|
|
Construction of foundry core boxes and their use for the production of silicone parts
Skalický, Jan ; Kaněra, Miloš (referee) ; Jelínek, Radim (advisor)
The thesis deals with the design of a mold for use in casting of plastics and rubbers. The product is two different gaskets used in the testing of tubes for automotive industry. The part has a cylindrical shape with a diameter of 19 mm and a length of 25 mm, where two holes with a diameter of 4 mm are additionally drilled in one of them. Depending on the service life, the batch size is approximately 200 pieces per year. The material was not specified, so after research two options were chosen. The first was RTV-2 condensation silicone rubber LUKOPREN N 1522 from Lučební závody a.s. Kolín and the second one was RTV-2 additive silicone rubber ELASTOSIL M 4642 A/B from Wacker-Chemie, s.r.o. The second material came out better from preliminary testing. By gradually improving the design of a simple single-piece steel mold, a final version was created which is double in size and consists of three parts. It is made by 3D printing using FDM method from PLA material. It was found that in order to achieve a defect-free casting, the mix must be vacuumed before casting.
|
|
|
Crude Oil Price Forecast based on Text News
Skalický, Jan ; Bojar, Ondřej (advisor) ; Žabokrtský, Zdeněk (referee)
For crude oil price forecast, there is a whole range of algorithms. In this thesis we bring out a new perspective on this issue and introduce our project COPF. Using a maximum entropy classifier, we try to predict the change in crude oil price from text information available on the Internet. We are taking advantage of the knowledge of experts in the field. As a part of the thesis, we tested and improved COPF precision. We have found out that this approach poses a lot of interesting problems. In the current state, the precision of our prediction surpassed the baseline but for further development, it is necessary to obtain more data sources. Our algorithm has never been regarded as a self-standing method but it may nicely complement numerical algorithms.
|
|
|
Crude Oil Price Forecast based on Text News
Skalický, Jan ; Bojar, Ondřej (advisor) ; Žabokrtský, Zdeněk (referee)
For crude oil price forecast, there is a whole range of algorithms. In this thesis we bring out a new perspective on this issue and introduce our project COPF. Using a maximum entropy classifier, we try to predict the change in crude oil price from text information available on the Internet. We are taking advantage of the knowledge of experts in the field. As a part of the thesis, we tested and improved COPF precision. We have found out that this approach poses a lot of interesting problems. In the current state, the precision of our prediction surpassed the baseline but for further development, it is necessary to obtain more data sources. Our algorithm has never been regarded as a self-standing method but it may nicely complement numerical algorithms.
|
guest ::
RSS feed.