Parametric optimisation of wire electrical discharge machining of γ titanium aluminide alloy through an artificial neural network model

TLDR: In this paper, a feed-forward back-propagation neural network is developed to model the machining process, which is capable of predicting the response parameters as a function of six different control parameters, i.e. pulse on time, pulse off time, peak current, wire tension, dielectric flow rate and servo reference voltage.

Abstract: In the present research, wire electrical discharge machining (WEDM) of γ titanium aluminide is studied. Selection of optimum machining parameter combinations for obtaining higher cutting efficiency and accuracy is a challenging task in WEDM due to the presence of a large number of process variables and complicated stochastic process mechanisms. In general, no perfect combination exists that can simultaneously result in both the best cutting speed and the best surface finish quality. This paper presents an attempt to develop an appropriate machining strategy for a maximum process criteria yield. A feed-forward back-propagation neural network is developed to model the machining process. The three most important parameters – cutting speed, surface roughness and wire offset – have been considered as measures of the process performance. The model is capable of predicting the response parameters as a function of six different control parameters, i.e. pulse on time, pulse off time, peak current, wire tension, dielectric flow rate and servo reference voltage. Experimental results demonstrate that the machining model is suitable and the optimisation strategy satisfies practical requirements.