A test method for acid dew point of boiler flue gas based on artificial neural network

An artificial neural network and neural network technology, which is applied in the field of boiler safety and energy saving, can solve the problems of increased cost of test device maintenance and maintenance, complex test process, and many measured parameters, and achieve rich functions, high flexibility, efficiency and accuracy high effect

Active Publication Date: 2022-01-28
XIAN SPECIAL EQUIP INSPECTION INST
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] For the boiler flue gas acid dew point measuring device disclosed in the patents with authorized patent numbers CN206930612U and CN107037082B, compared with the boiler flue gas composition test, the test process is relatively complicated, and there are too many parameters to be measured, which makes the cost of the test relatively high , in addition, the maintenance and maintenance of the test equipment will also increase the cost to a certain extent

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
  • A test method for acid dew point of boiler flue gas based on artificial neural network
  • A test method for acid dew point of boiler flue gas based on artificial neural network
  • A test method for acid dew point of boiler flue gas based on artificial neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045]In this embodiment, the flue gas sulfur dioxide content and the flue gas water vapor content in the boiler flue gas are measured by the flue gas analyzer. This embodiment only tests the acid dew point parameter of the flue gas, regardless of other known data. The neural network The number of nodes in the input layer and output layer are 2 and 1, respectively.

[0046] In this embodiment, the data format of the training data set of the neural network is:

[0047] {input layer: output layer: [T sld ]}

[0048] Before inputting into the neural network, the values ​​of flue gas sulfur dioxide content and flue gas water vapor content are normalized by mean variance, and the value of flue gas acid dew point is normalized by the maximum value.

[0049] In this example, 300 sets of data are extracted from the existing flue gas acid dew point experimental data, theoretical / empirical formula calculation data, and literature data, that is, the flue gas acid dew point and the co...

Embodiment 2

[0059] In this example, the power plant boiler with model HG-1100 / 25.4-YM1 is used as the test object. Compared with industrial boilers and heating boilers, the known data of power plant boilers are relatively complete, and the sulfur dioxide content of flue gas at the inlet of the economizer is selected. , flue gas water vapor content, flue gas oxygen content, fuel low calorific value, fuel ash content, and fuel sulfur content are used as input parameters. It is expected to test the flue gas acid dew point, the upper limit of the range of flue gas acid dew point, The lower limit of the acid dew point range and the conversion rate between sulfur dioxide and sulfur trioxide gas in the flue gas, the input layer nodes and output layer nodes of the neural network are determined to be 6 and 4 respectively, and the prototype of the neural network is as follows Figure 4 shown.

[0060] In this embodiment, the data format of the training data set of the neural network is:

[0061] {...

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 method for testing the acid dew point of boiler flue gas based on an artificial neural network, which includes step 1: selecting input parameters according to known data to determine the number of nodes in the input layer of the neural network, and then determining the output layer of the neural network according to the test requirements The number of expected output nodes; 2. Combining the boiler flue gas acid dew point experiment and calculation value, establish a training data set for the neural network; 3. Train and test the neural network, and optimize and improve the neural network according to the test accuracy requirements; 4. 1. Obtain the acid dew point of flue gas and other desired parameters by optimizing the improved neural network; 5. Update and enrich the training data set of the neural network for subsequent testing of working conditions. The method of the invention has simple steps, convenient realization and low test cost, can be effectively applied in boiler flue gas acid dew point test, has rich functions, high efficiency and precision, remarkable effect and is easy to popularize.

Description

technical field [0001] The invention belongs to the technical field of boiler safety and energy saving, and in particular relates to a method for testing the acid dew point of boiler flue gas based on an artificial neural network. Background technique [0002] The method to realize boiler flue gas waste heat recovery is mainly to install a flue gas waste heat recovery device at the tail flue of the boiler. However, for coal-fired boilers, oil-fired boilers, waste incinerators, etc., the fuel sulfur content is generally high, and the combustion products contain more sulfuric acid vapor. When the temperature of the heating surface of the energy-saving device is lower than the acid dew point of the flue gas, the sulfuric acid vapor will The heated surface condenses into acid, which in turn causes metal corrosion, also known as low-temperature corrosion, which brings greater safety hazards to boiler operation. In order to avoid low-temperature corrosion of boiler flue gas, a hi...

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 Patents(China)
IPC IPC(8): G06F30/27G06N3/04G06N3/08G01N25/66G06F111/06G06F113/08
CPCG06F30/27G06N3/08G01N25/66G06F2111/06G06F2113/08G06N3/045
Inventor 毕成杨旭鲁元贠柯刘金娥丁勇
Owner XIAN SPECIAL EQUIP INSPECTION INST
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