Abstract
Prediction of drilling cost in oil and gas field has an important impact on correct economic decision-making and economic efficiency of oilfield enterprises. Support Vector Machine (SVR) is used to predict the drilling cost of oil and gas in this paper. In order to overcome problem of easy to cause local optimum of SVR, this paper uses self-adaptive differential evolution (SaDE) to train SVR to accelerate the speed of parameters optimization and improve the predictive accuracy of the model. The proposed model is applied to predict the drilling costs in one of the Chinese oil company. SaDE is also compared with three parameter optimization methods, Differential Evolution(DE), Grid Search(GS) and Genetic Algorithms(GA). The experimental results show that, SaDE-SVR model is better than DE-SVR, GS-SVR and GA-SVR in terms of accuracy and convergence speed in predicting the drilling cost. It validates the effectiveness of SaDE-SVR applied in prediction of drilling cost of oil and gas field.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fan, M., et al.: Study of cost drivers of oil and gas drilling operations. Journal of Southwest Petroleum University 1, 113–117 (2007)
Liu, T., et al.: Drilling cost projection of oil and gas based on BP neural network. Journal of Xian Shiyou University(Natural Science Edition) 1, 87–90 (2010)
Ma, J.: Research on and Application of SVR-based Well-drilling Cost. Xian Shiyou University 1–3 (2010)
Price, K.: Differential evolution: A fast and simple numerical optimizer. In: Proc. North American Fuzzy Information Processing Conf, pp. 524–527 (1997)
Qin, A.K., Huang, V.L., Suganthan, P.N.: Differential Evolution Algorithm With Strategy Adaptation for Global Numerical Optimization. IEEE Transactions on Evolutionary Computation 13, 398–417 (2009)
Sanchez, A.D.: Advanced vector machines and kernel methods. J. Neurocomputing 1, 5–20 (2003)
Price, K., Storn, R.: Differential evolution. Dr. Dobbs J. 18–20 (1997)
Abbasss, H.A.: Self-adaptive pereto differential evolution. In: Proceedings of the IEEE 2002 Congress on Evolutionary Compution, pp. 831–836. IEEE Press (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pan, H., Cheng, G., Ding, J. (2013). Drilling Cost Prediction Based on Self-adaptive Differential Evolution and Support Vector Regression. In: Yin, H., et al. Intelligent Data Engineering and Automated Learning – IDEAL 2013. IDEAL 2013. Lecture Notes in Computer Science, vol 8206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41278-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-41278-3_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41277-6
Online ISBN: 978-3-642-41278-3
eBook Packages: Computer ScienceComputer Science (R0)