Comparison of data mining algorithms for pressure prediction of crude oil pipeline to identify congeal

Data mining is applied in many areas. In oil and gas industries, data may be implemented to support the decision making their operation prevent a massive loss. One of serious problems petroleum industry congeal phenomenon, since it leads block crude flow during transport pipeline system. system, pressure online monitoring usually control phenomenon. However, this system not able predict on next several days. This research purposed compare prediction using algorithms based real historical from field. To find best algorithms, was compared 4 i.e. Random Forest, Multilayer Perceptron (MLP), Decision Tree, Linear Regression. As result, Regression shows performance among with R 2 = 0.55 RMSE 28.34. confirmed that algorithm good method pipeline, even accuracy values should improved. have better accuracy, necessary collect more