Online trained controller for Electrical Submersible Pumps in liquid-gas flow

被引：2

作者：

Pineda, Luis R. ^{[1
,2
]}

Serpa, Alberto L. ^{[2
]}

Biazussi, Jorge L. ^{[3
]}

机构：

[1] Fdn Univ Amer, Dept Mech Engn, Bogota 111711, Colombia

[2] Univ Campinas Unicamp, Sch Mech Engn, Dept Computat Mech, BR-13030970 Campinas, SP, Brazil

[3] Univ Campinas Unicamp, Ctr Petr Studies CEPETRO, BR-13083893 Campinas, SP, Brazil

来源：

GEOENERGY SCIENCE AND ENGINEERING | 2023年 / 225卷

关键词：

Electrical Submersible Pump; Artificial Neural Network; Online training; Adaptive controller; MODEL-PREDICTIVE CONTROL; 2-PHASE FLOW;

D O I：

10.1016/j.geoen.2023.211713

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

The Electrical Submersible Pump (ESP) is an artificial lift method widely used in the oil industry. More than 150,000 wells worldwide are equipped with ESPs to produce cost-effective oil rates. An ESP unit usually includes an electric motor, a protective element, a gas separator (optional), and a multistage centrifugal pump. When free gas produced in the well reaches the pump stages, problems such surging and gas-locking can occur, leading to unexpected shutdowns in the oil production. In this work, a control based on Artificial Neural Networks (ANN) with online training is proposed as a solution to reduce these unplanned shutdowns. The proposed controller was designed using the direct inverse control method and the data obtained from an ESP working with a liquid-gas flow. The results of this work show that the controller can drive the operation of the ESP away from the regions where surging and gas-locking would occur. Since the controller is an online trained ANN, it was able to control the operation of two different pumps, namely the model P100 pump, the model P47 pump, and the model P23 pump.

引用

页数：9

共 25 条

[1]

Biazussi J.L., 2014, THESIS U CAMPINAS

[2] Fault identification using a chain of decision trees in an electrical submersible pump operating in a liquid-gas flow [J].

Castellanos, Mauricio Barrios ;

Serpa, Alberto Luiz ;

Biazussi, Jorge Luiz ;

Verde, William Monte ;

Dias Arrifano Sassim, Natache do Socorro .

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2020, 184

[3] Model Predictive Control with Adaptive Strategy Applied to an Electric Submersible Pump in a Subsea Environment [J].

Delou, Pedro de A. ;

de Azevedo, Julia P. A. ;

Krishnamoorthy, Dinesh ;

de Souza Jr, Mauricio B. ;

Secchi, Argimiro R. .

IFAC PAPERSONLINE, 2019, 52 (01) :784-789

[4]

El Gindy M., 2015, SOC PETROLEUM ENG AB, DOI [10.1016/j.foodchem.2015.04.057, DOI 10.1016/J.FOODCHEM.2015.04.057]

[5] Review of Electrical-Submersible-Pump Surging Correlation and Models [J].

Gamboa, Jose ;

Prado, Mauricio .

SPE PRODUCTION & OPERATIONS, 2011, 26 (04) :314-324

[6]

Hastie T., 2009, ELEMENTS STAT LEARNI

[7]

Kirby H, 2005, IEEE IND APPLIC SOC, P1908

[8] Modelling and Robustness Analysis of Model Predictive Control for Electrical Submersible Pump Lifted Heavy Oil Wells [J].

Krishnamoorthy, Dinesh ;

Bergheim, Elvira M. ;

Pavlov, Alexey ;

Fredriksen, Morten ;

Fjalestad, Kjetil .

IFAC PAPERSONLINE, 2016, 49 (07) :544-549

[9] Electrical Submersible Pump System Grounding: Current Practice and Future Trend [J].

Liang, Xiaodong ;

He, Jinwei ;

Du, Liang .

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2015, 51 (06) :5030-5037

[10]

Luenberger David G., 2008, Linear and nonlinear programming, international series in operations research management science, DOI [DOI 10.1007/978-0-387-74503-9, 10.1007/978-0-387-74503-9]

← 1 2 3 →