Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVM
Sucker-rod pumping systems are the most widely applied artificial lift equipment in the oil and gas industry. Accurate and intelligent working condition recognition of pumping systems imposes major impacts on oilfield production benefits and efficiency. The shape of dynamometer card reflects the wor...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/19/5659 |
_version_ | 1797551862516285440 |
---|---|
author | Haibo Cheng Haibin Yu Peng Zeng Evgeny Osipov Shichao Li Valeriy Vyatkin |
author_facet | Haibo Cheng Haibin Yu Peng Zeng Evgeny Osipov Shichao Li Valeriy Vyatkin |
author_sort | Haibo Cheng |
collection | DOAJ |
description | Sucker-rod pumping systems are the most widely applied artificial lift equipment in the oil and gas industry. Accurate and intelligent working condition recognition of pumping systems imposes major impacts on oilfield production benefits and efficiency. The shape of dynamometer card reflects the working conditions of sucker-rod pumping systems, and different conditions can be indicated by their typical card characteristics. In traditional identification methods, however, features are manually extracted based on specialist experience and domain knowledge. In this paper, an automatic fault diagnosis method is proposed to recognize the working conditions of sucker-rod pumping systems with massive dynamometer card data collected by sensors. Firstly, AlexNet-based transfer learning is adopted to automatically extract representative features from various dynamometer cards. Secondly, with the extracted features, error-correcting output codes model-based SVM is designed to identify the working conditions and improve the fault diagnosis accuracy and efficiency. The proposed AlexNet-SVM algorithm is validated against a real dataset from an oilfield. The results reveal that the proposed method reduces the need for human labor and improves the recognition accuracy. |
first_indexed | 2024-03-10T15:52:08Z |
format | Article |
id | doaj.art-ce4a505610764ae580451bc1e5bfcdf9 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T15:52:08Z |
publishDate | 2020-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-ce4a505610764ae580451bc1e5bfcdf92023-11-20T15:59:38ZengMDPI AGSensors1424-82202020-10-012019565910.3390/s20195659Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVMHaibo Cheng0Haibin Yu1Peng Zeng2Evgeny Osipov3Shichao Li4Valeriy Vyatkin5State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaDepartment of Computer Science, Electrical and Space Engineering, Luleå University of Technology, 97187 Luleå, SwedenState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaDepartment of Computer Science, Electrical and Space Engineering, Luleå University of Technology, 97187 Luleå, SwedenSucker-rod pumping systems are the most widely applied artificial lift equipment in the oil and gas industry. Accurate and intelligent working condition recognition of pumping systems imposes major impacts on oilfield production benefits and efficiency. The shape of dynamometer card reflects the working conditions of sucker-rod pumping systems, and different conditions can be indicated by their typical card characteristics. In traditional identification methods, however, features are manually extracted based on specialist experience and domain knowledge. In this paper, an automatic fault diagnosis method is proposed to recognize the working conditions of sucker-rod pumping systems with massive dynamometer card data collected by sensors. Firstly, AlexNet-based transfer learning is adopted to automatically extract representative features from various dynamometer cards. Secondly, with the extracted features, error-correcting output codes model-based SVM is designed to identify the working conditions and improve the fault diagnosis accuracy and efficiency. The proposed AlexNet-SVM algorithm is validated against a real dataset from an oilfield. The results reveal that the proposed method reduces the need for human labor and improves the recognition accuracy.https://www.mdpi.com/1424-8220/20/19/5659working condition recognitionsucker-rod pumping systemdynamometer cardconvolutional neural networktransfer learningsupport vector machine |
spellingShingle | Haibo Cheng Haibin Yu Peng Zeng Evgeny Osipov Shichao Li Valeriy Vyatkin Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVM Sensors working condition recognition sucker-rod pumping system dynamometer card convolutional neural network transfer learning support vector machine |
title | Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVM |
title_full | Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVM |
title_fullStr | Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVM |
title_full_unstemmed | Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVM |
title_short | Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVM |
title_sort | automatic recognition of sucker rod pumping system working conditions using dynamometer cards with transfer learning and svm |
topic | working condition recognition sucker-rod pumping system dynamometer card convolutional neural network transfer learning support vector machine |
url | https://www.mdpi.com/1424-8220/20/19/5659 |
work_keys_str_mv | AT haibocheng automaticrecognitionofsuckerrodpumpingsystemworkingconditionsusingdynamometercardswithtransferlearningandsvm AT haibinyu automaticrecognitionofsuckerrodpumpingsystemworkingconditionsusingdynamometercardswithtransferlearningandsvm AT pengzeng automaticrecognitionofsuckerrodpumpingsystemworkingconditionsusingdynamometercardswithtransferlearningandsvm AT evgenyosipov automaticrecognitionofsuckerrodpumpingsystemworkingconditionsusingdynamometercardswithtransferlearningandsvm AT shichaoli automaticrecognitionofsuckerrodpumpingsystemworkingconditionsusingdynamometercardswithtransferlearningandsvm AT valeriyvyatkin automaticrecognitionofsuckerrodpumpingsystemworkingconditionsusingdynamometercardswithtransferlearningandsvm |