Search results

Wire electric discharge machining (WEDM) is a non-conventional machining process, which is used to provide difficult and intricate shapes. The purpose of this research work is to apply Taguchi’s technique to optimize the process parameters in WEDM. Alloy steel 20MnCr5 has been selected as base material for experimentation. The effects of the input process parameters such as wire type, pulse-on time, pulse-off time, peak current, wire feed rate and servo voltage have been calculated on the material removal rate (MRR) and surface roughness (Ra) in WEDM operation.

In the research work, Taguchi's technique is applied to optimize the process parameters in WEDM.

ANOVA indicated that pulse-off time was the most significant factor for the MRR, and servo voltage was the most significant factor for surface roughness (SR). As a part of the project, 20MnCr5 was machined in wire electric discharge machine, and the optimal control parameters were found to get higher MRR and better SR using Taguchi’s technique.

To the best of authors’ knowledge, after reviewing the literature, materials including alloys of metals such as 16MnCr5 and 20MnCr5 have not been investigated so far, and research regarding machining of these materials is limited. Therefore, 20MnCr5 material has been selected for this research work to generate WEDM data.

The purpose of this paper is to predict the machining performance of electrical discharge machining of Ti-13Nb-13Zr (TNZ) alloy, a promising biomedical alloy, using artificial neural networks (ANN) models.

In the research, three major performance characteristics, i.e. the material removal rate (MRR), tool wear rate (TWR) and surface roughness (SR), were chosen for the study. The input parameters for machining were the voltage, current, pulse-on time and pulse-off time. For the ANN model, a two-layer feedforward network with sigmoid hidden neurons and linear output neurons were chosen. Levenberg–Marquardt backpropagation algorithm was used to train the neural networks.

The optimal ANN structure comprises four neurons in input layer, ten neurons in hidden layer and one neuron in the output layer (4–10-1). In predicting MRR, the 60–20-20 data split provides the lowest MSE (0.0021179) and highest R-value for training (0.99976). On the contrary, the 70–15-15 data split results in the best performance in predicting both TWR and SR. The model achieves the lowest MSE and highest R-value for training in predicting TWR as 1.17E-06 and 0.84488, respectively. Increasing the number of hidden neurons of the network further deteriorates the performance. In predicting SR, the authors find the best MSE and R-value as 0.86748 and 0.94024, respectively.

This is a novel approach in performance prediction of electrical discharge machining in terms of new workpiece material (TNZ alloys).