基于GAN的软测量缺失数据生成方法研究

TP273; 针对工业过程中传感器数据缺失造成软测量模型精度低的问题,提出一种基于生成对抗网络(generative adversarial nets,GAN)的传感器缺失数据生成方法.利用孤立森林算法检测出传感器数据的缺失区域;利用缺失数据属性特征训练条件生成对抗网络(conditional generative adversarial nets,CGAN),在CGAN的输入条件中添加随机序列作为附加信息迭代送入CGAN中生成数据,并借助WGAN-GP(wasserstein generative adversarial nets gradient penalty)成本函数提高网络训练的稳定...

Full description

Saved in:
Bibliographic Details
Published in西北工业大学学报 Vol. 42; no. 2; pp. 344 - 352
Main Authors 蒋栋年, 王仁杰
Format Journal Article
LanguageChinese
Published 兰州理工大学 电气工程与信息工程学院,甘肃 兰州 730050 01.04.2024
Subjects
软测量模型
生成对抗网络
数据缺失
孤立森林
data missing
GAN
isolated forest
soft sensor model
Online AccessGet full text
ISSN1000-2758
DOI10.1051/jnwpu/20244220344

Cover

Abstract TP273; 针对工业过程中传感器数据缺失造成软测量模型精度低的问题,提出一种基于生成对抗网络(generative adversarial nets,GAN)的传感器缺失数据生成方法.利用孤立森林算法检测出传感器数据的缺失区域;利用缺失数据属性特征训练条件生成对抗网络(conditional generative adversarial nets,CGAN),在CGAN的输入条件中添加随机序列作为附加信息迭代送入CGAN中生成数据,并借助WGAN-GP(wasserstein generative adversarial nets gradient penalty)成本函数提高网络训练的稳定性;针对缺失区域检测结果引入采样器,将采样的数据填补进缺失区域,形成完整数据集,以提高软测量模型精度.以镍闪速炉温度传感器数据为目标变量进行软测量建模,验证所提出的提高软测量模型精度方法的可行性与有效性.
AbstractList TP273; 针对工业过程中传感器数据缺失造成软测量模型精度低的问题,提出一种基于生成对抗网络(generative adversarial nets,GAN)的传感器缺失数据生成方法.利用孤立森林算法检测出传感器数据的缺失区域;利用缺失数据属性特征训练条件生成对抗网络(conditional generative adversarial nets,CGAN),在CGAN的输入条件中添加随机序列作为附加信息迭代送入CGAN中生成数据,并借助WGAN-GP(wasserstein generative adversarial nets gradient penalty)成本函数提高网络训练的稳定性;针对缺失区域检测结果引入采样器,将采样的数据填补进缺失区域,形成完整数据集,以提高软测量模型精度.以镍闪速炉温度传感器数据为目标变量进行软测量建模,验证所提出的提高软测量模型精度方法的可行性与有效性.
Abstract_FL To solve the problem of low precision in soft sensor models caused by sensor data loss in industrial processes,a new method of sensor data generation based on generative adversarial nets(GAN)is proposed.Firstly,the missing area of sensor data is detected by the isolated forest algorithm.Secondly,conditional generative adversarial nets(CGAN)are training using the attributes of missing data.By adding random sequences to the input conditions of CGAN as additional information,the data is generated iteratively in CGAN.The wasserstein generative adversarial nets gradient penalty(WGAN-GP)cost function is used to improve the stability of network training.Fi-nally,a sampler is introduced to fill the sampled data into the missing region and form a complete data set to im-prove the accuracy of the soft sensing model.In this paper,the temperature sensor data of a nickel flash furnace is used as the target variable for soft-sensing modelling,and the feasibility and effectiveness of the proposed method to improve the accuracy of the soft-sensing model are verified.
Author 王仁杰
蒋栋年
AuthorAffiliation 兰州理工大学 电气工程与信息工程学院,甘肃 兰州 730050
AuthorAffiliation_xml – name: 兰州理工大学 电气工程与信息工程学院,甘肃 兰州 730050
Author_FL JIANG Dongnian
WANG Renjie
Author_FL_xml – sequence: 1
  fullname: JIANG Dongnian
– sequence: 2
  fullname: WANG Renjie
Author_xml – sequence: 1
  fullname: 蒋栋年
– sequence: 2
  fullname: 王仁杰
BookMark eNotj7tKA0EYRqeIYIx5AB_BYs0_M__uzpQhaBSCNlqHmd3ZYJCJuISsvaAgXorEwiYWNjZeEAUXfRszq2_hilanO-f7FkjFDqwhZInCCgWfNvp2tD9sMGCIjAFHrJAqBQCPhb6YJ_U03dXgSwrIBFYJn03zz_y83dwsro--Ph7cy-n38UXxns9un9zk0Z3dF-OpO7l0V2_ueVLcjIu710Uyl6i91NT_WSM7a6vbrXWvs9XeaDU7XlrapRdxxVGoRMSJLgfECQt0CCiEERSVH8iAKQ7AjKY8EihDYFHIoyjUgqORhtfI8p93pGyibK_bHwwPbFnsZrp3GGeZ_r0JDKjkP9WeWmQ
ClassificationCodes TP273
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.1051/jnwpu/20244220344
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL Research on the generation method of missing data for soft measurement based on GAN
EndPage 352
ExternalDocumentID xbgydxxb202402019
GrantInformation_xml – fundername: (国家自然科学基金); (甘肃省重点研发计划); (兰州市科技计划); (甘肃省杰出青年基金); 兰州理工大学红柳杰出青年人才支持计划与陇原青年英才项目
  funderid: (国家自然科学基金); (甘肃省重点研发计划); (兰州市科技计划); (甘肃省杰出青年基金); 兰州理工大学红柳杰出青年人才支持计划与陇原青年英才项目
GroupedDBID 2B.
4A8
92I
93N
AFKRA
ALMA_UNASSIGNED_HOLDINGS
BENPR
CCPQU
PHGZM
PHGZT
PIMPY
PMFND
PSX
TCJ
ID FETCH-LOGICAL-s1049-c3a348af8dfb000df26b70488e814a56962a3002eb13c849702c73cc7b834e9e3
ISSN 1000-2758
IngestDate Thu May 29 04:00:29 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords 软测量模型
生成对抗网络
数据缺失
孤立森林
data missing
GAN
isolated forest
soft sensor model
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1049-c3a348af8dfb000df26b70488e814a56962a3002eb13c849702c73cc7b834e9e3
PageCount 9
ParticipantIDs wanfang_journals_xbgydxxb202402019
PublicationCentury 2000
PublicationDate 2024-04-01
PublicationDateYYYYMMDD 2024-04-01
PublicationDate_xml – month: 04
  year: 2024
  text: 2024-04-01
  day: 01
PublicationDecade 2020
PublicationTitle 西北工业大学学报
PublicationTitle_FL Journal of Northwestern Polytechnical University
PublicationYear 2024
Publisher 兰州理工大学 电气工程与信息工程学院,甘肃 兰州 730050
Publisher_xml – name: 兰州理工大学 电气工程与信息工程学院,甘肃 兰州 730050
SSID ssib059104284
ssib001129888
ssib046626106
ssib036436219
ssib044765131
ssib044604139
ssib051375596
ssib002258180
Score 2.423807
Snippet TP273; 针对工业过程中传感器数据缺失造成软测量模型精度低的问题,提出一种基于生成对抗网络(generative adversarial nets,GAN)的传感器缺失数据生成方法.利用孤立森林算...
SourceID wanfang
SourceType Aggregation Database
StartPage 344
Title 基于GAN的软测量缺失数据生成方法研究
URI https://d.wanfangdata.com.cn/periodical/xbgydxxb202402019
Volume 42
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  issn: 1000-2758
  databaseCode: M~E
  dateStart: 20180101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://road.issn.org
  omitProxy: true
  ssIdentifier: ssib044765131
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: ProQuest Central
  issn: 1000-2758
  databaseCode: BENPR
  dateStart: 20180201
  customDbUrl: http://www.proquest.com/pqcentral?accountid=15518
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.proquest.com/central
  omitProxy: true
  ssIdentifier: ssib059104284
  providerName: ProQuest
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3LbtQwMCrbCxcEAsRbFcKnVWjWsR376GwTKiRWCLVSb1WSTcppQXRXLD0jgYR4HFoOXMqBCxceQiCxgr-hu_AXzDjJrqE9FC7WxB6P5xHHM4k9cZwrEPQobHMpSzMIULhyVVcoN6eKJkUrKUQXX-jf6IjlVXZ9ja_NHbF3LQ366dVs68BzJf9jVagDu-Ip2X-w7JQoVAAM9oUSLAzloWxMIk5UTEJNIoaljK7pDokCogBmJJIkXCI6JpEgIScyJJEiEPzLGHHCtunIiYa-LcRRnIQeAhJ6RYYOQ_pYI4kyTQpIKUPQR3zA0R6iIaBIKGxnFxnQQDPGUWSbqACBMMBKZFginyUD2jRpGFdYAIyrAbm-KZCeokYOgcMiwJGdkM1QQLzItMAAIfjJhuklEMx-v0HtbTF4RxoOS_ENh6oUH8YQFs9_s9qsdATKRY2UiphiQylrTiRyhUBMtGEJGNPxQchT4RVRimgKc6C2hEQFSFCA39zPb9P8EsCzFhk8zU-DMmV9vQoxas02ai0pfpkfs_JO_DLf776FD56tuPD17t8d4Bkf0COj1Jv2_SOj-DDdeNAdDlPEgmgBk-bOU1gUvYYzH0adm7dm_jR4g9LOZ0c55gaor31wZwWd5QNkTHjMSjPLWCB4a_aZmQkIn63P-tAWQEQ7uwbfFcJhsxOk1lG9E4G3Fo10i5Zs5qBdr0h6G5ZPuHLcOVYFcwu6nJknnLmt2ycdf2939GP0DGbi5NXDn9_fjz8_-fXo-eTbaO_Nx_HOh_HTd5Pt3fHjF-OXX8efdiavtydvv5xyVuNopb3sVr8mcTeBReVmfuIzmRSyW6Ab3S2oSANcDHPZYgkXStAErE7BE_IzyVTg0SzwsyxIpc9ylfunnUbvTi8_4ywozOKWJzn10hbjCZepTCTSLrqMSZGfdS5XQq5Xj57N9X0WPHcYpPPO0dkEu-A0-vcG-UVwqfvppcrwvwGYNZFJ
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8EGAN%E7%9A%84%E8%BD%AF%E6%B5%8B%E9%87%8F%E7%BC%BA%E5%A4%B1%E6%95%B0%E6%8D%AE%E7%94%9F%E6%88%90%E6%96%B9%E6%B3%95%E7%A0%94%E7%A9%B6&rft.jtitle=%E8%A5%BF%E5%8C%97%E5%B7%A5%E4%B8%9A%E5%A4%A7%E5%AD%A6%E5%AD%A6%E6%8A%A5&rft.au=%E8%92%8B%E6%A0%8B%E5%B9%B4&rft.au=%E7%8E%8B%E4%BB%81%E6%9D%B0&rft.date=2024-04-01&rft.pub=%E5%85%B0%E5%B7%9E%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6+%E7%94%B5%E6%B0%94%E5%B7%A5%E7%A8%8B%E4%B8%8E%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E7%94%98%E8%82%83+%E5%85%B0%E5%B7%9E+730050&rft.issn=1000-2758&rft.volume=42&rft.issue=2&rft.spage=344&rft.epage=352&rft_id=info:doi/10.1051%2Fjnwpu%2F20244220344&rft.externalDocID=xbgydxxb202402019
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fxbgydxxb%2Fxbgydxxb.jpg