A Deep Nonnegative Matrix Factorization Approach via Autoencoder for Nonlinear Fault Detection

doi:10.1109/TII.2019.2951011

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 > 人工智能与机器学习

	A Deep Nonnegative Matrix Factorization Approach via Autoencoder for Nonlinear Fault Detection
	Ren, Zelin 1,2; Zhang, Wensheng 1,2; Zhang, Zhizhong 1,2
刊名	IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
	2020-08-01
卷号	16 期号:8 页码:5042-5052
关键词	Kernel Fault detection Feature extraction Matrix decomposition Neural networks Informatics Data-driven fault detection deep autoencoder nonlinear industrial process nonnegative matrix factorization (NMF)
ISSN号	1551-3203
DOI	10.1109/TII.2019.2951011
通讯作者	Zhang, Wensheng(zhangwenshengia@hotmail.com)
英文摘要	In the era of big data, data-driven fault detection is vital for modern industrial systems. This article considers the potential complexity of fault detection and proposes a novel nonlinear method based on nonnegative matrix factorization (NMF). Motivated by an autoencoder, in this article we first utilize the input data to learn an appropriate nonlinear mapping function, which transforms the original space into a high-dimensional feature space. Then, according to the decomposition rule of NMF, we divide the learned feature space into two subspaces, and two statistics in these subspaces are designed appropriately for nonlinear fault detection. The established method, i.e., deep nonnegative matrix factorization (DNMF), is implemented by three parts: an encoder module, an NMF module, and a decoder module. Unlike conventional NMF-based nonlinear methods using implicit and predetermined kernels, DNMF provides a new nonlinear scheme applied to NMF via a deep autoencoder framework and realizes nonlinear mapping for input data automatically. Our proposed nonlinear framework can be further generalized to other linear methods. Besides, DNMF greatly expands the NMF application scope by breaking through the limitation of nonnegative input. The Tennessee Eastman process as an industrial benchmark is employed to verify the effectiveness of the proposed method.
资助项目	National Natural Science Foundation of China[61602484] ; National Natural Science Foundation of China[61876183] ; National Natural Science Foundation of China[U1636220] ; Beijing Municipal Natural Science Foundation[4172063] ; Beijing Municipal Natural Science Foundation[TII-19-1879]
WOS关键词	DIAGNOSIS
WOS研究方向	Automation & Control Systems ; Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000537198400007
资助机构	National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/39632]
专题	精密感知与控制研究中心_人工智能与机器学习
通讯作者	Zhang, Wensheng
作者单位	1.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 2.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Ren, Zelin,Zhang, Wensheng,Zhang, Zhizhong. A Deep Nonnegative Matrix Factorization Approach via Autoencoder for Nonlinear Fault Detection[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2020,16(8):5042-5052.
APA	Ren, Zelin,Zhang, Wensheng,&Zhang, Zhizhong.(2020).A Deep Nonnegative Matrix Factorization Approach via Autoencoder for Nonlinear Fault Detection.IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,16(8),5042-5052.
MLA	Ren, Zelin,et al."A Deep Nonnegative Matrix Factorization Approach via Autoencoder for Nonlinear Fault Detection".IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 16.8(2020):5042-5052.