Please enable JavaScript for this site to function properly.
OnePetro
  • Help
  • About us
  • Contact us
Menu
  • Home
  • Journals
  • Conferences
  • Log in / Register

Log in to your subscription

and
Advanced search Show search help
  • Full text
  • Author
  • Company/Institution
  • Publisher
  • Journal
  • Conference
Boolean operators
This OR that
This AND that
This NOT that
Must include "This" and "That"
This That
Must not include "That"
This -That
"This" is optional
This +That
Exact phrase "This That"
"This That"
Grouping
(this AND that) OR (that AND other)
Specifying fields
publisher:"Publisher Name"
author:(Smith OR Jones)

Innovative Deep Autoencoder and Machine Learning Algorithms Applied in Production Metering for Sucker-Rod Pumping Wells

Authors
Peng Yi (RIPED PetroChina) | Xiong Chunming (RIPED PetroChina) | Zhang Jianjun (RIPED PetroChina) | Zhang Yashun (Data Company of Xin Jiang Oilfield Company PetroChina) | Gan Qinming (Oil & Gas Technology Research Institute of Changqing Oilfield Company PetroChina) | Xu Guojian (Data Company of Xin Jiang Oilfield Company PetroChina) | Zhang Xishun (RIPED PetroChina) | Zhao Ruidong (RIPED PetroChina) | Shi Junfeng (RIPED PetroChina) | Liu Meng (RIPED PetroChina) | Wang Cai (RIPED PetroChina) | Chen Guanhong (RIPED PetroChina)
DOI
https://doi.org/10.15530/urtec-2019-1090
Document ID
URTEC-2019-1090-MS
Publisher
Unconventional Resources Technology Conference
Source
SPE/AAPG/SEG Unconventional Resources Technology Conference, 22-24 July, Denver, Colorado, USA
Publication Date
2019
Document Type
Conference Paper
Language
English
Copyright
2019. Unconventional Resources Technology Conference
Downloads
15 in the last 30 days
101 since 2007
Show more detail
SPE Member Price: USD 9.50
SPE Non-Member Price: USD 28.00

Abstract

With the depletion of reservoirs, it is inevitable that once very prolific conventional and unconventional wells become stripper wells characterized as producing no more than 35 barrels of liquid equivalent per day over a 12-month period. Conventional metering strategy is not economic for its huge investment on facilities, equipment, sensors and ongoing maintenance compared to current low production. This paper presents an innovative method utilizing state-of-art artificial intelligent algorithms to predict the production rate from real-time IIot testing and producing data with very low cost and reliable accuracy.

Abundant real-time field and well data acquired from IIot and digital field facilities establish a fundamental foundation for developing a machine learning application. This paper presents a method to predict the real-time production rate from real-time IIot data. In our method, we start with constructing our datasets from different data sources by combining the dynamometer cards, pumping stroke and rate, pump, rod, wellbore and reservoir parameters as inputs and the corresponded production rate as targets. The machine-learning model contains two neural networks: first, a deep autoencoder to extract the feature representations from all the dynamometer cards; then another neural network combining all related features to predict the real-time production.

The deep autoencoder derived features from dynamometer cards are used as parts of inputs to further real-time production prediction model, which eliminate the disadvantage of conventional hand-crafted features. Hand-crafted features can lose important information whereas autoencoder is designed to minimize information loss by learning high level features that can be used to reconstruct the cards. The production prediction model with pump and producing data combining more informative abstract features generate a good accordance with the history data. After tested testing and validating data in several fields in one operator's fields in China, the model demonstrate very high accuracy and with R2 more than 0.92, MAE less than 0.5 of wells producing less 5m3/day, RMSE less than 1.6 of wells producing 5-10m3/day and RMSE less than 2.2 of wells producing more than 10m3/day. The model has also been tested on hundreds of newly producing wells and with error in 10%, comparing with high resolution real-time metering equipment.

The method described in this paper can be fully utilized to metering the real-time production with ultra-low cost in wells as long as acquiring real-time dynamometer card. With the fast development of artificial intelligence technology and expanding training datasets, artificial intelligence is a good choice to lower the investment and maintenance cost for conventional and unconventional fields in the low oil price trend.

File Size  404 KBNumber of Pages   8

Other Resources

Looking for more? 

Some of the OnePetro partner societies have developed subject- specific wikis that may help.


 


PetroWiki was initially created from the seven volume  Petroleum Engineering Handbook (PEH) published by the  Society of Petroleum Engineers (SPE).








The SEG Wiki is a useful collection of information for working geophysicists, educators, and students in the field of geophysics. The initial content has been derived from : Robert E. Sheriff's Encyclopedic Dictionary of Applied Geophysics, fourth edition.

  • Home
  • Journals
  • Conferences
  • Copyright © SPE All rights reserved
  • About us
  • Contact us
  • Help
  • Terms of use
  • Publishers
  • Content Coverage
  • Privacy
  Administration log in