期刊名称:International Journal of Computer Science and Network Security
印刷版ISSN:1738-7906
出版年度:2010
卷号:10
期号:11
页码:188-193
出版社:International Journal of Computer Science and Network Security
摘要:Composite materials have been used in many industrial applications due to their light weight and high tensile strength. However, the machining costs of these materials may be high and the grinding of these materials is much more susceptible to surface damage as compared to metals. Electrolytic In- Process Dressing (ELID) grinding can be used to machine hard and brittle materials to achieve high surface quality and high material removal rate. In the present work, to conduct experiments, the Design of Experiments (DOE) technique is developed for five factors at three levels. Experiments have been conducted for measuring surface roughness, hardness and metal removal rate based on the DOE technique in an ELID grinding machine using a carbon boron nitride wheel. The experimentally measured values are also used to train the feed forward back propagation neuro-fuzzy for prediction of surface roughness. The predictive neuro fuzzy model was found to be capable of better prediction of surface roughness, hardness and metal removal rate within the trained range.