scholarly journals Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Dynamometer Cards with Transfer Learning and SVM

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5659
Author(s):  
Haibo Cheng ◽  
Haibin Yu ◽  
Peng Zeng ◽  
Evgeny Osipov ◽  
Shichao Li ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
Working Conditions ◽  
Domain Knowledge ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Pumping System ◽  
Artificial Lift ◽  
Sucker Rod ◽  
Dynamometer Card

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.

scholarly journals A comprehensive review of sucker rod pumps’ components, diagnostics, mathematical models, and common failures and mitigations

2021 ◽  
Author(s):  
Sherif Fakher ◽  
Abdelaziz Khlaifat ◽  
M. Enamul Hossain ◽  
Hashim Nameer
Keyword(s):  
Mathematical Models ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Gas Industry ◽  
Holistic View ◽  
Comprehensive Review ◽  
Artificial Lift ◽  
Sucker Rod ◽  
Sucker Rod Pump

AbstractIn many oil reservoirs worldwide, the downhole pressure does not have the ability to lift the produced fluids to the surface. In order to produce these fluids, pumps are used to artificially lift the fluids; this method is referred to as artificial lift. More than seventy percent of all currently producing oil wells are being produced by artificial lift methods. One of the most applied artificial lift methods is sucker rod pump. Sucker rod pumps are considered a well-established technology in the oil and gas industry and thus are easy to apply, very common worldwide, and low in capital and operational costs. Many advancements in technology have been applied to improve sucker rod pumps performance, applicability range, and diagnostics. With these advancements, it is important to be able to constantly provide an updated review and guide to the utilization of the sucker rod pumps. This research provides an updated comprehensive review of sucker rod pumps components, diagnostics methods, mathematical models, and common failures experienced in the field and how to prevent and mitigate these failures. Based on the review conducted, a new classification of all the methods that can fall under the sucker rod pump technology based on newly introduced sucker rod pump methods in the industry has been introduced. Several field cases studies from wells worldwide are also discussed in this research to highlight some of the main features of sucker rod pumps. Finally, the advantages and limitations of sucker rod pumps are mentioned based on the updated review. The findings of this study can help increase the understanding of the different sucker rod pumps and provide a holistic view of the beam rod pump and its properties and modeling.

Key Technologies of Sucker Rod Pump Card Diagnosis Based on BP Neural Network

2011 ◽  
Vol 201-203 ◽  
pp. 433-437
Author(s):  
Xiao Dong Wu ◽  
Rui Dong Zhao ◽  
Zhang Hao ◽  
Tao Zhen ◽  
Su Lei
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Production Engineering ◽  
Pumping System ◽  
Artificial Lift ◽  
Sucker Rod ◽  
Key Technologies ◽  
Hidden Layer ◽  
Dynamometer Card ◽  
Selection Of

Sucker rod pumping is a dominated artificial lift method for oil production engineering. In the production process, diagnosing the condition of pump using dynamometer card is vitally significant to monitor and manage the pumping system. With the ability to reflect arbitrary non-linear mappings, the BP neural network can be used in pattern recognition of the pump dynamometer card. In this paper, some key technologies of establishing reasonable neural network are introduced. The number of neurons in input layer depends on the selection of characteristic value. The number of neurons in hidden layer can be obtained by some models, optimum value will be chosen out. The number of neurons in output layer depends on the recognized behavior of pump. After the construction of neural network, the more effective and practical BP neural network will be obtained by suitable samples and appropriate training strategies.

Digital innovation in subsea integrity management

2020 ◽  
Vol 60 (1) ◽  
pp. 215
Author(s):  
Ricky Thethi ◽  
Dharmik Vadel ◽  
Mark Haning ◽  
Elizabeth Tellier
Keyword(s):  
Domain Knowledge ◽  
Oil And Gas ◽  
Digital Technologies ◽  
Oil And Gas Industry ◽  
Gas Industry ◽  
Cost Efficiencies ◽  
Exploration And Production ◽  
Integrity Management ◽  
Offshore Oil And Gas ◽  
Dynamic Structures

Since the 2014 oil-price downturn, the offshore oil and gas industry has accelerated implementation of digital technologies to drive cost efficiencies for exploration and production operations. The upstream offshore sector comprises many interfacing disciplines such as subsurface, drilling and completions, facilities and production operations. Digital initiatives in subsurface imaging, drilling of subsea wells and topsides integrity have been well publicised within the industry. Integrity of the subsea infrastructure is one area that is currently playing catch up in the digital space and lends itself well for data computational efficiencies that artificial-intelligence technologies provide, to reduce cost and lower the risk of subsea equipment downtime. This paper details digital technologies employed in the area of subsea integrity management to meet the objectives of centralising access to critical integrity data, automating workflows to collect and assess data, and using machine learning to perform more accurate and faster engineering analysis with large volumes of field-measured data. A comparison of a typical subsea field is presented using non-digital and digital approaches to subsea integrity management (IM). The comparison demonstrates where technologies such as digital twins for dynamic structures, and auto anomaly detection by using image recognition algorithms can be deployed to provide a step change in the quality of subsea integrity data coming from field. It is demonstrated how the use of a smart IM approach, combined with strong domain knowledge in subsea engineering, can lead to cost efficiencies in operating subsea assets.

scholarly journals Deep Transfer Learning-Based Fault Diagnosis for Gearbox under Complex Working Conditions

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Zitong Wan ◽  
Rui Yang ◽  
Mengjie Huang
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
Working Conditions ◽  
Evaluation Method ◽  
Working Condition ◽  
Negative Effects ◽  
Gear Fault ◽  
Diagnosis Method ◽  
Fault Feature Extraction ◽  
Better Than

In the large amount of available data, information insensitive to faults in historical data interferes in gear fault feature extraction. Furthermore, as most of the fault diagnosis models are learned from offline data collected under single/fixed working condition only, this may cause unsatisfactory performance for complex working conditions (including multiple and unknown working conditions) if not properly dealt with. This paper proposes a transfer learning-based fault diagnosis method of gear faults to reduce the negative effects of the abovementioned problems. In the proposed method, a cohesion evaluation method is applied to select sensitive features to the task with a transfer learning-based sparse autoencoder to transfer the knowledge learnt under single working condition to complex working conditions. The experimental results on wind turbine drivetrain diagnostics simulator show that the proposed method is effective in complex working conditions and the achieved results are better than those of traditional algorithms.

Sign in / Sign up

Export Citation Format

Share Document