LAUSR

Abstract This paper proposes a real-time diagnosis method that addresses the limitations of traditional "dynamometer cards" used for sucker-rod pump performance analysis. The "power vs. position plots" are proposed to demonstrate an improved diagnostic method for rod pump performance. On this basis, the working condition diagnosis plate of the sucker-rod pump well is created. The eigenvalues of dynamometer cards and "power vs. position plots" under different working conditions are extracted, and a combined diagnosis model based on feature recognition is established. The model not only diagnoses the wellbore condition but also the surface condition, which improves the diagnosis effect and expands the diagnosis range. In addition, considering the surface dynamometer card as the known condition, the one-dimensional damping wave equation is used to solve the downhole pump dynamometer card. By analyzing the change law of the pump-load slope-time relationship curve, the opening and closing points of the pump valve are accurately extracted, and the load difference between the upstroke and downstroke, and the effective stroke of the downhole pump dynamometer card are determined. On this basis, a calculation model of the dynamic fluid level and fluid production is established to determine the change in reservoir energy and analyze the supply and discharge relationship of the sucker-rod pump wells. Combined with the online collection of the surface dynamometer cards and "power vs. position plots," the real-time diagnosis of oil well production systems can be realized. This can effectively improve the timeliness of sucker-rod pump performance analysis, reduce production management costs, and improve the production efficiency and benefits of the oilfield.