Using the curve moment and the PSO-SVM method to diagnose downhole conditions of a sucker rod pumping unit

Li, Kun; Gao, Xianwen; Tian, Zhongda; Qiu, Zhixue

doi:10.1007/s12182-013-0252-y

Cited by 83 publications

(30 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is based on algorithms that can learn patterns from data (Tian 2007, Li 2013. Manual feature engineering is required such as dividing dynamometer cards using the "four point method" (Li 2013) and then extracting moment invariants for pattern recognition using a support vector machine (SVM), a popular machine learning algorithm. However, the studies conducted using deep learning have mostly used neural networks trained from scratch.…”

Section: Machine Learning With Manual Feature Extractionmentioning

confidence: 99%

Beam Pump Dynamometer Card Prediction using Artificial Neural Networks

Sharaf¹

2018

KEG

View full text Add to dashboard Cite

show abstract

Section: Machine Learning With Manual Feature Extractionmentioning

confidence: 99%

Beam Pump Dynamometer Card Prediction using Artificial Neural Networks

Sharaf¹

2018

KEG

View full text Add to dashboard Cite

show abstract

“…Nowadays, many computer diagnosis methods have been used to achieve intelligent identification of the dynamometer cards. These include expert systems (Derek et al 1988;Martinez et al 1993), artificial neural networks (Rogers et al 1990;Xu et al 2007;Tian et al 2007a, b;de Souza et al 2009;Wu et al 2011), rough set theory (Wang and Bao 2008), support vector machine (Tian et al 2007a, b;Li et al 2013a;Yu et al 2013), fuzzy theory (Li et al 2013b, c), and designed component analysis (Li et al 2013b). The current research mainly focuses on supervised learning methods, which rely on manual work to select training samples.…”

Section: Introductionmentioning

confidence: 99%

“…In order to eliminate the effects of deformation, viscous resistance, vibration and inertia of the sucker rod string, the surface dynamometer card is first transformed into a downhole dynamometer card which can truly reflect the working conditions of the subsurface pump. In this paper, we use the Fourier coefficient method (Chen 1988;Li et al 2013a) to solve the one-dimensional wave equation proposed by Gibbs (Gibbs and Neely 1966) to complete this transformation. Then, graphic feature vectors of the down-hole dynamometer card are used as the inputs of the fault diagnosis model (in this paper, all feature vector sets we use are extracted from the down-hole dynamometer card).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fault diagnosis for down-hole conditions of sucker rod pumping systems based on the FBH–SC method

Gao

Zhou

et al. 2015

Pet. Sci.

Self Cite

View full text Add to dashboard Cite

Dynamometer cards are commonly used to analyze down-hole working conditions of pumping systems in actual oil production. Nowadays, the traditional supervised learning methods heavily rely on the classification accuracy of the training samples. In order to reduce the errors of manual classification, an automatic clustering algorithm is proposed and applied to diagnose down-hole conditions of pumping systems. The spectral clustering (SC) is a new clustering algorithm, which is suitable for any data distribution. However, it is sensitive to initial cluster centers and scale parameters, and needs to predefine the cluster number. In order to overcome these shortcomings, we propose an automatic clustering algorithm, fast black hole-spectral clustering (FBH-SC). The FBH algorithm is used to replace the K-mean method in SC, and a CritC index function is used as the target function to automatically choose the best scale parameter and clustering number in the clustering process. Different simulation experiments were designed to define the relationship among scale parameter, clustering number, CritC index value, and clustering accuracy. Finally, an example is given to validate the effectiveness of the proposed algorithm.

show abstract

“…Many advanced analytical methods were used in classification of Dynamometer Cards in several works, such as hierarchical systems specialists (Abello, Houang, and Russell 1993), symbolic neural networks (Corrêa 1995), artificial neural networks (Bezerra, Schnitman, and Filho 2009), analysis of frequency spectrum (de Lima, Guedes, and Silva 2009) and Support Vector Machines (Li et al 2013).…”

Section: Introductionmentioning

confidence: 99%

A New Approach To Diagnosis of Sucker Rod Pump Systems by Analyzing Segments of Downhole Dynamometer Cards

et al. 2015

View full text Add to dashboard Cite

This work proposes a new method of diagnosing the Sucker Rod Pump Systems, by analyzing segments between the points of opening and closing valves identified in the Downhole Dynamometer Cards. An analysis of the shape of the pumping condition classes represented in the Downhole Dynamometer Cards, especially regarding the behavior of segments between the valve opening and closing points is presented. The feasibility of the classification of Downhole Dynamometer Cards by the curvature characteristics of segments is demonstrated. Then, methods of classification of 16 pumping condition classes are presented, 4 by simple statistics and 12 of them extracting curvature characteristics of the segments andusing statistics to implement Mamdani fuzzy inference systems. Tests are developed with classifiers created by the method, and the test results over a library of Dynamometer Cards from real wells, previously classified by human experts, demonstrate the feasibility of the approach and the precision of the classification even without a deeper study to choose the better characteristics and statistics. In addition the classifiers were developed using samples of Dynamometer Cards from the literature, showing that the method reduces the need of many samples of the great variety of the Dynamometer Cards Shapes from real wells. Different from other methods, these results indicate the severity degree of many pumping condition classes and demonstrate the concomitant pumping condition detection feature. The classifiers were even able to spot misleading classifications by the human experts thanks to deeper understanding of the behavior of the Dynamometer Cards segments in the case of one or more anomalies in the system. The features to quantify and identify concomitant classes of so many pumping conditionsdemonstrated in this approach are novel in the area. The paper shows the feasibility of the approach and the potential for greater identification precision.

show abstract

Using the curve moment and the PSO-SVM method to diagnose downhole conditions of a sucker rod pumping unit

Abstract: computer from the analysis of dynamometer cards. In this process, extraction of feature parameters and include different production information according to the "four point method" used in actual oilfield C and g

Cited by 83 publications

References 22 publications

Beam Pump Dynamometer Card Prediction using Artificial Neural Networks

Beam Pump Dynamometer Card Prediction using Artificial Neural Networks

Fault diagnosis for down-hole conditions of sucker rod pumping systems based on the FBH–SC method

A New Approach To Diagnosis of Sucker Rod Pump Systems by Analyzing Segments of Downhole Dynamometer Cards

Contact Info

Product

Resources

About