Optimization method of nuclear power steam turbine unit based on stochastic forest algorithm

Chunliang Fu; Linhua Gong; Jiafa Hu; Jiangjing Lin

doi:10.1117/12.2635827

25 April 2022 Optimization method of nuclear power steam turbine unit based on stochastic forest algorithm

Chunliang Fu, Linhua Gong, Jiafa Hu, Jiangjing Lin

Proceedings Volume 12244, 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022); 122443I (2022) https://doi.org/10.1117/12.2635827
Event: 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022), 2022, Guilin, China

Abstract

The electric power of nuclear power unit is mainly limited by the seawater temperature of external factors. When the seawater temperature rises, in order to avoid the thermal power and the opening of high-pressure regulating valve exceeding the limit, the unit operator must reduce the set value of electric power accordingly so as to affect the output of the unit. The internal operation parameters of the unit, such as main steam pressure, are more affected by the primary circuit, which is relatively stable and rarely fluctuated. To solve this problem, a regression model based on Stochastic Forest algorithm is established for the relationship between seawater temperature and electric power settings on the opening and thermal power of high pressure regulating valve. The predicted value of seawater temperature at a certain time and the set value of electric power gradually increasing from the smaller value are input into the random forest regression model so that the opening and thermal power of the high-pressure regulating valve output by the model at that time just do not exceed the limits of the operation regulations of the power station. The maximum electric power setting value that makes the opening of the high-pressure regulating valve and the thermal power just not exceed the limit is taken as the optimal electric power setting value at that time. Experiments show that the effect of this algorithm is more prominent than the traditional calculation methods, and the accuracy of the actual value of high-pressure regulating valve opening and thermal power meets the requirements. The research content of this paper promotes the application of smart turbine technology in the field of nuclear power, and has reference significance for the construction of nuclear power smart plant.

Citation Download Citation

Chunliang Fu, Linhua Gong, Jiafa Hu, and Jiangjing Lin "Optimization method of nuclear power steam turbine unit based on stochastic forest algorithm", Proc. SPIE 12244, 2nd International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2022), 122443I (25 April 2022); https://doi.org/10.1117/12.2635827

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
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Statistical modeling

Principal component analysis

Stochastic processes

Thermal modeling

Optimization (mathematics)

Performance modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years