Automated feature learning for nonlinear process monitoring – An approach using stacked denoising autoencoder and k-nearest neighbor rule

•Automated feature learning based on stacked denoising autoencoder (SDAE) and k-nearest neighbor rule (kNN) for nonlinear process monitoring.•SDAE is used to automatically learn the patterns inherent in the nonlinear process and extract key features.•New monitoring statistics that are HD2 and RD2 ar...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of process control Vol. 64; pp. 49 - 61
Main Authors:	Zhang, Zehan, Jiang, Teng, Li, Shuanghong, Yang, Yupu
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01.04.2018
Subjects:	Automated feature learning Deep learning k-Nearest neighbor rule Nonlinear process monitoring Stacked denoising autoencoder Deep learning Nonlinear process monitoring Stacked denoising autoencoder Automated feature learning k-Nearest neighbor rule
ISSN:	0959-1524, 1873-2771
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	•Automated feature learning based on stacked denoising autoencoder (SDAE) and k-nearest neighbor rule (kNN) for nonlinear process monitoring.•SDAE is used to automatically learn the patterns inherent in the nonlinear process and extract key features.•New monitoring statistics that are HD2 and RD2 are constructed based on kNN rule using the extracted key features.•The effectiveness of the proposed method is verified by two case studies including a nonlinear numerical example and TE benchmark process. Modern industrial processes have become increasingly complicated, consequently, the nonlinearity of data collected from these systems continues to increase. However, the feature extraction methods of existing process monitoring are not capable of extracting crucial features from these highly nonlinear data, which affects the performance of monitoring. In this paper, a novel nonlinear process monitoring method based on stacked denoising autoencoder (SDAE) and k-nearest neighbor (kNN) rule is proposed. Specifically, stacked denoising autoencoder is utilized to model the nonlinear process data and automatically extract crucial features. The original nonlinear space is then mapped to the feature space and the residual space via SDAE. Two new statistics in the above spaces are constructed by introducing the kNN rule with their corresponding control limits determined by kernel density estimation. Case studies on a nonlinear numerical system and the Tennessee Eastman benchmark process verify the effectiveness of the proposed method.
ISSN:	0959-1524 1873-2771
DOI:	10.1016/j.jprocont.2018.02.004