A review on data-driven process monitoring methods: Characterization and mining of industrial data

C Ji, W Sun - Processes, 2022 - mdpi.com
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 …

A review of kernel methods for feature extraction in nonlinear process monitoring

KE Pilario, M Shafiee, Y Cao, L Lao, SH Yang - Processes, 2019 - mdpi.com
Kernel methods are a class of learning machines for the fast recognition of nonlinear
patterns in any data set. In this paper, the applications of kernel methods for feature …

A novel multivariate statistical process monitoring algorithm: Orthonormal subspace analysis

Z Lou, Y Wang, Y Si, S Lu - Automatica, 2022 - Elsevier
Partial least squares (PLS) and canonical correlation analysis (CCA) are two most popular
key performance indicators (KPI) monitoring algorithms, which have shortcomings in dealing …

Key-performance-indicator-related process monitoring based on improved kernel partial least squares

Y Si, Y Wang, D Zhou - IEEE Transactions on Industrial …, 2020 - ieeexplore.ieee.org
Although the partial least squares approach is an effective fault detection method, some
issues of nonlinear process monitoring related to key performance indicators (KPIs) still …

Statistical process monitoring of a multiphase flow facility

C Ruiz-Cárcel, Y Cao, D Mba, L Lao… - Control Engineering …, 2015 - Elsevier
Industrial needs are evolving fast towards more flexible manufacture schemes. As a
consequence, it is often required to adapt the plant production to the demand, which can be …

Nonlinear process fault diagnosis based on serial principal component analysis

X Deng, X Tian, S Chen… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
Many industrial processes contain both linear and nonlinear parts, and kernel principal
component analysis (KPCA), widely used in nonlinear process monitoring, may not offer the …

Independent component analysis application for fault detection in process industries: Literature review and an application case study for fault detection in multiphase …

GLP Palla, AK Pani - Measurement, 2023 - Elsevier
In process industries, early detection and diagnosis of faults is crucial for timely identification
of process upsets, equipment and/or sensor malfunctions. Machine learning techniques …

Key-performance-indicator-related state monitoring based on kernel canonical correlation analysis

Q Chen, Y Wang - Control Engineering Practice, 2021 - Elsevier
As a multivariate statistical analysis method, canonical correlation analysis (CCA) performs
well for state monitoring of linear processes, but most industrial processes are nonlinear. To …

Intelligent fault diagnosis for chemical processes using deep learning multimodel fusion

N Wang, F Yang, R Zhang, F Gao - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Deep learning technology has been widely used in fault diagnosis for chemical processes.
However, most deep learning technologies currently adopted only use a single network …

Monitoring nonlinear and non-Gaussian processes using Gaussian mixture model-based weighted kernel independent component analysis

L Cai, X Tian, S Chen - IEEE transactions on neural networks …, 2015 - ieeexplore.ieee.org
A kernel independent component analysis (KICA) is widely regarded as an effective
approach for nonlinear and non-Gaussian process monitoring. However, the KICA-based …