Anomaly Detection with GRU Based Bi-autoencoder for Industrial Multimode Process

doi:10.1007/s12555-021-0323-6

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 精密感知与控制

	Anomaly Detection with GRU Based Bi-autoencoder for Industrial Multimode Process
	Xu, Xinyao 2,3; Qin, Fangbo 2,3; Zhao, Wenjun 1; Xu, De 2,3; Wang, Xingang 2,3; Yang, Xihao 1
刊名	INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS
	2022-04-29
页码	14
关键词	Anomaly detection autoencoder gated recurrent unit multimode process
ISSN号	1598-6446
DOI	10.1007/s12555-021-0323-6
通讯作者	Xu, Xinyao(xuxinyao2018@ia.ac.cn)
英文摘要	The anomaly detection for multimode industrial process is a challenging problem, because the multiple operation modes present various main distributions of monitored variables, and the dynamic sequential characteristics exist within each operation mode. This paper proposes an anomaly detection method based on sequence-to-sequence gated recurrent units (SGRU). First, to better model both the cross-mode trends and mode-specific sequential characteristics, a main reconstruction module and residual reconstruction module are integrated to improve the ability to represent complex process. Both modules are implemented by SGRUs. Second, a reconstruction error prediction module is designed to estimate the mean values of mode-specific reconstruction errors, which helps to determine the more reliable alarm thresholds. Third, the two anomaly indicators are utilized to represent the deviation degree of monitored variables against the normal conditions, according to the statistical errors and biases of reconstructions, respectively. The effectiveness of the proposed method is validated on simulations with multimode process, and on the practical data set collected from the Cleaning-in-Place multimode process of an aseptic beverage filling line in a real factory.
资助项目	National Key R&D Program of China[2018YFD0400902] ; State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System[GZ2019KF008]
WOS关键词	MULTIPLE OPERATING MODES ; FAULT-DETECTION ; NETWORK ; PCA
WOS研究方向	Automation & Control Systems
语种	英语
出版者	INST CONTROL ROBOTICS & SYSTEMS, KOREAN INST ELECTRICAL ENGINEERS
WOS记录号	WOS:000788953900005
资助机构	National Key R&D Program of China ; State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48425]
专题	精密感知与控制研究中心_精密感知与控制
通讯作者	Xu, Xinyao
作者单位	1.State Key Lab Smart Mfg Special Vehicles & Transm, Baotou City 014000, Inner Mongolia, Peoples R China 2.Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Res Ctr Precis Sensing & Control, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Xu, Xinyao,Qin, Fangbo,Zhao, Wenjun,et al. Anomaly Detection with GRU Based Bi-autoencoder for Industrial Multimode Process[J]. INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS,2022:14.
APA	Xu, Xinyao,Qin, Fangbo,Zhao, Wenjun,Xu, De,Wang, Xingang,&Yang, Xihao.(2022).Anomaly Detection with GRU Based Bi-autoencoder for Industrial Multimode Process.INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS,14.
MLA	Xu, Xinyao,et al."Anomaly Detection with GRU Based Bi-autoencoder for Industrial Multimode Process".INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS (2022):14.