Application of neuro-fuzzy systems and genetic programming for modeling surface roughness in electrical discharge machining
1. Marin Gostimirović, Faculty of Technical Sciences, Department for Production Engineering, Serbia
2. mr Dragan Rodić, Faculty of Technical Sciences, Department for Production Engineering, Serbia
3. Pavel Kovač, Faculty of Technical Sciences, Department for Production Engineering, Serbia
4. mr Vladimir Pucovsky, Faculty of Technical Sciences, Department for Production Engineering, Serbia
5. MsC Borislav Savković, Faculty of Technical Sciences, Department for Production Engineering, Serbia
This paper reports the development of two intelligent models for the electric discharge machining (EDM) process using adaptive-neuro-fuzzy-inference system (ANFIS) and genetic programming (GP). Experiments were conducted by varying the pulse duration and discharge current and the corresponding values of surface roughness (Ra) were measured. The values of surface roughness predicted by these models are then compared. Both models show good agreement with experimental results. The results indicate that the genetic programming technique gives slightly smaller deviation of the measured values of model than neuro-fuzzy model.
Кључне речи : neuro-fuzzy systems genetic programming surface roughness
Тематска област:
Датум:
14.02.2013.
Датотека уз рад
(2.01 MB)