Working condition recognition of sucker rod pumping system based on 4-segment time-frequency signature matrix and deep learning
作者机构:State Key Laboratory of RoboticsShenyang Institute of AutomationChinese Academy of SciencesShenyang 110016LiaoningChina Key Laboratory of Networked Control SystemsChinese Academy of SciencesShenyang 110016LiaoningChina Institutes for Robotics and Intelligent ManufacturingChinese Academy of SciencesShenyang 110169LiaoningChina University of Chinese Academy of SciencesBeijing100049China School of Artifcial IntelligenceShenyang University of TechnologyShenyang 110870LiaoningChina
出 版 物:《Petroleum Science》 (石油科学(英文版))
年 卷 期:2024年第21卷第1期
页 面:641-653页
核心收录:
学科分类:0820[工学-石油与天然气工程] 08[工学] 082002[工学-油气田开发工程]
基 金:We would like to thank the associate editor and the reviewers for their constructive comments.This work was supported in part by the National Natural Science Foundation of China under Grant 62203234 in part by the State Key Laboratory of Robotics of China under Grant 2023-Z03 in part by the Natural Science Foundation of Liaoning Province under Grant 2023-BS-025 in part by the Research Program of Liaoning Liaohe Laboratory under Grant LLL23ZZ-02-02
主 题:Sucker-rod pumping system Dynamometer card Working condition recognition Deep learning Time-frequency signature Time-frequency signature matrix
摘 要:High-precision and real-time diagnosis of sucker rod pumping system(SRPS)is important for quickly mastering oil well *** learning-based method for classifying the dynamometer card(DC)of oil wells is an efficient diagnosis ***,the input of the DC as a two-dimensional image into the deep learning framework suffers from low feature utilization and high computational ***,different SRPSs in an oil field have various system parameters,and the same SRPS generates different DCs at different ***,there is heterogeneity in field data,which can dramatically impair the diagnostic *** solve the above problems,a working condition recognition method based on 4-segment time-frequency signature matrix(4S-TFSM)and deep learning is presented in this ***,the 4-segment time-frequency signature(4S-TFS)method that can reduce the computing power requirements is proposed for feature extraction of DC ***,the 4S-TFSM is constructed by relative normalization and matrix calculation to synthesize the features of multiple data and solve the problem of data ***,a convolutional neural network(CNN),one of the deep learning frameworks,is used to determine the functioning conditions based on the *** on field data verify that the proposed diagnostic method based on 4S-TFSM and CNN(4S-TFSM-CNN)can significantly improve the accuracy of working condition recognition with lower computational *** the best of our knowledge,this is the first work to discuss the effect of data heterogeneity on the working condition recognition performance of SRPS.