Stuck pipe is known to be influenced by drilling fluid properties and other parameters, such as the characteristics of rock formations. In this paper, we develop a support-vector-machine (SVM) based model to predict stuck pipe during drilling design and operations. To develop the model, we use a dataset, including stuck and nonstuck cases. In addition, we develop radial-base-function (RBF) neural network based model, using the same dataset, and compare its results with the SVM model. The results show that the performance of both models for prediction of stuck pipe does not differ significantly and both of them have highly accurate and can be used as the heart of an expert system to support drilling design and operations.
A New Support Vector Machine and Artificial Neural Networks for Prediction of Stuck Pipe in Drilling of Oil Fields
Contributed by the Advanced Energy Systems Division of ASME for publication in the JOURNAL OF ENERGY RESOURCES TECHNOLOGY. Manuscript received July 16, 2013; final manuscript received January 28, 2014; published online April 9, 2014. Assoc. Editor: Christopher J. Wajnikonis.
- Views Icon Views
- Share Icon Share
- Cite Icon Cite
- Search Site
Rostami, H., and Khaksar Manshad, A. (April 9, 2014). "A New Support Vector Machine and Artificial Neural Networks for Prediction of Stuck Pipe in Drilling of Oil Fields." ASME. J. Energy Resour. Technol. June 2014; 136(2): 024502. https://doi.org/10.1115/1.4026917
Download citation file:
- Ris (Zotero)
- Reference Manager