2017
DOI: 10.1088/1361-6501/aa57e2
|View full text |Cite
|
Sign up to set email alerts
|

Soft sensor modelling by time difference, recursive partial least squares and adaptive model updating

Abstract: To investigate time-variant and nonlinear characteristics in industrial processes, a soft sensor modelling method based on time difference moving-window recursive partial least square (PLS) and adaptive model updating is proposed. In this method, time difference values of input and output variables are used as training samples to construct the model, which can reduce the effects of the nonlinear characteristic on modelling accuracy and retain the advantages of recursive PLS algorithm. To solve the high updatin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
6
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(6 citation statements)
references
References 15 publications
0
6
0
Order By: Relevance
“…The former is commonly based on the first principle model but hard to be extensively used on account of its complicated processes and unquantifiable parametric relationships. The most popular modeling techniques for data-driven soft sensors include principal component regression (PCR) [12,13], partial least squares (PLS) [14,15], artificial neural networks (ANN) [16,17] and support vector machines (SVM) [18,19]. Wang et al [20] integrated random forest with Bayesian optimization to predict and maintain product quality and validated model superiorities through semiconductor production line data.…”
Section: Quality Control In Process Industriesmentioning
confidence: 99%
“…The former is commonly based on the first principle model but hard to be extensively used on account of its complicated processes and unquantifiable parametric relationships. The most popular modeling techniques for data-driven soft sensors include principal component regression (PCR) [12,13], partial least squares (PLS) [14,15], artificial neural networks (ANN) [16,17] and support vector machines (SVM) [18,19]. Wang et al [20] integrated random forest with Bayesian optimization to predict and maintain product quality and validated model superiorities through semiconductor production line data.…”
Section: Quality Control In Process Industriesmentioning
confidence: 99%
“…The time difference modelling approach is based on the difference of an output variable in two moments in time (Δy ) according to the difference of the input values for those time moments (Δx). This time difference representation can avoid process linear changes in time, which causes degradation in the accuracy model [121,122].…”
Section: Model Maintenancementioning
confidence: 99%
“…In recent decades, various soft measurement methods have been widely used in different industries. By using the soft measurement technology, an inferential model can be constructed between some variables that can be measured online (also called auxiliary variables) and other variables that cannot be measured online (also called objective variables), and the inferential model can be used to estimate the objective variables to achieve the optimal control of industrial processes [3]. With the wide application of machine learning technology in soft measurement, Vallejo [4] presented a review on soft metrology systems based on machine learning techniques and defined the tendencies, challenges and opportunities in their development.…”
Section: Introductionmentioning
confidence: 99%