Pregled bibliografske jedinice broj: 895952
Development and optimization of surface roughness predictive models in turning super duplex stainless steel by using artificial intelligence methods
Development and optimization of surface roughness predictive models in turning super duplex stainless steel by using artificial intelligence methods // MECHANICAL TECHNOLOGIES AND STRUCTURAL MATERIALS / Jozić, Sonja ; Lela, Branimir (ur.).
Split: Hrvatsko društvo za zaštitu materijala (HDZaMa), 2017. str. 149-158 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 895952 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Development and optimization of surface roughness predictive models in turning super duplex stainless steel by using artificial intelligence methods
Autori
Veić, Mario ; Jozić, Sonja ; Bajić Dražen
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
MECHANICAL TECHNOLOGIES AND STRUCTURAL MATERIALS
/ Jozić, Sonja ; Lela, Branimir - Split : Hrvatsko društvo za zaštitu materijala (HDZaMa), 2017, 149-158
Skup
7th International Conference, Mechanical Technology and Structural Materials 2017
Mjesto i datum
Split, Hrvatska, 21.09.2017. - 22.09.2017
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Super duplex stainless steel , ANFIS, Genethic algorithm, Response surface method, Surface roughness
Sažetak
Super duplex stainless steels are alloys that have good corrosion resistance properties and are intended for applications in corrosive environments. Due to their chemical composition and microstructure providing high strength and thermal resistance as well as high ductility, the machinability of these alloys is difficult, resulting in longer production cycles and higher costs in terms of more frequent replacement of tools. In this paper the machinability of the superduplex EN 1.4410 was investigated in the machining process without using a cooling and lubricating medium. Experimental data were generated using the range of selected input parameters and correspondingly analyzed surface roughness as output data. Predictive and mathematical models were developed that were used in the optimization process to minimize the surface roughness. The influence of input parameters on surface roughness was analyzed and the optimum values of the input parameters were obtained using the genetic algorithm. The accuracy of developed predictive models was analyzed using different sets of experimental data. Developed predictive models could be in practice used by operators while selecting optimal processing parameters to achieve the surface roughness value requested by the constructor.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo
