CN112966436B - Boiler efficiency and NO are taken into considerationxMulti-objective operational optimization method for emissions - Google Patents
Boiler efficiency and NO are taken into considerationxMulti-objective operational optimization method for emissions Download PDFInfo
- Publication number
- CN112966436B CN112966436B CN202110230825.2A CN202110230825A CN112966436B CN 112966436 B CN112966436 B CN 112966436B CN 202110230825 A CN202110230825 A CN 202110230825A CN 112966436 B CN112966436 B CN 112966436B
- Authority
- CN
- China
- Prior art keywords
- subinterval
- operation data
- coal quality
- quality ratio
- representing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Geometry (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Regulation And Control Of Combustion (AREA)
- Control Of Steam Boilers And Waste-Gas Boilers (AREA)
Abstract
The invention provides a multi-target operation optimization method giving consideration to both boiler efficiency and NOx emission. On the basis, the optimal coal quality ratio corresponding to different loads can be known, the optimal coal quality ratio can be determined according to the loads, and the method for determining the coal quality ratio can give consideration to both boiler efficiency and unit outlet NOx concentration.
Description
Technical Field
The invention relates to the technical field of optimization of NOx concentration at an outlet of a unit, in particular to a multi-target operation optimization method considering both boiler efficiency and NOx emission.
Background
The uncertainty of multivariable coupling exists in the problem of boiler unit emission, and how to provide a method for determining the coal quality ratio which can give consideration to the concentration of NOx at the outlet of the unit and the efficiency of the boiler becomes a technical problem to be solved urgently.
Disclosure of Invention
The invention aims to provide a multi-target operation optimization method considering both boiler efficiency and NOx emission so as to provide a determination method of coal quality ratio considering both unit outlet NOx concentration and boiler efficiency.
In order to achieve the purpose, the invention provides the following scheme:
a multi-objective operational optimization method that accounts for both boiler efficiency and NOx emissions, the optimization method comprising the steps of:
acquiring operation data of a unit in a stable operation state within a preset time period, and dividing the operation data into a plurality of sub-intervals according to loads;
performing cluster analysis on the operating data of each subinterval according to the boiler efficiency and the concentration of NOx at the outlet of the unit in the operating data respectively to obtain a plurality of first cluster results and a plurality of second cluster results of each subinterval;
determining a first fit point representing the corresponding relation between the coal quality ratio and the boiler efficiency in each first clustering result and a second fit point representing the corresponding relation between the coal quality ratio and the unit outlet NOx concentration in each first clustering result to obtain a first fit point set and a second fit point set of each subinterval;
respectively performing function fitting on a first fit point in the first fit point set of each subinterval by adopting a regression analysis algorithm to obtain a fit function representing the relation between the coal quality ratio and the boiler efficiency of each subinterval, subtracting the fit function from 1 to obtain a first mathematical model, and performing function fitting on a second fit point in the second fit point set of each subinterval by adopting the regression analysis algorithm to obtain a second mathematical model representing the relation between the coal quality ratio and the concentration of NOx at the outlet of the unit of each subinterval;
and determining the coal quality ratio of each subinterval when the concentration of NOx at the outlet of the unit and the boiler efficiency are optimal by taking the first mathematical model and the second mathematical model of each subinterval as an objective function and adopting a multi-objective optimization algorithm, and taking the coal quality ratio as the optimal coal quality ratio of each subinterval.
Optionally, the obtaining of the operation data of the unit in the stable operation state within the preset time period and dividing the operation data into a plurality of sub-intervals according to the load specifically include:
determining whether each set of operation data in the preset time period of the unit is operation data in a stable operation state according to the main steam pressure, the coal feeding amount, the water feeding amount and the steam turbine valve opening degree in each set of operation data in the preset time period;
acquiring all running data in a stable running state within a preset time period as the running data in the stable running state within the preset time period of the unit;
and dividing the operation data of the sub-time period in which the unit is in the stable operation state into a plurality of sub-intervals according to the load.
Optionally, determining whether each set of operation data in the preset time period of the unit is operation data in a stable operation state according to the main steam pressure, the coal feeding amount, the water feeding amount and the steam turbine valve opening in each set of operation data in the preset time period specifically includes:
judging inequality according to main steam pressure, coal feeding quantity, water feeding quantity and steam turbine valve opening degree in the ith group of operation data
And
whether all the judgment results are established, and a first judgment result is obtained;
if the first judgment result shows that the operation data is in a stable operation state, determining the ith group of operation data as the operation data in the stable operation state;
if the first judgment result shows that the operation data is not stable, determining that the ith group of operation data is the operation data in the unstable operation state;
wherein p isiAnd pjThe main steam pressure in the ith group of operation data and the jth group of operation data respectively, n' is the group number of the operation data in the preset time period,
and
respectively the coal feeding amount in the ith group of operation data and the jth group of operation data,
and
the water supply amount in the ith group of operation data and the jth group of operation data respectively,
and
the opening degree of the steam turbine valve, epsilon, in the ith group of operation data and the jth group of operation data respectively1、ε2、ε3And ε4Respectively representing a main steam pressure fluctuation threshold value, a coal feeding quantity fluctuation threshold value, a water feeding quantity fluctuation threshold value and a steam turbine valve opening fluctuation threshold value.
Optionally, the performing cluster analysis on the operating data of each subinterval according to the boiler efficiency and the unit outlet NOx concentration in the operating data respectively to obtain a plurality of first clustering results and a plurality of second clustering results of each subinterval, and then further includes:
using a formula
Normalizing each operation data in each first clustering result and each second clustering result; wherein, a'lsRepresents the s-th operating data in the l-th clustering result, alsRepresents the s normalized operation data, min (a'l) Represents the minimum value of the same kind of operation data in the l-th clustering result, max (a'l) Representing the maximum value of the same type of operation data in the first clustering result; a'lAnd representing the set of all the operating data in the ith clustering result, wherein the clustering results are a first clustering result and a second clustering result.
Optionally, the determining a first fitting point representing a corresponding relationship between the coal quality ratio and the boiler efficiency in each first clustering result specifically includes:
for the l1The first clustering result adopts a trigonometric membership function algorithm to each ith1Fuzzification processing is carried out on the coal quality ratio and the boiler efficiency in each operation data in the first clustering result, and the ith1Attributes of coal quality ratio and boiler efficiency in each operation data in the first clustering result;
first1Determining the ith clustering result according to the attribute of the coal quality ratio and the attribute of the boiler efficiency in each operation data1A rule representing the relation between the coal quality ratio and the boiler efficiency in each operation data in each first clustering result;
according to item l1Selecting a rule with the most occurrence times as a discovery rule according to a rule representing the relation between the coal quality ratio and the boiler efficiency in each operation data in each first clustering result;
obtaining the first1The coal quality ratio and the boiler efficiency of the operation data meeting the discovery rule in the first clustering result;
will be first1The coal quality ratio of the operation data meeting the discovery rule in the first clustering result is the mostThe average value of the large value and the minimum value is used as the input data of the first fitting point, and the l < th > value is used as the input data of the first fitting point1The average value of the maximum value and the minimum value of the boiler efficiency of the operation data meeting the discovery rule in the first clustering result is used as the output data of the first fitting point to obtain the ith1And a first fitting point in the first clustering result.
Optionally, the performing function fitting on the second fitting point in the second fitting point set of each subinterval by using a regression analysis algorithm to obtain a second mathematical model representing a relationship between the coal quality ratio and the unit outlet NOx concentration of each subinterval specifically includes:
for the f sub-interval, respectively performing function fitting on second fitting points in the second fitting point set of the f sub-interval by adopting a regression analysis algorithm, and determining that the expression of a second fitting function of the f sub-interval is as follows:
wherein, y2Denotes the concentration of NOx, xnAnd xhRespectively represents the mixture ratio of the nth coal and the h-th coal, beta2nCoefficient of quadratic term, beta, representing the quality of the nth coalnCoefficient of first order term, beta, representing quality of the nth coalnhRepresents the cross term coefficient, beta, of the nth coal quality and the h-th coal quality0Representing constant term coefficient, N represents the type of coal quality;
fitting coefficients in an expression of the second fitting function by using a second fitting point set of the f-th subinterval to obtain a plurality of second fitting functions under different coefficient combinations; the coefficients include quadratic term coefficients, first order term coefficients, cross term coefficients, and constant term coefficients;
and selecting a second fitting function which passes through F test and t test from the plurality of second fitting functions and has the maximum judgment coefficient as a second mathematical model of the F subinterval.
Optionally, the determining, with the first mathematical model and the second mathematical model of each subinterval as objective functions and using a multi-objective optimization algorithm, a coal quality ratio of each subinterval at which the unit outlet NOx concentration and the boiler efficiency are optimized as an optimal coal quality ratio of each subinterval specifically includes:
for the f-th subinterval, initializing a parent population with the scale of M; the parent population comprises M individuals, and each individual represents a combination of coal quality ratios;
calculating a first objective function value and a second function value of each individual in the parent population by using the first mathematical model and the second mathematical model of the f-th subinterval;
sorting each individual in the parent population according to the dominance degree and the distance between the individuals according to the first objective function value and the second function value of each individual in the parent population;
obtaining the top M in the sorted parent population0Crossing and varying the individuals to generate a progeny population; wherein M is0<M；
Calculating a first objective function value and a second objective function value of each individual in the offspring population by using the first mathematical model and the second mathematical model of the f-th subinterval;
sorting each individual in the parent population and the child population according to the domination degree and the distance between the individuals according to a first objective function value and a second objective function value of each individual in the parent population and the child population, selecting the first M individuals in the sorted parent population and child population to form an updated parent population, and returning to the step of sorting each individual in the parent population according to the domination degree and the distance between the individuals according to the first objective function value and the second function value of each individual in the parent population; outputting the parent population updated by the last iteration as the output population of the f-th subinterval until the iteration number reaches the iteration number threshold;
and calculating the optimal compromise solution of the output population of the f-th subinterval as the optimal coal quality ratio of the f-th subinterval.
Optionally, the calculating, by using the first mathematical model and the second mathematical model of the f-th sub-interval, a first objective function value and a second function value of each individual in the parent population includes:
for each individual in the parent population, a judgment formula
If yes, obtaining a second judgment result; wherein x isnThe mixture ratio of the nth coal quality in the individual is shown, and N is the number of the types of the coal quality in the individual;
if the second judgment result shows that the first objective function value and the second objective function value of the individual are calculated by using the first mathematical model and the second mathematical model of the f-th sub-interval respectively;
if the second judgment result shows no, setting the first objective function value of the individual to be infinite, and setting the second objective function value of the individual to be infinite.
Optionally, the calculating an optimal compromise solution of the output population of the f-th sub-interval as the optimal coal quality ratio of the f-th sub-interval specifically includes:
using formulas
Calculating the optimal compromise solution of the output population of the f-th subinterval as the optimal coal quality ratio of the f-th subinterval;
wherein the content of the first and second substances,
representing the jth compromise objective function value of the mth individual in the output population,
representing the jth objective function value of the mth individual in the output population, and when the value of j is 1,
a first objective function value representing the mth individual in the output population, when the value of j is 2,
representing a second objective function value for the mth individual in the output population,
and
respectively representing the maximum value and the minimum value of the jth objective function value of the output population, and mu representing the optimal compromise solution of the output population.
Optionally, the determining, by using the first mathematical model and the second mathematical model of each subinterval as objective functions and using a multi-objective optimization algorithm, a coal quality ratio of each subinterval at which the unit outlet NOx concentration and the boiler efficiency are optimized as an optimal coal quality ratio of each subinterval further includes:
and performing curve fitting on the optimal coal quality ratio of each subinterval to determine a fitting curve representing the relationship between the load and the optimal coal quality ratio.
A multi-objective operational optimization system that accounts for both boiler efficiency and NOx emissions, the optimization system comprising:
the system comprises an operation data acquisition module, a data processing module and a data processing module, wherein the operation data acquisition module is used for acquiring operation data of a unit in a stable operation state within a preset time period and dividing the operation data into a plurality of sub-intervals according to loads;
the clustering module is used for clustering and analyzing the operating data of each subinterval according to the boiler efficiency and the concentration of NOx at the outlet of the unit in the operating data respectively to obtain a plurality of first clustering results and a plurality of second clustering results of each subinterval;
the fit point determining module is used for determining a first fit point representing the corresponding relation between the coal quality ratio and the boiler efficiency in each first clustering result and a second fit point representing the corresponding relation between the coal quality ratio and the outlet NOx concentration of the unit in each first clustering result to obtain a first fit point set and a second fit point set of each subinterval;
the function fitting module is used for performing function fitting on the first fit points in the first fit point set of each subinterval by adopting a regression analysis algorithm to obtain a fit function representing the relation between the coal quality ratio and the boiler efficiency of each subinterval, subtracting the fit function from 1 to obtain a first mathematical model, and performing function fitting on the second fit points in the second fit point set of each subinterval by adopting the regression analysis algorithm to obtain a second mathematical model representing the relation between the coal quality ratio and the NOx concentration at the outlet of the unit of each subinterval;
and the optimal coal quality ratio determining module is used for determining the coal quality ratio of each subinterval when the concentration of NOx at the outlet of the unit and the boiler efficiency are optimal as the optimal coal quality ratio of each subinterval by taking the first mathematical model and the second mathematical model of each subinterval as an objective function and adopting a multi-objective optimization algorithm.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a multi-target operation optimization method considering both boiler efficiency and NOx emission, which comprises the following steps: acquiring operation data of a unit in a stable operation state within a preset time period, and dividing the operation data into a plurality of sub-intervals according to loads; performing cluster analysis on the operating data of each subinterval according to the boiler efficiency and the concentration of NOx at the outlet of the unit in the operating data respectively to obtain a plurality of first cluster results and a plurality of second cluster results of each subinterval; determining a first fit point representing the corresponding relation between the coal quality ratio and the boiler efficiency in each first clustering result and a second fit point representing the corresponding relation between the coal quality ratio and the unit outlet NOx concentration in each first clustering result to obtain a first fit point set and a second fit point set of each subinterval; respectively performing function fitting on a first fit point in the first fit point set of each subinterval by adopting a regression analysis algorithm to obtain a fit function representing the relation between the coal quality ratio and the boiler efficiency of each subinterval, subtracting the fit function from 1 to obtain a first mathematical model, and performing function fitting on a second fit point in the second fit point set of each subinterval by adopting the regression analysis algorithm to obtain a second mathematical model representing the relation between the coal quality ratio and the concentration of NOx at the outlet of the unit of each subinterval; and determining the coal quality ratio of each subinterval when the concentration of NOx at the outlet of the unit and the boiler efficiency are optimal by taking the first mathematical model and the second mathematical model of each subinterval as an objective function and adopting a multi-objective optimization algorithm, and taking the coal quality ratio as the optimal coal quality ratio of each subinterval. The method comprises the steps of firstly carrying out interval division on operation data according to load, and then determining the optimal coal quality ratio considering both boiler efficiency and NOx concentration in each subinterval by adopting a clustering algorithm, a regression analysis algorithm and a multi-objective optimization algorithm. On the basis, the optimal coal quality ratio corresponding to different loads can be known, the optimal coal quality ratio can be determined according to the loads, and the method for determining the coal quality ratio can give consideration to the concentration of NOx at the outlet of the unit and the efficiency of the boiler.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a multi-objective operational optimization method for both boiler efficiency and NOx emissions in accordance with the present invention;
FIG. 2 is a schematic diagram of a multi-objective operational optimization method for both boiler efficiency and NOx emissions in accordance with the present invention;
FIG. 3 is a flow chart of the fitting point determination provided by the present invention;
FIG. 4 is a flow chart of a regression analysis algorithm provided by the present invention;
FIG. 5 is a flow chart of a multi-objective optimization algorithm provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a multi-target operation optimization method considering both boiler efficiency and NOx emission so as to provide a determination method of coal quality ratio considering both unit outlet NOx concentration and boiler efficiency.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1 and 2, the present invention provides a multi-objective operation optimization method considering both boiler efficiency and NOx emission, the optimization method comprising the steps of:
The method comprises the following steps of determining whether each set of operation data in a preset time period of a unit is operation data in a stable operation state according to main steam pressure, coal feeding quantity, water feeding quantity and steam turbine valve opening in each set of operation data in the preset time period, and specifically comprises the following steps: judging inequality according to main steam pressure, coal feeding quantity, water feeding quantity and steam turbine valve opening degree in the ith group of operation data
And
whether all the judgment results are established, and a first judgment result is obtained; if the first judgment result shows that the operation data is in a stable operation state, determining the ith group of operation data as the operation data in the stable operation state; if the first judgment result shows that the operation data is not stable, determining that the ith group of operation data is the operation data in the unstable operation state; wherein p isiAnd pjThe main steam pressure in the ith group of operation data and the jth group of operation data respectively, n' is the group number of the operation data in the preset time period,
and
respectively the coal feeding amount in the ith group of operation data and the jth group of operation data,
and
the water supply amount in the ith group of operation data and the jth group of operation data respectively,
and
the opening degree of the steam turbine valve, epsilon, in the ith group of operation data and the jth group of operation data respectively1、ε2、ε3And ε4Respectively representing a main steam pressure fluctuation threshold value, a coal feeding quantity fluctuation threshold value, a water feeding quantity fluctuation threshold value and a steam turbine valve opening fluctuation threshold value.
Specifically, the operation data of the unit in the last year is selected, the steady-state data in the operation data are selected, and the operation data are divided into cells according to the load.
And 102, performing cluster analysis on the operating data of each subinterval according to the boiler efficiency and the concentration of NOx at the outlet of the unit in the operating data to obtain a plurality of first cluster results and a plurality of second cluster results of each subinterval.
102, performing cluster analysis on the operating data of each subinterval according to the boiler efficiency and the concentration of NOx at the outlet of the unit in the operating data to obtain a plurality of first clustering results and a plurality of second clustering results of each subinterval, and then: using a formula
Normalizing each operation data in each first clustering result and each second clustering result; wherein, a'lsRepresents the s-th operating data in the l-th clustering result, alsRepresents the s normalized operation data, min (a'l) Represents the minimum value of the same kind of operation data in the l-th clustering result, max (a'l) Representing the maximum value of the same type of operation data in the first clustering result; a'lAnd representing the set of all the operating data in the ith clustering result, wherein the clustering results are a first clustering result and a second clustering result.
Specifically, the steps can be summarized as follows:
and (5) converting the coal quality ratio. If N kinds of coal quality participate in the combustion, the proportion of the former N-1 kinds of coal quality to the total coal quantity is calculated.
And (5) clustering analysis. And respectively carrying out cluster analysis on the operating data of each subinterval according to the boiler efficiency and the concentration of NOx at the outlet of the unit in the operating data to obtain a plurality of first cluster results and a plurality of second cluster results of each subinterval.
And (4) normalizing the data. Converting the proportion of each coal quality, the concentration of NOx at the outlet of the unit and the boiler efficiency value into a numerical value in a [0,1] interval in each cluster, wherein the normalization formula is as follows:
and 103, determining a first fit point representing the corresponding relation between the coal quality ratio and the boiler efficiency in each first clustering result and a second fit point representing the corresponding relation between the coal quality ratio and the unit outlet NOx concentration in each first clustering result to obtain a first fit point set and a second fit point set of each subinterval.
The determining a first fitting point representing a corresponding relation between the coal quality ratio and the boiler efficiency in each first clustering result specifically includes: for the l1The first clustering result adopts a trigonometric membership function algorithm to each ith1Fuzzification processing is carried out on the coal quality ratio and the boiler efficiency in each operation data in the first clustering result, and the ith1Attributes of coal quality ratio and boiler efficiency in each operation data in the first clustering result; first1Determining the ith clustering result according to the attribute of the coal quality ratio and the attribute of the boiler efficiency in each operation data1A rule representing the relation between the coal quality ratio and the boiler efficiency in each operation data in each first clustering result; according to item l1Selecting a rule with the most occurrence times as a discovery rule according to a rule representing the relation between the coal quality ratio and the boiler efficiency in each operation data in each first clustering result; obtaining the first1The coal quality ratio and the boiler efficiency of the operation data meeting the discovery rule in the first clustering result; will be first1Taking the average value of the maximum value and the minimum value of the coal quality ratio of the running data meeting the discovery rule in the first clustering result as the input data of a first fitting point, and taking the ith value1The average value of the maximum value and the minimum value of the boiler efficiency of the operation data meeting the discovery rule in the first clustering result is used as the output data of the first fitting point to obtain the ith1And a first fitting point in the first clustering result.
The second fitting point is obtained in the same manner as the first fitting point, and is not described herein again.
And fuzzifying the operation data subjected to normalization processing in each cluster by adopting a triangular membership function algorithm.
After fuzzifying each coal quality ratio and boiler efficiency, analyzing the rule corresponding to the most coal quality ratio and boiler efficiency as the rule found in the cluster;
similarly, fuzzifying the coal quality ratio, and after NOx is discharged, analyzing the rule with the most coal quality ratio and the most NOx discharge as the rule found in the cluster;
in the rule found after the boiler efficiency clustering, the coal quality ratio values the middle points of the upper limit and the lower limit, and the corresponding middle point of the boiler efficiency is taken as the fitting point of an optimization target 1 (a first mathematical model); in the rule found after NOx emission clustering, the coal quality ratio values are middle points of upper and lower limits, and the corresponding middle point of NOx emission is used as a fitting point of an optimization target 2 (a second mathematical model).
Step 103 comprises the steps of:
fuzzification is carried out on the coal quality ratio and NOx emission in a certain cluster (if the clustering is 5 types through NOx in the cell) in the cell through a triangular membership function, so that qualitative attributes are given to specific data values;
secondly, on the premise of meeting the minimum support degree, searching the corresponding rule of each coal quality proportion and NOx emission with the most occurrence times (if 4 kinds of coal quality exist, such as coal quality 1 with the maximum attribute, coal quality 2 with the medium attribute, coal quality 3 with the minimum attribute, corresponding to the maximum attribute of NOx emission, the rule with the most occurrence is represented as coal 1large and coal middle and coal 3small → NOx large, the rule is used as a discovery rule)
Selecting middle points of upper and lower limits of all points corresponding to the coarse 1, middle points of upper and lower limits of all points corresponding to the coarse 2 middle and middle 3small as input data, and middle points of all points corresponding to the NOx large as output points;
fourthly, the same operation is carried out in the other 4 clusters, and 5 groups of data with coal quality 1, coal quality 2 and coal quality 3 as input and NOx emission as output in the small interval are obtained.
Using the 5 groups of data to fit the curve of coal quality ratio and NOx emission, f 2.
Curves of coal quality proportioning and boiler efficiency, f1, can be obtained in the same way.
And 104, respectively performing function fitting on the first fit points in the first fit point set of each subinterval by adopting a regression analysis algorithm to obtain a fit function representing the relation between the coal quality ratio and the boiler efficiency of each subinterval, subtracting the fit function from 1 to obtain a first mathematical model, and performing function fitting on the second fit points in the second fit point set of each subinterval by adopting the regression analysis algorithm to obtain a second mathematical model representing the relation between the coal quality ratio and the NOx concentration at the outlet of the unit of each subinterval.
The performing function fitting on the second fitting points in the second fitting point set of each subinterval by using a regression analysis algorithm to obtain a second mathematical model representing the relation between the coal quality ratio and the unit outlet NOx concentration of each subinterval specifically comprises: for the f sub-interval, respectively performing function fitting on second fitting points in the second fitting point set of the f sub-interval by adopting a regression analysis algorithm, and determining that the expression of a second fitting function of the f sub-interval is as follows:
wherein, y2Denotes the concentration of NOx, xnAnd xhRespectively represents the mixture ratio of the nth coal and the h-th coal, beta2nCoefficient of quadratic term, beta, representing the quality of the nth coalnCoefficient of first order term, beta, representing quality of the nth coalnhRepresents the cross term coefficient, beta, of the nth coal quality and the h-th coal quality0Representing constant term coefficient, N represents the type of coal quality; fitting coefficients in an expression of the second fitting function by using a second fitting point set of the f-th subinterval to obtain a plurality of second fitting functions under different coefficient combinations; the coefficients include quadratic term coefficients, first order term coefficients, cross term coefficients, and constant term coefficients; and selecting a second fitting function which passes through F test and t test from the plurality of second fitting functions and has the maximum judgment coefficient as a second mathematical model of the F subinterval. It doesThe manner of determining the first mathematical model is the same as the manner of determining the second mathematical model, and is not described herein again.
As shown in fig. 4, the specific steps of step 104 are:
and fitting m groups of fitting data by adopting a multivariate polynomial least square regression method. Taking n-1 coal quality ratios (occupied ratios) as input, taking the concentration of NOx at the outlet of a unit as output, and adopting a fitting polynomial function (multivariate polynomial regression) as follows:
and secondly, keeping the first term in the formula, freely combining the second term and the cross term, and respectively fitting the obtained other functions.
And thirdly, calculating a judgment coefficient R2 of all the fitted functional relations.
And fourthly, performing F test on the obtained fitting model, and if the fitting model passes the F test, performing coefficient t test.
Selecting the model which passes the test of model F and the coefficient passes the test of t, and taking the model with the maximum R2 as the mathematical model a to F of the coal quality ratio and the NOx concentration at the outlet of the unit2(x)＝ynox，f2(x) Representing a second mathematical model, ynoxA fitting function representing the coal quality ratio and the NOx concentration at the outlet of the unit;
obtaining a model b of the relation between the coal quality ratio and the boiler efficiency by the same method: f. of1(x)＝1-yeffi， yeffiFitting function f representing coal quality ratio and efficiency1(x) Representing a first mathematical model.
And 105, taking the first mathematical model and the second mathematical model of each subinterval as an objective function, and determining the coal quality ratio of each subinterval when the concentration of NOx at the outlet of the unit and the boiler efficiency are optimal by adopting a multi-objective optimization algorithm to serve as the optimal coal quality ratio of each subinterval.
Step 105, using the first mathematical model and the second mathematical model of each subinterval as objective functions, and adopting multi-meshAnd a standard optimization algorithm, which determines the coal quality ratio of each subinterval when the concentration of NOx at the outlet of the unit and the boiler efficiency are optimal, and specifically comprises the following steps of: for the f-th subinterval, initializing a parent population with the scale of M; the parent population comprises M individuals, and each individual represents a combination of coal quality ratios; calculating a first objective function value and a second function value of each individual in the parent population by using the first mathematical model and the second mathematical model of the f-th subinterval; sorting each individual in the parent population according to the dominance degree and the distance between the individuals according to the first objective function value and the second function value of each individual in the parent population; obtaining the top M in the sorted parent population0Crossing and varying the individuals to generate a progeny population; wherein M is0<M; calculating a first objective function value and a second objective function value of each individual in the offspring population by using the first mathematical model and the second mathematical model of the f-th subinterval; sorting each individual in the parent population and the child population according to the domination degree and the distance between the individuals according to a first objective function value and a second objective function value of each individual in the parent population and the child population, selecting the first M individuals in the sorted parent population and child population to form an updated parent population, and returning to the step of sorting each individual in the parent population according to the domination degree and the distance between the individuals according to the first objective function value and the second function value of each individual in the parent population; outputting the parent population updated by the last iteration as the output population of the f-th subinterval until the iteration number reaches the iteration number threshold; and calculating the optimal compromise solution of the output population of the f-th subinterval as the optimal coal quality ratio of the f-th subinterval.
The calculating of the first objective function value and the second function value of each individual in the parent population by using the first mathematical model and the second mathematical model of the f-th subinterval specifically includes: for each individual in the parent population, a judgment formula
If yes, obtaining a second judgment result; wherein x isnThe mixture ratio of the nth coal quality in the individual is shown, and N is the number of the types of the coal quality in the individual; if the second judgment result shows that the first objective function value and the second objective function value of the individual are calculated by using the first mathematical model and the second mathematical model of the f-th sub-interval respectively; if the second judgment result shows no, setting the first objective function value of the individual to be infinite, and setting the second objective function value of the individual to be infinite.
The calculating of the optimal compromise solution of the output population of the f-th sub-interval as the optimal coal quality ratio of the f-th sub-interval specifically includes: using formulas
Calculating the optimal compromise solution of the output population of the f-th subinterval as the optimal coal quality ratio of the f-th subinterval; wherein the content of the first and second substances,
representing the jth compromise objective function value of the mth individual in the output population,
representing the jth objective function value of the mth individual in the output population, and when the value of j is 1,
a first objective function value representing the mth individual in the output population, when the value of j is 2,
representing a second objective function value for the mth individual in the output population,
and
j-th target functions respectively representing output populationThe maximum and minimum values of the values, μ, represent the optimal compromise solution for the output population.
As shown in fig. 5, step 105 specifically includes:
for the f-th subinterval, initializing a parent population with the scale of M; the parent population comprises M individuals, and each individual represents a combination of coal quality ratios;
on the premise of meeting individual variable value constraints, calculating a first objective function value and a second function value of each individual in the population by using the first mathematical model and the second mathematical model of the f-th subinterval, and then performing evolutionary operator operation on each individual to generate an offspring population;
in the offspring population, calculating a first objective function value and a second objective function value for individuals meeting individual variable value constraints;
and according to the first objective function value and the second objective function value of each individual, sorting each individual in the parent population and the child population according to the dominance degree and the distance between individuals, wherein the individual with the highest dominance level and the individual with the highest dominance level among the individuals with the highest dominance level have the highest level. And selecting the first M sorted parent population with higher levels to form an updated parent population. Returning to the step of performing evolutionary operator operation on each individual in the parent population to generate a child population; outputting the parent population updated by the last iteration as the output population of the f-th subinterval until the iteration number reaches the iteration number set value;
and calculating the optimal compromise solution of the output population of the f-th subinterval as the optimal coal quality ratio of the f-th subinterval. .
and performing curve fitting on the optimal coal quality ratio of each subinterval to determine a fitting curve representing the relationship between the load and the optimal coal quality ratio.
The invention also provides a multi-objective operation optimization system considering both boiler efficiency and NOx emission, comprising:
the system comprises an operation data acquisition module, a data processing module and a data processing module, wherein the operation data acquisition module is used for acquiring operation data of a unit in a stable operation state within a preset time period and dividing the operation data into a plurality of sub-intervals according to loads;
the clustering module is used for clustering and analyzing the operating data of each subinterval according to the boiler efficiency and the concentration of NOx at the outlet of the unit in the operating data respectively to obtain a plurality of first clustering results and a plurality of second clustering results of each subinterval;
the fit point determining module is used for determining a first fit point representing the corresponding relation between the coal quality ratio and the boiler efficiency in each first clustering result and a second fit point representing the corresponding relation between the coal quality ratio and the outlet NOx concentration of the unit in each first clustering result to obtain a first fit point set and a second fit point set of each subinterval;
the function fitting module is used for performing function fitting on the first fit points in the first fit point set of each subinterval by adopting a regression analysis algorithm to obtain a fit function representing the relation between the coal quality ratio and the boiler efficiency of each subinterval, subtracting the fit function from 1 to obtain a first mathematical model, and performing function fitting on the second fit points in the second fit point set of each subinterval by adopting the regression analysis algorithm to obtain a second mathematical model representing the relation between the coal quality ratio and the NOx concentration at the outlet of the unit of each subinterval;
and the optimal coal quality ratio determining module is used for determining the coal quality ratio of each subinterval when the concentration of NOx at the outlet of the unit and the boiler efficiency are optimal as the optimal coal quality ratio of each subinterval by taking the first mathematical model and the second mathematical model of each subinterval as an objective function and adopting a multi-objective optimization algorithm.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a multi-target operation optimization method considering both boiler efficiency and NOx emission, which comprises the following steps: acquiring operation data of a unit in a stable operation state within a preset time period, and dividing the operation data into a plurality of sub-intervals according to loads; performing cluster analysis on the operating data of each subinterval according to the boiler efficiency and the concentration of NOx at the outlet of the unit in the operating data respectively to obtain a plurality of first cluster results and a plurality of second cluster results of each subinterval; determining a first fit point representing the corresponding relation between the coal quality ratio and the boiler efficiency in each first clustering result and a second fit point representing the corresponding relation between the coal quality ratio and the unit outlet NOx concentration in each first clustering result to obtain a first fit point set and a second fit point set of each subinterval; respectively performing function fitting on a first fit point in the first fit point set of each subinterval by adopting a regression analysis algorithm to obtain a fit function representing the relation between the coal quality ratio and the boiler efficiency of each subinterval, subtracting the fit function from 1 to obtain a first mathematical model, and performing function fitting on a second fit point in the second fit point set of each subinterval by adopting the regression analysis algorithm to obtain a second mathematical model representing the relation between the coal quality ratio and the concentration of NOx at the outlet of the unit of each subinterval; and determining the coal quality ratio of each subinterval when the concentration of NOx at the outlet of the unit and the boiler efficiency are optimal by taking the first mathematical model and the second mathematical model of each subinterval as an objective function and adopting a multi-objective optimization algorithm, and taking the coal quality ratio as the optimal coal quality ratio of each subinterval. The method comprises the steps of firstly carrying out interval division on operation data according to load, and then determining the optimal coal quality ratio considering both boiler efficiency and NOx concentration in each subinterval by adopting a clustering algorithm, a regression analysis algorithm and a multi-objective optimization algorithm. On the basis, the optimal coal quality ratio corresponding to different loads can be known, the optimal coal quality ratio can be determined according to the loads, and the method for determining the coal quality ratio can give consideration to the concentration of NOx at the outlet of the unit and the efficiency of the boiler.
The equivalent embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts between the equivalent embodiments can be referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In summary, this summary should not be construed to limit the present invention.
Claims (10)
1. A multi-objective operation optimization method considering both boiler efficiency and NOx emission is characterized by comprising the following steps:
acquiring operation data of a unit in a stable operation state within a preset time period, and dividing the operation data into a plurality of sub-intervals according to loads;
performing cluster analysis on the operating data of each subinterval according to the boiler efficiency and the concentration of NOx at the outlet of the unit in the operating data respectively to obtain a plurality of first cluster results and a plurality of second cluster results of each subinterval;
determining a first fit point representing the corresponding relation between the coal quality ratio and the boiler efficiency in each first clustering result and a second fit point representing the corresponding relation between the coal quality ratio and the unit outlet NOx concentration in each first clustering result to obtain a first fit point set and a second fit point set of each subinterval;
respectively performing function fitting on a first fit point in the first fit point set of each subinterval by adopting a regression analysis algorithm to obtain a fit function representing the relation between the coal quality ratio and the boiler efficiency of each subinterval, subtracting the fit function from 1 to obtain a first mathematical model, and performing function fitting on a second fit point in the second fit point set of each subinterval by adopting the regression analysis algorithm to obtain a second mathematical model representing the relation between the coal quality ratio and the concentration of NOx at the outlet of the unit of each subinterval;
and determining the coal quality ratio of each subinterval when the concentration of NOx at the outlet of the unit and the boiler efficiency are optimal by taking the first mathematical model and the second mathematical model of each subinterval as an objective function and adopting a multi-objective optimization algorithm, and taking the coal quality ratio as the optimal coal quality ratio of each subinterval.
2. The multi-objective operation optimization method considering both boiler efficiency and NOx emission according to claim 1, wherein the obtaining of the operation data of the unit in a stable operation state within a preset time period and the dividing of the operation data into a plurality of sub-intervals according to load specifically comprises:
determining whether each set of operation data in the preset time period of the unit is operation data in a stable operation state according to the main steam pressure, the coal feeding amount, the water feeding amount and the steam turbine valve opening degree in each set of operation data in the preset time period;
acquiring all running data in a stable running state within a preset time period as the running data in the stable running state within the preset time period of the unit;
and dividing the operation data of the sub-time period in which the unit is in the stable operation state into a plurality of sub-intervals according to the load.
3. The multi-objective operation optimization method considering both boiler efficiency and NOx emission according to claim 2, wherein determining whether each set of operation data in a preset time period of the unit is operation data in a stable operation state according to the main steam pressure, the coal feeding amount, the water feeding amount, and the steam turbine valve opening degree in each set of operation data in the preset time period specifically includes:
judging inequality according to main steam pressure, coal feeding quantity, water feeding quantity and steam turbine valve opening degree in the ith group of operation data
And
whether all the judgment results are established, and a first judgment result is obtained;
if the first judgment result shows that the operation data is in a stable operation state, determining the ith group of operation data as the operation data in the stable operation state;
if the first judgment result shows that the operation data is not stable, determining that the ith group of operation data is the operation data in the unstable operation state;
wherein p isiAnd pjThe main steam pressure in the ith group of operation data and the jth group of operation data respectively, n' is the group number of the operation data in the preset time period,
and
respectively the coal feeding amount in the ith group of operation data and the jth group of operation data,
and
the water supply amount in the ith group of operation data and the jth group of operation data respectively,
and
the opening degree of the steam turbine valve, epsilon, in the ith group of operation data and the jth group of operation data respectively1、ε2、ε3And ε4Respectively representing a main steam pressure fluctuation threshold value, a coal feeding quantity fluctuation threshold value, a water feeding quantity fluctuation threshold value and a steam turbine valve opening fluctuation threshold value.
4. The multi-objective operation optimization method considering both boiler efficiency and NOx emission according to claim 1, wherein the clustering analysis is performed on the operation data of each subinterval according to boiler efficiency and unit outlet NOx concentration in the operation data, respectively, to obtain a plurality of first clustering results and a plurality of second clustering results for each subinterval, and thereafter further comprising:
using a formula
Normalizing each operating data in each first clustering result and each second clustering result; wherein, a'lsRepresents the s-th operating data in the l-th clustering result, alsRepresents the s normalized operation data, min (a'l) Represents the minimum value of the same kind of operation data in the l-th clustering result, max (a'l) Representing the maximum value of the same type of operation data in the first clustering result; a'lAnd representing the set of all the operating data in the ith clustering result, wherein the clustering results are a first clustering result and a second clustering result.
5. The method according to claim 1, wherein the determining a first fit point representing a corresponding relationship between coal quality ratio and boiler efficiency in each first clustering result specifically comprises:
for the l1The first clustering result adopts a trigonometric membership function algorithm to each ith1Fuzzification processing is carried out on the coal quality ratio and the boiler efficiency in each operation data in the first clustering result, and the ith1Attributes of coal quality ratio and boiler efficiency in each operation data in the first clustering result;
first1Determining the ith clustering result according to the attribute of the coal quality ratio and the attribute of the boiler efficiency in each operation data1A rule representing the relation between the coal quality ratio and the boiler efficiency in each operation data in each first clustering result;
according to item l1Selecting a rule with the most occurrence times as a discovery rule according to a rule representing the relation between the coal quality ratio and the boiler efficiency in each operation data in each first clustering result;
obtaining the first1The number of operations satisfying the discovery rule in the first clustering resultAccording to the coal quality ratio and the boiler efficiency;
will be first1Taking the average value of the maximum value and the minimum value of the coal quality ratio of the running data meeting the discovery rule in the first clustering result as the input data of a first fitting point, and taking the ith value1The average value of the maximum value and the minimum value of the boiler efficiency of the operation data meeting the discovery rule in the first clustering result is used as the output data of the first fitting point to obtain the ith1And a first fitting point in the first clustering result.
6. The method of claim 1, wherein the performing function fitting on the second fitting points in the second fitting point set of each subinterval by using a regression analysis algorithm to obtain a second mathematical model representing a relationship between a coal quality ratio and a unit outlet NOx concentration for each subinterval specifically comprises:
for the f sub-interval, respectively performing function fitting on second fitting points in the second fitting point set of the f sub-interval by adopting a regression analysis algorithm, and determining that the expression of a second fitting function of the f sub-interval is as follows:
wherein, y2Denotes the concentration of NOx, xnAnd xhRespectively represents the mixture ratio of the nth coal and the h-th coal, beta2nCoefficient of quadratic term, beta, representing the quality of the nth coalnCoefficient of first order term, beta, representing quality of the nth coalnhRepresents the cross term coefficient, beta, of the nth coal quality and the h-th coal quality0Representing constant term coefficient, N represents the type of coal quality;
fitting coefficients in an expression of the second fitting function by using a second fitting point set of the f-th subinterval to obtain a plurality of second fitting functions under different coefficient combinations; the coefficients include quadratic term coefficients, first order term coefficients, cross term coefficients, and constant term coefficients;
and selecting a second fitting function which passes through F test and t test from the plurality of second fitting functions and has the maximum judgment coefficient as a second mathematical model of the F subinterval.
7. The method for optimizing multi-target operation considering both boiler efficiency and NOx emission according to claim 1, wherein the determining the coal quality ratio of each subinterval at which the unit outlet NOx concentration and the boiler efficiency are optimized, as the optimal coal quality ratio of each subinterval, using the first mathematical model and the second mathematical model of each subinterval as objective functions and using a multi-target optimization algorithm, specifically comprises:
for the f-th subinterval, initializing a parent population with the scale of M; the parent population comprises M individuals, and each individual represents a combination of coal quality ratios;
calculating a first objective function value and a second function value of each individual in the parent population by using the first mathematical model and the second mathematical model of the f-th subinterval;
sorting each individual in the parent population according to the dominance degree and the distance between the individuals according to the first objective function value and the second function value of each individual in the parent population;
obtaining the top M in the sorted parent population0Crossing and varying the individuals to generate a progeny population; wherein M is0<M；
Calculating a first objective function value and a second objective function value of each individual in the offspring population by using the first mathematical model and the second mathematical model of the f-th subinterval;
sorting each individual in the parent population and the child population according to the domination degree and the distance between the individuals according to a first objective function value and a second objective function value of each individual in the parent population and the child population, selecting the first M individuals in the sorted parent population and child population to form an updated parent population, and returning to the step of sorting each individual in the parent population according to the domination degree and the distance between the individuals according to the first objective function value and the second function value of each individual in the parent population; outputting the parent population updated by the last iteration as the output population of the f-th subinterval until the iteration number reaches the iteration number threshold;
and calculating the optimal compromise solution of the output population of the f-th subinterval as the optimal coal quality ratio of the f-th subinterval.
8. The method of claim 7, wherein calculating the first objective function value and the second objective function value for each individual in the parent population using the first mathematical model and the second mathematical model for the f-th sub-interval comprises:
for each individual in the parent population, a judgment formula
If yes, obtaining a second judgment result; wherein x isnThe mixture ratio of the nth coal quality in the individual is shown, and N is the number of the types of the coal quality in the individual;
if the second judgment result shows that the first objective function value and the second objective function value of the individual are calculated by using the first mathematical model and the second mathematical model of the f-th sub-interval respectively;
if the second judgment result shows no, setting the first objective function value of the individual to be infinite, and setting the second objective function value of the individual to be infinite.
9. The method according to claim 7, wherein the calculating of the optimal compromise solution of the output population of the f-th sub-interval as the optimal coal quality ratio of the f-th sub-interval specifically comprises:
using formulas
And
calculating the optimal compromise solution of the output population of the f-th subinterval as the optimal coal quality ratio of the f-th subinterval;
wherein the content of the first and second substances,
representing the jth compromise objective function value of the mth individual in the output population,
representing the jth objective function value of the mth individual in the output population, and when the value of j is 1,
a first objective function value representing the mth individual in the output population, when the value of j is 2,
representing a second objective function value for the mth individual in the output population,
and
respectively representing the maximum value and the minimum value of the jth objective function value of the output population, and mu representing the optimal compromise solution of the output population.
10. The method of claim 1, wherein the first mathematical model and the second mathematical model of each sub-interval are used as objective functions, and a multi-objective optimization algorithm is adopted to determine the coal quality ratio of each sub-interval for optimizing the unit outlet NOx concentration and the boiler efficiency as the optimal coal quality ratio of each sub-interval, and then the method further comprises:
and performing curve fitting on the optimal coal quality ratio of each subinterval to determine a fitting curve representing the relationship between the load and the optimal coal quality ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110230825.2A CN112966436B (en) | 2021-03-02 | 2021-03-02 | Boiler efficiency and NO are taken into considerationxMulti-objective operational optimization method for emissions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110230825.2A CN112966436B (en) | 2021-03-02 | 2021-03-02 | Boiler efficiency and NO are taken into considerationxMulti-objective operational optimization method for emissions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112966436A CN112966436A (en) | 2021-06-15 |
| CN112966436B true CN112966436B (en) | 2022-02-18 |
Family
ID=76276645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110230825.2A Active CN112966436B (en) | 2021-03-02 | 2021-03-02 | Boiler efficiency and NO are taken into considerationxMulti-objective operational optimization method for emissions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112966436B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102654768A (en) * | 2012-05-09 | 2012-09-05 | 北京华电天仁电力控制技术有限公司 | Rule-based power station boiler combustion coal-saving nitrogen-reducing control method and device |
| CN111199304A (en) * | 2018-11-19 | 2020-05-26 | 天津市职业大学 | Multi-target combustion optimization method based on data-driven fusion strategy |
| CN111765445A (en) * | 2020-07-01 | 2020-10-13 | 河北工业大学 | Boiler on-line combustion optimization control method and system and computer equipment |
-
2021
- 2021-03-02 CN CN202110230825.2A patent/CN112966436B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102654768A (en) * | 2012-05-09 | 2012-09-05 | 北京华电天仁电力控制技术有限公司 | Rule-based power station boiler combustion coal-saving nitrogen-reducing control method and device |
| CN111199304A (en) * | 2018-11-19 | 2020-05-26 | 天津市职业大学 | Multi-target combustion optimization method based on data-driven fusion strategy |
| CN111765445A (en) * | 2020-07-01 | 2020-10-13 | 河北工业大学 | Boiler on-line combustion optimization control method and system and computer equipment |
Non-Patent Citations (6)
| Title |
|---|
| Multi-objective Optimization of Coal-Fired Boiler Efficiency and NOx Emission under Different Ecological Environment.;Wang Weiqing;《Future Communication, Computing, Control and Management》;20121231;第141卷;433-439 * |
| Research and designing of boiler-turbine model linearization balance operating point based on energy-saving and non-linear measurement analysis;Chen Yanqiao 等;《IECON 2012 - 38th Annual Conference on IEEE Industrial Electronics Society》;20121224;1145-1149 * |
| Research on NOx emission of coal-fired unit based on multi-model clustering ensemble;Chenggang Zhen 等;《International Journal of Simulation and Process Modelling》;20200421;第15卷(第1-2期);30-39 * |
| 基于全工况数据挖掘的燃烧优化;郑伟 等;《热力发电》;20170602;第46卷(第6期);C039-66 * |
| 基于智能算法的燃煤电站锅炉经济运行与NOx排放多目标优化研究;耿平;《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》;20170315(第03期);C042-1548 * |
| 锅炉运行燃烧优化模型研究及其验证;周思远;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20130715(第07期);69-74 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112966436A (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461421B (en) | Cascade reservoir risk assessment method and system based on mutual feedback relationship analysis | |
| Wang et al. | A deep learning based dynamic COD prediction model for urban sewage | |
| CN110619360A (en) | Ultra-short-term wind power prediction method considering historical sample similarity | |
| CN112116153A (en) | Park multivariate load joint prediction method for coupling Copula and stacked LSTM network | |
| CN111858715B (en) | Sewage treatment plant water inlet quality prediction method based on data mining | |
| CN106372739B (en) | Demand response effect evaluation method based on demand response baseline | |
| CN114386700A (en) | Power transmission system planning method and device considering wind-light correlation and storage medium | |
| CN115759336A (en) | Prediction method and storage medium for short-term power load prediction | |
| CN109829244A (en) | The blower optimum design method of algorithm optimization depth network and three generations's genetic algorithm | |
| CN115730228A (en) | Central air conditioner energy consumption analysis method based on BP neural network | |
| CN112966436B (en) | Boiler efficiency and NO are taken into considerationxMulti-objective operational optimization method for emissions | |
| CN114037138A (en) | Subway short-time arrival passenger flow prediction system based on double-layer decomposition and deep learning and implementation method | |
| CN113240330A (en) | Multi-dimensional value evaluation method and scheduling strategy for demand side virtual power plant | |
| Prasanna et al. | Fuzzy mutated evolutionary programming based algorithm for combined economic and emission dispatch | |
| CN113780686A (en) | Distributed power supply-oriented virtual power plant operation scheme optimization method | |
| CN115409282A (en) | Water-wind-light long-term complementary scheduling rule extraction method | |
| CN115034443A (en) | Boiler performance prediction method based on working condition division and neural network | |
| CN113379093B (en) | Energy consumption analysis and optimization method for oil-gas gathering and transportation system | |
| CN113935230A (en) | Implementation of NO based on attention mechanism LSTM modelxEmission amount prediction method | |
| CN113609768A (en) | Bidirectional LSTM network-based distribution room line loss rate calculation method | |
| CN112465145A (en) | Unmanned cluster intelligent qualitative evaluation method based on logical reasoning and fuzzy synthesis | |
| CN111860923A (en) | Boiler flue gas NO based on multi-model clustering integrationxEmission prediction algorithm | |
| CN110818072A (en) | Optimal control method of wastewater aerobic biochemical treatment process based on NSGA-III | |
| CN110932265B (en) | Static voltage stability evaluation method and system | |
| CN116526496B (en) | Novel auxiliary decision-making method for power system load control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |