diplomsko delo
Povzetek
V diplomskem delu smo analizirali podatke jeklarskega procesa izdelave titanovih jekel s programom Orange. Naredili smo analize šarž s posameznimi napakami glede na dodeljene podatke o postopku izdelave. Prva podatkovna baza uporablja podatke o izdelavi v EOP, druga podatkovna baza pa uporablja podatke o izdelavi s postopki sekundarne metalurgije. Šarže smo primerjali po skupinah napak in po posameznih napakah, analizirali pa smo tudi vplivne parametre za nastanek napake. Pri analizi smo uporabili podatkovne modele, in sicer nevronske mreže, odločitveno drevo in model AdaBoost. Z dobljenimi rezultati smo izdelali grafe violinske razporeditve, stolpčne diagrame, drevesne prikaze in matrike zmede. Primerjali smo natančnost napovedi med posameznimi podatkovnimi modeli.
Ključne besede
podatkovno rudarjenje;odločitveno drevo;nevronske mreže;AdaBoost;Orange;
Podatki
Jezik: |
Slovenski jezik |
Leto izida: |
2022 |
Tipologija: |
2.11 - Diplomsko delo |
Organizacija: |
UL NTF - Naravoslovnotehniška fakulteta |
Založnik: |
[N. Flisek] |
UDK: |
669 |
COBISS: |
105554947
|
Št. ogledov: |
185 |
Št. prenosov: |
42 |
Ocena: |
0 (0 glasov) |
Metapodatki: |
|
Ostali podatki
Sekundarni jezik: |
Angleški jezik |
Sekundarni naslov: |
use of data mining for analysis of steelmaking processes |
Sekundarni povzetek: |
In the diploma work, we analysed the data of the steel process of titanium steel production with the program Orange. We performed batch analyses with individual errors according to the assigned data on the manufacturing process. The first database was attributed production data in the EAF, with secondary metallurgy processes and continuous casting, and the second database was attributed production data with secondary metallurgy processes and continuous casting. The batches were compared by groups of errors and by individual errors, and the influential parameters for the occurrence of the error were also analysed. Data models were used in the analysis, namely neural networks, decision tree and AdaBoost model. With the obtained results, we produced graphs of violin arrangement, bar charts, tree representations and confusion matrices. We compared the accuracy of the forecast between individual data models. |
Sekundarne ključne besede: |
data mining;decision tree;neural networks;AdaBoost;Orange; |
Vrsta dela (COBISS): |
Diplomsko delo/naloga |
Študijski program: |
0 |
Konec prepovedi (OpenAIRE): |
1970-01-01 |
Komentar na gradivo: |
Univ. v Ljubljani, Naravoslovnotehniška fak., Oddelek za materiale in metalurgijo |
Strani: |
XII, 55 f. |
ID: |
14976272 |