Prediction performance analysis of neural network models for an electrical discharge turning process

In many of the modern-day manufacturing industries, electrical discharge machining (EDM) now appears as an effective non-traditional material removal process for generating intricate shape geometries on various hard-to-cut work materials to meet ever-increasing demands higher dimensional accuracy and better surface quality. Development appropriate prediction model any EDM processes is quite difficult due complex mechanism, dynamic interactions between input parameters responses. To address problem, this paper proposes development deployment five neural network models, i.e. feed forward network, convolutional recurrent general regression long short term memory-based tools turning (EDT) process. The EDT a variant involving from cylindrical workpieces. considered are magnetic field, pulse current, duration angular velocity, whereas, responses rate overcut. Several statistical error metrics, like R-squared (R2), adjusted (R2adj), root mean square relative employed compare all investigated models. Based past experimental dataset, it observed that provides more accurate both under consideration. On other hand, noticed be extremely robust having highly repetitive performance.