期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2015
期号：MULTICON
页码：1602
出版社：S&S Publications
摘要：The electrochemical micromachining (EMM) belongs to the unconventional machining methods. EMMis suitable for hard and extra hard materials used for cutting and moulding tools manufacturing and also for specialforms machine part manufacturing used in aeronautics, prothesis and hydropneumatic machinery. EMM is a verycomplex process as the result of a set of electric, mechanics and chemical parameters. So the analytical modeling of theprocess is difficult. Due to the large number of measurements required, the artificial neural network very greatlysimplifies the relationship between the input and the output parameters. The neural network was trained with a set ofdata containing very different machining parameter choices. This paper presents the results obtained for the predictionof some output parameters.In this paper, artificial neural network (ANN) is used to establish the parameter optimizationmodel. An ANN model which adapts Levenberg-Marquardt algorithm and Bayesian regularization has been set up torepresent the relationship between machining rate, overcut and input parameters. The model is shown to be effective,and machining rate and overcut are improved using optimized machining parameters.
