Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Optimal controlling method for boiler intelligent combustion based on big data

A combustion optimization and control method technology, applied in the direction of combustion control, genetic models, genetic rules, etc., can solve problems such as wrong models, insufficient "quantity", increased NOx emissions, etc., to improve optimization performance, optimization effect, and quality Effect

Inactive Publication Date: 2018-10-12
NANJING GUITU TECH DEV
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1) The "quantity" of samples is not enough: some existing methods only use boiler combustion test data as sample modeling, and the built models cannot cover all possible operating conditions of boiler operation, and the model performance has great limitations;
[0006] 2) The "quality" of samples is not good: some methods also use a large amount of boiler operation data as model training samples, but the data containing boiler soot blowing conditions in the samples are not eliminated, and the built model cannot have good quality. Even the wrong model, because the sootblowing data does not correctly reflect the combustion characteristics of the boiler, and the boiler is sootblown nearly one-third of the time every day
Since improving boiler efficiency and reducing flue gas NOx emissions are typical multi-objective optimization problems, it is difficult to determine the values ​​of weight coefficients a and b in specific applications. Improper selection of a and b values ​​will cause the optimization results to improve boiler efficiency , but NOx emissions also increased, or on the contrary, it is difficult to achieve multi-objective optimization in the true sense, that is, to improve boiler efficiency and reduce flue gas NOx emissions
In addition, this type of method cannot meet the actual requirements of various optimization objectives, such as the optimization objective of improving boiler efficiency as much as possible without increasing flue gas NOx emissions, which is difficult to achieve with existing methods
[0010] 3. To measure the pros and cons of boiler combustion performance, in addition to the two indicators of boiler efficiency and flue gas NOx emissions, the temperature difference between the two sides of the furnace outlet is also an important indicator. Boiler combustion operation generally requires that the temperature difference between the two sides of the furnace outlet should not be greater than a certain Given the value of , none of the currently public methods address this issue

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
  • Optimal controlling method for boiler intelligent combustion based on big data
  • Optimal controlling method for boiler intelligent combustion based on big data
  • Optimal controlling method for boiler intelligent combustion based on big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to describe the technical solutions disclosed in the present invention in detail, the present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.

[0039] refer to figure 1 As shown, the steps of the boiler intelligent combustion optimization control method based on big data provided by the present invention are as follows:

[0040] (1) Collect DCS data of the unit, and process and form neural network training samples;

[0041] (2) Establish a combustion optimization neural network model according to the training samples;

[0042] (3) According to the combustion optimization neural network model, a multi-objective genetic algorithm is used to optimize the combustion parameters;

[0043] (4) Calculate the optimal bias according to the optimized combustion parameters, and send it to DCS to realize closed-loop optimal control.

[0044] The steps of the present invention will be described in detail b...

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 an optimal controlling method for boiler intelligent combustion based on big data. The method comprises the following steps that firstly, the DCS data of a unit is collected and processed to form neural network training samples, and then a combustion optimization neural network model is established according to the training samples; then combustion parameters are optimizedby using multi-objective non-dominated fast sorting genetic algorithm (NSGA) according to the combustion optimization neural network model; and finally, optimization bias is calculated according to the optimized combustion parameters and sent to a DCS for realizing closed-loop optimization control. According to the optimal controlling method for boiler intelligent combustion based on big data, because the big data is adopted and the data of boiler ash blowing conditions is eliminated, the quality of the combustion optimization neural network model is improved; the optimization performance andoptimization effect are improved by adopting the multi-objective genetic algorithm optimize combustion parameters, and the optimal controlling method can adapt to the various optimization requirementsin practical application; and in addition to the boiler efficiency and the flue gas NOx emission of the optimizing objectives, the temperature difference index of smoke on both sides of a chamber outlet is further considered, and the optimal controlling method is more suitable for practical application of engineering.

Description

technical field [0001] The invention belongs to a power plant boiler combustion optimization control method, in particular to a big data-based boiler intelligent combustion optimization control method. Background technique [0002] The quality of boiler combustion conditions directly affects the safe, economical and environmentally friendly operation of the unit. The operating efficiency of the boiler and flue gas NOx emissions are closely related to the operation mode of the boiler's air distribution and coal blending combustion. At present, the combustion operation of domestic power plant boilers is mainly adjusted by the operators according to their own operating experience. Due to the complexity of boiler combustion, it is difficult to manually coordinate the two indicators of boiler efficiency and flue gas NOx emissions to achieve optimal operation of boiler combustion. Therefore, realizing boiler intelligent combustion optimization control is of great significance for ...

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): F23N5/00G06N3/12
CPCF23N5/00F23N2223/44G06N3/126
Inventor 陈雪峰雎刚
Owner NANJING GUITU TECH DEV
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
Eureka Blog
Learn More
PatSnap group products