A Review on Data-Driven Process Monitoring Methods: Characterization and Mining of Industrial Data

Safe and stable operation plays an important role in the chemical industry. Fault detection and diagnosis (FDD) make it possible to identify abnormal process deviations early and assist operators in taking proper action against fault propagation. After decades of development, data-driven process mon...

Full description

Saved in:
Bibliographic Details
Published inProcesses Vol. 10; no. 2; p. 335
Main Authors Ji, Cheng, Sun, Wei
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.02.2022
Subjects
Artificial intelligence
Carbon
Chemical industry
Data analysis
Data processing
Datasets
Distributed control systems
False alarms
Fault detection
Fault diagnosis
Industrial applications
Monitoring
Reviews
Simulation
Online AccessGet full text

Cover

More Information
Summary:Safe and stable operation plays an important role in the chemical industry. Fault detection and diagnosis (FDD) make it possible to identify abnormal process deviations early and assist operators in taking proper action against fault propagation. After decades of development, data-driven process monitoring technologies have gradually attracted attention from process industries. Although many promising FDD methods have been proposed from both academia and industry, challenges remain due to the complex characteristics of industrial data. In this work, classical and recent research on data-driven process monitoring methods is reviewed from the perspective of characterizing and mining industrial data. The implementation framework of data-driven process monitoring methods is first introduced. State of art of process monitoring methods corresponding to common industrial data characteristics are then reviewed. Finally, the challenges and possible solutions for actual industrial applications are discussed.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2227-9717
2227-9717
DOI:10.3390/pr10020335