Algorithm Number of hidden layer Epoch The obtained MRE% for each output (for testing data) Average of MRE% for all outputs (for testing data) Average of MRE% for all outputs (for training data) Ic10 Ic20 Ic30 Ic40 Ic50 Ic60 Ic70 Ic80 trainbr 2 400 27.0151 17.9206 16.7244 12.0143 13.0745407 13.3276 14.1787 17.6571 16.48 12.16 trainbr 2 700 22.3788 20.0544 16.5557 15.6283 16.7017502 10.9127 17.2621 16.4354 16.99 0.3 trainbr 1 500 21.048 16.0378 17.6698 15.5808 18.6307329 14.1561 20.4347 22.0517 18.2 10.68 trainbr 1 1300 33.8414 21.0104 18.3558 12.529 15.1277031 18.2815 17.0795 19.6552 19.48 9.44 trainoss 1 700 20.7053 14.4374 15.1151 13.5781 14.2723244 17.5177 20.7295 23.9746 17.54 12.59 trainoss 1 1350 20.2299 20.2299 20.2299 20.2299 20.2299053 20.2299 20.2299 20.2299 20.22 14.21 trainoss 2 300 23.0166 17.9729 18.5065 15.644 13.347814 12.675 20.2906 24.0792 18.19 11.08 trainoss 2 800 27.17 24.0429 22.0162 19.1207 19.0589384 19.9404 16.5142 19.2009 20.88 14.5 trainrp 1 800 22.8237 18.1264 15.4406 12.8661 13.3224577 9.71382 12.1282 12.817 14.5 13.74 trainrp 1 1400 21.3078 16.2821 18.6634 17.2872 19.5747347 12.6446 21.9342 23.6726 18.92 10.46 trainrp 2 600 23.183 19.7428 22.5653 17.6145 19.198957 9.78751 20.6894 18.6031 18.923 10.62 trainrp 2 1000 36.9176 25.7577 22.384 16.2173 16.4267443 14.7662 15.7739 18.5915 20.854 9.47 trainlm 1 700 17.5779 15.7346 16.2147 14.6758 15.2469949 18.1365 15.1962 15.5707 16.04 9.29 trainlm 1 1400 33.8414 21.0104 18.3558 12.529 15.1277031 18.2815 17.0795 19.6552 19.48 9.44 trainlm 2 600 35.5098 40.2898 41.9465 43.7499 40.9964492 37.1257 48.6457 55.9676 43.028 0.022 trainlm 2 400 19.9041 19.6094 21.8283 21.7855 24.9685346 25.5053 29.3438 33.3467 24.536 0.45 trainlm 3 1000 14.13 12.28 8.3911 9.562 7.1886 11.57 13.4965 14.4031 11.375 0.311

Table 2: Comparison of the ANN configurations with different training algorithm, number of hidden layers and number of epochs.