Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for detecting flow characteristic offset fault of CV control valve

A flow characteristic, high-profile technology, applied in the direction of engine components, machines/engines, mechanical equipment, etc., can solve problems affecting the safety and stable operation of the unit, and achieve the effect of reliable data analysis

Pending Publication Date: 2021-11-02
HARBIN ELECTRIC POWER GENERATION EQUIP NAT ENG RES CENT CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Therefore, once the flow characteristics deviate during operation, it can cause a series of unit failures, seriously affecting the safe and stable operation of the unit.

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
  • Method for detecting flow characteristic offset fault of CV control valve
  • Method for detecting flow characteristic offset fault of CV control valve
  • Method for detecting flow characteristic offset fault of CV control valve

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Embodiment 1, with reference to Figure 1-Figure 4 Describe this implementation mode, a method for detecting a high-profile door flow characteristic deviation fault, including the following steps:

[0042] S110 collects unit design data; the unit design data includes unit rated working condition data and unit failure-free historical data.

[0043] Specifically, the main steam flow rate, the regulating stage pressure, the regulating stage temperature, and the exhaust pressure of the high-pressure cylinder under the rated working condition of the unit;

[0044] Specifically, the history data of the unit without failure is specifically the historical data collected in the DCS system of the comprehensive flow command, the pressure of the regulating stage, the exhaust pressure of the high-pressure cylinder, and the temperature of the regulating stage.

[0045] The actual flow characteristics of the S120 computer group, and construct the flow characteristic equation;

[0046]...

Embodiment 2

[0066] Embodiment 2, with reference to Figure 1-Figure 4 Describe this implementation mode, a method for detecting a high-profile door flow characteristic deviation fault, including the following steps:

[0067] S110 collects unit design data; the unit design data includes unit rated working condition data and unit failure-free historical data.

[0068] Specifically, the actual main steam flow ratio, regulating stage pressure, regulating stage temperature and high discharge pressure under the rated working condition of the unit;

[0069] Specifically, the historical data of the unit without faults is specifically the historical data of the comprehensive valve position command, regulating stage pressure, high exhaust steam temperature, regulating stage temperature and other parameters collected in the DCS system and the actual flow characteristics of the S120 computer unit;

[0070] The collected data at a certain moment of collecting unit design data is shown in Table 1 (col...

Embodiment 3

[0086] Embodiment 3 is different from Embodiment 2 in that this embodiment adopts the support vector machine (SVM) algorithm to fit the flow characteristic curve of the unit in step S120 (calculating the actual flow characteristics of the group) described in Embodiment 2.

[0087] Suppose you have training data:

[0088] (x 1 ,y 1 ), (x 2 ,y 2 ),..., (x n ,y n ), x∈R n , y∈{-1,+1} (11)

[0089] Then the hyperplane is:

[0090] w*x+b=0 (12)

[0091] Then the distance from the support vector to the hyperplane is:

[0092]

[0093] For support vectors, there are

[0094] y(w T x+b)=|w T x+b|=1 (14)

[0095] Bringing formula (19) into formula (18) can convert the maximum segmentation distance into solving the following optimization problem:

[0096]

[0097] s.t.1-y i [(w*x t +b)]≤0, i=1, ..., n (15)

[0098] Introducing the Lagrangian multiplier α i Transform this into a dual problem:

[0099]

[0100]

[0101] The values ​​of w and b can be obtaine...

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 method for detecting a flow characteristic offset fault of a CV control valve, and belongs to the technical field of steam turbine operation detection. The method specifically comprises the steps of firstly, collecting design data of a unit, wherein the design data of the unit comprise rated working condition data and fault-free historical data of the unit; secondly, calculating actual flow characteristics of the unit, and constructing a flow characteristic equation; then, determining an upper limit and a lower limit of a normal flow characteristic range; and finally, according to the combination corresponding to actual flow, judging whether the point is distributed within the upper limit and the lower limit of a normal range, thereby judging whether the flow characteristic of the CV control valve has a fault, and if the point is out of the range, indicating that the flow characteristic of the CV control valve has an offset fault phenomenon. According to the method, the technical problem that the flow characteristic deviation fault cannot be effectively judged in the prior art is solved, the actual operation characteristics of the unit are effectively considered, the deviation degree of the flow characteristics can be accurately reflected, and reliable data analysis is provided for long-term safe operation of a steam turbine.

Description

technical field [0001] The present application relates to a fault detection method, in particular to a detection method for a high-profile door flow characteristic deviation fault, which belongs to the technical field of steam turbine operation detection. Background technique [0002] The flow characteristics of the high profile door of the steam turbine refer to the corresponding relationship between the steam flow flowing through the high profile door of the steam turbine and the opening of the valve. Since the valve opening of the steam turbine has a nonlinear relationship with the flow, and this nonlinear relationship is very unfavorable to the control of the steam turbine, it is necessary to correct the valve flow characteristic curve so that the comprehensive valve position command and the steam flow have a linear relationship to achieve The purpose of efficiently controlling the steam turbine. The flow characteristic curve of the high-profile valve of the steam turbi...

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): F01D21/00F01D17/10
CPCF01D21/003F01D17/10
Inventor 曲晓峰范双双宋为平毛静轩苗东旭杨永明姜漫利王克剑李梧桐万杰刘东旭姚坤
Owner HARBIN ELECTRIC POWER GENERATION EQUIP NAT ENG RES CENT CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com