A method and device for predicting NOx emissions from pulverized coal boilers based on improved ssa-gpr
A technology for pulverized coal boilers and emissions, which is applied in instruments, chemical machine learning, biological models, etc., can solve the problems of complex combustion process, complex mechanism model, and many parameters, so as to improve data quality, reduce environmental pollution and economic efficiency. effect of loss
Active Publication Date: 2022-08-02
NORTHEAST DIANLI UNIVERSITY
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, for a multi-disciplinary system involving combustion, heat transfer, fluid, etc., the combustion process is complex, and the parameters are many and coupled with each other. It is very complicated to establish its mechanism model, and it is difficult to obtain high-precision prediction values. big impact
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0071] In order to understand the above solutions of the present invention more clearly, the present invention will be further described in detail below with reference to the accompanying drawings. It should be noted that the specific implementation described here is only used to explain the present application, but not to limit the present application.
[0072] figure 1 This is a flow chart of a method for predicting NOx (nitrogen oxides) emissions from an improved SSA-GPR pulverized coal boiler of the present invention, and the specific steps are as follows:
[0073] Step 1000: Acquire historical data of characteristic parameters and NOx emissions of coal-fired boilers from the DCS system of the power plant to form a first data set, the first data set is a two-dimensional matrix X composed of n rows and m columns of data, wherein , the n sample data collected in the matrix are listed as the m-1 features and NOx emissions involved in each sample, and the n×m data form the ma...
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
Login to View More Abstract
The invention discloses a method and device for predicting NOx emission of a pulverized coal boiler based on an improved SSA-GPR. The prediction method includes the following steps: (1) collecting historical characteristic parameter data of the pulverized coal boiler; (2) normalizing the data (3) Perform dimensionality reduction processing on the data; (4) Divide the data set into training set and validation set; (5) Use the improved SSA algorithm to optimize the hyperparameters of the Gaussian process to obtain the optimized Gaussian process; ( 6) Input the training set into the model for model training; (7) Input the validation set into the model for model verification, and obtain the final NOx emission prediction model for pulverized coal boilers based on the improved SSA‑GPR. The NOx emission prediction method and device provided by the invention effectively improve the NOx emission prediction accuracy of the pulverized coal boiler, provide technical support for reducing the NOx emission in the actual operation process of the subsequent power station boiler, and respond to the energy saving and emission reduction of the power station. The national green environmental protection policy has important practical engineering significance.
Description
technical field [0001] The invention relates to the field of boiler control, in particular to a method for predicting NOx (nitrogen oxides) emissions of a pulverized coal boiler. Background technique [0002] With the rapid development of the economy, the coal consumption of thermal power plants is also increasing year by year, accompanied by more and more NOx emissions. NOx easily forms acid rain and photochemical smog, which not only pollutes the environment but also causes certain economic losses. At the same time, as one of the three core equipment of the power plant, the boiler is also the main place where harmful gases are generated. Therefore, by predicting the nitrogen oxide emissions of the boiler and then optimizing the subsequent control, the boiler can be extremely Greatly reduce environmental pollution. [0003] The traditional NOx emission prediction method is to select the operating characteristics for modeling through artificial experience, and the modeling...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G16C10/00G16C20/70G06N3/00G06N7/08
CPCG16C10/00G16C20/70G06N3/006G06N7/08Y02E40/70Y04S10/50
Inventor 周欣欣赵政李茂源薛青常张丹楠郭树强霍光
Owner NORTHEAST DIANLI UNIVERSITY