Klasifikacija tvrdoće obratka kod bušenja kamena primjenom signala vibracija

master's thesis

• Title (english): Workpiece hardness classification using vibration signals in stone drilling
• Author: Matej Šlankovič
• Mentor: Danko Brezak (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2023-07-20, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering; Production Mechanical Engineering

Abstract

Kroz rad se istražuje mogućnost primjene neuronske mreže s radijalnim baznim funkcijama za klasifikaciju tvrdoće kamena na temelju signala vibracija snimljenih pri obradi bušenjem. U prvom dijelu rada iznosi se značaj i vrste nadzora obradnih procesa, što je dodatno prošireno dubljim pregledom karakteristika signala snimanih tijekom indirektnog nadzora. Na kraju teorijskog dijela, analizirani su model obradnog sustava s modulom za indirektni nadzor tvrdoće kamena i novodizajnirano svrdlo s kanalom za ispuhivanje. Nakon teorijskog dijela, detaljno je prikazan provedeni eksperiment. Redom su opisani: eksperimentalni postav, korištene vrste kamenih uzoraka, mjerenje i obrada signala, te izdvajanje značajki. Zatim je iznesena struktura, matematički model i principi rada neuronske mreže s radijalnim baznim funkcijama. Naposljetku su prikazani rezultati provedenog eksperimenta te je iznesen konačan zaključak o primjenjivosti mreže za klasifikaciju tvrdoće.

Abstract (english)

The paper explores the possibility of applying the radial basis function neural network for the stone hardness classification based on vibration signals measured during drilling process. In the first part of the paper, the importance and types of monitoring of machining processes are presented. Which is additionally expanded by a deeper overview of indirectly monitored signals. At the end of the theoretical part, the model of machining system with the module for indirect stone hardness monitoring and the newly designed drill bit with a channel that allows the flow of cutting fluids were analyzed. After the theoretical part, the conducted experiment is thoroughly described in the following order: the experimental setup, used types of stone samples, measurement and processing of signals, and feature extraction. Subsequently followed by explanation of the structure, mathematical model and operating principles of the radial basis function neural network. Final chapter presents the results of conducted experiment and concluding remarks of applicability of neural network for hardness classification.

• Keywords: bušenje; indirektni nadzor; klasifikacija tvrdoće kamena; neuronske mreže
• Keywords (english): drilling; indirect monitoring; stone hardness classification; neural networks
• Language: croatian
• URN:NBN: urn:nbn:hr:235:570663
• Study programme: Title: Mechanical Engineering; specializations in: Design, Process and Energy Engineering, Production Engineering, Engineering Modelling and Computer Simulation, Marine Engineering, Industrial Engineering and Management, Materials Engineering, Mechatronics and Robotics, Autonomous Systems; Course: Autonomous Systems; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2023-07-05 18:52:15