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

Abstract

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.

Multisource working condition recognition via nonlinear kernel learning and p-Laplacian manifold learning

“…Accordingly, C(F) → D → A(E) is the downward stroke stage, involving the unloading to the working process, and A(E) → B → C(F) → D → A(E) is a stroke, i.e., a working cycle time of oil well pump. The key to efficiently and accurately calculate the feature parameters of the above three measured information sources lies in the location to the valve opening and closing points (i.e., point A(E) , B, C(F), and D ), and the four-point location adopts the technology based on prior knowledge, expert experience, and mechanism analysis [ 42 ] in this paper.…”

Study on Equivalent Viscous Damping Coefficient of Sucker Rod Based on the Principle of Equal Friction Loss

“…Since the 1960s, many researchers have carried out the study of equivalent viscous damping coefficient [8]. Now, there are many methods to determine the equivalent viscous damping coefficient, such as experiential algorithm, deduction formula of hypothetical conditions, calculated by surface dynamometer cards, etc.…”

Indicator diagram analysis based on deep learning

“…Owing to the specific nature of their structural characteristics and working environment, their failure rate is high. Therefore, it is crucial to understand the working state of the pumping unit as well as to analyze and rectify faults in a timely and accurate manner (Li et al, 2013a;Reges et al, 2015). The indicator diagram is a closed curve composed of the load-versusdisplacement curves.…”