Naslov
Adaptive Neuro-Fuzzy Inference System Model for Technological Parameters Prediction

Autori
Šimunović, Goran ; Šarić, Tomislav ; Svalina, Ilija

Izvornik
Strojarstvo (0562-1887) 53 (2011), 4; 311-318

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, prethodno priopćenje, znanstveni

Ključne riječi
Adaptive Neuro-Fuzzy Inference System; Artificial intelligence; Technological parameters

Sažetak
The main goal of each technologist is the prediction of technological parameters by fulfilling the set design and technological demands. The work of the technologist is made easier by acquired knowledge and previous experience. A plan of input-output data was made by using the hybrid system of modelling ANFIS (Adaptive Neuro-Fuzzy Inference System) based on the results of seam tube production. This plan is the prerequisite for generating the system of fuzzy logic. The generated system can be used to estimate the output (speed of polishing) based on the given input (external tube diameter, oval shaping of the tube after the first phase of production, gradation of belts for grinding or polishing, condition of belts - time of usage, pressure of belts).The more precise predictions of technological time provided by the model supplement the previously defined manufacturing operations, replace the predictions based on the technologists' experience and form the basis on which to plan production and control delivery times. The work of technologists is thus made easier and the production preparation technological time shorter.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA