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

Power station boiler water wall temperature online prediction method based on gating neural network

A neural network and power plant boiler technology, applied in neural learning methods, biological neural network models, electrical digital data processing, etc., can solve problems such as long-term real-time accurate prediction of difficult water-cooled wall tube temperature, and reduce training and update time. Ensuring precise control and reducing effects

Active Publication Date: 2022-03-01
华电新疆哈密煤电开发有限公司 +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The invention aims to solve the problem that it is difficult to realize the long-term real-time and accurate prediction of the temperature of the water-cooled wall tube by using the existing update model

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
  • Power station boiler water wall temperature online prediction method based on gating neural network
  • Power station boiler water wall temperature online prediction method based on gating neural network
  • Power station boiler water wall temperature online prediction method based on gating neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0026] DETAILED DESCRIPTION OF THE INVENTION 1: Taking the actual operation of the power plant boiler as an example, based on the real data collected by the actual operation process, a wall temperature online prediction method based on the power station boiler water-cooled wall of the gantry neural network is described in detail. Refer Figure 1-4 Specifically, the present embodiment, the present embodiment is based on the wall temperature online prediction method of the water-cooled wall temperature of the power station boiler of the grooming neural network, including:

[0027] Step 1, the water-cooling wall pipe temperature is acquired by the sensor or the like, and the temperature-related variable of the water-cooled wall pipe is used, the water-free wall pipe temperature is the surface temperature of the metal pipe in the water-cooled wall obtained by the specific temperature sensor, the associated variable The variable obtained by different sensors in real time in real time, w...

specific Embodiment approach 2

[0034] DETAILED DESCRIPTION OF THE INVENTION Different: The present embodiment differs from the specific embodiment that the step two pairs the collected water-cooled wall pipe temperature and the water-cooled wall conduit temperature-related variables to obtain pre-process data, as a history Training data set, the specific process includes:

[0035] Step 2, eliminate all data that contains missing or damaged data collected at a certain moment;

[0036] During the actual production process, due to the length of the communication distance between the various sensors, the site acquisition environment attached and transmission changes, the sensor may cause data loss and damage during the acquisition and transmission, and lose data in collecting records. In the form of NAN, damage data appears in the form of exceeding the measurement amplitude upper and lower limits, and the acquired data is lost or corrupted, then the data collected by all sensors is deleted together to ensure data i...

specific Embodiment approach 3

[0042] BEST MODE FOR CARRYING OUT THE INVENTION One or two of the present embodiment is different from the specific embodiment, and the temperature-related variables of the water-cooled wall pipe temperature correlation variable and the water-free wall pipe temperature correlation variable after the coded data are normalized. The specific process is:

[0043]

[0044] Where x * represents the normalized sample data, X min Represents the minimum of sample data, x max Represents the maximum value in the sample data.

[0045] Other steps and parameters are identical to those of the specific embodiments.

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 power station boiler water-cooled wall temperature online prediction method based on a gating neural network, and belongs to the field of power station boiler equipment water-cooled wall pipeline temperature measurement. According to the method, the problem that long-term real-time accurate prediction of the temperature of the water wall tube is difficult to realize by utilizing the existing updating model is solved. The method comprises the steps that the water wall pipeline temperature and temperature related variables are collected; preprocessing the water wall pipeline temperature and the temperature related variables to obtain preprocessed data, and taking the preprocessed data as a historical training data set; establishing a gating neural network model, and performing offline training on the gating neural network model by using historical training data; performing model parameter online updating on the offline trained gating neural network model to obtain a gating neural network model of which the parameters are updated online; and inputting the water-cooled wall pipeline temperature related variables collected in real time into the online updated gating neural network model, and outputting to obtain the predicted water-cooled wall pipeline temperature. The method is used for predicting the temperature of the boiler water wall pipeline.

Description

Technical field [0001] The present invention relates to a temperature online prediction method based on a water-cooled wall conduit of a gantry neural network. Soft measuring technology field of water-free wall pipelines that belong to the power station boiler equipment. Background technique [0002] The boiler is one of the three major hosts of the thermal power unit. The internal structure of the furnace is complicated, and the size of the accident is frequent. The reliability of the boiler directly affects the safety of the power station in the thermal power plant. It will be mainly in fire power over a period of time. Strengthen the safety and economy of the boiler, and ensure that the unit's sustained stability is the future direction. [0003] The non-planned shuttle due to boiler failure accounts for 58% of the total time of the planned shutdown, which is caused by boiler failure. With the high-speed development of the thermal power generation industry, the design indicato...

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): G06F30/27G06N3/08G06F113/14G06F119/08
CPCG06F30/27G06N3/08G06F2113/14G06F2119/08Y04S10/50
Inventor 马甜甜管志伟夏良伟于强王欢黄莺马孝纯李亚坤魏国华梁宝琦沈涛孟晓冬杨天昱孙晶朱绘娟姜文婷
Owner 华电新疆哈密煤电开发有限公司
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