基于PCA-PSO-SVC模型的有杆抽油系统故障诊断技术  

Fault Diagnosis Technology of Rod Pumping System Based on PCA-PSO-SVC Model

作　　者：王斌 黄港港 周阳 武树宝 Wang Bin;Huang Ganggang;Zhou Yang;Wu Shubao(College of Petroleum Engineering,Xi’an Shiyou University,Xi’an 710065,China)

机构地区：[1]西安石油大学石油工程学院,陕西西安710065

出　　处：《山东化工》2021年第17期158-159,161,共3页Shandong Chemical Industry

摘　　要：有杆抽油方法是我国各大油田使用最多的机械采油方法。由于工作环境恶劣,抽油系统事故频发。不同故障下泵功图形状有较大差异,因此可从泵功图出发进行故障诊断。本文在分析不同故障工况下泵功图特点,以25组样本数据建立PCA-PSO-SVC故障诊断模型。通过与PCA-GA-SVC、PCA-CV-SVC、PCA-LS-SVC三种模型对比结果可知,PCA-PSO-SVC故障诊断模型计算速度快、诊断精度高,对于故障工况诊断准确率达100%,适用于有杆抽油系统故障诊断。文中问题的分析及建模过程,对于现场人员掌握和分析抽油系统运行情况以及危险工况的规避都有重要意义。Rod pumping is the most widely used method of mechanical oil production in China's major oil fields.Because of the bad working environment,the pumping system accidents happen frequently.The shape of pump power diagram is different under different faults,so the fault diagnosis can be carried out based on the pump power diagram.In this paper,PCA-PSO-SVC fault diagnosis model was established based on 25 groups of sample data by analyzing the characteristics of pump power diagram under different fault conditions.Compared with PCA-GA-SVC,PCA-CV-SVC and PCA-LS-SVC,the PCA-PSO-SVC fault diagnosis model has high calculation speed and high diagnosis accuracy,and the fault diagnosis accuracy of the PCA-PSO-SVC is 100%,which is suitable for the fault diagnosis of rod pumping system.The analysis and modeling process of the problems in this paper are of great significance for the field personnel to grasp and analyze the operation of the pumping system and avoid the dangerous working conditions.

关 键 词：有杆抽油系统 泵功图 数据降维 PCA-PSO-SVC 故障诊断 

分 类 号：TE355.5[石油与天然气工程—油气田开发工程]