UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Analysis of Oil and Gas Big Data Using Artificial Intelligence

Vahabi, N; (2017) Analysis of Oil and Gas Big Data Using Artificial Intelligence. Presented at: UNSPECIFIED. Green open access

[thumbnail of EEE Barlow Lecture 2017(Nafiseh_Vahabi)Final.pdf]
Preview
Text
EEE Barlow Lecture 2017(Nafiseh_Vahabi)Final.pdf

Download (1MB) | Preview

Abstract

Monitoring in-well flow is essential for the oil and gas industry to manage the oil field. The flow surveillance identifies the well condition allowing optimisation of the quality and volume of oil or gas production and saving costs for the oil companies. The well operators need to know the type of fluid in the pipe, the combination and ratio of each fluid in multi phase flow regimes (e.g. gas, oil, water), the settings of Inflow Control Valves (ICVs) which control the flow rate in the main pipe and from several side branching pipes coming from different underground reservoirs. The well operators also need to know the speed and direction of the fluid flow at each point down the well. Distributed Acoustic Fibre optic Sensors alongside or inside the well pipe are used to collect acoustic data as a function of time from effective acoustic sensors spaced by about a metre or less along thousands of kilometres of oil and gas well. The size of collected sound data from sensors is more than a Terabyte which can be analysed successfully using Artificial Intelligence Machine Learning algorithms.

Type: Poster
Title: Analysis of Oil and Gas Big Data Using Artificial Intelligence
Open access status: An open access version is available from UCL Discovery
Language: English
Keywords: Big data, classification algorithms, multi phase flow classification.
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/1571727
Downloads since deposit
44Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item