{"title":"Fault Diagnosis of Rod Pump Oil Well Based on Support Vector Machine Using Preprocessed Indicator Diagram","authors":"Jinze Liu, Jian Feng, Qiong Xiao, Shaoning Liu, Feiran Yang, Senxiang Lu","doi":"10.1109/DDCLS52934.2021.9455702","DOIUrl":null,"url":null,"abstract":"With the continuous development of the petroleum industry, rod pumping has been vigorously developed and widely used in the petroleum industry, so the fault diagnosis of rod pumping wells has become very important. Today, most of the fault diagnosis for pumping wells is based on analyzing the indicator diagram. The indicator diagram can effectively reflect the working status of the rod pump pumping well. By observing the indicator diagram, various failures of the pumping well can be judged, and corresponding measures can be taken to solve the relative failure. This is of great significance to ensure the safe, stable and efficient production of pump devices. This paper takes indicator diagram as the research object, and uses support vector machine (SVM) to identify and classify indicator diagrams to diagnose the fault types of pumping wells. A series of preprocessing is adopted for the indicator diagram, and the improved Fourier descriptor is used for feature extraction to establish a sample database of indicator diagrams. The experimental results show that this indeed improves the accuracy of SVM learning, increases the fault recognition rate, and provides a guarantee for the safe operation of rod pumping wells.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DDCLS52934.2021.9455702","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
With the continuous development of the petroleum industry, rod pumping has been vigorously developed and widely used in the petroleum industry, so the fault diagnosis of rod pumping wells has become very important. Today, most of the fault diagnosis for pumping wells is based on analyzing the indicator diagram. The indicator diagram can effectively reflect the working status of the rod pump pumping well. By observing the indicator diagram, various failures of the pumping well can be judged, and corresponding measures can be taken to solve the relative failure. This is of great significance to ensure the safe, stable and efficient production of pump devices. This paper takes indicator diagram as the research object, and uses support vector machine (SVM) to identify and classify indicator diagrams to diagnose the fault types of pumping wells. A series of preprocessing is adopted for the indicator diagram, and the improved Fourier descriptor is used for feature extraction to establish a sample database of indicator diagrams. The experimental results show that this indeed improves the accuracy of SVM learning, increases the fault recognition rate, and provides a guarantee for the safe operation of rod pumping wells.