Method and device for establishing boiler combustion process model by utilizing Bayesian network algorithm
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A Bayesian network, boiler combustion technology, applied in computing, special data processing applications, instruments, etc.
Inactive Publication Date: 2016-06-29
叶翔 +1
View PDF2 Cites 8 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] In order to solve the problems of the above-mentioned technologies, and improve the calculation efficiency caused by processing a large amount of implementation data in the process of establishing the boiler combustion model, the present invention provides a method and device for establishing a boiler combustion process model using Bayesian network algorithm, Improve the accuracy of the established boiler combustion process model, which can adapt to complex and changeable working conditions in power plant production
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0056] figure 2 A method for establishing a boiler combustion process model using a Bayesian network algorithm provided in Embodiment 1 of the present invention; figure 2 As indicated, it may specifically include:
[0057] S101: Setting input variables and output variables of the boiler combustion process model.
[0058] Specifically, the input variables of the boiler combustion process model can include controllable variables and non-controllable variables, see Table 1, the input variables and output variables of the boiler combustion process model can include one or more or other variables in Table 1, There is no limit to this, and it can be set according to actual application conditions.
[0059] Table 1
[0060]
[0061] S102: According to the causal relationship between the input variable and the output variable, a Bayesian network structure of the input variable and the output variable is established.
[0062] For the multi-input-multi-output combustion process ...
Embodiment 2
[0092] Figure 5 A device for establishing a boiler combustion process model using the Bayesian network algorithm provided by Embodiment 2 of the present invention, such as Figure 5 As indicated, it may specifically include:
[0093] The setting module 201 is used to set the input variables and output variables of the boiler combustion process model;
[0094] Establishing module 202, for establishing the Bayesian network structure of input variables and output variables according to the causal relationship between input variables and output variables;
[0095] Obtaining module 203, for obtaining the historical sample data of boiler combustion;
[0096] The offline learning module 204 is used to learn the boiler combustion process model offline by using the historical sample data of boiler combustion to obtain the conditional probability relationship parameters between input variables and output variables in the Bayesian network structure;
[0097] The determination module ...
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 establishing a boiler combustion process model by utilizing a Bayesian network algorithm, and belongs to the technical field of energy power. The method comprises the following steps: setting an input variable and an output variable of the boiler combustion process model; establishing a Bayesian network structure of the input variable and the output variable according to a causal relationship between the input variable and the output variable; acquiring historical sample data of boiler combustion; carrying out offline learning on the boiler combustion process model by using the historical sample data of the boiler combustion so as to obtain a conditional probability relationship parameter between the input variable and the output variable in the Bayesian network structure; and determining the boiler combustion process model according to the conditional probability relationship parameter between the input variable and the output variable in the Bayesian network structure. The device comprises a setting module, an establishing module, an acquisition module, an offline learning module and a determining module. The method and device disclosed in the invention are capable of improving the precision of the established boiler combustion process model, and can be adapted to the complicated changeable working conditions in the power plant production.
Description
technical field [0001] The invention relates to the technical field of energy and electric power, in particular to a method and a device for establishing a boiler combustion process model by using a Bayesian network algorithm. Background technique [0002] In recent years, various domestic environmental protection regulations have become more and more stringent, so how to improve boiler combustion efficiency and reduce pollutant emissions will become one of the key considerations for power generation companies. It is a commonly used method to establish a model of the boiler combustion process and optimize and adjust the boiler combustion process through the model to improve boiler efficiency and reduce pollutant emissions. [0003] At present, a commonly used method to establish a boiler combustion process model is: use artificial neural network algorithm to establish a boiler combustion process model. [0004] However, because there is a large amount of uncertain informati...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.