Long-term and short-term classified prediction on well production based on grey model and time series

Authors

  • Ziyu J

Keywords:

big data, BP neural network

Abstract

The calculation methods for predicting well production in pilot production and stable production stages are disadvantageous for insufficient precision, low efficiency, and small application scope. In order to solve these problems, a method that divides the prediction model into short-term production and long-term production was proposed. For short-term production prediction, based on the grey prediction model GM (1,1), the parameter correction on production conversion is added depending on the changes in short-term production environment, and the discrete process of the model is optimized, which makes up for the deviation of the gray derivative discrete process. For long-term production prediction, based on time series, and combing with BP neural network and the extraction results of short-term sampling eigenvalues, the cumulative production data were modeled and predicted. Using the production data of multiple wells in 2018~2020, model training, prediction and comparison were performed, and the accuracy of the results predicted by the model was analyzed. The results show that the average relative error of the prediction results of the long-term prediction model is 0. 091 4, and the average absolute error of the prediction results of the short-term prediction model is 0. 118 7. The calculation accuracy is higher than the average relative error of 0. 15 66 calculated by traditional ARIMA algorithm, which can meet the needs of actual working conditions, providing a new method for predicting of well production. © 2022 Well Testing. All rights reserved.

References

ZHAO Gaishan, Digital transformation of petroleum geophysical exploration: towards the era of real-time data acquisition, automatic processing and intelligent interpretation, Geophysical Prospecting for Petroleum, 60, 2, pp. 175-189, (2021); XUE Liang, GU Shaohua, WANG Jiabao, Et al., Production dynamic prediction of gas well based on particle swarm optimization and long short-term memory, Oil Drilling & Production Technology, 43, 4, pp. 525-531, (2021); LI Yanzun, BAI Yuhu, CHEN Guihua, Et al., ANN method based on novel technology for production of shale oil and gas:a case study in Eagle Ford, China Offshore Oil and Gas, 32, 4, pp. 104-110, (2020); ZHOU Peng, CHEN Ming, WANG Qingyong, Et al., Generalized Weibull model for predicting the production and recoverable reserves of oil and gas fields, Petroleum Geology & Oilfield Development in Daqing, 36, 5, pp. 93-97, (2017); CUI Chuanzhi, WU Zhongwei, LI Yudong, Et al., Application of the PSO-Modified GM (1,1) model to oilfield production forecast, Practice and Understanding of Mathematics, 48, 17, pp. 119-123, (2018); CUN Shaoni, CHEN Tao, XIN Yichao, Et al., Analysis of production decline law and production prediction, China Petroleum and Chemical Standard and Quality, 41, 17, pp. 29-30, (2021); GUO Liang, Application of improved multivariate linear regression to prediction of an oilfield, Journal of Xidian University (Social Science Edition), 19, 3, pp. 71-75, (2009); ROJAS IGNACIO, POMARES HECTOR, VALENZUELA OLGA, Advances in time series analysis and forecasting [ M ]; BOX GEORGE E P, JENKINS GWILYM M, REINSEL GREGORY C., Time series analysis [ M ]; CHEN Lin, LIU Zhibin, MA Nannan, Optimize production allocation for the oil-gas field basing on a novel grey model, Journal of Natural Gas Geoscience, 4, 2, pp. 121-128, (2019); HAMILTON JAMES D., Time series analysis [ M ]; WANG Xiaoli, Research on the prediction of per capita coal consumption based on the ARIMA-BP combined model, Energy Reports, 8, 4, pp. 285-294, (2022); YANG Yang, CHENG Yuefei, QIAO Ying, Et al., A study on oil pell production prediction based in time series dynamic analysis, Journal of Southwest Petroleum University (Science & Technology Edition), 42, 6, pp. 82-88, (2020); LI Jianzhou, GUAN Lijun, GAO Yonghai, Et al., Regional prediction method of hydrate formation under different yield conditions during deepwater gas well testing, Well Testing, 21, 2, pp. 17-19, (2012); DING Xianfeng, ZHANG Jinliang, LIU Zhibin, A new model for oil and gas field production prediction, Petroleum Exploration and Development, 180, 3, pp. 104-106, (2004); GAO Wenjun, XU Jun, WANG Zuojin, Et al., Improvement and Research on generalized model of oil and gas field production prediction, Petroleum Exploration and Development, 5, pp. 56-59, (2001)

Published

30-09-2022

How to Cite

Ziyu, J. (2022). Long-term and short-term classified prediction on well production based on grey model and time series. Well Testing Journal, 31(2), 26–32. Retrieved from https://welltestingjournal.com/index.php/WT/article/view/46

Issue

Section

Research Articles

Similar Articles

1 2 3 4 5 6 > >> 

You may also start an advanced similarity search for this article.