Recently, the team of Zhang Kai has made new progress in the field of intelligent wellfield, and the related research has been published in the SPE Journal. The paper is titled " Trajectory Recognition and Working Condition Analysis of Rod Pumping Systems Based on Pose Estimation Method with Heatmap-Free Joint Detection ".
Innovation: Traditional methods for analyzing the working conditions of rod pumping systems rely on dynamometers to obtain load diagrams, which reflect changes in the load at the hanging point and displacement, indirectly expressing the motion trajectory of the hanging point. However, there is a gap between this and the actual motion process of the pumping unit. This study addresses the aforementioned challenge by combining the problem of obtaining the trajectory of the pumping unit with computer vision technology, thereby constructing a keypoint recognition framework based on deep learning. The pose estimation algorithm is used to train a pumping unit recognition model, which identifies the key joints in the motion process of the pumping unit through on-site operation video data, further expressing the actual motion trajectory of different points. This method provides a new approach for the trajectory recognition and working condition analysis of pumping units, achieving good results in both accuracy and efficiency.
Abstract: Rod pump systems are the primary production tools in oilfield development. Analyzing their working conditions provides a theoretical foundation for formulating production optimization plans and adjusting equipment parameters. Existing machine learning–based condition analysis methods rely on dynamometer cards and cannot capture the actual operational trajectory of the pumping unit. To address this issue, this paper proposes a keypoint detection method for pumping units based on pose estimation of heatmap-free joint detection from video data. A data annotation scheme suitable for the task of detecting pumping unit keypoints was developed, and the learning criteria for this task were optimized. An end-to-end heatmap-free pose estimation algorithm was used to process images of the pumping unit, yielding predicted keypoint positions, thereby enabling the identification of the keypoint motion trajectories of the pumping unit. Experiments validated the proposed method and compared it with general learning criteria. Results show that this method accurately captures the keypoint positions of the pumping unit, with the optimized learning criteria model improving by more than 5% compared with general methods and increasing the keypoint object keypoint similarity (OKS) by more than 30%. The model’s results can be used for the actual operational trajectory recognition of the pumping unit, automatically calculating the motion parameters of the polished rod, and intelligently assessing the balance and working condition analysis of the pumping unit. This realizes the intelligent application of video surveillance data, significantly contributing to the dynamic study of rod pump systems.
SPE Journal encompasses fundamental and applied research in subsurface energy for sustainable oil and gas exploration and production, while also broadening its scope to include circular carbon economy, energy transition, and alternative/renewable energy sources. The journal features innovative theories, emerging concepts, and research and development across basic and applied fields, along with invited review papers, case histories, and field application studies. It covers all aspects of petroleum science and engineering, including drilling and completion, production and operations, reservoir engineering, formation evaluation, petrophysics, geology, geophysics, geochemistry, geomechanics, numerical simulation and modeling, injection/production facilities, oilfield chemistry, water management and treatment, carbon capture, utilization, and storage (CCUS), hydrogen transportation and storage, geothermal energy, digitalization, artificial intelligence, data analysis, economics, health, safety, environment, sustainability, and other special topics of current interest. The latest impact factor of the journal is 3.2, and the average impact factor IF in the past 3 years is 3.467. This journal currently appears in the JCR Q1 or the Chinese Academy of Sciences ranking 3.
Paper link:
https://doi.org/10.2118/223095-PA
Citation:
Zhang K, Xia X, Song Z, et al. Trajectory Recognition and Working Condition Analysis of Rod Pumping Systems Based on Pose Estimation Method with Heatmap-Free Joint Detection [J]. SPE Journal, 2024:1-17.
