Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Context-aware in-situ in-process material-defect detection for cnc-milled workpieces based on machining vibration
Thesis (MEng)--Stellenbosch University, 2025.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Stellenbosch : Stellenbosch University
2025
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867614117275107328 |
|---|---|
| access_status_str | Open Access |
| author | Kimmle, Johannes |
| author2 | Von Leipzig, Konrad |
| author_browse | Kimmle, Johannes Von Leipzig, Konrad |
| author_facet | Von Leipzig, Konrad Kimmle, Johannes |
| author_sort | Kimmle, Johannes |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MEng)--Stellenbosch University, 2025. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/134659 |
| institution | Stellenbosch University (South Africa) |
| language | English |
| last_indexed | 2026-06-10T12:46:56.603Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/134659 Context-aware in-situ in-process material-defect detection for cnc-milled workpieces based on machining vibration Kimmle, Johannes Von Leipzig, Konrad Lucke, Dominik Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering. Engineering Management. Machine-tools -- Numerical control Milling machinery -- Defects Manufacturing industries -- Quality control Machining -- Automation Thesis (MEng)--Stellenbosch University, 2025. Kimmle, J. 2025. Context-Aware In-Situ In-Process Material-Defect Detection for CNC-Milled Workpieces Based on Machining Vibration. Unpublished masters thesis. Stellenbosch: Stellenbosch University [online]. Available: https://scholar.sun.ac.za/items/ede9954c-0edc-4f76-b41a-fdf09ff5ac62 ENGLISH ABSTRACT: Reliable and lot-size-one capable online quality monitoring for CNC-machined parts remains elusive. To address this challenge, this research proposes a cost-effective, reference-independent monitoring concept for material defect detection in CNC-machined parts. This work presents a novel digital twin-based method, utilising machining vibrations and a G-code-based encoding of the cutting process that serves as context. The objective is to detect material defects, such as blowholes, without the need for individual workpiece references. The proposed method aims to reduce barriers to entry, minimise waste, and enhance machine productivity by enabling automated early online quality control. To develop and validate the system, a dataset is generated that combines machining vibration data with technological context data, such as undeformed chip shape. Based on a proof-of-concept imple-mentation, several machine learning-based process state classifiers are developed and validated. The potential of the system is demonstrated through a simplified implementation, showcasing the feasibil-ity of context-based monitoring and ultimately contributing to improved product quality and process efficiency. AFRIKAANSE OPSOMMING: Betroubare lot-grootte-een wat in staat is tot aanlyn kwaliteitsmonitering van CNC-gemasjineerde onderdele bly steeds moeilik om te bereik. Om hierdie uitdaging aan te spreek, stel hierdie navorsing ’n kostedoeltreffende, verwysings-onafhanklike moniteringskonsep voor vir die opspoor van materiaaldefekte in CNC-gemasjineerde onderdele. Hierdie werk bied ’n nuwe metode gebaseer op ’n digitale tweeling, wat gebruik maak van masjinerings-vibrasies en ’n G-kode-gebaseerde kodering van die snyproses wat as konteks dien. Die doelwit is om materiaaldefekte, soos blaasgate, op te spoor sonder die behoefte aan individuele werkstukverwysings. Die voorgestelde metode is daarop gemik om hindernisse tot toegang te verminder, afval te verminder, en masjienproduktiwiteit te verbeter deur geoutomatiseerde vroeë aanlyn kwaliteitsbeheer moontlik te maak. Om die stelsel te ontwikkel en te valideer, word ’n datastel gegenereer wat masjinerings-vibrasiedata kombineer met tegnologiese konteksdata, soos onvervormde skyf-vorms. Gebaseer op ’n bewys-vankonsep- implementering, word verskeie masjienleer-gebaseerde klassifiseerders vir die prosesstatus ontwikkel en gevalideer. Die potensiaal van die stelsel word gedemonstreer deur middel van ’n vereenvoudigde implementering, wat die haalbaarheid van konteksgebaseerde monitering ten toon stel en uiteindelik bydra tot verbeterde produkkwaliteit en prosesdoeltreffendheid. Masters 2025-12-22T10:02:13Z 2025-12-22T10:02:13Z 2025-12 Thesis https://scholar.sun.ac.za/handle/10019.1/134659 en Stellenbosch University 114 pages : illustrations application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Machine-tools -- Numerical control Milling machinery -- Defects Manufacturing industries -- Quality control Machining -- Automation Kimmle, Johannes Context-aware in-situ in-process material-defect detection for cnc-milled workpieces based on machining vibration |
| title | Context-aware in-situ in-process material-defect detection for cnc-milled workpieces based on machining vibration |
| title_full | Context-aware in-situ in-process material-defect detection for cnc-milled workpieces based on machining vibration |
| title_fullStr | Context-aware in-situ in-process material-defect detection for cnc-milled workpieces based on machining vibration |
| title_full_unstemmed | Context-aware in-situ in-process material-defect detection for cnc-milled workpieces based on machining vibration |
| title_short | Context-aware in-situ in-process material-defect detection for cnc-milled workpieces based on machining vibration |
| title_sort | context aware in situ in process material defect detection for cnc milled workpieces based on machining vibration |
| topic | Machine-tools -- Numerical control Milling machinery -- Defects Manufacturing industries -- Quality control Machining -- Automation |
| url | https://scholar.sun.ac.za/handle/10019.1/134659 |
| work_keys_str_mv | AT kimmlejohannes contextawareinsituinprocessmaterialdefectdetectionforcncmilledworkpiecesbasedonmachiningvibration |