Nonlinear Quality-Related Fault Detection Using Neighborhood Embedding Neural Orthogonal Mapping Algorithm for Batch Process

doi:10.1002/ceat.202200577

	Nonlinear Quality-Related Fault Detection Using Neighborhood Embedding Neural Orthogonal Mapping Algorithm for Batch Process
	Liu, Kai 1,2; Zhao, Xiaoqiang1,2,3 ; Hui, Yongyong1,2,3 ; Jiang, Hongmei1,2,3
	2024-03-30
在线发表时间	2024-03
发表期刊	CHEMICAL ENGINEERING & TECHNOLOGY
ISSN	0930-7516
摘要	Quality-related fault detection has become a hot research topic in recent years. It is not reliable to measure quality-related relationships only by mutual information among process variables and single-quality variables. Frequent alarms for quality-unrelated faults seriously affect the normal operation of industrial production. At the same time, the strong nonlinearity of the process data leads to the difficulty of feature extraction. In this paper, we propose a fault detection algorithm based on nonlinear quality-related neighborhood embedding neural orthogonal mapping (QR-NENOM). First, quality-related and quality-unrelated variables are selected by Bayesian fusion mutual information, and the weighted method of mutual information is used to enhance the quality-related information and suppress the quality-unrelated information. Second, local manifold information is obtained by reconstructing nearest neighbors of process data, and key features are extracted by the nonlinear method composed of neural network and orthogonal mapping. Then, statistical indicators are established to complete fault detection. Finally, the nonlinear feature extraction ability of NENOM is verified by numerical examples, and the QR-NENOM algorithm proposed in this paper is applied to the penicillin fermentation process. Comparative experiments show that QR-NENOM has better detection performance for quality-related faults and fewer alarms for quality-unrelated faults. The QR-NENOM algorithm not only has a high fault detection rate for quality-related faults, but also has fewer alarms for unrelated faults. Moreover, it preserves the local flow structure information while extracting the key nonlinear features of the data. image
关键词	Batch process Fault detection Neighborhood preserving embedding Neural network Quality related
DOI	10.1002/ceat.202200577
收录类别	SCIE ; EI
语种	英语
资助项目	National Natural Science Foundation of China; College Industrial Support Project of Gansu Province [2023CYZC-24]; Open Fund project of Gansu Provincial Key Laboratory of Advanced Control for Industrial Process [2022KX07]; [62263021]
WOS研究方向	Engineering
WOS类目	Engineering, Chemical
WOS记录号	WOS:001193520900001
出版者	WILEY-V C H VERLAG GMBH
EI入藏号	20241415831682
EI主题词	Embeddings
EI分类号	723.2 Data Processing and Image Processing ; 723.4 Artificial Intelligence ; 802.3 Chemical Operations
原始文献类型	Article;Early Access
EISSN	1521-4125
引用统计	无
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/170207
专题	电气工程与信息工程学院
通讯作者	Zhao, Xiaoqiang
作者单位	1.Lanzhou Univ Technol, Coll Elect & Informat Engn, Qilihe St, Lanzhou 730050, Peoples R China; 2.Lanzhou Univ Technol, Gansu Key Lab Adv Control Ind Proc, Qilihe St, Lanzhou 730050, Peoples R China; 3.Lanzhou Univ Technol, Natl Expt Teaching Ctr Elect & Control Engn, Qilihe St, Lanzhou 730050, Peoples R China
第一作者单位	电气工程与信息工程学院; 兰州理工大学
通讯作者单位	电气工程与信息工程学院; 兰州理工大学
第一作者的第一单位	电气工程与信息工程学院
推荐引用方式 GB/T 7714	Liu, Kai,Zhao, Xiaoqiang,Hui, Yongyong,et al. Nonlinear Quality-Related Fault Detection Using Neighborhood Embedding Neural Orthogonal Mapping Algorithm for Batch Process[J]. CHEMICAL ENGINEERING & TECHNOLOGY,2024.
APA	Liu, Kai,Zhao, Xiaoqiang,Hui, Yongyong,&Jiang, Hongmei.(2024).Nonlinear Quality-Related Fault Detection Using Neighborhood Embedding Neural Orthogonal Mapping Algorithm for Batch Process.CHEMICAL ENGINEERING & TECHNOLOGY.
MLA	Liu, Kai,et al."Nonlinear Quality-Related Fault Detection Using Neighborhood Embedding Neural Orthogonal Mapping Algorithm for Batch Process".CHEMICAL ENGINEERING & TECHNOLOGY (2024).