The Applications of BP Neural Network Based on MIV in Hydraulic Fracturing

Abstract:

As a effective stimulation, hydraulic fracturing was commonly used in the mining process of complicated low permeability reservoirs, especially in horizontal shale gas wells more widely. In this paper, we establish the BP (Back Propagation) neural network based on MIV (Mean Impact Value) which is different from traditional BP neural network. We choose the independent variables of training set, plus or minus a certain percentages. Measured by the absolute size of MIV value and analyze the changes of MIV value, we identify the main factors in hydraulic fracturing. Combined qualitative analysis with quantitative calculation, the hydraulic fracturing evaluation model was established. Compared with the traditional BP neural network, the evaluation model shows a high precision, and good stability. Above all, we succeed in achieving a rapid, objective and impartial productivity prediction after hydraulic fracturing in complicated low permeability reservoirs. So in the future, this new hydraulic fracturing evaluation model is about to having abroad applications in the field of hydraulic fracturing.

• Periodical: Advanced Materials Research (Volumes 971-973)
• Pages: 300-305
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.971-973.300
• Online since: June 2014
• Authors: Yu Jie Su*, Rui Wu
• Keywords: Evaluation Model, Hydraulic Fracturing, MIV, Neural Network (NN), Weight

References

[1] Zhang Shi-cheng, Zhang Jin. Fracturing Theory and Application [M]. Beijing: Petroleum Industry Press. (2003).

[2] Tang Ying, Tang Xuan, Wang Guang-yuan, ZHANG Qin. Summary of shale gas development technology of hydraulic fracturing[J]. Geological Bulletin of China. 2011(Z1).

[3] Ma Chaoqun, Huang Lei, Fan Hu, Zeng Junfeng, Hou Mingming, Liu TaoFracture in shale gas play and the evaluation of its effects[J] Petrochemical Industry Application. 2011(05).

[4] MAYERHOFER MJ, RICHARDSON M F, Walkerjr R N, et al. Proppants-we don't need no proppants. SPE Annual Technical Conference and Exhibition . (1997).

DOI: 10.2118/38611-ms

[5] P Kaufman, G S Penny, J Paktinat. Critical eval-uations of additives used in shale Slickwater Fracs. SPE Shale Gas Production Conference SPE 119900 . (2008).

DOI: 10.2118/119900-ms

[6] Mcdanlel B W, Surjatmdjaj B, Sutherland R L, et al. Evolving newstimulation process proves highly ef-fective in level1Dual-Lateral Completion. SPE East-ern Regional Meeting SPE 78697 . (2002).

[7] Al-Fattah SM, Startzman RA. Neural Network Approach Predicts US. Natural Gas Production. SPE82411 . (2003).

DOI: 10.2118/67260-ms

[8] LI Yun, LIU Zhi-Bin. Modern optimization techniques in oil field development application[M]. 2011. 63-67.

[9] Sun Dong-Sheng, Wang Hong-Cai, Hou Mo, Zhao Wei-Hua, Song Qing-Xin, Liu Zhen-Hua, Niu Shu-Fang. factors influencing the hydrofracturing in a low permeability oilfield and potential evaluation using artificial neutral network[J]. Journal of Geomechanics, 2006, 12(4): 485~491.

[10] Chen Shou-Ping, Dong Rui. MATLAB Neural Networks 30 Case Studies[M]. Beijing University of Aeronautics and Astronautics Press: Matlab Chinese Forum, (2010).

[11] Wei Yun-Sheng. Hu Yong-Quan. Zhao Jin-zhou. Artificial Neural Network in hydraulic fracturing wells election assessment layer[J]. Fault-block Oil & Gas Field, 2005, 12(4): 42~46.

[12] WANG Da-li, CHEN Yu-ying. Feedforward neural network is used to predict the effect of fracturing GEOPHYSICAL PROSPECTING FOR PETROLE, 2000, 39(3): 121-126.

[13] Sun Wen-Bins，Liu Xi-liang. Weight analysis of cast blasting effective factors based on MIV method[J] . Journal of China University of Mining & Technology2012, 41(6): 993-998.

[14] Zeng Shun-peng, Fan Xue-ping, Yang Xiu-wen. Application of nervous net expert system in choosing fracturing well and layer[J]. SPECIAL OIL & GAS RESERVOIRS, 1997, 4 (3)42- 46.