Matej Paulič (Author), David Močnik (Author), Mirko Ficko (Author), Jože Balič (Author), Tomaž Irgolič (Author), Simon Klančnik (Author)

Abstract

This article presents developed intelligent system for prediction of mechanical properties of material based on metallographic images. The system is composed of two modules. The first module of the system is an algorithm for features extraction from metallographic images. The first algorithm reads metallographic image, which was obtained by microscope, followed by image features extraction with developed algorithm and in the end algorithm calculates proportions of the material microstructure. In this research we need to determine proportions of graphite, ferrite and ausferrite from metallographic images as accurately as possible. The second module of the developed system is a system for prediction of mechanical properties of material. Prediction of mechanical properties of material was performed by feed-forward artificial neural network. As inputs into artificial neural network calculated proportions of graphite, ferrite and ausferrite were used, as targets for training mechanical properties of material were used. Training of artificial neural network was performed on quite small database, but with parameters changing we succeeded. Artificial neural network learned to such extent that the error was acceptable. With the oriented neural network we successfully predicted mechanical properties for excluded sample.

Keywords

nevronske mreže;mehanika loma;lomna žilavost;procesiranje slik;mehanske lastnosti;natezna trdnost;napetost tečenja;artificial neural network;factor of phase coherence between the surfaces;fracture toughness;image processing;mechanical properties;metallographic image;ultimate tensile strength;yield strength;

Data

Language: English
Year of publishing:
Typology: 1.01 - Original Scientific Article
Organization: UM FS - Faculty of Mechanical Engineering
UDC: 620.172.25:669:004.92
COBISS: 19203862 Link will open in a new window
ISSN: 1330-3651
Views: 936
Downloads: 378
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: Croatian
Secondary title: Inteligentni sustav za predviđanje mehaničkih svojstava materijala na osnovu metalografskih slika
Secondary abstract: U radu se predstavlja razvijeni inteligentni sustav za predviđanje mehaničkih svojstava materijala na temelju metalografskih slika. Sustav se sastoji od dva modula. Prvi je modul algoritam za dobivanje karakteristika iz metalografskih slika. Prvi algoritam očitava metalografsku sliku dobivenu mikroskopom, zatim se dobivaju karakterisike razvijenim algoritmom, i na kraju algoritam izračunava omjere mikrostrukture materijala. U ovom istraživanju potrebno je što točnije odrediti omjere grafita, ferita i ausferita iz metalografskih slika. Drugi modul razvijenog sustava je sustav za predviđanje mehaničkih svojstava materijala. Predviđanje mehaničkih svojstava materijala izvršeno je pomoću feed-forward umjetne neuronske mreže. Kao ulazi u umjetnu neuronsku mrežu rabljeni su izračunati omjeri grafita, ferita i ausferita, dok su mehanička svojstva materijala upotrebljena kao ciljevi za uvježbavanje. Uvježbavanje umjetnih neuronskih mreža obavljeno je na prilično maloj bazi podataka, no mijenjajući parametre nama je to uspjelo. Umjetna neuronska mreža je naučila do te mjere da je greška bila prihvatljiva. S orijentiranom neuronskom mrežom uspješno smo predvidjeli mehanička svojstva izuzetog uzorka.
Secondary keywords: umetne nevronske mreže;mehanika loma;lomna žilavost;procesiranje slik;mehanske lastnosti;natezna trdnost;napetost tečenja;
URN: URN:SI:UM:
Type (COBISS): Scientific work
Pages: str. 1419-1424
Volume: ǂVol. ǂ22
Issue: ǂno. ǂ6
Chronology: 2015
DOI: 10.17559/TV-20130718090927
ID: 10847606