Incipient fault detection and diagnosis of nonlinear industrial process with missing data

doi:10.1016/j.jtice.2021.10.015

	Incipient fault detection and diagnosis of nonlinear industrial process with missing data
	Mou, Miao 2; Zhao, Xiaoqiang 1,2,3
刊名	Journal of the Taiwan Institute of Chemical Engineers
	2022-03-01
卷号	132
关键词	Data acquisition Embeddings Fault detection Matrix algebra Recovery Data missing Dissimilarity analysis Embeddings Fault detection and diagnosis Incipient faults Low rank matrix decomposition Low-rank matrices Matrix decomposition Mixed kernel function Neighborhood preserving embedding Neighbourhood
ISSN号	1876-1070
DOI	10.1016/j.jtice.2021.10.015
英文摘要	Background: In real industrial process, timely detection and diagnosis incipient fault is often more meaningful. At the same time, due to sensor failures or data acquisition system failures, process data may be missing or corrupted, resulting in loss of process information. Methods: In view of the above problems, a Mixed Kernel function Dissimilarity Neighborhood Preserving Embedding (MKDNPE) method is proposed. Firstly, Low Rank Matrix Decomposition (LRMD) is used to recover the missing data, the recovered low rank matrix contains the main information of the process. Then, the MKDNPE model is developed in the recovered low rank matrix, where the mixed kernel function is composed of a Gaussian radial basis kernel function and a polynomial kernel function. It can simultaneously extract the local information of process data and the global characteristics of data structure, and deal with the nonlinear characteristic of process. Finally, the dissimilarity statistic is introduced for incipient fault detection, and the method based on contribution chart is used for fault diagnosis. Significant findings: A numerical example and two benchmark processes are carried out for simulation verification. The simulation results further verified that the proposed method has good detection and diagnosis capabilities for incipient nonlinear faults in industrial processes with missing data. © 2021 Taiwan Institute of Chemical Engineers
WOS研究方向	Engineering
语种	英语
出版者	Taiwan Institute of Chemical Engineers
WOS记录号	WOS:000819932600006
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/157932]
专题	电气工程与信息工程学院
作者单位	1.National Experimental Teaching Center of Electrical and Control Engineering, Lanzhou University of Technology, Lanzhou; 730050, China 2.College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou; 730050, China; 3.Gansu Key Laboratory Advanced Control for Industrial Processes, Lanzhou, University of Technology, Lanzhou; 730050, China;
推荐引用方式 GB/T 7714	Mou, Miao,Zhao, Xiaoqiang. Incipient fault detection and diagnosis of nonlinear industrial process with missing data[J]. Journal of the Taiwan Institute of Chemical Engineers,2022,132.
APA	Mou, Miao,&Zhao, Xiaoqiang.(2022).Incipient fault detection and diagnosis of nonlinear industrial process with missing data.Journal of the Taiwan Institute of Chemical Engineers,132.
MLA	Mou, Miao,et al."Incipient fault detection and diagnosis of nonlinear industrial process with missing data".Journal of the Taiwan Institute of Chemical Engineers 132(2022).