Dewatering gas wells typically exhibit a high gas–liquid ratio, making tapered electrical submersible pump (ESP) systems a common choice. However, the flow rate within the pump varies significantly along its length, and production parameters fluctuate considerably across different stages of operation for a gas reservoir. Traditional ESP sizing methods typically consider one single operating case and one single pump model. In contrast, tapered ESP systems require the designer to manually select and combine pump models, stage numbers, and operating frequencies based largely on experience. This process can be cumbersome and time-consuming. To address the limitations of existing ESP sizing methods, this study develops a computational program for ESP operation parameters stage by stage and generates extensive training data. A fully connected neural network (FCNN) based on the backpropagation (BP) algorithm is then trained on these data. The model can predict key parameters such as gas volume fraction (GVF) and flow rate along the pump, operating frequency, and total pump efficiency, using input data such as fluid parameters at the pump’s intake and discharge, as well as pump stage numbers and performance curve data. The model demonstrates high accuracy, with a mean absolute error (MAE) of 0.3431, a mean squared error (MSE) of 0.3231, and a coefficient of determination (R2) of 0.9991. By integrating a wellbore two-phase flow model and leveraging industry experience in pump sizing, a hybrid model for automatic ESP sizing under multiple working conditions is proposed, with the objective of maximizing pump efficiency. This model enables optimal pump sizing, calculates the operating frequency corresponding to given working cases, significantly reduces the workload of designers, and enhances the overall design outcomes.
Flexible ultra-long stroke pumping units (FULSPUs) are widely adopted in low-yield oil wells due to their structural simplicity and high operational efficiency. However, current equipment selection methods lack precision, leading to mismatched configurations, low utilization rates, and unnecessary costs. To address this challenge, this study develops a systematic optimization framework integrating motion dynamics analysis and empirical data. First, a simplified formula for peak polished rod load (PPRL) is concluded by analyzing the unit’s stable motion characteristics. Second, a multi-parameter selection method incorporating stroke length, frequency, pump efficiency, and dynamic liquid level constraints is developed. This method generates interactive selection charts that map maximum liquid production across varying pumping depths, providing a rapid decision-making tool for optimal equipment pairing. A double-layer circle visualization that quantifies equipment utilization by linking pumping unit load and pump load, offering actionable insights for cost-effective upgrades. The model is validated through a field case, where overdesign risks are reduced. Significantly, this work replaces traditional beam-pump selection models with a tailored solution for flexible FULSPUs, delivering two major contributions: (1) a standardized workflow balancing technical feasibility and economic efficiency and (2) a visual tool that when adopted in the oilfield, the efficiency and applicability of equipment selection are improved. These advancements establish a transformative framework for sustainable resource management in mature low-permeability reservoirs.