Pregled bibliografske jedinice broj: 946703
New Method of Sequences Spiral Hybrid Using Machine Learning Systems and Its Application to Engineering
New Method of Sequences Spiral Hybrid Using Machine Learning Systems and Its Application to Engineering // New Technologies, Development and Application, Lecture Notes in Networks and Systems / Karabegović, Isak (ur.).
Sarajevo: Springer, 2018. str. 227-237 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 946703 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
New Method of Sequences Spiral Hybrid Using Machine Learning Systems and Its Application to Engineering
Autori
Babič, Matej ; Karabegović, Isak ; Martinčić- Ipšić, Sanda ; Varga, Gyula
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
New Technologies, Development and Application, Lecture Notes in Networks and Systems
/ Karabegović, Isak - Sarajevo : Springer, 2018, 227-237
ISBN
978-3-319-90892-2
Skup
4th International Conference "New Technologies and Applications" (NT-2018)
Mjesto i datum
Sarajevo, Bosna i Hercegovina, 28.06.2018. - 30.06.2018
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Intelligent system ; Hybrid machine learning ; Laser Hardening ; Visibility graphs ; Fractal dimension ; Metallurgy
Sažetak
In an era of increased emphasis on sustainability and quality assurance, knowledge about metals and other materials used in products, manufacturing processes, and construction is invaluable. Metallurgy is the study of the physical and chemical behaviour of metallic elements. CNC operators typically test many materials with different CNC machine parameters to optimize the topological properties of materials. In this article we present a solution to this problems. We analyse SEM pictures of the microstructure of robot laser hardened specimens using graph theory and fractal geometry. Intelligent systems methods enable predictions for mechanical engineering based on a hybrid of genetic programming and multiple regression, with applications to metallurgy and mechanical engineering. Hybrid evolutionary computation is a generic, flexible, robust, and versatile method for solving complex global optimisation problems that can also be used in practical applications. Hybrid intelligent systems enhance laser hardening by decreasing the process time and increasing the topographical properties of materials.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Strojarstvo, Informacijske i komunikacijske znanosti
POVEZANOST RADA
Ustanove:
Fakultet informatike i digitalnih tehnologija, Rijeka
Profili:
Sanda Martinčić - Ipšić
(autor)
