PDG Pressure Estimation in Offshore Oil Well: Extended Kalman Filter vs. Artificial Neural Networks

被引：7
|
作者：
Apio, Andressa [1 ]
Dambros, Jonathan W., V [1 ,2 ]
Diehl, Fabio C. [1 ,3 ]
Farenzena, Marcelo [1 ]
Trierweiler, Jorge O. [1 ]
机构：
[1] Fed Univ Rio Grande do Sul UFRGS, GIMSCOP, Chem Engn Dept, R Engn Luiz Englert S-N,Campus Cent, Porto Alegre, RS, Brazil
[2] Univ Kaiserslautern, Dept Comp Sci, D-67663 Kaiserslautern, Germany
[3] Res & Dev Ctr, BR-21941915 Petrobras, RJ, Brazil
来源：
IFAC PAPERSONLINE | 2019年 / 52卷 / 01期
关键词：
Modelling and System Identification; Data Analytics and Machine Learning; Inferential sensing; State Estimation and Sensor Development; GAS-LIFT;
D O I：
10.1016/j.ifacol.2019.06.113
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The Permanent Downhole Gauge (PDG) pressure measurement is of great importance for offshore oil well modeling and control since it is measured close to the bottom hole. The PDG is installed in a remote undersea environment, which makes expensive the maintenance in case of fault. For this reason, PDG measurements are frequently unavailable. To overcome this limitation, the PDG pressure can be estimated using other available measurements. The estimation is not a simple task since, depending on process operational conditions, the multiphase flow might present limit cycles. In this work, Artificial Neural Network (ANN) and Extended Kalman Filter (EKF) are proposed as potential techniques for the PDG pressure estimation. The comparison of the results shows that ANN returns precise estimation for a short-time window after the failure, but fails when a different process operating condition is applied, while EKF returns good estimation in all the cases. (C) 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.
引用
收藏
页码：508 / 513
页数：6
相关论文
共 50 条
  • [1] State estimation in bioprocesses -: Extended Kalman Filter vs. Neural Network
    Hoerrmann, J.
    Barth, D.
    Kraeling, M.
    Roeck, H.
    [J]. NINTH IASTED INTERNATIONAL CONFERENCE ON CONTROL AND APPLICATIONS, 2007, : 238 - +
  • [2] Artificial Neural Networks and Extended Kalman Filter for Easy-to-Implement Runoff Estimation Models
    Yoosefdoost, Arash
    Tahsien, Syeda Manjia
    Gadsden, S. Andrew
    Lubitz, William David
    Kaviani, Mitra
    [J]. PROCEEDINGS OF THE CANADIAN SOCIETY OF CIVIL ENGINEERING ANNUAL CONFERENCE 2022, VOL 1, CSCE 2022, 2023, 363 : 1071 - 1099
  • [3] Extrapolative models of dynamics systems: Neural networks vs. Kalman Filter
    Muawin, A
    Chowdhury, FN
    [J]. PROCEEDINGS OF THE TWENTY-NINTH SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY, 1997, : 315 - 319
  • [4] System identification of a robot arm with extended Kalman filter and artificial neural networks
    Horvath, Sabine
    Neuner, Hans
    [J]. JOURNAL OF APPLIED GEODESY, 2019, 13 (02) : 135 - 150
  • [5] Estimation of unmeasured inputs using recurrent neural networks and the extended Kalman filter
    Habtom, R
    Litz, L
    [J]. 1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 2067 - 2071
  • [6] A comparison of artificial neural network and extended Kalman filter based sensorless speed estimation
    Aydogmus, Zafer
    Aydogmus, Omur
    [J]. MEASUREMENT, 2015, 63 : 152 - 158
  • [7] Targeted on-line modeling for an extended Kalman filter using artificial neural networks
    Stubberud, SC
    Owen, MW
    [J]. IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 1019 - 1023
  • [8] Artificial vs. Natural Neural Networks
    Lacrama, Dan L.
    Viscu, Loredana Ileana
    Drugarin, Cornelia Victoria Anghel
    [J]. 2016 13TH SYMPOSIUM ON NEURAL NETWORKS AND APPLICATIONS (NEUREL), 2016, : 1 - 1
  • [9] State estimation of a nonlinear system by Neural Extended Kalman Filter
    Rajagopal, K.
    Pappa, N.
    [J]. 2006 ANNUAL IEEE INDIA CONFERENCE, 2006, : 23 - +
  • [10] Artificial Neural Networks vs. Artificial Immune Systems
    Dasgupta, D
    [J]. INTELLIGENT SYSTEMS, 1997, : 174 - 177
12345