Napredna pretraga

Pregled bibliografske jedinice broj: 106022

Expert System for Troubleshooting in Injection Moulding Process


Šercer, Mladen; Rujnić-Sokele, Maja; Slavica, Mladen
Expert System for Troubleshooting in Injection Moulding Process // Plastko 2001
Zlin, 2001. (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Expert System for Troubleshooting in Injection Moulding Process

Autori
Šercer, Mladen ; Rujnić-Sokele, Maja ; Slavica, Mladen

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Skup
Plastko 2001

Mjesto i datum
Zlin, Češka, 13-15.06.2001.

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Sažetak
Injection moulding of thermoplastic melt is the most important cyclic procedure of thermoplastic processing, but also the most complicated, complex and the most improved procedure of polymer processing in general. In order to ensure a constant quality of the molded part it is necessary to prevent the occurrence of faults or, if this is not possible, to eliminate them when they do occur. In order to prevent/eliminate faults, the application of computers in manufacturing of injection thermoplastic mouldings can be of great help. A computer makes it possible to develop expert systems as the currently most discussed field of artificial intelligence (AI), and which can be described in short as software which simulates the behaviour of a human expert in the scientific field under consideration. An expert system for process control of injection moulding of thermoplastics has been developed, which is comprised of two modules: one for removing of faults in the moulded parts, and the other one for the process control in accordance with the trend. A special learning capability upgrades the performance with usage while the expert system is running by changing certainty factors and, therefore, adjusting the order of recommended fault-removing remedies. The tests have shown that the fault-removing efficiency of an expert system is 97%.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo



POVEZANOST RADA


Projekt / tema
120036

Ustanove
Fakultet strojarstva i brodogradnje, Zagreb