Warning: Undefined array key 20 in /customers/2/c/3/ijaiem.org/httpd.www/pabstract2.php on line 40
Call of Papers for Current Volume **************** OnLine Submission of Paper

Title: Surface Finish Analysis of D2 Steel in WEDM using ANN & Regression Modelling along with Fractional Factorial Design of Experiments

_____________________________________________________________________________

Title:
Surface Finish Analysis of D2 Steel in WEDM using ANN & Regression Modelling along with Fractional Factorial Design of Experiments
Author Name:
U.K.Vates, N.K. Singh, Mr. B.N.Tripathi
Abstract:
Wire electrical discharge machining (WEDM) is an important metal removal process in precision manufacturing of mould and dies, which comes under non traditional machining processes. It is also quite difficult to find the correct input parametric combinations to give lowest possible values of surface roughness of D2 steel under WEDM.. Non-conventional WEDM process under low temperature dielectric (DI water) is more robust and powerful approach than conventional machining process to obtaining better surface finish in low temperature treated tool steels. Low temperature dielectric cooling medium implementation generally used as secondary treatment to enhance the surface smoothness. Present work aimed to effect of WEDM parameters on surface finish of low temperature treated AISI D2 tool steel is investigated. Montgomery fractional factorial design of experiment, L16 orthogonal array was selected for conducting the experiments. The surface roughness and its corresponding material removal rate (MRR) were considered as responses for improving surface finish. The Analysis of variance (ANOVA) was done to find the optimum machining parametric combination for better surface finish. The experimental result shows that the model suggested by the Montgomerys method is suitable for improving the surface finish. Regression (RA) analysis method and Artificial Neural Network (ANN) were used to formulate the mathematical models. Based on optimal parametric combination, experiments were conducted to confirm the effectiveness of the proposed ANN model.
Back