基于支持向量机的有杆抽油系统工况监测与诊断分析-condition monitoring and diagnosis analysis of sucker rod pumping system based on support vector machine.docx

英文摘要Subject ： A Study on Condition Monitoring and Diagnosis of Sucker-rod PumpingSystem Based on SVM Speciality：Mechinery and Electronics EngineeringName ：Meng yangyang (signature) Instructor：Wu Wei(signature) Wei Hangxin(signature) ABSTRACTSucker-rod pumping system dominates the main position in the petroleum production of the current world, especially during the tail development of oilfields, to understand and master working-pump’s condition of oilfields plays an important role in the exploit oil well. This paper introduces a fault diagnosis method based on support vector machine (SVM), using its good recognition ability to small sample problems to diagnose the fault under the oilfields.（ 1 ） This paper thinks the sucker rod pumping wells as the research objects to deeplyanalyze the /dict_result.aspx?searchword=%e7%a4%ba%e5%8a%9f%e5%9b%beamp;tjType=sentenceamp;styleamp;t=indicator%2Bdiagramindicator diagram and it’ s formation principle.（ 2 ） Then aiming at /dict_result.aspx?searchword=%e7%a4%ba%e5%8a%9f%e5%9b%beamp;tjType=sentenceamp;styleamp;t=indicator%2Bdiagramindicator diagram of pretreatment and normalization, using two methods to extract the /dict_result.aspx?searchword=%e7%a4%ba%e5%8a%9f%e5%9b%beamp;tjType=sentenceamp;styleamp;t=indicator%2Bdiagramindicator diagram’s eigenvector of image moment invariants andwavelet packet-energy entropy (WP-EE).（3）Discussing the important theory of statistical learning theory and SVM, they are VC dimension, promotional boundary and structural risk minimization principle. Then introducessome algorithms of linear, nonlinear and classification based on support vector machine.（ 4 ） Based on the above ， researching the method to identify the /dict_result.aspx?searchword=%e7%a4%ba%e5%8a%9f%e5%9b%beamp;tjType=sentenceamp;styleamp;t=indicator%2Bdiagramindicator diagram classification based on SVM. Through comparing the final results by different normalizationmethods, different kernel functions and different param