Nuclear power device two-loop multi-variable integrated model fuzzy predication control method

An integrated model and fuzzy prediction technology, applied in the field of control, can solve the problems of long stabilization time and large overshoot of system parameters.

Inactive Publication Date: 2008-04-30
HARBIN ENG UNIV
View PDF1 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the control system has the shortcomings of large overshoot and long stabilization time under the condition of large load changes, which needs to be improved

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Nuclear power device two-loop multi-variable integrated model fuzzy predication control method
  • Nuclear power device two-loop multi-variable integrated model fuzzy predication control method
  • Nuclear power device two-loop multi-variable integrated model fuzzy predication control method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] The present invention is described in more detail below in conjunction with accompanying drawing example:

[0091] 1 Training of static DLF neural network

[0092] The opening degree of the nozzle valve cam angle Δθ and the water supply valve opening degree Δ of the nuclear power plant secondary circuit are used as the input of the DLF network; the intermediate variable x of the nonlinear link 1 and x 2 Output for the DLF network. The BP in the DLF network adopts a 2-10-2 network structure. After 25,000 times of training, the cumulative error does not exceed the expected error.

[0093] Let the threshold of the jth unit of the output layer be r j , the connection matrix W∈R between the units of the output layer and the hidden layer H p×2 ,

[0094] And the connection matrix W between the output layer and the input layer U F ; The connection matrix V∈R between the hidden layer and each unit of the input layer U p×2 .

[0095] 1) The weight matrix between the inp...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a fuzzy forecasting and controlling method for the two-circuit multivariable integrated model of a nuclear power device. The state parameter information for the nuclear power device is measured out by utilizing a measuring system. The state parameter information is converted into digital signals, and then sent to a controller through a filter. The controller selects the optimum control input of the two-circuit system of the nuclear power device. The control signals generated by the controller are converted into analog signals through a digital-analog converter, strengthened by a signal amplifier and then output to an executing mechanism. The executing mechanism executes to transform the whole system to a specified working condition as commanded. The invention is applicable to a system like a nuclear power device that has serious non-linearity, coupling and time-variation. The invention has high control precision and good robustness.

Description

(1) Technical field [0001] The invention relates to a control method, in particular to a dynamic control method for a secondary loop of a nuclear power plant. (2) Background technology [0002] Due to the characteristics of strong coupling, nonlinearity and different dynamic characteristics of the secondary loop system of nuclear power plant, the design of its control system is challenging. The traditional control method has the shortcomings of large fluctuations in the main parameters of the system and slow response in solving the variable working conditions and coupling problems of nuclear power plants. The multivariable integrated model fuzzy predictive control method introduces an integrated model combining the artificial neural network model and the multivariable linear predictive model, dynamically optimizes the predictive model, and introduces fuzzy theory to establish the input quantity of the secondary loop control system of the nuclear power plant. The performance...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G05B13/04
Inventor 夏国清苏杰张伟边信黔施小成付明玉王元慧
Owner HARBIN ENG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap