Performance degradation monitoring method of predictive control based on improved weighted DSVDD

Zhangcheng Xie; Lijuan Li

doi:10.1117/12.2685936

28 July 2023 Performance degradation monitoring method of predictive control based on improved weighted DSVDD

Zhangcheng Xie, Lijuan Li

Proceedings Volume 12756, 3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023); 127562J (2023) https://doi.org/10.1117/12.2685936
Event: 2023 3rd International Conference on Applied Mathematics, Modelling and Intelligent Computing (CAMMIC 2023), 2023, Tangshan, China

Abstract

The operation data of the predictive control system is nonlinear, sequential and dynamic. The implicit nonlinear transformation of the traditional support vector data description (SVDD) cannot represent the timing and dynamic characteristics of the operation data of the control system. To solve this problem, this paper proposes a predictive control performance degradation detection method based on weighted Deep-SVDD. First of all, the target optimization function of SVDD is redefined based on the architecture of deep neural network, and the Deep-SVDD monitoring model is constructed using the extracted deep features. Secondly, the concept of sliding windows is introduced in view of the difference in sensitivity of deep features to predicted performance degradation of control systems. Using dynamic data from the window to weight the impact of sensitive features to highlight system performance degradation and construct a weighted Deep-SVDD monitoring model. Finally, the algorithm implementation process is theoretically deduced. The effectiveness of the proposed method is verified by the simulation of Wood-Berry distillation tower predictive control system.

Citation Download Citation

Zhangcheng Xie and Lijuan Li "Performance degradation monitoring method of predictive control based on improved weighted DSVDD", Proc. SPIE 12756, 3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023), 127562J (28 July 2023); https://doi.org/10.1117/12.2685936

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
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Control systems

Data modeling

Neural networks

Performance modeling

Feature extraction

Process modeling

Windows

Show All Keywords

Keywords/Phrases

Search In:

Publication Years