Pregled bibliografske jedinice broj: 201515
The application of artificial intelligence methods in heat treatment
The application of artificial intelligence methods in heat treatment // Proceedings of the 1st International Conference on Heat Treatment and SurfaceEngineering of Tools and Dies / Smoljan, Božo ; Jaeger, Heimo ; Leskovšek, Vojteh (ur.).
Zagreb: Hrvatsko društvo za toplinsku obradu i inženjerstvo površina, 2005. str. 469-476 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 201515 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
The application of artificial intelligence methods
in heat treatment
Autori
Filetin, Tomislav ; Žmak, Irena ; Lisjak, Dragutin ; Novak, Davor ; Landek, Darko
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the 1st International Conference on Heat Treatment and SurfaceEngineering of Tools and Dies
/ Smoljan, Božo ; Jaeger, Heimo ; Leskovšek, Vojteh - Zagreb : Hrvatsko društvo za toplinsku obradu i inženjerstvo površina, 2005, 469-476
Skup
1st International Conference on Heat Treatment and Surface Engineering of Tools and Dies
Mjesto i datum
Pula, Hrvatska, 08.06.2005. - 11.06.2005
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
steel properties ; MARAGING steel ; thermochemical treatment
Sažetak
Over the past few years a detailed study of artificial neural network, genetic algorithm and programming, as well as the expert systems in predicting the steel properties and determination of heat treatment process parameters has been performed at the Department for Materials of FMENA. This paper presents the short overview of applied methods and results in predicting different properties of the heat treatable steels and process parameters. Based on known chemical composition and heat treatment condition the following properties has been predicted by means of neural network: tempering curve of tool steels, coefficient of heat conductivity. The duration and surface hardness of gas and plasma nitriding has been also successfully determined using neural network. The genetic algorithm and genetic programming has been used for definition of the relations between different variables, for optimisation of neural network parameters, as well as for determination of carburising parameters. The expert system for selection of steel and surface modification treatment has been developed, which integrate the above-mentioned methods. The results are encouraging and open the wide possibilities for further investigation in heat treatment and surface engineering technologies.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo
POVEZANOST RADA
Ustanove:
Fakultet strojarstva i brodogradnje, Zagreb