A Working Condition Diagnosis Model of Sucker Rod Pumping Wells Based on Big Data Deep Learning

2019 ◽  
Author(s):  
Xiang Wang ◽  
Yanfeng He ◽  
Fajun Li ◽  
Xiangji Dou ◽  
Zhen Wang ◽  
...  
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Working Condition ◽  
Pumping Wells ◽  
Sucker Rod ◽  
Diagnosis Model ◽  
Condition Diagnosis

A Working Condition Diagnosis Model of Sucker Rod Pumping Wells Based on Deep Learning

2021 ◽  
pp. 1-10
Author(s):  
Xiang Wang ◽  
Yangeng He ◽  
Fajun Li ◽  
Zhen Wang ◽  
Xiangji Dou ◽  
...  
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Working Conditions ◽  
Working Condition ◽  
Data Set ◽  
Pumping Wells ◽  
Sucker Rod ◽  
Diagnosis Model ◽  
Dynamometer Card ◽  
Condition Diagnosis

Summary Monitoring the working conditions of sucker rod pumping wells in a timely and accurate manner is important for oil production. With the development of smart oil fields, more and more sensors are installed on the well, and the monitored data are continuously transmitted to the data center to form big data. In this work, we aim to utilize the big data collected during oil well production and a deep learning technique to build a new generation of intelligent diagnosis model to monitor working condition of sucker rod pumping wells. More than 5×106 of well monitoring records, which covers information from about 1 year for more than 300 wells in an oilfield block, are collected and preprocessed. To show the dynamic changes of the working conditions for the wells, the overlay dynamometer card is proposed and plotted for each data record. The working conditions are divided into 30 types, and the corresponding data set is created. An intelligent diagnosis model using the convolutional neural network (CNN), one of the deep learning frameworks, is proposed. By the convolution and pooling operation, the CNN can extract features of an image implicitly without human effort and prior knowledge. That makes a CNN very suitable for the recognition of the overlay dynamometer cards. The architecture for a working condition diagnosis CNN model is designed. The CNN model consists of 14 layers with six convolutional layers, three pooling layers, and three fully connected layers. The total number of neurons is more than 1.7×106. The overlay dynamometer card data set is used to train and validate the CNN model. The accuracy and efficiency of the model are evaluated. Both the training and validation accuracies of the CNN model are greater than 99% after 10 training epochs. The average training elapsed time for an epoch is 8909.5 seconds, and the average time to diagnosis a sample is 1.3 milliseconds. Based on the trained CNN model, a working condition monitoring software for a sucker rod pumping well is developed. The software runs 7 × 24 hours to diagnosis the working conditions of wells and post a warning to users. It also has a feedback learning workflow to update the CNN model regularly to improve its performance. The on-site run shows that the actual accuracy of the CNN model is greater than 90%.

Research and Application of Rod Pump Working Condition Diagnosis and Virtual Production Metering Based on Electric Parameters

2021 ◽  
Author(s):  
Ruidong Zhao ◽  
Cai Wang ◽  
Hanjun Zhao ◽  
Chunming Xiong ◽  
Junfeng Shi ◽  
...  
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Working Conditions ◽  
Working Condition ◽  
Learning Technology ◽  
Electrical Parameters ◽  
Electric Parameter ◽  
Virtual Production ◽  
Electric Parameters ◽  
Condition Diagnosis

Abstract The conventional configurations of pumping well IOT consist of electric parameter indicator and dynamometer. The current, voltage, power, and other electrical parameters are easy to access, low costs, stable, and acquired daily during pumping well operation. If the working condition diagnosis and virtual production metering of pumping well can be realized through electrical parameters, the utilization of dynamometers can be cancelled or reduced, which is of great significance to reduce the investment and improve the coverage of IOT in oil wells. The conventional methods of diagnosis and analysis based on electrical parameters and virtual production metering are lack of theoretical basis. The combination of deep learning technology of big data and traditional methods will provide solutions to solve related technical problems. Considering that there are many energy transmission segments from the motor to the downhole pump, the characteristics of the electric parameter curve are more sophisticated and difficult to identify compared with dynamometer card due to the influence of the unbalance, pump fullness, rod/tube vibration, wax deposition and leakage. The shape characteristics of the electric parameter curve of the pumping well are analyzed in the time domain and frequency domain, which provides the basis for further diagnosis, analysis and production measurement. In this paper, an integrated multi-model diagnosis method is proposed. For the working conditions with a large scale of samples, the electrical parameters are converted to dynamometer cards for diagnosis by using the deep learning technology of big data. For the working conditions with sparse samples, the machine learning model is used to diagnosis directly with electrical parameters. The deep learning electric parameter model for production measurement is established. Through the combination of the big data model of electric parameters to dynamometer card, 3D mechanical model of rod string, and big data model of plunger leakage coefficient, the virtual production metering function of pumping well based on electrical parameters is successfully realized. The diagnosis and virtual production metering method and software based on electrical parameters have been applied in many oilfields of CNPC. The accuracy of identifying the upper and lower dead points of electric parameters is 98.0%; the coincidence rate of working condition diagnosis under electrical parameters is 92.0%; the average error of virtual production metering with electric parameters is 13.4%. The dynamometer and gauging room have been canceled in the demonstration area. The application of electrical parameters to diagnose working conditions and meter the production of pumping wells is the key to the low-cost IOT construction. Traditional mathematical and physical methods are difficult to solve this problem, but the application of big data analysis technology could do the job successfully.

Working-condition diagnosis of a beam pumping unit based on a deep-learning convolutional neural network

2021 ◽  
pp. 095440622110296
Author(s):  
Zhewei Ye ◽  
Qinjue Yi
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Expert Systems ◽  
Convolutional Neural Network ◽  
Working Condition ◽  
Indicator Diagram ◽  
Conventional Machine ◽  
Pumping Units ◽  
Condition Diagnosis

At present, beam pumping units are the most extensively-applied component in rod pumping systems, and the analysis of the indicator diagram of a rod pump is an important means of judging its downhole working condition. However, the synthetic study and judgment of the indicator diagram by manual means has a low efficiency, large error, and poor immediacy, and it is difficult to apply the conclusions in time and accurately to adjust the operating parameters of the pumping units. Moreover, expert systems rely on expert experience and conventional machine learning requires manual pre-selection of geometric features such as moments and vector curves, which will reduce the accuracy of recognition when similar indicator diagrams appear. To solve the above technical defects, in this paper, a deep-learning convolutional neural network (CNN) is proposed using the CNN model based on AlexNet. The automatic recognition of the indicator diagram is thus realized, and, on the basis of previous studies, this model simplifies the structure of the model and takes into account 15 common downhole working conditions of the pumping unit. In this model, the batch normalization (BN) layer is used to replace the local response normalization (LRN) and dropout layers and all kinds of indicator diagrams are put into the same model frame for automatic identification. The experimental application of the measured data shows that the model not only has a short training time, but also has a working-condition diagnosis accuracy of 96.05%, which can solve the deficiencies and defects of artificial identification, expert systems, and conventional machine learning to a certain extent. A deep-learning CNN can provide a new reference for fast working-condition diagnosis of indicator diagram, making indicator-diagram judgment timely and accurate, and thus it is possible to provide a direct basis for parameter adjustment of pumping units.

scholarly journals Research on Feature Extraction of Indicator Card Data for Sucker-Rod Pump Working Condition Diagnosis

2013 ◽  
Vol 2013 ◽  
pp. 1-6 ◽  
Author(s):  
Yunhua Yu ◽  
Haitao Shi ◽  
Lifei Mi
Keyword(s):  
Feature Extraction ◽  
Working Condition ◽  
Fourier Descriptors ◽  
Gray Level ◽  
Memory Space ◽  
Geometric Moment ◽  
Moment Vector ◽  
Sucker Rod ◽  
Sucker Rod Pump ◽  
Condition Diagnosis

Three feature extraction methods of sucker-rod pump indicator card data have been studied, simulated, and compared in this paper, which are based on Fourier Descriptors (FD), Geometric Moment Vector (GMV), and Gray Level Matrix Statistics (GLMX), respectively. Numerical experiments show that the Fourier Descriptors algorithm requires less running time and less memory space with possible loss of information due to nonoptimal numbers of Fourier Descriptors, the Geometric Moment Vector algorithm is more time-consuming and requires more memory space, while the Gray Level Matrix Statistics algorithm provides low-dimension feature vectors with more time consumption and more memory space. Furthermore, the characteristic of rotational invariance, both in the Fourier Descriptors algorithm and the Geometric Moment Vector algorithm, may result in improper pattern recognition of indicator card data when used for sucker-rod pump working condition diagnosis.

Well Condition Diagnosis of Sucker-Rod Pumping Wells Based on the Machine Learning of Electrical Power Curves in the Context of IoT

2020 ◽  
Author(s):  
Cai Wang ◽  
Chunming Xiong ◽  
Hanjun Zhao ◽  
Ruidong Zhao ◽  
Junfeng Shi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Electrical Power ◽  
Pumping Wells ◽  
Sucker Rod ◽  
Condition Diagnosis ◽  
Power Curves

Intelligence artificielle : le futur de l’Orthodontie ?

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligence Artificielle ◽  
Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Sign in / Sign up

Export Citation Format

Share Document