A Production Estimation Algorithm in Commingled Oil Wells Based Kernel Partial Least Square

Abstract:

Commingling is employed in the petroleum industry to enhance oil recovery and reduce costs. It is of great importance to monitor the production of each oil well oilfields. Nowadays, more and more oilfields use chromatographic fingerprint to estimate single-zone production allocation. In order to insure the efficiency and affectivity of the commingled oil well exploiting, the productivity contribution of every single layer must be acquainted. Kernel partial least squares (KPLS) is a promising regression method for tackling nonlinear systems because it can efficiently compute regression coefficients in high-dimensional feature spaces by means of nonlinear kernel functions. Unlike other nonlinear partial least squares (PLS) techniques KPLS does not entail any nonlinear optimization procedures and has a complexity similar to that of linear PLS. Using the technology of crude oil chromatography fingerprint, an algorithm for predicting productivity contribution based on KPLS is proposed. The validity of the method is proved by laboratory artificial experiments. The maximum absolute error of predicted and real proportion is less than 10%. The model can also be applied to other wells which are similar to those used in the experiment. The experiment results show the prediction model is feasible.

• Periodical: Advanced Materials Research (Volume 1051)
• Pages: 1023-1027
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1051.1023
• Online since: October 2014
• Authors: Xiao Min Yang, Bin Yu Yan*, Zong Rui Yang
• Keywords: Chromatography Fingerprinting, Commingled Oil well, Kernel Partial Least Square, Single-Zone Production Contribution

References

[1] Hwang R. J., D. K. Baskin and S. C. Teeerman, Allocation of Commingled Pipeline Oils to Field Production. Organic Geochemistry. 31(2000)1463-1474.

DOI: 10.1016/s0146-6380(00)00123-6

[2] Kaufman, R. L., A. S. Ahmed and W. B. Hempkins, A New Technique for the Analysis of Commingled Oils and its Application to Production Allocation Calculations. Paper IPA 87-23/21 (1987)247-268.

[3] Nicolle, G., Boibien, C., ten-Haven, H.L., Tegelaar, E., Chavagnac, P. H, Geochemistry: A powerful Tool for Reservoir Monitoring. SPE 37804. Society of Petroleum Engineers. Bahrain (1997).

DOI: 10.2118/37804-ms

[4] Bazan L. W, The Allocation of Gas Well Production Data Using Isotope Analysis: Proceedings of the 1998 Society of Petroleum Engineers Gas Technology Symposium, March 15-18, 1998. SPE Paper40032, (1998)1-9.

DOI: 10.2118/40032-ms

[5] Larter S. R. and Aplin A. C, Reservoir Geochemistry: Methods, Applications and Opportunities. In: England W.A., Cubitt J. (eds. ) The Geochemistry of reservoirs. 86 (1995)5-32.

DOI: 10.1144/gsl.sp.1995.086.01.02

[6] Milkov A. V., Goebel E., Dzou L., Fisher D. A., Kutch A., McCaslin N. and Bergman D. F, Compartmentalization and Time-lapse Geochemical Reservoir Surveillance of the Horn Mountain Oil Field, AAPG Bulletin 91 (2007). 847-876.

DOI: 10.1306/01090706091

[7] Hastie, T. J., Tibshirani, R. J, Generalized Additive Models M. Chapman and Hall, London ( 1990).

[8] Wenxiang He, Peirong Wang, Yi Liu, Caixue Li, Proportion Fingerprint Palte of Single-source Oil Sample and its Application to Analysis of Commingled wells J. Petroleum Exploration and Development. 28 (2001)82-83. (in Chinese).

[9] Zhengping Wang, Xiaotai Fu, Shuangfang Lu, et al, A Monitoring Technique for Production Allocation of Commingled Production Well with Liquid Chromatography J. Geochimica. 29 (2000) 297-301. (in Chinese).

[10] Shijia Chen, Feng Lin, Xiaofan Chen et al, Calculating Xeparate Zone Peoduction of Commingled Wells Using Oil Chromatography Fingerprint technique J. Petroleum Exploration and Development. 26, (1999)63-71. (in Chinese).

[11] Lei Xue, Wei Wu, et al, A Forecasting Model of Productivity Contribution in single Zone of Multi-Zone Production Based on Support Vector regression. Journal of Petrochemical Universities. 19(4 )(2006)576-587 (in Chinese).

[20] D.J. Richards, W.K. Shieh, Anoxic-oxic activated-sludge treatment of cyanides and phenols, Biotechnol. Bioeng. 33 (1989) 32-38.

DOI: 10.1002/bit.260330106

[12] Milkov A. V., Goebel E., Dzou L., Fisher D. A., Kutch A., McCaslin N. and Bergman D. F, Compartmentalization and Time-lapse Geochemical Reservoir Surveillance of the Horn Mountain Oil Field, AAPG Bulletin 91 (2007). 847-876.

DOI: 10.1306/01090706091

[13] Y. Zhang, H. Zhou, S. -J. Qin, T. Chai, Decentralized fault diagnosis of large-scale processes using multiblock kernel partial least squares, IEEE Transactions on Industrial Informatics 6 (1) (2010) 3–10.

DOI: 10.1109/tii.2009.2033181