Novel semi-supervised sparse stacked autoencoder integrated with local linear embedding for industrial soft sensing

Data-driven industrial soft sensor modeling techniques have been widely applied in predicting key variables in complex industrial processes. However, with industrial processes becoming increasingly intricate, the data they produce exhibit characteristics such as strong temporal dependencies, high di...

Full description

Saved in:
Bibliographic Details
Published in:ISA transactions
Main Authors: He, Yan-Lin, Jiang, Yu, Gao, Hui-Hui, Xu, Yuan, Zhu, Qun-Xiong
Format: Journal Article
Language:English
Published: United States Elsevier Ltd 04.06.2025
Subjects:
Data-driven modelling
Industrial processes
Industrial soft sensors
Local features
Industrial processes
Industrial soft sensors
Local features
Data-driven modelling
ISSN:0019-0578, 1879-2022, 1879-2022
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Data-driven industrial soft sensor modeling techniques have been widely applied in predicting key variables in complex industrial processes. However, with industrial processes becoming increasingly intricate, the data they produce exhibit characteristics such as strong temporal dependencies, high dimensionality, and local structures, posing significant challenges for soft sensing. To address these issues, this paper proposes novel Semi-Supervised Sparse Stacked Autoencoder integrated with the Local Linear Embedding algorithm (SS-SAE-LLE). Unlike traditional autoencoders (AE), which capture hierarchical data features by minimizing global fitting error, SS-SAE-LLE simultaneously accounts for the spatio-temporal characteristics of the data through the local linear embedding algorithm. Moreover, it incorporates supervised tuning by leveraging labeled data and training with a semi-supervised learning framework, further improving prediction accuracy. To evaluate the feasibility of the proposed method, experiments are conducted on PTA solvent and SRU system datasets. The simulation results demonstrate that SS-SAE-LLE achieves higher prediction accuracy than other models, highlighting its applicability in the field of industrial soft sensor modeling. •SS-SAE-LLE is proposed for data-driven industrial soft sensor modeling.•SS-SAE-LLE captures hierarchical and spatio-temporal features simultaneously.•Supervised tuning with labeled data enhances the regression performance.•SS-SAE-LLE effectively addresses high dimensionality and temporal dependencies in process data.•Experimental results on PTA solvent and SRU datasets demonstrate the superior accuracy of SS-SAE-LLE.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0019-0578
1879-2022
1879-2022
DOI:10.1016/j.isatra.2025.05.044