Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning

Peng Gao; Xuefeng Jin; Jieyu Du; Yu Han; Yanhui Zhu

doi:doi:10.11648/j.sd.20200801.13

| Peer-Reviewed

Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning

Peng Gao, Xuefeng Jin, Jieyu Du, Yu Han, Yanhui Zhu

Published in Science Discovery (Volume 8, Issue 1)

Received: 6 February 2020 Published: 17 April 2020

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

The working condition diagnosis of pumping wells is an important basis for judging it's running condition. For a long time, indicator diagram is used to solve the wave equation by mathematical method to get the downhole pump indicator diagram which is obtained to judge and analyze the working condition of oil pumping equipment. In recent years, with the development of AI (artificial intelligence) technology, how to combine artificial intelligence technology with rod pumping wells lifting technology to provide a new way of thinking for pumping wells lifting and improve the intelligence level to achieve real-time control of the well has become a difficult problem in front of technicians. After several years of research, technicians in huabei oilfield innovatively proposed to establish working diagnosis model of pumping wells through machine learning neural network algorithm. The model can realize working diagnosis of oil well by using a large number of labeled indicator diagram and working diagnostic data as training samples. As long as the labeled data provided is of high accuracy and large amount, the accuracy of the model can reach more than 90%. The model is simple in structure, fast in operation speed, and has high application value in the field. Several rod pumping wells were randomly selected from a working area of huabei oilfield, and the above model was used to diagnose the working conditions. The results showed that the average error between the diagnosis results and the real ones was only 7%, less than 10% of the common requirements, which met the needs of engineering application.

Published in	Science Discovery (Volume 8, Issue 1)
DOI	10.11648/j.sd.20200801.13
Page(s)	7-11
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2020. Published by Science Publishing Group

Keywords

Machine Learning, Rod Pumped Well, Neural Network, Working Diagnostic

References

[1]	张兴华，王俊琦，高志光，郑欣.计量油井产量的功图法技术[J].河南石油，2005，19(5)：38-40。
[2]	唐庆，王新红，孙福山，檀朝东，关成尧.抽油机井功图法量油技术先导试验[J].油气井测试，2006，15(6)：64-65。
[3]	严长亮，彭勇.泵示功图单井自动量油技术研究[J].西安石油大学学报(自然科学版) ，2006，21(6)： 92-95。
[4]	高鹏，常鹏刚，张胜利，金学锋，户虎等.基于地面功图功图算产模型建立与应用[J].钻采工艺，2018，41(2)：51-53。
[5]	韩赢，张翼翔.浅谈斜井有杆泵泵况诊断[J].石化技术，2018，25(2)：186-187。
[6]	侯延彬，陈炳均，高宪文.基于GM-ELM的有杆泵抽油井故障诊断[J].东北大学学报(自然科学版) ，2019，40(12)：1673-1678。
[7]	袁文琪，胡敏.基于示功图的油井故障诊断专家系统研究[J].电子设计工程，2015，23(18)：119-122。
[8]	陈德春，陈逸芸，孟红霞，秦延才，庄栋.助力深抽有杆泵井工况诊断模型[J].特种油气藏，2015，22(03)：144-147。
[9]	饶建华，刘宏昭，李冬平，黄伟，鄢长灏.定向井有杆抽油系统动态数值仿真与预测[J].石油机械，2004，32(8)：4-6。
[10]	薛国民，沈毅.油井计量方法及关键技术发展方向[J].工业计量，2006，16(14)：14-16。
[11]	丁建林，姜建胜，刘甦等.抽油机变频调速智能控制技术研究[J].石油机械，2003，31(1)：18-20。
[12]	S. G. Gibbs. Computer Diagnosis of Down-hole Conditions in Sucker-Rod Pumping Wells [J]. Journal of Petroleum Technology, 1966, 18 (1): 27-29。
[13]	S.G. Gibbs. A Method of Determining Sucker Rod Pump Performance [J]. U. S. Patent. 1967, 3 (3): 18-20。
[14]	Dory, D. R and Schmidt Z. An Improved Model for Sucker Rod Pumping[ J]. SPE Engineers Journal, 1983, 2 (2): 33-40。
[15]	R. R. Dickinson. The Use of Pattern Recognition Techniques in Analyzing Down Hole Dynamometer Cards [J]. A Thesis for the Degree of Master of science, 1987, 3 (6): 187-192。

Cite This Article

Plain Text BibTeX RIS

APA Style

Peng Gao, Xuefeng Jin, Jieyu Du, Yu Han, Yanhui Zhu. (2020). Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning. Science Discovery, 8(1), 7-11. https://doi.org/10.11648/j.sd.20200801.13

Copy | Download

ACS Style

Peng Gao; Xuefeng Jin; Jieyu Du; Yu Han; Yanhui Zhu. Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning. Sci. Discov. 2020, 8(1), 7-11. doi: 10.11648/j.sd.20200801.13

Copy | Download

AMA Style

Peng Gao, Xuefeng Jin, Jieyu Du, Yu Han, Yanhui Zhu. Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning. Sci Discov. 2020;8(1):7-11. doi: 10.11648/j.sd.20200801.13

Copy | Download

@article{10.11648/j.sd.20200801.13,
  author = {Peng Gao and Xuefeng Jin and Jieyu Du and Yu Han and Yanhui Zhu},
  title = {Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning},
  journal = {Science Discovery},
  volume = {8},
  number = {1},
  pages = {7-11},
  doi = {10.11648/j.sd.20200801.13},
  url = {https://doi.org/10.11648/j.sd.20200801.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20200801.13},
  abstract = {The working condition diagnosis of pumping wells is an important basis for judging it's running condition. For a long time, indicator diagram is used to solve the wave equation by mathematical method to get the downhole pump indicator diagram which is obtained to judge and analyze the working condition of oil pumping equipment. In recent years, with the development of AI (artificial intelligence) technology, how to combine artificial intelligence technology with rod pumping wells lifting technology to provide a new way of thinking for pumping wells lifting and improve the intelligence level to achieve real-time control of the well has become a difficult problem in front of technicians. After several years of research, technicians in huabei oilfield innovatively proposed to establish working diagnosis model of pumping wells through machine learning neural network algorithm. The model can realize working diagnosis of oil well by using a large number of labeled indicator diagram and working diagnostic data as training samples. As long as the labeled data provided is of high accuracy and large amount, the accuracy of the model can reach more than 90%. The model is simple in structure, fast in operation speed, and has high application value in the field. Several rod pumping wells were randomly selected from a working area of huabei oilfield, and the above model was used to diagnose the working conditions. The results showed that the average error between the diagnosis results and the real ones was only 7%, less than 10% of the common requirements, which met the needs of engineering application.},
 year = {2020}
}

Copy | Download

TY  - JOUR
T1  - Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning
AU  - Peng Gao
AU  - Xuefeng Jin
AU  - Jieyu Du
AU  - Yu Han
AU  - Yanhui Zhu
Y1  - 2020/04/17
PY  - 2020
N1  - https://doi.org/10.11648/j.sd.20200801.13
DO  - 10.11648/j.sd.20200801.13
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 7
EP  - 11
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20200801.13
AB  - The working condition diagnosis of pumping wells is an important basis for judging it's running condition. For a long time, indicator diagram is used to solve the wave equation by mathematical method to get the downhole pump indicator diagram which is obtained to judge and analyze the working condition of oil pumping equipment. In recent years, with the development of AI (artificial intelligence) technology, how to combine artificial intelligence technology with rod pumping wells lifting technology to provide a new way of thinking for pumping wells lifting and improve the intelligence level to achieve real-time control of the well has become a difficult problem in front of technicians. After several years of research, technicians in huabei oilfield innovatively proposed to establish working diagnosis model of pumping wells through machine learning neural network algorithm. The model can realize working diagnosis of oil well by using a large number of labeled indicator diagram and working diagnostic data as training samples. As long as the labeled data provided is of high accuracy and large amount, the accuracy of the model can reach more than 90%. The model is simple in structure, fast in operation speed, and has high application value in the field. Several rod pumping wells were randomly selected from a working area of huabei oilfield, and the above model was used to diagnose the working conditions. The results showed that the average error between the diagnosis results and the real ones was only 7%, less than 10% of the common requirements, which met the needs of engineering application.
VL  - 8
IS  - 1
ER  -

Copy | Download

Author Information

Peng Gao

Institute of Oil and Gas Recovery, Engineering Technology Research Institute of Huabei Oilfield Company, Renqiu, China
Xuefeng Jin

Institute of Oil and Gas Recovery, Engineering Technology Research Institute of Huabei Oilfield Company, Renqiu, China
Jieyu Du

Institute of Engineering Technology, The Fourth Exploit Factory of Huabei Oilfield Company, Langfang, China
Yu Han

Institute of Engineering Technology, The Fourth Exploit Factory of Huabei Oilfield Company, Langfang, China
Yanhui Zhu

Institute of Oil and Gas Recovery, Engineering Technology Research Institute of Huabei Oilfield Company, Renqiu, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Peng Gao, Xuefeng Jin, Jieyu Du, Yu Han, Yanhui Zhu. (2020). Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning. Science Discovery, 8(1), 7-11. https://doi.org/10.11648/j.sd.20200801.13

Copy | Download

ACS Style

Peng Gao; Xuefeng Jin; Jieyu Du; Yu Han; Yanhui Zhu. Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning. Sci. Discov. 2020, 8(1), 7-11. doi: 10.11648/j.sd.20200801.13

Copy | Download

AMA Style

Peng Gao, Xuefeng Jin, Jieyu Du, Yu Han, Yanhui Zhu. Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning. Sci Discov. 2020;8(1):7-11. doi: 10.11648/j.sd.20200801.13

Copy | Download

@article{10.11648/j.sd.20200801.13,
  author = {Peng Gao and Xuefeng Jin and Jieyu Du and Yu Han and Yanhui Zhu},
  title = {Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning},
  journal = {Science Discovery},
  volume = {8},
  number = {1},
  pages = {7-11},
  doi = {10.11648/j.sd.20200801.13},
  url = {https://doi.org/10.11648/j.sd.20200801.13},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sd.20200801.13},
  abstract = {The working condition diagnosis of pumping wells is an important basis for judging it's running condition. For a long time, indicator diagram is used to solve the wave equation by mathematical method to get the downhole pump indicator diagram which is obtained to judge and analyze the working condition of oil pumping equipment. In recent years, with the development of AI (artificial intelligence) technology, how to combine artificial intelligence technology with rod pumping wells lifting technology to provide a new way of thinking for pumping wells lifting and improve the intelligence level to achieve real-time control of the well has become a difficult problem in front of technicians. After several years of research, technicians in huabei oilfield innovatively proposed to establish working diagnosis model of pumping wells through machine learning neural network algorithm. The model can realize working diagnosis of oil well by using a large number of labeled indicator diagram and working diagnostic data as training samples. As long as the labeled data provided is of high accuracy and large amount, the accuracy of the model can reach more than 90%. The model is simple in structure, fast in operation speed, and has high application value in the field. Several rod pumping wells were randomly selected from a working area of huabei oilfield, and the above model was used to diagnose the working conditions. The results showed that the average error between the diagnosis results and the real ones was only 7%, less than 10% of the common requirements, which met the needs of engineering application.},
 year = {2020}
}

Copy | Download

TY  - JOUR
T1  - Study on Working Diagnosis of Rod Pumping Wells Based on Machine Learning
AU  - Peng Gao
AU  - Xuefeng Jin
AU  - Jieyu Du
AU  - Yu Han
AU  - Yanhui Zhu
Y1  - 2020/04/17
PY  - 2020
N1  - https://doi.org/10.11648/j.sd.20200801.13
DO  - 10.11648/j.sd.20200801.13
T2  - Science Discovery
JF  - Science Discovery
JO  - Science Discovery
SP  - 7
EP  - 11
PB  - Science Publishing Group
SN  - 2331-0650
UR  - https://doi.org/10.11648/j.sd.20200801.13
AB  - The working condition diagnosis of pumping wells is an important basis for judging it's running condition. For a long time, indicator diagram is used to solve the wave equation by mathematical method to get the downhole pump indicator diagram which is obtained to judge and analyze the working condition of oil pumping equipment. In recent years, with the development of AI (artificial intelligence) technology, how to combine artificial intelligence technology with rod pumping wells lifting technology to provide a new way of thinking for pumping wells lifting and improve the intelligence level to achieve real-time control of the well has become a difficult problem in front of technicians. After several years of research, technicians in huabei oilfield innovatively proposed to establish working diagnosis model of pumping wells through machine learning neural network algorithm. The model can realize working diagnosis of oil well by using a large number of labeled indicator diagram and working diagnostic data as training samples. As long as the labeled data provided is of high accuracy and large amount, the accuracy of the model can reach more than 90%. The model is simple in structure, fast in operation speed, and has high application value in the field. Several rod pumping wells were randomly selected from a working area of huabei oilfield, and the above model was used to diagnose the working conditions. The results showed that the average error between the diagnosis results and the real ones was only 7%, less than 10% of the common requirements, which met the needs of engineering application.
VL  - 8
IS  - 1
ER  -

Copy | Download