抽油机井人工举升智能控制系统的应用  

Application of Artificial Lift Intelligent Control System of Pumping Well

作　　者：李雪 张战敏 朱丽萍[1] 金学锋 朱丹丹 高鹏 Li Xue;Zhang Zhanmin;Zhu Liping;Jin Xuefeng;Zhu Dandan;Gao Peng(School of Information Science and Engineering,China University of Petroleum-Beijing,Beijing,102249,China;Engineering Technology Research Institute of PetroChina Huabei Oilfield Company,Renqiu,062550,China)

机构地区：[1]中国石油大学(北京)信息科学与工程学院,北京102249 [2]中国石油华北油田公司工程技术研究院,河北任丘062552

出　　处：《石油化工自动化》2021年第1期12-16,共5页Automation in Petro-chemical Industry

摘　　要：抽油机井智能控制平台是实现井用户、井信息、井服务三者互联互通的知识库系统。将人工智能技术融入到抽油机井用户服务互联知识库的构建中,提出了一套智能分析引擎,包括产液量预测模型、泵效计算模型和工况诊断模型,以及一种具有自寻优的电机变速控制方法,解决了关键生产参数在线预测及系统自适应提效等实际问题,并采用JavaWeb实现了抽油机井智能控制平台的设计及开发。应用结果表明:该系统的运算速度和精度能够支持在线智能分析和变速控制。The intelligent control platform of pumping well is a knowledge base system to realize the interconnection among well users, well information and well service. To integrate artificial intelligence technology into the construction of the user service interconnection knowledge base, an intelligent analysis engine, which includes an oil production prediction model, a pump efficiency calculation model and a working condition diagnosis model, as well as a motor variable speed control method with the self-optimization is proposed. The practical problems of online prediction of key production parameters and system self-adaptive efficiency improvement are solved. The design and development of intelligent control platform for pumping wells are realized by the application of JavaWeb. The application results show that the operating speed and accuracy of the system can support the online intelligent analysis and variable speed control.

关 键 词：抽油机井 人工智能 强化学习 变速控制 数据管理 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]