摘要
针对在钻井过程中面临的提速困难、地层可钻性难以预测以及成本高等问题,提出一种混合深度神经网络模型来预测地层的可钻性,从而实现钻井提速以及降低成本的效果。岩石可钻性评价指标有多种,重新定义单位能量下的钻进速度作为岩石可钻性的评价标准,并对比3种人工智能模型,采用决定系数(R^(2))、均方根误差(root mean square error,RMSE)和平均绝对误差(mean absolute error,MAE)作为模型的评估指标。岩石性质作为地层的物理特性之一,对钻井效率有直接的影响。为此,根据岩石性质的不同,将岩性划分为5个等级并进行数字化编码。通过比较加入岩性前后的模型预测精度,结果显示,加入岩性后模型的预测精度显著提高,其中卷积神经网络(convolutional neural networks,CNN)-双向门控循环单元(bidirectional gated recurrent unit,BIGRU)-注意力机制(Attention)模型的R2从0.91提升至0.97,增幅为0.06。由此可见,岩性对地层可钻性预测具有重要影响,且CNN-BIGRU-Attention模型的预测效果最佳,建议在类似地层区域推广应用,以指导区块钻井提速。
In response to the challenges encountered during the drilling process,such as difficulties in increasing speed,unpredictable formation drillability,and high costs,a hybrid deep neural network model for predicting formation drillability measures was proposed.Given that multiple evaluation metrics were available for rock drillability,a novel metric for evaluating rock drillability was redefined as the drilling speed per unit of energy.The performance of three artificial intelligence models was compared using the coefficient of determination(R^(2)),root mean square error(RMSE),and mean absolute error(MAE)as evaluation criteria.The direct impact of rock properties on drilling efficiency was recognized,and the lithology was categorized into five distinct grades and digitally encoded.The inclusion of lithological data is found to improve the model s predictive accuracy significantly.Among the models,the convolutional neural networks(CNN)-bidirectional gated recurrent unit(BIGRU)-Attention model demonstrates the most substantial enhancement,with its R^(2) value increasing from 0.91 to 0.97,marking a 0.06 improvement.The results underscore the critical role of lithology in predicting formation drillability,and this the CNN-BIGRU-Attention model exhibits the highest predictive accuracy.It is recommended that this model be extensively applied in analogous geological settings to enhance drilling efficiency.
作者
刘伟吉
张家辉
程灵
祝效华
谭宾
罗鑫
LIU Wei-ji;ZHANG Jia-hui;CHENG Ling;ZHU Xiao-hua;TAN Bin;LUO Xin(School of Mechatronic Engineering,Southwest Petroleum University,Chengdu 610500,China;Oil and Gas Equipment Technology Sharing Platform in Sichuan Province,Chengdu 610500,China;Chuanqing Drilling Engineering Company Limited,CNPC,Guanghan 618399,China)
出处
《科学技术与工程》
北大核心
2025年第36期15473-15484,共12页
Science Technology and Engineering
基金
国家杰出青年科学基金(52225401)。
关键词
神经网络
机械比能
岩石可钻性
岩石性质
可钻性预测
neural network
mechanical specific energy
drillability of rock
rock property
drillability prediction
