Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Few-Shot Indicator Diagram Based on Meta-learning

2021 ◽  
pp. 436-444
Author(s):  
Yunpeng He ◽  
Chuanzhi Zang ◽  
Peng Zeng ◽  
Mingxin Wang ◽  
Guangxi Wan ◽  
...  
Keyword(s):  
Working Conditions ◽  
Automatic Recognition ◽  
Indicator Diagram ◽  
Pumping System ◽  
Sucker Rod ◽  
Meta Learning

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.

A Fault Diagnosis of Suck Rod Pumping System Based on SVM

2013 ◽  
Vol 307 ◽  
pp. 285-289 ◽  
Author(s):  
Wei Wu ◽  
Yu Zhou ◽  
Hang Xin Wei
Keyword(s):  
Fault Diagnosis ◽  
Support Vector ◽  
Oil Well ◽  
Pump System ◽  
Indicator Diagram ◽  
Invariant Moments ◽  
Pumping System ◽  
System A ◽  
Fault Type ◽  
Shape Characteristics

Aiming at the defects of fault diagnosis in the traditional method for sucker rod pump system, a new method based on support vector machine (SVM) pump fault diagnosis is proposed. Through studying the theory of invariant moment and the shape characteristics of pump indicator diagram, seven invariant moments is extracted from the indicator diagram as a pumping unit well condition of the characteristic parameters. Then these parameters are pretreatment, and it makes up seven eigenvector which are regarded as the input eigenvector of the SVM. The experiment indicates that the method can not only detect the fault of the pumping oil well but also can recognize the fault type of it, which is very effective for safety protection and fault diagnosis of the pumping oil.

Installation of A Sucker Rod Pumping System Over a Failed Electrical Submersible Pumping System to Recover Production Using Rigless Intervention

2020 ◽  
Author(s):  
Fábio Soares De Lima ◽  
Carlos Francisco Sales De Souza ◽  
José Paulino Da Silva Neto
Keyword(s):  
Pumping System ◽  
Sucker Rod

scholarly journals Improved method on hydraulic power calculations for conventional sucker rod pumping system

2020 ◽  
Vol 431 ◽  
pp. 012026
Author(s):  
O E Mwangupili ◽  
P Chunsheng ◽  
C Bululu ◽  
S L Nyanswi ◽  
S M Muya
Keyword(s):  
Improved Method ◽  
Hydraulic Power ◽  
Power Calculations ◽  
Pumping System ◽  
Sucker Rod

scholarly journals Application of CNN-LSTM in Gradual Changing Fault Diagnosis of Rod Pumping System

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Yanfeng He ◽  
Yali Liu ◽  
Shuai Shao ◽  
Xuhang Zhao ◽  
Guojun Liu ◽  
...  
Keyword(s):  
Mathematical Model ◽  
Short Term Memory ◽  
Fault Classification ◽  
Training Dataset ◽  
Irreversible Damage ◽  
Indicator Diagram ◽  
Well Production ◽  
Pumping System ◽  
Lstm Network ◽  
Model Diagnosis

Owing to the importance of rod pumping system fault detection using an indicator diagram, indicator diagram identification has been a challenging task in the computer-vision field. The gradual changing fault is a special type of fault because it is not clearly indicated in the indicator diagram at the onset of its occurrence and can only be identified when an irreversible damage in the well has been caused. In this paper, we proposed a new method that combines the convolutional neural network (CNN) and long short-term memory (LSTM) network to perform a gradual changing fault classification. In particular, we employed CNN to extract the indicator diagram multilevel abstraction features based on its hierarchical structure. We considered the change in the time series of indicator diagrams as a sequence and employed LSTM to perform recognition. Compared with traditional mathematical model diagnosis methods, CNN-LSTM overcame the limitations of the traditional mathematical model theoretical analysis such as unclear assumption conditions and improved the diagnosis accuracy. Finally, 1.3 million sets of well production were set as a training dataset and used to evaluate CNN-LSTM. The results demonstrated the effectiveness of utilizing CNN and LSTM to recognize a gradual changing fault using the indicator diagram and characteristic parameters. The accuracy reached 98.4%, and the loss was less than 0.9%.

Sign in / Sign up

Export Citation Format

Share Document