Optimization of the Parameters of the Electrochemical Micromachining Process Using Artificial Neural Network (ANN) Models to established a Simple Relationship Between Machining Rate (MR), Overcut (OC) and Input Data

Unconventional machining methods include electrochemical micromachining (EMM). EMM is suitable for hard and difficult-to-cut materials used in the manufacture of special forms of machine parts used in aeronautics and hydro pneumatic machinery. As a result of a set of electrical, mechanical and chemical parameters, the EMM process is a very complex process. The analytical modeling of the method is therefore difficult. The artificial neural network (ANN) significantly simplifies the relationship between input and output parameters due to the large number of measurements required. With a set of data containing very different machining parameter choices, the neural network was trained. This paper presents the results obtained for predicting certain output parameters. The ANN is used in this paper to determine the model for parameter optimization. To represent the relationship between machining rate (MR), overcut (OC) and input parameters, an ANN model has been established that adapts the Levenberg-Marquardt algorithm and Bayesian regularization (LMABR). The model is shown to be efficient, and optimized machining parameter improves the MR and OC.