第 48 卷第 3 期
2021 年 3 月
Vol. 48 No. 3
Mar. 2021:21-30
钻探工程
Drilling Engineering
基于人工智能的钻速预测模型数据有效性下限分析
李 谦
1
,曹彦伟
1
,朱海燕
2
(1. 成都理工大学环境与土木工程学院,四川 成都 610059;2. 成都理工大学能源学院,四川 成都 610059)
摘要:钻速预测对于 优化钻 探工艺 、降低作业成本、实现科学钻探具有 重要意 义,它是 钻探钻井作业的一项重要内
容。基于人工智能的钻速预测精度令人瞩目,但该技术需求的海量数据对传统钻探钻井作业的要求较高。为明确
使用人工智能建立钻速预测模型的最少数据量,本文基于中国南海 10 口井的 21917 条数据进行了分析。通过相关
性分析,所有的输入参数可被划分为高、中、低相关性 3 大类。通过逐步引入参数建立预测模型和对比预测精度,发
现当引入的参数数量足够时,3 种相关性参数均可建立起高精度(≥85%)的预测模型。引入参数的相关性越高,建
立高精度预测模型需求的参数量越少。通过逐步扩大取样间隔的方式,对比发现所有的预测模型均呈现随取样间
隔的增大、预 测模型 的准确性降低的规律。而预测模 型建模 的取样间隔下限可通过寻 找精度 降低时的拐点获得。
经过验证,在数据维度与取样精度均为下限时,基于 3 种相关性参数建立的 BP 神经网络预测模型仍然能够获得较
高的预测精度。
关键词:钻速预测;BP 神经网络;数据需求;有效性下限;人工智能
中图分类号:P634.9 文献标识码:A 文章编号:2096-9686(2021)03-0021-10
Discussion on the lower limit of data validity for ROP prediction
based on artificial intelligence
LI Qian
1
,CAO Yanwei
1
,ZHU Haiyan
2
(1.College of Environment and Civil Engineering, Chengdu University of Technology, Chengdu Sichuan 610059, China;
2.College of Energy, Chengdu University of Technology, Chengdu Sichuan 610059, China)
Abstract:Prediction of ROP is of great significance for optimizing drilling technology,reducing operating costs,and
realizing scientific drilling,and it is also an important part of drilling operations. The accuracy of ROP prediction with
artificial intelligence technology is remarkable,but the massive data required by this technology puts forward higher
requirements for the traditional drilling operations. To determine the minimum amount of data for ROP modeling based
on artificial intelligence,analysis was carried out based on 21917 data samples collected from 10 wells at South China
Sea. Through correlation analysis,all input parameters were divided into three categories:high,medium and low
correlation. By gradually introducing parameters to establish a prediction model to compare the accuracy,it was found
that when the number of parameters was sufficient,the parameters in all three categories can be used to establish a
high⁃precision(≥85%)prediction model;however,the higher the correlation of the parameters,the less the number
of the parameters required to set up a high accuracy prediction model. When the sampling interval is gradually
expanded,comparison found that the accuracy of all the prediction models decreased with the sampling interval
increased. The lower limit of the data sampling interval for setting up the prediction model can be obtained through
finding out the downward inflection point of prediction accuracy. It is verified that the BP neural network prediction
model based on any of the three correlation parameters can still obtain high prediction accuracy when both data
收稿日期:2020-10-30 DOI:10.12143/j.ztgc.2021.03.003
基金项目:中海石油(中国)有限公司项目“南海西部油田上产 2000 万方钻完井关键技术研究”(编号:CNOOC-KJ135ZDXM38ZJ05ZJ)子课题
“乐东 10 区超高温高压井综合提速技术研究”
作者简介:李谦,男,汉族,1987 年生,讲师,地质资源与地质工程 专 业,博士 ,从事钻井智能化分析与应用研究工作,四川 省 成都市成华区二仙
桥东三路 1 号,liqian2014@cdut.edu.cn。
引用格式:李谦,曹彦伟,朱海燕 . 基于人工智能的钻速预测模型数据有效性下限分析[J]. 钻探工程,2021,48(3):21-30.
LI Qian,CAO Yanwei,ZHU Haiyan. Discussion on the lower limit of data validity for ROP prediction based on artificial intelligence
[J]. Drilling Engineering,2021,48(3):21-30.