
Title: Robust Monitoring Procedures for Dependent Data Author: Ondřej Chochola Department: Department of Probability and Mathematical Statistics Supervisor: Prof. RNDr. Marie Hušková, DrSc. Supervisor's e-mail address: huskova@karlin.mff.cuni.cz Abstract: In the thesis we focus on sequential monitoring procedures. We extend some known results towards more robust methods. The robustness of the procedures with respect to outliers and heavy-tailed observations is introduced via use of M-estimation instead of classical least squares estimation. Another extension is towards dependent and multivariate data. It is assumed that the observations are weakly dependent, more specifically they fulfil strong mixing condition. For several models, the appropriate test statistics are proposed and their asymptotic properties are studied both under the null hypothesis of no change as well as under the alternatives, in order to derive proper critical values and show consistency of the tests. We also introduce retrospective change-point procedures, that allow one to verify in a robust way the stability of the historical data, which is needed for the sequential monitoring. Finite sample properties of the tests need to be also examined. This is done in a simulation study and by application on some real data in the capital asset...
|
|
|
Two-sample tests
Janoušková, Kateřina ; Hlávka, Zdeněk (advisor) ; Chochola, Ondřej (referee)
Two-sample T tests are described in this thesis. They are an im- portant method for testing hypotheses when samples have normal distribution. The main emphasis is laid on testing expected values when unknown variances are unequal. The test statistics used for testing hypotheses are presented and their null distribution is derived. In the beginning Student's distribution is de- scribed. The next chapters show how the Welch's and Satterthwaite's statistics are derived and it is described how to use them when testing hypotheses. Special paired test with missing samples is presented in the last chapter. 1
|
|
|
Recursive procedures for detection of changes
Chochola, Ondřej ; Hušková, Marie (advisor)
In the thesis we study a sequential monitoring scheme for detecting a change in variance. We assume to have a stable historical period of length m. The goal is to propose tests with asymptotically small probability of type I error and power 1 as m tends to infinity. Two such procedures were proposed. The first uses estimates of variance from the historical period, the second uses recursive estimates. The distribution under the null hypothesis and also under the alternative hypothesis was derived for both test statistics. Furthermore a simulation study for of the finite sample performance of the monitoring schemes was conducted.
|
|
|
Application of the SW ESTE AI for the recommandation on an optimal strategy of liquidation H-3 produced by 5 blocks of the NPP Dukovany
CHOCHOLA, Ondřej
This thesis deals with the influence of the discharges of the Dukovany Nuclear Power Plant ("Dukovany NPP") and the assessment of impacts on the population and the vicinity of the power plant. The thesis summarizes the issues of tritium 3H discharges into waterways and partially deals with the 14C discharges. Attention is paid especially to the radioisotope of hydrogen 3H, due to its chemical and physical form and its presence in the cooling medium (light water) used by that type of nuclear power reactor. The thesis also contains a description of the current state of the Dukovany NPP, especially the existing discharges of the radioactive substances to the surroundings of the nuclear power plant, both to the air and into the waterway. Also was discussed the issue of the new planned blocks of the Dukovany NPP and impacts of the projected discharges on the population during the simultaneous operation of the existing blocks and the planned blocks, again in relation to the 3H discharged into the waterway. The application ESTE AI was used for the determination of individual groups of inhabitants who are most exposed to the radioactive discharges (also called representative person). Based on the current discharges of the Dukovany NPP and the planned blocks discharges were determined the annual effective doses for a representative person. The doses were compared with the legislation on the conditions for the peaceful use of nuclear energy requirements and then with the water management legislation. In order to avoid exceeding these limits were set up recommendations how to dispose of radioactive substances optimally. The thesis answer to the research question: What impacts on the population will have discharges of the Dukovany NPP after the construction of a new nuclear source, especially in relation to the discharges of the 3H into the waterway and which measures will must be applied on the optimization of the inhabitants doses.
|
|
|
Robust Monitoring Procedures for Dependent Data
Chochola, Ondřej ; Hušková, Marie (advisor) ; Antoch, Jaromír (referee) ; Černíková, Alena (referee)
Title: Robust Monitoring Procedures for Dependent Data Author: Ondřej Chochola Department: Department of Probability and Mathematical Statistics Supervisor: Prof. RNDr. Marie Hušková, DrSc. Supervisor's e-mail address: huskova@karlin.mff.cuni.cz Abstract: In the thesis we focus on sequential monitoring procedures. We extend some known results towards more robust methods. The robustness of the procedures with respect to outliers and heavy-tailed observations is introduced via use of M-estimation instead of classical least squares estimation. Another extension is towards dependent and multivariate data. It is assumed that the observations are weakly dependent, more specifically they fulfil strong mixing condition. For several models, the appropriate test statistics are proposed and their asymptotic properties are studied both under the null hypothesis of no change as well as under the alternatives, in order to derive proper critical values and show consistency of the tests. We also introduce retrospective change-point procedures, that allow one to verify in a robust way the stability of the historical data, which is needed for the sequential monitoring. Finite sample properties of the tests need to be also examined. This is done in a simulation study and by application on some real data in the capital asset...
|
guest ::
RSS feed.