Issue |
E3S Web Conf.
Volume 325, 2021
ICST 2021 – The 2nd Geoscience and Environmental Management Symposium
|
|
---|---|---|
Article Number | 02002 | |
Number of page(s) | 5 | |
Section | Land, Water, and Natural Resources | |
DOI | https://doi.org/10.1051/e3sconf/202132502002 | |
Published online | 17 November 2021 |
Comparison of data mining algorithms for pressure prediction of crude oil pipeline to identify congeal
1
Department of Electrical Engineering and Information Engineering, Faculty of Engineering, Universitas Gadjah Mada, Jl. Grafika 2, Yogyakarta, Indonesia
2
Department of Mechanical and Industrial Engineering, Faculty of Engineering, Universitas Gadjah Mada, Jl. Grafika 2, Yogyakarta, Indonesia
* Corresponding author: agussantosokul@gmail.com
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
© The Authors, published by EDP Sciences, 2021
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.