Wire EDM process optimization for machining AISI 1045 steel by use of Taguchi method, artificial neural network and analysis of variances

Wire electrical discharge machining (WEDM) process used in a wide spectrum of industrial applications. AISI 1045 is medium carbon steel, because of its excellent physical and chemical properties, it is used in many applications. However, the review of the state of the art literature reveals that literature is lacking research to optimize WEDM process for machining AISI 1045 steel. The objectives of this research are building ANN model to predict metal removal rate (MRR) and surface roughness (Ra) values for machining AISI 1045 steel, identifying the significance of the pulse on-time (T ON ), pulse off time (T OFF ) and servo feed (S F ) for the MRR and Ra, and selecting optimal machining parameters that give maximum MRR value and that give the minimum Ra value. Taguchi method (Design of Experiments), artificial neural network (ANN), and analysis of variances (ANOVA) used in this research as a methodology to fulfill research objectives. This research reveals that the architecture (3-5-1) of ANN models is the best architecture to predict the Ra and MRR with about 98.136% and 97.3% accuracy respectively. It can be realized that T ON is the most significant cutting parameter affecting Ra by P % value 42.922% followed by T OFF with a P % value of 24.860%. S F was not a significant parameter for Ra because of Fα > F. For MRR, the most significant parameter is T ON with a P % value of (71.733%), i.e. about three times the T OFF P % value (21.796%) and the S F parameter has a small influence with P % value 3.02%. The analysis confirmed that the optimal cutting parameters for maximum MRR were: T ON at the third level (25 µs), T OFF at the first level (20 µs), and S F at the third level (700 mm/min). On the other hand, the optimal cutting parameters for minimum Ra were: T ON at the first level (10 µs), T OFF at the third level (40 µs), and S F at the first level (500 mm/min). Future work may focus on optimizing the WEDM process for machining other types of materials or other sets of parameters and performance measures.