Fault detection and classification in oil wells and production/service lines using random forest

被引：46

作者：

Marins, Matheus A. ^{[1
]}

Barros, Bettina D. ^{[1
,2
]}

Santos, Ismael H. ^{[3
]}

Barrionuevo, Daniel C. ^{[3
]}

Vargas, Ricardo E. V. ^{[4
]}

Prego, Thiago de M. ^{[5
]}

de Lima, Amaro A. ^{[5
]}

de Campos, Marcello L. R. ^{[1
]}

da Silva, Eduardo A. B. ^{[1
]}

Netto, Sergio L. ^{[1
]}

机构：

[1] Univ Fed Rio de Janeiro, Elect Engn Program, POB 68504, BR-21947970 Rio De Janeiro, RJ, Brazil

[2] Norwegian Univ Sci & Technol, Dept Elect Syst, Trondheim, Norway

[3] Petr Brasileiro SA, BR-20211160 Rio De Janeiro, RJ, Brazil

[4] Petr Brasileiro SA, BR-29057570 Vitoria, ES, Brazil

[5] CEFET NI, BR-26041271 Nova Iguacu, RJ, Brazil

来源：

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING | 2021年 / 197卷

关键词：

Fault detection and classification; Oil well monitoring; Abnormal event management; Random forest classifier; Machine learning; MACHINE;

D O I：

10.1016/j.petrol.2020.107879

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：

This papers deals with the automatic detection and classification of faulty events during the practical operation of oil and gas wells and lines. The events considered here are part of the publicly available 3W database developed by Petrobras, the Brazilian oil holding. Seven fault classes are considered, with distinct dynamics and patterns, as well as several instances of normal operation. A random forest classifier is employed with different statistical measures to identify each fault type. Three experiments are devised in order to evaluate the system performance in distinct classification scenarios. An accuracy rate of 94% indicates a successful performance for the proposed system in detecting real events. Also, the system's time of detection was on average 12% of the transient period that precedes the fault steady-state.

引用

页数：10

共 32 条

[1]

Abu-Mostafa Y.S., 2012, Learning from Data AML Book

[2]

Aggarwal CC, 2001, LECT NOTES COMPUT SC, V1973, P420

[3] Automatic Detection of Anomalous Drilling Operations Using Machine Learning Methods and Drilling Process Simulations [J].

Ambrus, A. ;

Saadallah, N. ;

Alyaev, S. ;

Iversen, F. .

OIL GAS-EUROPEAN MAGAZINE, 2019, 45 (01) :17-18

[4]

[Anonymous], BRAZ MAR BIODIV

[5]

[Anonymous], 2013, Pattern Recognition and Machine Learning, DOI [DOI 10.18637/JSS.V017.B05, 10.1117/1.2819119]

[6] Random forest in remote sensing: A review of applications and future directions [J].

Belgiu, Mariana ;

Dragut, Lucian .

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2016, 114 :24-31

[7] Random forests [J].

Breiman, L .

MACHINE LEARNING, 2001, 45 (01) :5-32

[8] On the meaning and use of kurtosis [J].

DeCarlo, LT .

PSYCHOLOGICAL METHODS, 1997, 2 (03) :292-307

[9] Gene selection and classification of microarray data using random forest -: art. no. 3 [J].

Díaz-Uriarte, R ;

de Andrés, SA .

BMC BIOINFORMATICS, 2006, 7 (1)

[10]

Feng Changyong, 2014, Shanghai Arch Psychiatry, V26, P105, DOI 10.3969/j.issn.1002-0829.2014.02.009

← 1 2 3 4 →