23.12.2014 Views

OCTOBER 19-20, 2012 - YMCA University of Science & Technology

OCTOBER 19-20, 2012 - YMCA University of Science & Technology

OCTOBER 19-20, 2012 - YMCA University of Science & Technology

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

Proceedings <strong>of</strong> the National Conference on<br />

Trends and Advances in Mechanical Engineering,<br />

<strong>YMCA</strong> <strong>University</strong> <strong>of</strong> <strong>Science</strong> & <strong>Technology</strong>, Faridabad, Haryana, Oct <strong>19</strong>-<strong>20</strong>, <strong>20</strong>12<br />

5.8<br />

Best Linear Fit: A = (1.2) T + (-0.386)<br />

Best Linear Fit: A = (0.296) T + (0.00579)<br />

5.6<br />

R = .979<br />

R = 1<br />

Pred Ra (A)<br />

5.4<br />

5.2<br />

5<br />

4.8<br />

4.6<br />

Data Points<br />

Best Linear Fit<br />

A = T<br />

Pred MRR (A)<br />

9<br />

8.5<br />

8<br />

9.5 x 10-3 Expt MRR (T)<br />

Data Points<br />

Best Linear Fit<br />

A = T<br />

4.4<br />

7.5<br />

4.2<br />

7<br />

4<br />

3.8<br />

3.8 4 4.2 4.4 4.6 4.8 5<br />

Expt Ra (T)<br />

6.5<br />

6.5 7 7.5 8 8.5 9 9.5<br />

x 10 -3<br />

Figure 7 Correlation <strong>of</strong> the testing patterns for MRR and R a<br />

5. Conclusion<br />

The training and testing data set was taken from experiments on self developed setup on EDM, based on L 9 OA.<br />

The ANN back propagation algorithm with four inputs, two outputs, and one hidden layer with 23 neurons has<br />

been employed to establish the process model. The model after proper training is capable <strong>of</strong> predicting the<br />

response parameter. The number <strong>of</strong> hidden layer neurons and the learning factors employed are found to be<br />

suitable for the present investigation. There exist highly non-linear relationships between MRR, R a and the<br />

machining conditions. This justifies the use <strong>of</strong> ANN to develop the model.<br />

6. References<br />

1.Aguair P. R., Dotto F. R. L. and Bianch E. C. (<strong>20</strong>05), “Study <strong>of</strong> Thresholds to Burning in Surface Grinding<br />

Process,” Journal <strong>of</strong> the Brazillian Society <strong>of</strong> Mechanical <strong>Science</strong>s and Engineering, Vol. 27(2), pp 150-156.<br />

2.Erden A., and Kaftanoglu B. (<strong>19</strong>81), “Heat Transfer Modeling <strong>of</strong> Electric Discharge Machining, in: Proc. 21st<br />

Int. Mach. Tool Des. Research Conf., London.<br />

3.Schalk<strong>of</strong>f, R.B. (<strong>19</strong>97) “Artificial Neural Networks” McGraw-Hill International Ed.<br />

549

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!