Research of Oilfield Production Forecast Based on Least Squares Fitting and Improved BP Neural Network

Abstract:

A new method which is least squares fitting combined with improved BP neural network based on LM algorithm was put forward. In order to overcome the weak points that easy to fall into local minimum, slow convergence of traditional BP neural network, we use LM algorithm to improve it. Least-squares curve fitting can be used to reflect the overall trend of the data changes, so we adopted least squares method firstly to make curve fitting for sample data firstly. Then, we corrected the fitting error by the improved BP Neural Network which has the advantages that reflecting external factors. Finally, the fitted values and error correction values were added to get oilfield production forecast. The results show that the oilfield production forecast error is significantly lower than the single curve fitting, BP Neural Network or LMBP.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 1456-1460
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.1456
• Online since: July 2013
• Authors: Wen Bo Na, Zhi Wei Su, Ping Zhang
• Keywords: BP Neural Network (BPNN), Error Correction, Improve, Least Square Fitting, Production Forecast

References

[1] Xiuting Liu, Jun Yang, Zhongping Cheng, etc: A new method of predicting oilfield output and its application, Petroleum Exploration and Development. Vol. 29 (2002), p.74.

[2] Jixiang Fan, Hong Zhang, Hui Li, etc: Application of BP neural network and multi-variable linear regression in rate, Computer Engineering and Applications. Vol. 43 (23) (2007), p.203.

[3] Weili Xiong, Xiangjun Xie, Li Tao, etc: The Application of GM (1. 1) Gray and BP Neural Network Integrated Model in the Forecasting of Crude Oil Output, Automation in Petro-Chemical Industry. Vol. 6 (2007), p.43.

[4] Xiufeng Shao, Li Li: Single Well Production Prediction Based on Least-square Principle Curve-fitting Method, Microcomputer Application. Vol. 25 (2009), p.13.

[5] Chunsheng Li, Minxi Tan, Kejia Zhang: Research on Single Well Production Prediction Based on Improved BP Neural Networks, Science Technology and Engineering. Vol. 11 (31) (2011), p.7766.

[6] Melesse AM, Krishnaswamy J, Zhang K: Modeling coastal eutrophication at Florida Bay using neural net-works, Journal of Coastal Research. Vol. 24 (2008), p.190.

DOI: 10.2112/06-0646.1

[7] Narendra K, Parthasarathy K: Nonlinear System Identification Using Neural Networks, Int J Control, Vol. 1 (1990), p.1191.