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 mining may be implemented to support the decision making in their operation to prevent a massive loss. One of serious problems in the petroleum industry is congeal phenomenon, since it leads to block crude oil flow during transpor...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN FR |
| Publicado: |
EDP Sciences
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/b4fdc25638fb4d57a3a7fcaad53664ce |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Data mining is applied in many areas. In oil and gas industries, data mining may be implemented to support the decision making in their operation to prevent a massive loss. One of serious problems in the petroleum industry is congeal phenomenon, since it leads to block crude oil flow during transport in a pipeline system. In the crude oil pipeline system, pressure online monitoring in the pipeline is usually implemented to control the congeal phenomenon. However, this system is not able to predict the pipeline pressure on the next several days. This research is purposed to compare the pressure prediction of the crude oil pipeline using data mining algorithms based on the real historical data from the petroleum field. To find the best algorithms, it was compared 4 data mining algorithms, i.e. Random Forest, Multilayer Perceptron (MLP), Decision Tree, and Linear Regression. As a result, the Linear Regression shows the best performance among the 4 algorithms with R2 = 0.55 and RMSE = 28.34. This research confirmed that data mining algorithm is a good method to be implemented in petroleum industry to predict the pressure of the crude oil pipeline, even the accuracy of the prediction values should be improved. To have better accuracy, it is necessary to collect more data and find better performance of the data mining algorithm |
|---|