Internet of things and big data analytics for smart oil field malfunction diagnosis

Birong Xu, Weijiang Wang, Yuyan Wu, Yueting Shi, Chang Lu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Citations (Scopus)

Abstract

With the rapid development of information technology and digital communication, the data types are more abundant by integration of various technologies. In this paper, based on the analysis of a large number of historical data of oil and water wells, the changes of some important parameters of the wells can be monitored and then used in the trend prediction and the early warning system. Subsequently, we use 6 Sigma algorithm to process the historical data, and by the big data trend analysis combining with various parameters, we can diagnose six operating conditions, such as sand production, abnormal of moisture content etc. Through experiments, the algorithm is stable and reliable in practical application, and it has great significance to ensure the normal production of oil field and improve the management ability for oil field.

Original languageEnglish
Title of host publication2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages178-181
Number of pages4
ISBN (Electronic)9781509036189
DOIs
Publication statusPublished - 20 Oct 2017
Event2nd IEEE International Conference on Big Data Analysis, ICBDA 2017 - Beijing, China
Duration: 10 Mar 201712 Mar 2017

Publication series

Name2017 IEEE 2nd International Conference on Big Data Analysis, ICBDA 2017

Conference

Conference2nd IEEE International Conference on Big Data Analysis, ICBDA 2017
Country/TerritoryChina
CityBeijing
Period10/03/1712/03/17

Keywords

  • 6 sigma
  • big data
  • internet of thing
  • oil field fault diagnosis
  • warning thresholds scheme

Fingerprint

Dive into the research topics of 'Internet of things and big data analytics for smart oil field malfunction diagnosis'. Together they form a unique fingerprint.

Cite this