Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 1, 2026

Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control
05:47

Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control

Published on: August 29, 2025

308

A Deep Supervised Learning Framework for Data-Driven Soft Sensor Modeling of Industrial Processes.

Xiaofeng Yuan, Yongjie Gu, Yalin Wang

    IEEE Transactions on Neural Networks and Learning Systems
    |December 28, 2019
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Enhancing interpretable soft sensing with embedded hybrid modeling: the GraphTrans approach for industrial processes.

    ISA transactions·2026
    Same author

    Endometrial Cancer of the Uterine Isthmus: A Cohort Study on Clinicopathological Features and Prognosis.

    Cancer medicine·2026
    Same author

    Dietary Fermented Chinese Chive Juice Improves Growth Performance and Reshapes the Fresh Meat Volatile Flavor Profile of Small-Tailed Han Sheep.

    Animals : an open access journal from MDPI·2026
    Same author

    Distribution of divalent small interfering RNA into neurons of sensory ganglia produces selective, durable knockdown of Nav1.7 and strong analgesia.

    Pain·2026
    Same author

    HoStB-DVGNN: A Flotation Fault Recognition Method Using Higher Order Spatial-Temporal Block and Dual-Stream Variational GNN.

    IEEE transactions on cybernetics·2026
    Same author

    Epidemiology of respiratory infectious diseases after the relaxation of COVID-19 policies: a retrospective study in Xiamen, China.

    Frontiers in public health·2026

    A new deep learning framework, stacked supervised encoder-decoder (SSED), enhances soft sensor models by learning quality-relevant features. This improves prediction accuracy in industrial processes.

    Area of Science:

    • Artificial Intelligence
    • Chemical Engineering
    • Process Control

    Background:

    • Traditional deep learning for soft sensors often uses unsupervised pretraining, which may not prioritize quality-relevant features.
    • Effective soft sensor modeling requires extracting features directly linked to product quality for accurate predictions.

    Purpose of the Study:

    • To propose a novel deep layerwise supervised pretraining framework, stacked supervised encoder-decoder (SSED), for enhanced soft sensor modeling.
    • To improve the extraction of quality-relevant features for better prediction performance in industrial processes.

    Main Methods:

    • Developed a stacked supervised encoder-decoder (SSED) framework utilizing multiple supervised encoder-decoder (SED) models.
    • Each SED model learns hierarchical quality-relevant features by using previous layer outputs as input and constraining predictions to the quality data.

    Related Experiment Videos

    Last Updated: Jan 1, 2026

    Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control
    05:47

    Simulation of a Scaled Assembly Process with Collaboration of a Robotic Arm and Monitoring through a Vision System for Quality Control

    Published on: August 29, 2025

    308
  • Stacked SED models progressively learn features and reduce irrelevant information.

    • Main Results:

    • The proposed SSED framework effectively learns hierarchical quality-relevant features.
    • The method demonstrated significant improvements in prediction performance compared to existing approaches.
    • Validation was performed on a numerical example and a debutanizer column industrial process.

    Conclusions:

    • The SSED framework offers a superior approach for soft sensor modeling by focusing on quality-relevant feature extraction.
    • This deep learning strategy enhances prediction accuracy in industrial applications.
    • The layerwise supervised pretraining effectively reduces irrelevant information and improves model performance.