基于深度学习的电潜泵井虚拟流量计量系统研究

Deep Learning-Based Virtual Flow Metering System for Electric Submersible Pump Wells

本文针对国内、外采油计量系统地面建设投资和维护费用高的问题,建立了以电潜泵井为研究对象的趋势分析、工况诊断预警、产液量计量等业务模型和算法,并研发形成了一套虚拟流量计量系统。该系统具备实时数据采集监控、产量计量等功能,为优化油田地面流程工艺、生产降本增效和提升精细化管理水平提供了技术支撑。

Addressing the high investment and maintenance costs of domestic and international oil production metering systems,this study takes electric submersible oil pump wells as the research object,develops business models and algorithms for trend analysis,diagnosis,early warning,and production metering,and develops a set of virtual flow metering system.Equipped with functions of real-time data acquisition and monitoring,production metering,the system provides technical support for the oilfield to optimize the ground process technology,reduce cost and increase efficiency,and improve the level of finemanagement.