Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Few-Shot Indicator Diagram Based on Meta-learning

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 工业控制网络与系统研究室

	Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Few-Shot Indicator Diagram Based on Meta-learning
	He YP(贺云鹏)1,3,4,5; Zang CZ(臧传治)1,3,4; Zeng P(曾鹏)1,3,4; Wang MX(王明新)1,2,3,4; Wan GX(万广喜)1,3,4,5; Dong QW(董青卫)1,3,4,5
	2021
会议日期	May 26-28, 2021
会议地点	Chicago
关键词	Few-shot learning Indicator diagram Meta-learning Sucker-rod pumping system Working condition recognition
页码	436-444
英文摘要	It is necessary to recognize the working condition of pumping wells accurately and intelligently. The traditional intelligent algorithm recognizes indicator diagrams require a substantial amount of manual calibration data for training. However, artificially selected geometric features of indicator diagrams are often disturbed by human factors, resulting in inaccurate feature extraction and reduced classification accuracy. This paper proposes an automatic fault diagnosis method based on meta-learning algorithm to identify the sucker-rod pumping systems working conditions with few-shot indicator diagrams. The algorithm trains a model on existing various working conditions tasks so that it can use only a small number of calibrated samples of new working conditions to solve new learning tasks. The experimental results show that the proposed meta-learning method greatly reduces the need for manual calibration data volume and improves the accuracy of working condition identification.
产权排序	1
会议录	2021 International Conference on Intelligent Automation and Soft Computing (IASC 2021)
会议录出版者	Springer Science and Business Media Deutschland GmbH
会议录出版地	Berlin
语种	英语
ISSN号	2367-4512
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/29407]
专题	沈阳自动化研究所_工业控制网络与系统研究室
通讯作者	Zang CZ(臧传治)
作者单位	1.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China 2.School of Automation and Electrical Engineering, Shenyang Ligong University, Shenyang 110159, China 3.Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang 110016, China 4.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 5.University of Chinese Academy of Sciences, Beijing 100049, China
推荐引用方式 GB/T 7714	He YP,Zang CZ,Zeng P,et al. Automatic Recognition of Sucker-Rod Pumping System Working Conditions Using Few-Shot Indicator Diagram Based on Meta-learning[C]. 见:. Chicago. May 26-28, 2021.