Coal-fired unit drum boiler water level control method capable of improving dynamic property based on neural network

A coal-fired unit and neural network technology, applied in the field of control, can solve the problems of no theoretical basis, affecting the control effect, slow convergence speed, etc., to achieve the effect of suppressing overshoot, strong anti-interference ability, and speeding up the convergence speed

Active Publication Date: 2020-04-03
浙江省能源集团有限公司 +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the water level control of the drum boiler, many scholars have made various types of improvements to the PID control method, and achieved certain results, but the accuracy achieved is not high, and there is no theoretical basis
However, due to the limitation of modeling technology, the existing models have uncertainty and dynamic modeling, which makes the control difficult; at the same time, the water level fluctuates greatly and the convergence speed is slow, which seriously affects the control effect. Therefore, it is necessary to eliminate the unbuilt Mode dynamics while improving transient performance

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
  • Coal-fired unit drum boiler water level control method capable of improving dynamic property based on neural network
  • Coal-fired unit drum boiler water level control method capable of improving dynamic property based on neural network
  • Coal-fired unit drum boiler water level control method capable of improving dynamic property based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0056] The present invention provides a water level control method for a coal-fired unit steam drum boiler based on a neural network to improve dynamic performance. The flow chart of the control method is as follows figure 1 As shown, the block diagram of the water level control system is shown in figure 2As shown, among them, the boiler drum water level height y is measured by the water level sensor, the water level height y is transmitted to the controller, and the user-defined expected water level height y d , the output preset boundary y and y Input to the controller, the control law is calculated by the controller to output the control input variable, which is tr...

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 discloses a coal-fired unit drum boiler water level control method capable of improving a dynamic property based on a neural network. The method comprises the following steps of buildinga state space model, designing an output conversion function, carrying out output conversion, defining a filtering error, enabling a filtering error derivative to be a zero design ideal controller, using the neural network to approach to a part, containing an unknown quantity, in the ideal controller, and designing an actual controller. For an unknown structure and unknown parameters in the model, the neural network is used for approaching to the unknown dynamic condition. In addition, according to the safety production needs of a power station, in order to prevent a steam pocket from being too hot or prevent steam from flowing out, and improve the control effect on the drum boiler water level, the control method considers the output limit condition, the nondeterminacy in an existing model can be overcome, the anti-interference capacity can be achieved, the system transient output is kept within the preset boundary layer, it is ensured that the overshoot is not too large, and the control effect can be improved as much as possible while safety production is ensured.

Description

technical field [0001] The invention belongs to the field of control, in particular to a method for controlling the water level of a drum boiler of a coal-fired unit based on a neural network to improve dynamic performance. Background technique [0002] As countries and organizations around the world are actively exploring new alternative energy technologies, renewable energy has been highly valued for its renewable and non-polluting characteristics. The development of new energy technology has led to the integration of various new energy sources into the grid. The energy form is no longer limited to electric energy, but a combination of various energy forms such as electric energy, natural gas energy, and petroleum energy. However, as multiple energy sources are integrated into the grid The challenges brought about increase, and the regulation ability of traditional coal-fired units needs to be improved, so it is necessary to develop better control methods to control coal-f...

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): F22D5/26G06N3/04
CPCF22D5/26G06N3/045
Inventor 梁琪陈积明杨秦敏李清毅范海东解剑波
Owner 浙江省能源集团有限公司
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