摘要
传统产量预测方法易受到单井生产历史和模型假设条件的限制,预测结果无法量化不确定性,难以考虑区块其他生产井开发规律对目标井的指导作用,无法充分利用大量相关的生产历史数据。为此,提出一种以深度自回归神经网络为基础,多井产量数据驱动的概率预测新模型。考虑生产时间、油/套压等动态协变量数据,结合贝叶斯推断,利用梯度下降算法和极大似然估计方法,得到多井共有的广义历史—未来产量概率演化模式,实现基于数据驱动的多井产量概率预测。利用鄂尔多斯盆地某两个区块943口致密气井的数据,研究了深度自回归神经网络模型在单井预测、分类预测和总体区块产量预测上的性能。研究结果表明:相比传统深度学习模型(LSTM),新模型利用学习得到的广义产量概率演化模式与目标井的特定产量历史数据相结合,形成“广义+特定”的产量概率预测方法,平均意义上较LSTM模型相对误差降低了45%。分类模型较全局模型相对误差降低了24%,实现了在全局模型的基础上,进一步降低了概率预测的不确定性,提高了特定精细分类井的预测精度。经过实际数据验证,新模型预测精度更好,鲁棒性更强,可以用于油气藏多井产量预测分析。
Traditional production rate forecasting methods are often limited by the production history of individual wells and assumptions of the models,leading to unquantified uncertainties in the prediction results and difficulty in considering the guidance of development patterns from other wells in the block on the target well.Additionally,they fail to fully utilize a large amount of relevant production history data.To address these issues,a new model for probabilistic production rate forecasting driven by multi-well production data is proposed,based on deep autoregressive neural networks.This model integrates dynamic covariate data such as production time and tubing/casing pressure,and employs Bayesian inference along with gradient descent and maximum likelihood estimation methods to derive a generalized historical-future production probability evolution pattern shared among multiple wells.Through data-driven approaches,it achieves probabilistic production forecasting for multiple wells.The performance of the deep autoregressive neural network model is studied using data from 943 tight gas wells in two blocks in the Ordos Basin.Results indicate that compared to traditional deep learning models like LSTM,the new model combines the learned generalized production probability evolution pattern with specific production history data of the target well,forming a“generalized+specific”production probability prediction method.On average,it reduces the relative error by 45%compared to the LSTM model.The classification model reduces the relative error by 24%compared to the global model,further reducing the uncertainty of probability prediction based on the global model and improving the prediction accuracy of specific fine-classified wells.Through validation with actual data,the new model demonstrates better prediction accuracy and stronger robustness,making it applicable for multi-well production forecasting analysis in oil and gas reservoirs.
作者
韩江峡
薛亮
位云生
齐亚东
王军磊
陈海洋
刘月田
HAN Jiangxia;XUE Liang;WEI Yunsheng;QI Yadong;WANG Junlei;CHEN Haiyang;LIU Yuetian(State Key Laboratory of Petroleum Resources and Engineering,China University of Petroleum-Beijing,Beijing 102249,China;College of Petroleum Engineering,China University of Petroleum-Beijing,Beijing 102249,China;PetroChina Research Institute of Petroleum Exploration&Development,Beijing 100083,China)
出处
《石油科学通报》
CAS
2024年第4期679-689,共11页
Petroleum Science Bulletin
基金
国家自然科学基金(52274048)
北京市自然科学基金(3222037)
中国石油天然气股份有限公司“十四五”前瞻性基础性科技项目子课题“致密气生产规律与开发接替模式研究”(2021DJ2104)联合资助。
关键词
产量预测
多井预测
神经网络
致密气
概率预测
区块预测
production rate forecasting
multiple well production rate forecasting
neural networks
tight gas
probabilistic forecasting
block production rate forecasting
