Wasserstein domain adversarial neural networks for grade prediction in zinc flotation process

Xuanpu Li; Lihui Cen

doi:10.1117/12.3011590

1 December 2023 Wasserstein domain adversarial neural networks for grade prediction in zinc flotation process

Xuanpu Li, Lihui Cen

Proceedings Volume 12940, Third International Conference on Control and Intelligent Robotics (ICCIR 2023); 129402Q (2023) https://doi.org/10.1117/12.3011590
Event: Third International Conference on Control and Intelligent Robotics (ICCIR 2023), 2023, Sipsongpanna, China

Abstract

In zinc flotation process, concentrate grade is an important indicator which cannot be measured online. To ensure the stability of froth flotation process, the deep learning has been widely used for the prediction of concentrate grade. However, the grade prediction based on deep learning leads to the dataset bias problem. A popular network for addressing dataset bias issues is the domain adversarial neural network (DANN), but the domain prediction of DANN is a binary classification, which cannot accurately reflect the data distribution of dataset. To solve the deficiency of the binary classification, a wasserstein domain adversarial neural networks (W-DANN) is proposed, which calculates the domain loss with wasserstein distance and enhances the domain prediction performance. Finally, the experimental results on the Office31 dataset and flotation dataset demonstrate the effectiveness of the proposed W-DANN model and its possibility of application in zinc flotation process.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xuanpu Li and Lihui Cen "Wasserstein domain adversarial neural networks for grade prediction in zinc flotation process", Proc. SPIE 12940, Third International Conference on Control and Intelligent Robotics (ICCIR 2023), 129402Q (1 December 2023); https://doi.org/10.1117/12.3011590

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Education and training

Neural networks

Feature extraction

Zinc

Data modeling

Binary data

Performance modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years