Drago Bračun (Avtor), Igor Lekše (Avtor)

Povzetek

Many metal components in automotive industry are surface-protected using the electrophoretic cathode metal coating (KTL). As surface defects can occur in this process, the components need to be 100% inspected, especially if the manufacturers are committed to delivering zero-defect products. Due to complicated 3D curved shapes and black shiny colour of the coating, inspection is typically carried out manually. To avoid labour-intensive manual inspection in serial production, an automated visual inspection system is developed. The paper presents the implementation of a control device for mass inspection of the products, typical KLT coating defects, and the visual inspection method for the detection of coating defects. A difference image acquisition method is implemented in order to reveal the defects on the black shiny colored parts. An image processing algorithm for the recognition of light patterns and a clustering approach for the recognition of defects are presented.

Ključne besede

površinske napake;nadzor kakovosti;slikovni sistemi;razpoznavanje vzorcev;KTL;surface defect;inspection;imaging system;pattern recognition;cluster;

Podatki

Jezik: Angleški jezik
Leto izida:
Tipologija: 1.08 - Objavljeni znanstveni prispevek na konferenci
Organizacija: UL FS - Fakulteta za strojništvo
UDK: 658.56:620.191(045)
COBISS: 16688411 Povezava se bo odprla v novem oknu
ISSN: 2212-8271
Št. ogledov: 718
Št. prenosov: 410
Ocena: 0 (0 glasov)
Metapodatki: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Ostali podatki

Sekundarni jezik: Slovenski jezik
Sekundarne ključne besede: površinske napake;nadzor kakovosti;slikovni sistemi;razpoznavanje vzorcev;
Vrsta dela (COBISS): Članek v reviji
Strani: f. 771-774
Zvezek: ǂVol. ǂ81
Čas izdaje: 2019
DOI: 10.1016/j.procir.2019.03.192
ID: 11185817