西南石油大学学报(自然科学版) ›› 2020, Vol. 42 ›› Issue (6): 107-114.DOI: 10.11885/j.issn.1674-5086.2020.06.10.01

• 油气田人工智能技术与应用专刊 • 上一篇    下一篇

基于主成分分析法的电潜泵故障诊断

隋先富1, 彭龙2, 韩国庆2, 范白涛1, 于继飞1   

  1. 1. 中海油研究总院有限责任公司, 北京 朝阳 100027;
    2. 中国石油大学(北京)石油工程教育部重点实验室, 北京 昌平 102249
  • 收稿日期:2020-06-10 发布日期:2020-12-21
  • 通讯作者: 彭龙,E-mail:18611745494@163.com
  • 作者简介:隋先富,1982年生,男,汉族,山东高密人,工程师,博士,主要从事采油工程理论与技术、智能油田等方面的研究工作。E-mail:suixf@cnooc.com.cn;彭龙,1996年生,男,汉族,湖北黄石人,博士研究生,主要从事油气田开发方面的研究工作。E-mail:18611745494@163.com;韩国庆,1969年生,男,汉族,山东济南人,教授,博士,主要从事油气田开发方面的研究工作。E-mail:hanguoqing@163.com;范白涛,1975年生,男,汉族,河南邓州人,教授级高级工程师,博士,主要从事海洋石油钻完井技术等方面的研究工作。E-mail:fanbt@cnooc.com.cn;于继飞,1982年生,男,汉族,山东枣庄人,高级工程师,硕士,主要从事海上油田采油工艺及智能化等方面的研究工作。E-mail:yujf2@cnooc.com.cn

Fault Diagnosis of Electric Submersible Pump Based on Principal Component Analysis

SUI Xianfu1, PENG Long2, HAN Guoqing2, FAN Baitao1, YU Jifei1   

  1. 1. CNOOC Research Institute Co. Ltd., Chaoyang, Beijing 100027, China;
    2. MOE Key Laboratory of Petroleum Engineering, China University of Petroleum(Beijing), Changping, Beijing 102249, China
  • Received:2020-06-10 Published:2020-12-21

摘要: 电潜泵(Electric Submersible Pump,ESP)举升技术在非自喷高产井和高含水井中应用广泛,ESP在生产过程易发生故障,进而导致作业中断,造成严重经济损失。如何有效利用传感器、数据采集系统,SCADA系统实时采集的ESP系统生产数据,对ESP的工作状态进行提前预估至关重要。采用主成分分析法(PCA)对泵实时生产数据进行研究分析,根据电潜泵生产数据之间线性组合进行特征提取,降低生产数据的维度,创造新的主元空间,用很少的主元重新评估ESP生产系统,得出ESP井故障原因并预估ESP剩余使用寿命。主成分分析采用霍特林平方统计算法和平方误差分析算法建立诊断模型,该模型可以预估ESP剩余作业时间并确定泵出现故障的主因。以渤海油田为例,对ESP井实时数据进行主成分建模,预测泵故障的主因及故障时间,对比ESP实际生产作业时间,验证PCA进行故障诊断的可行性。证明PCA作为模式识别的一种方法可以有效监测ESP健康状况,预测ESP故障的主因。

关键词: 电潜泵, 主成分分析, 特征提取, 模式识别, 故障诊断

Abstract: Electric Submersible Pump (ESP) is currently widely employed to help enhance production for non-flowing well with high production and high water cut well. However, ESP failures are common in the oil industry, and these failures lead to production disruptions, resulting in significant economic loses. The purpose of this paper is to evaluate Principal Component Analysis (PCA) as an unsupervised machine learning technique to detect the cause of ESP failures and estimate the remaining life of ESP. The data provided by the ESP system are usually closely correlated; principal component analysis utilizes these data to extract eigenvalues and create new space, then reevaluate ESP system with multiple new principal components. Hortlin square statistical algorithm and the square error analysis algorithm are used to establish a PCA diagnostic model. This model was successfully applied in the Bohai oilfield to diagnose the ESP performance real-time. The most responsible decision variable for the potential ESP failures are determined according to the order of contribution. Also, the PCA diagnostic model was able to determine the time at which the ESP failures occurs. This paper demonstrates that the application of PCA method preforms well in monitoring ESP operations and predicts the impending ESP failures.

Key words: electric submersible pump, principal component analysis, pattern recognition, feature extraction, fault diagnosis

中图分类号: