Rebooting data-driven soft-sensors in process industries: A review of kernel methods

•Kernel learning is investigated for data pre-processing, sample selection, variable selection.•Online, multi-output, small-data, multi-step and semi-supervised soft-sensors are investigated.•Soft-sensors to achieve fault diagnosis and advanced control of process industries are discussed.•Potential...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of process control Ročník 89; s. 58 - 73
Hlavní autori: Liu, Yiqi, Xie, Min
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.05.2020
Predmet:
Data-driven
Kernel
Process industries
Soft-sensors
Soft-sensors
Process industries
Data-driven
Kernel
ISSN:0959-1524, 1873-2771
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•Kernel learning is investigated for data pre-processing, sample selection, variable selection.•Online, multi-output, small-data, multi-step and semi-supervised soft-sensors are investigated.•Soft-sensors to achieve fault diagnosis and advanced control of process industries are discussed.•Potential perspectives on kernel-based soft-sensors are highlighted for future explorations. Soft-sensors usually assist in dealing with the unavailability of hardware sensors in process industries, thus allowing for less fault occurrence and better control performance. However, nonlinear, non-stationary, ill-data, auto-correlated and co-correlated behaviors in industrial data always make general data-driven methods inadequate, thus resorting to kernel-based methods provide a necessary alternative. This paper gives a systematic review of various state-of-the-art kernel-based methods with applications for data pre-processing, sample selection, variable selection, model construction and reliability analysis of soft-sensors. An integrated review of various kernel-based soft-sensor modeling methods is attempted, including on-line, multi-output, small-data-driven, multi-step-ahead and semi-supervised applications. The discussion is further to provide an overview of achieving hard-to-measure variable prediction, fault detection and advanced control of process industries. Finally, data-driven soft-sensors with kernel methods perspectives on potential challenges and opportunities have been highlighted for future explorations in the process industrial communities.
ISSN:0959-1524
1873-2771
DOI:10.1016/j.jprocont.2020.03.012