Principal Component Analysis Based Dynamic Fuzzy Neural Network for Internal Corrosion Rate Prediction of Gas Pipelines

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr><td class="align_left">Evaluation metrics</td><td class="align_center">ANN</td><td class="align_center">FNN</td><td class="align_center">D-FNN</td><td class="align_center">PCA-D-FNN</td></tr><tr><td class="align_left" colspan="5"><hr/></td></tr><tr><td class="align_left">RMSE</td><td class="align_center">0.7324</td><td class="align_center">0.6121</td><td class="align_center">0.4931</td><td class="align_center">0.4133</td></tr><tr><td class="align_left">MAPE (%)</td><td class="align_center">8.56</td><td class="align_center">7.82</td><td class="align_center">6.01</td><td class="align_center">5.32</td></tr><tr class="table-tr"><td colspan="5"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The result of LOOCV with different algorithm.</div>

Mathematical Problems in Engineering

tab4

Table 4

Table 4: Principal Component Analysis Based Dynamic Fuzzy Neural Network for Internal Corrosion Rate Prediction of Gas Pipelines 