Journal of Engineering / 2013 / Article / Tab 7

Research Article

Estimation of Optimum Dilution in the GMAW Process Using Integrated ANN-GA

Table 7

Comparison of actual and predicted values of the clad bead parameters using neural network data (training).

Trial no.Actual bead parametersPredicted bead parametersError

(mm)

(mm)

(mm)

(%)

(mm)

(mm)

(mm)

(%)

(mm)

(mm)

(mm)

(%)

17.7411.84665.875211.42737.3352.09866.079210.82220.406−0.252−0.2040.6051
27.32312.164755.7209515.290976.82142.06175.694614.93790.50170.103050.026350.35307
39.61712.694956.3744518.540779.37132.89826.408417.45780.24580.20325−0.03391.08297
46.63352.30895.55417.231387.43062.29275.623215.7908−0.79710.0162−0.06921.44058
510.5142.72985.464520.87557.89912.51545.807818.06642.61490.2144−0.34332.8091
66.55571.990455.8058513.657626.57611.91585.786714.2039−0.02040.074650.01915−0.5462
77.47722.57376.6550515.741217.3932.71916.711214.75250.0842−0.1454−0.05610.98871
87.58862.504556.406915.778167.59432.43176.383415.9881−0.00570.072850.0235−0.2099
97.50142.18425.678216.823497.46522.28145.767416.57440.0362−0.0972−0.08920.24909
106.14211.37526.09768.9417995.65831.446.20549.37530.4838−0.0648−0.1078−0.4335
118.56473.185365.6365522.947219.97242.9625.522718.9566−1.40770.223360.113853.99061
127.95752.20185.828115.749419.06932.69196.233717.5548−1.1118−0.4901−0.4056−1.8053
137.70851.858856.0751513.272856.76991.78076.10912.85840.93860.07815−0.03380.41445
147.83652.35775.7491516.632878.53642.94316.673515.9653−0.6999−0.5854−0.92430.66757
158.20822.36585.9900516.380438.00832.3716.018616.37010.1999−0.0052−0.02850.01033
167.93712.13626.015315.183747.94412.11976.0115.3735−0.0070.01650.0053−0.1897
178.47312.171455.6989514.827588.67352.51655.498515.2875−0.2001−0.34500.2031−0.4599

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.