Ultra supercritical unit high temperature superheater wall temperature prediction method based on neural network

A technology of ultra-supercritical units and high-temperature superheaters, which is applied in the direction of temperature control using electric methods, and can solve problems such as large prediction errors and control influences

Inactive Publication Date: 2019-12-03
HUADIAN POWER INTERNATIONAL CORPORATION LTD
View PDF11 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It involves temperature prediction, but the disadvantage is that the...

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
  • Ultra supercritical unit high temperature superheater wall temperature prediction method based on neural network
  • Ultra supercritical unit high temperature superheater wall temperature prediction method based on neural network
  • Ultra supercritical unit high temperature superheater wall temperature prediction method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Such as figure 1 , 2 As shown, a method for predicting the wall temperature of the high-temperature superheater of an ultra-supercritical unit based on a neural network is characterized in that: comprising the following steps:

[0030] 1) Establish a temperature measurement system, set up wall temperature measuring points in the high-temperature superheater package of the ultra-supercritical unit, collect data from the wall temperature measuring points, connect them to the DCS control system of the power plant through cables, and transmit the data to the power plant information center PI and platform data, the data is divided into training set and validation set;

[0031] 2) Use the backpropagation algorithm to predict, construct the neural network structure, preprocess the data, and establish the training model;

[0032] 3) After standardizing the verification set, bring it into the trained prediction model, carry out model testing on the data, and finally obtain the...

Embodiment 2

[0062] A prediction system for installing the above-mentioned neural network-based ultra-supercritical unit high-temperature superheater wall temperature prediction method, characterized in that it includes a handheld test terminal, the handheld test terminal connects to platform data through a wireless network, and the handheld test terminal is set based on Neural network prediction method for high temperature superheater wall temperature of ultra-supercritical unit.

[0063] Based on the data set in the superheater package containing 700 measurement points of the high-temperature superheater of a 660MW ultra-supercritical unit boiler in the past four months (2018.11-2019.03), the two superheater wall temperature measurement points in the furnace are predicted. Dataset measurement point data is sampled one piece per minute on average, with a total of about 200,000 pieces of data. The experimental data set is divided into a training set and a verification set. The training set...

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 belongs to the field of power plant safety control systems, and particularly relates to an ultra supercritical unit high temperature superheater wall temperature prediction method basedon a neural network. The ultra supercritical unit high temperature superheater wall temperature prediction method based on the neural network is characterized by comprising the following steps of (1)building a temperature measuring system; (2) utilizing a back propagation algorithm for predicting, building a neural network structure, preprocessing data, building a training model, and obtaining aprediction model; (3) after standardizing a validation set, bringing into the trained prediction model, carrying out model measurement on the data, finally obtaining a prediction value of the validation set, comparing the prediction value of the validation set with an actual value of the validation set, and obtaining a residual error; and (4) utilizing guiding fault early warning. A hearth inner wall temperature prediction model is built by adopting a BP neural network, the potential faults of the equipment are further identified, and the state prediction of unconventional monitoring equipmentsuch as a high-temperature superheater is realized.

Description

technical field [0001] The invention belongs to the field of power plant safety control systems, and in particular relates to a method for predicting the wall temperature of a high-temperature superheater of an ultra-supercritical unit based on a neural network. Background technique [0002] Tube burst in superheater of large thermal power unit is one of the important reasons for unplanned shutdown. The causes of superheater tube bursting are very complicated, mainly including: (1) superheater tubes are operated at high temperature for a long time, and the inner wall of the tube produces scale, which accumulates at the elbow of the tube and causes tube bursting; (2) superheater tubes are exposed to high temperature for a long time (3) The pipe wall is frequently overheated for a short time during the operation of the unit, which reduces the design life and safety margin of the pipe; (4) The temperature distribution of the pipe row and pipe section along the width and depth o...

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
IPC IPC(8): G05D23/19
CPCG05D23/19
Inventor 蒋蓬勃侯德安李其浩孔凡义张文鹏邵磊刘烨潘广强李峰周宽宋峰
Owner HUADIAN POWER INTERNATIONAL CORPORATION LTD
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