magistrsko delo
Uroš Žurman (Author), Aleš Hace (Mentor), Uroš Župerl (Mentor)

Abstract

V magistrski nalogi so opisani modeli za napovedovanje rezalnih sil in principe delovanja nevronskih mrež. V osrednjem delu so predstavljeni trije umetni nevronski modeli za napovedovanje rezalne sile. Za primerjavo je bil narejen statistični model linearne regresije za napovedovanje rezalne sile. Nevronski modeli so bili narejeni s programom MATLAB, model linearne regresije pa z Microsoft Excel. Na koncu so predstavljeni rezultati treh modelov nevronske mreže in statističnega modela linearne regresije.

Keywords

frezanje;umetna nevronska mreža;regresijska analiza;rezalne sile;magistrske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [U. Žurman]
UDC: 004.8.032.26:621.914(043.2)
COBISS: 143716611 Link will open in a new window
Views: 107
Downloads: 23
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Artificial neural network based cutting force model for milling process
Secondary abstract: The master's thesis describes models for predicting cutting forces and the principles of neural networks. In the central part, three artificial neural models for predicting the cutting force are presented. For comparison, a statistical linear regression model was built to predict the cutting force. Neural models were made using MATLAB, and linear regression models were made using Microsoft Excel. Finally, the results of three neural network models and a statistical linear regression model are presented.
Secondary keywords: milling;artificial neural network;regression analysis;cutting forces;
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Mehatronika
Pages: 1 spletni vir (1 datoteka PDF (X, 42 f.))
ID: 16500812