Deep Bayesian Slow Feature Extraction With Application to Industrial Inferential Modeling

Inferential modeling has been of significance for modern manufacturing in estimating the quality-related process variables. As an effective inferential model, probabilistic slow feature analysis (PSFA) has gained attention in regression tasks to interpret dynamic properties with a slowness preferenc...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2023-01, Vol.19 (1), p.40-51
Main Authors: Jiang, Chao, Lu, Yusheng, Zhong, Weimin, Huang, Biao, Tan, Dayu, Song, Wenjiang, Qian, Feng
Format: Article
Language:English
Subjects:
Bayes methods
Data models
Deep learning (DL)
Error reduction
Feature extraction
Hydrocracking
industrial hydrocracking process
Inference
inferential modeling
Informatics
Labels
Linear programming
Machine learning
Modelling
Probabilistic logic
probabilistic slow feature analysis (PSFA)
Process variables
Statistical analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Inferential modeling has been of significance for modern manufacturing in estimating the quality-related process variables. As an effective inferential model, probabilistic slow feature analysis (PSFA) has gained attention in regression tasks to interpret dynamic properties with a slowness preference. However, PSFA is often challenged by the nonlinear sequential data due to its linear state-space structure. In this article, a new nonlinear extension of PSFA is proposed under the deep learning framework to enhance the dynamic feature extraction with limited labels, incorporating variational inference and Monte Carlo inference to derive the objective function. The proposed model considers the relevance of inputs with outputs as the input weights to upgrade prediction performance. The proposed model is verified through an industrial hydrocracking process to predict diesel yield with missing labels ranged from 0% to 50%, and the root mean squared error is reduced by at least 8.78% compared to PSFA.
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2021.3129888