摘要
Oscillation detection has been a hot research topic in industries due to the high incidence of oscillation loops and their negative impact on plant profitability.Although numerous automatic detection techniques have been proposed,most of them can only address part of the practical difficulties.An oscillation is heuristically defined as a visually apparent periodic variation.However,manual visual inspection is labor-intensive and prone to missed detection.Convolutional neural networks(CNNs),inspired by animal visual systems,have been raised with powerful feature extraction capabilities.In this work,an exploration of the typical CNN models for visual oscillation detection is performed.Specifically,we tested MobileNet-V1,ShuffleNet-V2,Efficient Net-B0,and GhostNet models,and found that such a visual framework is well-suited for oscillation detection.The feasibility and validity of this framework are verified utilizing extensive numerical and industrial cases.Compared with state-of-theart oscillation detectors,the suggested framework is more straightforward and more robust to noise and mean-nonstationarity.In addition,this framework generalizes well and is capable of handling features that are not present in the training data,such as multiple oscillations and outliers.
基金
the National Natural Science Foundation of China(62003298,62163036)
the Major Project of Science and Technology of Yunnan Province(202202AD080005,202202AH080009)
the Yunnan University Professional Degree Graduate Practice Innovation Fund Project(ZC-22222770)。
作者简介
Tao Wang received the B.S.degree in communications engineering from Qiqihar University in 2021.He is currently a master student in communications engineering at the Department of Electronic Engineering,Information School,Yunnan University.His main research interests include control performance evaluation,process monitoring,computer vision,and machine learning.(e-mail:wt199905@mail.ynu.edu.cn);Qiming Chen received the Ph.D.degree in control science and engineering from the State Key Laboratory of Industrial Control Technology,Institute of Cyber-Systems and Control,Zhejiang University in 2022.He works at DAMO Academy,Alibaba Group,as a Senior Algorithm Engineer.His main research interests include control system performance evaluation and fault diagnosis,signal decomposition and time-frequency analysis,industrial big data causality analysis and knowledge mining.(e-mail:chenqiming@zju.edu.cn);Corresponding author:Xun Lang received the B.S.and Ph.D.degrees in automation from Zhejiang University in 2014 and 2019,respectively.He was a Visiting Scholar with the Department of Mechanical Engineering,University of California,USA,from 2017 to 2018.He is currently an Associate Professor at the School of Information,Yunnan University.His current research interests include process monitoring,control performance assessment and signal processing.(e-mail:langxun@ynu.edu.cn);Lei Xie received the B.S.and Ph.D.degrees in control science and engineering from Zhejiang University in 2000 and 2005,respectively.From 2005 to 2006,he was a Postdoctoral Researcher with the Berlin University of Technology,was an Assistant Professor,from 2005 to 2008,and is currently a Professor with the State Key Laboratory of Industrial Control Technology,Institute of Cyber-Systems and Control,Zhejiang University.His research interests focus on the interdisciplinary area of statistics and system control theory.(e-mail:leix@iipc.zju.edu.cn);Peng Li received the B.S.and Ph.D.degrees in control science and engineering from East China University of Science and Technology in 1999 and 2007,respectively.He was a Postdoctoral Researcher with the Department of Automation at Tsinghua University and Yunnan Power Grid Co.,Ltd from 2012 to 2014.He is currently an Associate Professor with the Department of Electronic Engineering,Yunnan University.His research interests include process monitoring,control and optimization,especially in the field of smart grid.(e-mail:lipeng@ynu.edu.cn);Hongye Su(Senior Member,IEEE)received the B.S.degree in industrial automation from the Nanjing University of Chemical Technology in 1990,and the M.S.and Ph.D.degrees in control science and engineering from Zhejiang University in 1993 and 1995,respectively.He was an Associate Professor with the Institute of Advanced Process Control,from 1998 to 2000,and is currently a Professor with State Key Laboratory of Industrial Control Technology,Institute of Cyber-Systems and Control,Zhejiang University.His current research interests include the robust control,time-delay systems,and advanced process control theory and applications.(e-mail:hysu@iipc.zju.edu.cn).
