CN114065100B - Boiler nitrogen oxide emission control method, terminal and storage medium - Google Patents
Boiler nitrogen oxide emission control method, terminal and storage medium Download PDFInfo
- Publication number
- CN114065100B CN114065100B CN202111334994.7A CN202111334994A CN114065100B CN 114065100 B CN114065100 B CN 114065100B CN 202111334994 A CN202111334994 A CN 202111334994A CN 114065100 B CN114065100 B CN 114065100B
- Authority
- CN
- China
- Prior art keywords
- boiler
- model
- working condition
- under
- emission
- 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
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 19
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 claims description 90
- 229910021529 ammonia Inorganic materials 0.000 claims description 45
- 230000006870 function Effects 0.000 claims description 26
- 238000002347 injection Methods 0.000 claims description 22
- 239000007924 injection Substances 0.000 claims description 22
- 238000005507 spraying Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 18
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 14
- 239000003546 flue gas Substances 0.000 claims description 14
- 239000003245 coal Substances 0.000 claims description 11
- 239000013598 vector Substances 0.000 description 24
- 230000008569 process Effects 0.000 description 17
- 210000002569 neuron Anatomy 0.000 description 11
- 239000011159 matrix material Substances 0.000 description 9
- 239000002245 particle Substances 0.000 description 8
- 208000037466 short stature, oligodontia, dysmorphic facies, and motor delay Diseases 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000005457 optimization Methods 0.000 description 6
- 239000000243 solution Substances 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000002485 combustion reaction Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 230000009469 supplementation Effects 0.000 description 4
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 238000010238 partial least squares regression Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003638 chemical reducing agent Substances 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Algebra (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
Abstract
The invention provides a method, a terminal and a storage medium for controlling the emission of nitrogen oxides of a boiler, comprising the following steps: acquiring a plurality of data samples according to historical data, wherein the input parameter of each data sample is a working state parameter of a boiler, the working state parameter comprises an adjustable parameter and an unadjustable parameter, and the output parameter is a value of NO x emission; clustering a plurality of data samples according to input parameters of each data sample to obtain t subsets, and training a preset model through each subset to obtain t sub-models; determining a target model in t sub-models according to non-adjustable parameters of the boiler under a given working condition; and determining an objective function according to the lowest emission of the outlet NO x of the boiler, and optimizing the adjustable parameters of the boiler according to the objective function and the objective model to obtain the optimized value of the adjustable parameters of the boiler. The invention can optimize the boiler operation parameters to reduce the emission of NO x.
Description
Technical Field
The present invention relates to the field of boiler control technologies, and in particular, to a method, a terminal, and a storage medium for controlling emission of nitrogen oxides from a boiler.
Background
In the coal combustion process, a large amount of pollutants such as nitrogen oxides NO x and the like can be generated, so that serious environmental problems are caused, and how to optimize the operation parameters of the boiler is an effective technical means for reducing the emission of the coal-fired boiler and improving the operation efficiency of the boiler.
The method requires modeling analysis of a combustion system of the boiler, and in the current research content, most of the method only models and optimizes a certain load point or a plurality of load points of a unit, so that operation guidance of the unit in different load states can not be realized. However, as various new energy power generation is connected to the power grid, the operation elasticity is a higher requirement of the power system for adapting to the current and future new energy power large-scale connection to the power grid on the coal-fired unit, and the load of the coal-fired unit is frequently changed and the boiler load is not limited to the typical design load point of the unit in order to improve the absorption efficiency of the new energy power generation.
The discharge amount of the coal-fired unit is unstable due to the frequently-changed load instruction, so that how to optimize the operation parameters of multiple boilers under the condition of frequent load change is a technical problem which needs to be solved urgently in the prior art.
Disclosure of Invention
In view of the above, the invention provides a method, a terminal and a storage medium for controlling the emission of nitrogen oxides of a boiler, which can solve the problem that the optimization of the operation parameters of the boiler can not be realized under the condition of frequent load change in the prior art.
In a first aspect, an embodiment of the present invention provides a method for controlling emission of nitrogen oxides from a boiler, including:
Acquiring a plurality of data samples according to historical data, wherein the input parameter of each data sample is a working state parameter of a boiler, the working state parameter comprises an adjustable parameter and an unadjustable parameter, and the output parameter is a value of NO x emission;
clustering the plurality of data samples according to the input parameters of each data sample to obtain t subsets, and training a preset model through each subset to obtain t sub-models;
Determining a target model in the t sub-models according to the non-adjustable parameters of the boiler under the given working condition;
And determining an objective function according to the lowest emission of the NO x at the outlet of the boiler, and optimizing the adjustable parameters of the boiler according to the objective function and the objective model to obtain the optimized value of the adjustable parameters of the boiler.
In one possible implementation, the adjustable parameters of the boiler include the opening degree of each layer of overgrate air baffle and each layer of burnout door of the boiler, and the non-adjustable parameters of the boiler include the coal feeding amount of each layer of coal feeder of the boiler, the total air quantity of the boiler and the load of the boiler.
In one possible implementation manner, the determining at least one sub-model as the target model according to the non-adjustable parameters of the boiler under the given working condition includes:
And according to the non-adjustable parameters of the boiler under the given working condition, sequentially calculating the membership value of the clustering center corresponding to each sub-model under the given working condition, and obtaining one sub-model with the largest membership as the target model.
In one possible implementation, the method further includes:
Obtaining a predicted value of NO x emission under the given working condition according to the input parameters of the boiler under the given working condition and the target model;
Or obtaining the predicted value of the NO x emission under the given working condition according to the input parameters of the boiler under the given working condition, the membership value of the clustering center corresponding to each sub-model under the given working condition and each sub-model.
In one possible implementation manner, the obtaining the predicted value of the NO x emission under the given working condition according to the input parameter of the boiler under the given working condition, the value of the membership degree of the clustering center corresponding to each sub-model under the given working condition, and each sub-model includes:
obtaining a predicted value of NO x emission under the given working condition according to a first formula, wherein the first formula is that
Wherein g (-) represents an integrated model, f k (-) represents a kth submodel, a value representing membership degree of a clustering center corresponding to the kth submodel under the given working condition, and x represents an input parameter of a data sample under the given working condition.
In one possible implementation, the method further includes:
Obtaining the variation of the discharge amount from the current moment to the next moment NO x of the boiler outlet according to the actual value of the discharge amount of the boiler at the current moment NO x and the predicted value of the discharge amount of the boiler at the next moment NO x;
Determining the variation of the ammonia spraying amount of the denitration system according to the variation of the NO x emission amount, the denitration efficiency of the denitration system and the flue gas flow of the boiler;
and obtaining the variation of the valve opening of the ammonia spraying valve according to the variation of the ammonia spraying amount of the denitration system.
In one possible implementation manner, the determining the variation of the ammonia injection amount of the denitration system according to the variation of the NO x emission amount of the boiler outlet, the denitration efficiency of the denitration system, and the flue gas flow of the boiler includes:
Obtaining the variation of the ammonia spraying amount of the denitration system according to a first formula, wherein the first formula is that
Wherein Deltay is the variation of ammonia spraying amount of the denitration system, deltac NOx is the variation of NO x emission amount from the current moment to the next moment of the boiler outlet, deltac NOx is mg/Nm 3, eta is the denitration efficiency of the denitration system, Q is the flue gas flow of the boiler, Q is m 3/h,Is NH 3 molar mass,/>Is the molar mass of NO x;
the obtaining the variation of the valve opening of the ammonia spraying valve according to the variation of the ammonia spraying amount of the denitration system comprises the following steps: obtaining the variation of the valve opening according to a second formula, wherein the second formula is that
Wherein delta n is the variation of the valve opening, and b and k are preset fitting coefficients.
In one possible implementation, the method further includes:
Obtaining a target value of ammonia spraying amount according to a predicted value of NO x emission of the boiler at the next moment, denitration efficiency of the denitration system and flue gas flow of the boiler;
Obtaining a target value of the valve opening according to the target value of the ammonia injection amount;
And performing PID control on the valve opening according to the target value of the valve opening and the valve opening value at the current moment so that the valve opening of the ammonia injection valve at the next moment is the target value.
In a second aspect, embodiments of the present invention provide a terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect when the computer program is executed.
In a third aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
According to the method, the historical data are processed to obtain the data samples, the data samples are clustered according to the input parameters of the data samples to obtain a plurality of subsets, the sample load in each subset is small in change, the preset model is trained through each subset to obtain a model corresponding to each sub-working condition, the target model is determined through the non-adjustable parameters under the given working condition, the adjustable parameters under the given working condition are optimized through the target model, and therefore optimization of the boiler operation parameters under the scene with frequent load change is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an implementation of a method for controlling emissions of nitrogen oxides from a boiler according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating another method for controlling emissions of nitrogen oxides from a boiler according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating another method for controlling emissions of nitrogen oxides from a boiler according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a boiler nitrogen oxide emission control device according to an embodiment of the present invention;
Fig. 5 is a schematic diagram of a terminal according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.
Referring to fig. 1, a flowchart for implementing a method for controlling emission of nitrogen oxides in a boiler according to an embodiment of the present invention is shown, and details are as follows:
In step 101, a plurality of data samples are obtained according to the historical data, wherein the input parameter of each data sample is an operating state parameter of the boiler, including an adjustable parameter and an non-adjustable parameter, and the output parameter is a value of NO x emission.
In the embodiment of the invention, the operation data with the time span of 1 month can be selected from the operation database of the power station boiler system and is recorded as a data set D, the sampling frequency is 1 data sample per second, and the boiler combustion system has no fault or shutdown process within the time span range of the acquired data; the acquired data is then preprocessed.
It should be noted that, the embodiment of the present invention does not limit the process of collecting the operation data, and the time span and the sampling frequency are also only examples, and are not limited by the process of collecting the operation data.
The operation data are original data, and the original data are supplemented and cleaned according to the data missing and distortion conditions of the original data, and normalization processing is carried out on the supplemented and cleaned data in order to accelerate the convergence of the loss function.
The data supplementing and cleaning process comprises the following steps: the basic idea of data supplementation and cleaning is to consider that certain samples in a data set D deviate seriously from the statistical characteristic rules presented by most data, and then consider the samples as outlier samples, and delete and fill the outlier samples.
After the outliers are deleted, in order to keep the trend of the data and not reduce the number of the depth network training samples, linear interpolation supplementation is carried out on the outliers, wherein the linear interpolation supplementation is carried out according to the following formula (1):
In the formula (1), the components are as follows, For the value to be supplemented on the node to be interpolated, y t is the value at a certain time before the node to be interpolated, and y t-1 is the value at the previous time.
After supplementation, carrying out normalization calculation on the data, wherein the calculation formula of the normalization calculation is as follows (2):
Wherein, Representing the normalized boiler operation data of the boiler parameters,/>Is the mean value of the boiler operation data,/>And e, carrying out inverse normalization after finally obtaining output, wherein epsilon is a non-zero constant for the variance of the boiler operation data.
For any one data sample, the input parameters of the data sample are working state parameters of the boiler, including adjustable parameters and non-adjustable parameters, and the output parameters are the values of NO x emission.
Optionally, the adjustable parameters of the boiler comprise openings of secondary air baffles and a combustion air door of each layer of the boiler, and the non-adjustable parameters of the boiler comprise coal feeding amount of each layer of coal feeders of the boiler, total air quantity of the boiler and load of the boiler.
It should be noted that, the selection of the adjustable parameters and the non-adjustable parameters of the boiler can be set according to specific application scenarios and boiler types, and other types of adjustable parameters and non-adjustable parameters are also within the protection scope of the present invention.
In step S102, the plurality of data samples are clustered according to the input parameters of each data sample to obtain t subsets, and training is performed on the preset model through each subset to obtain t sub-models.
Specifically, in the first part of the step, clustering, through the SOFM model, the plurality of data samples according to the input parameters of each data sample, to obtain t subsets includes:
In the embodiment of the invention, a Self-organizing feature mapping algorithm (Self-Organizing Feature Map, SOFM) is an unsupervised clustering method. In this algorithm, when the external input mode is accepted, the external input mode is divided into different corresponding areas, each area has different response characteristics to the input mode, and the process is automatically completed. In contrast to conventional clustering methods, cluster centers formed in this way can be mapped onto curved surfaces or planes while preserving topology. The existing background of the power industry is that renewable energy sources are connected in a large scale, thermal power units are forced to frequently participate in peak shaving, and the depth is increased increasingly. Therefore, the boiler operation working condition is frequently changed in a large range and cannot be operated for a long time under a typical load, so that an SOFM algorithm is used for clustering a plurality of samples according to the input parameters of each data sample, and the method accords with the application scene that the boiler operation working condition is frequently changed in a large range.
First, according to formula (3), a sample x and a weight vector w j are input and the euclidean distance between them is calculated.
For a data sample, the inputs thereof form an input vector, and this step is used to calculate the Euclidean distance of the input vector and the weight vector for each data sample.
In addition to calculating the euclidean distance of the input vector of each sample to the weight, the cosine similarity of the input vector of each sample to the weight may also be calculated.
The weight vector w j refers to the weight vector of each neuron in the competitive layer corresponding to the input vector of the SOFM.
And a second step of: the weight vector is adjusted to modify the weight vector between all neurons in the vicinity of the competing layer and neurons in the input layer.
The adjustment process of the weight vector is as follows:
Firstly, normalizing all current input vector X of the SOFM network and weight vector W j (corresponding to j neurons) corresponding to each neuron in a competition layer, so that X and W j are 1; when the network obtains an input vector X, all the weight vectors corresponding to all the neurons of the competition layer are compared with the input vector X in similarity, and the most similar weight vector is judged as the competition winning neuron. Weights are adjusted based on formulas after the winning neurons are known.
Wherein j is: the number of the winning neuron;
o j: output of neurons;
W: the adjusted weight;
The weight before adjustment;
Wherein, eta is the learning rate, and the competition layer is fully connected with the input layer.
wij(t+1)=wij(t)+η(t)[xi(t)-wij(t)]
Where η (t) is the gain term, gradually approaching 0 over time, is generally requiredOr alternatively
After the weight vector is adjusted, the neurons tend to cluster centers, so that the purpose of judging which class the new sample belongs to can be achieved when the new sample is input.
And thirdly, calculating output is O k=f(min(dj)), and realizing clustering in sample data with larger load change.
Wherein f () is the Euclidean distance calculation formula.
And fourthly, after clustering, the samples with large load change are clustered and then divided into t sample sets (L 1、L2…Lt respectively) with small load change, so that each sub-model can be trained under relatively stable working conditions.
Specifically, the second part in this step trains the preset model through each sub-set, and the specific implementation process for obtaining t sub-models includes:
The adaptive multiscale kernel partial least squares (Self-adaptive Multi-scale KemelPartialLeastSquares, SMKPLS) introduces kernel functions into the partial least squares regression method. The nonlinear modeling of the original input space is realized by mapping the input space to a high-dimensional feature space through a nonlinear function, regarding the feature space as the dual of the original input space, and constructing a linear partial least squares regression in the feature space. SMKPLS have very good performance in handling nonlinear objects.
The coal-fired unit is one of thermal power units, and for NO x discharged by the unit, an SCR denitration control system is most commonly used. The reducing agent in the SCR utilizes ammonia to reduce nitrogen oxides discharged by the unit into nitrogen and water. The traditional SCR system can finish most denitration tasks, but the control quality of the SCR denitration control system is difficult to guarantee due to further improvement of the environmental protection requirement and the operation elasticity requirement of the current thermal power unit. The control quality of the SCR denitration control system directly influences the running cost and the denitration effect of the unit, so that the improvement of the control quality of the SCR denitration control system becomes a technical problem which needs to be solved currently.
Accurate prediction of NO x emission of a thermal power generating unit is a key for optimizing ammonia injection quantity and further improving control quality of an SCR denitration control system. The SCR reaction mechanism is complex, the process has the characteristics of large delay, multivariable coupling and the like, so that SMKPLS algorithm can be adopted for constructing the submodel.
In the embodiment of the invention, t sub-models are obtained in the following manner, and each sub-model is a prediction model and can be used for predicting the value of the emission amount of NO x.
The SMKPLS model was trained on the L 1,L2,…,Lt subset, resulting in the SM 1,…,SMt submodel.
Firstly, determining a multiscale Gaussian kernel function width sigma i (i=1, …, p), establishing a KPLS regression model by using a training sample, optimizing a parameter sigma i by using an optimization algorithm, calculating a fitting error as a precision evaluation index, and taking a parameter sigma i corresponding to the optimal precision model as an optimizing result.
The multi-scale Gaussian kernel function has different widths and a plurality of sigma, and the data fluctuation degree in each subset is considered to be different, so that the multi-scale Gaussian kernel function formed by the linear combination of different coefficients is adopted on each subset, the sum space of the regenerated kernel Hilbert space generated by the Gaussian kernels with different scales is taken as an assumed space, the learning is simultaneously and independently carried out through a least square regression algorithm, a local estimation is obtained, and finally, the overall estimation of the sample is obtained by weighting and synthesizing all the local estimates.
Second, SMKPLS modeling and prediction, selecting training samples, constructing a multi-scale Gaussian kernel function, and establishing a MKPLS model.
1) Calculating a kernel matrix by the formula (7)
Wherein phi (x l) refers to nonlinear mapping from an original data space to a feature space, and a multi-scale Gaussian kernel function is adopted for computing a kernel matrix element, and the expression is as follows (8):
where σ i (i=1, …, p) is the gaussian kernel width, x l (i) is any point in space, x l (j) is the kernel center, and σ l is the gaussian kernel width.
2) Randomly initializing a score vector u of Y;
Wherein Y is the output of the training.
3) The score vector t h for X in the feature space is calculated by equation (9) and normalized:
wherein phi h is the nonlinear mapping from training data space to feature space, K h is the corresponding kernel matrix of the training sample,
4) Calculating the weight vector c of Y h by the formula (10) h
ch=Yh Tth (10)
Wherein Y h is the fitting result of the training data.
5) Score vector u h of Y h is calculated by equation (11) and normalized
6) Repeating 3) to 5) until t h converges.
7) Shrinking the matrix K, Y according to equation (12) and equation (13), repeating 2) through 6) until p t, u are extracted.
Kh+1=Kh-thth TKh-Khthth T+thth TKhthth T (12)
Yh+1=Yh-thth TYh (13)
The training sample fitting formula is formula (14):
T, U is a matrix of score vectors t, u, The fitting result is obtained.
The predictive sample fitting formulas are formula (15) and formula (16):
Yt=KtU(TTKU)-1TTY (15)
Kt=Φ(xnew)Φ(x)T (16)
Where x new is newly sampled data, x is input training data, Y is output training data, K t is a kernel matrix corresponding to the new data, and Y t is a prediction result.
Thirdly, updating the model, wherein the process is as follows: let the window length be m, then the kernel matrix be K m×m, and the sliding length be n, i.e. n sample points need to be updated each time. The model updating process comprises the following steps: firstly deleting matrix elements corresponding to the n discarded samples, then changing the positions of reserved elements, finally calculating elements corresponding to the n new samples, and adding the elements into a core matrix to finish updating the model. And updating the model by adopting an adaptive model updating strategy and returning to the second step of the part.
Through the steps, t submodels are obtained.
In step 103, a target model is determined among t sub-models based on non-adjustable parameters of the boiler under a given operating condition.
In one possible implementation, the target model is determined by:
And according to the non-adjustable parameters of the boiler under the given working condition, sequentially calculating the membership value of the clustering center corresponding to each sub-model under the given working condition, and obtaining one sub-model with the largest membership as the target model.
Namely, the membership degree of the clustering center corresponding to each sub-model of the given working condition is obtained through the SOFM clustering model in the step 102 by the non-adjustable parameters of the given working condition, such as the coal feeding amount of each layer of coal feeders of the boiler, the total air quantity of the boiler and the load of the boiler.
The data samples in the t subsets in step 102 actually represent the data samples under different working conditions in t, and the load change under the same working condition is smaller.
And training the SMKPLS models through the t sub-models respectively to obtain t sub-models, wherein each model also corresponds to a working condition substantially, and the corresponding working condition is the same as the working condition represented by the subset for training the sub-models.
When a given working condition exists, the given working condition corresponds to a data sample, the non-adjustable parameters of the boiler under the given working condition are determined, and the membership degree of the data sample corresponding to the given working condition and the clustering center corresponding to each subset, namely the membership degree of the clustering center corresponding to each sub-model, can be obtained through the SOFM clustering model in step 102.
For example, in step 102, 3 subsets, namely subset 1, subset 2 and subset 3, are respectively used, each subset trains SMKPLS models to obtain a submodel, the submodel trained by subset 1 is submodel 1, the submodel trained by subset 2 is submodel 2, and the submodel trained by subset 3 is submodel 3.
And obtaining the membership degree of the non-adjustable parameters of the data sample under the given working condition and the clustering center of each sub-set through the step SOFM clustering model, namely the membership degree of the clustering center corresponding to the given working condition and each sub-model.
For example, the membership degree of the clustering center of the given working condition and the subset 1 is 0.7, the membership degree of the clustering center of the subset 2 is 0.2, and the membership degree of the clustering center of the subset 3 is 0.1, so that the membership degree of the clustering center of the given working condition and the subset 1, namely the highest membership degree of the clustering center of the sub-model 1, can be judged through the method, and the sub-model 1 is the target model in the step.
In step 104, the objective function is determined with the lowest emission of the outlet NO x of the boiler, and the adjustable parameters of the boiler are optimized according to the objective function and the objective model, so as to obtain the optimized values of the adjustable parameters of the boiler.
After the target model is obtained, the minimum emission amount of the outlet NO x of the boiler is used for determining a target function, and the adjustable parameters of the boiler are optimized according to the target function and the target model to obtain the optimized value of the adjustable parameters of the boiler, and the specific process is as follows:
Firstly, initializing a population size m, the number N of optimized variables, an optimized algebra t, the range of the optimized variables X, a forgetting factor w, a learning factor c and the like.
The fitness Q of the initial population in the second step is expressed as formula (17):
Wherein y (i) is the acquired ith output test data, y d (i) is the acquired identification output data under the action of the ith input, and m is the number of the acquired test data;
Third, optimal position of particle i: x besti=(xi1,xi2,...,xiN)
The best position of the adaptation value Q besti is expressed as formula (18):
fourth, the velocity v in and the position x in are updated according to the following equations (19) and (20), respectively:
vin(t+1)=ωvin(t)+c1r1[Xbestin-xin(t)]+c2r2[Xbestgn-xin(t)] (19)
xin(t+1)=xin(t)+vin(t+1) (20)
where v in is the velocity of the particle, X in is the position of the particle, ω is the inertial weight, c 1 is the acceleration factor, typically a value of 2, r 1 is a random number between 0 and 1, X bestin is the optimal position of the particle itself, and X bestgn is the optimal position of the whole population.
Fifthly, calculating new fitness of each particle in the population;
Sixth, comparing the values of X bestin and X bestgn, if the values are superior, replacing the values again;
The two values are updated in each iteration, and only the position of a certain particle is better than before, and the position of the whole population becomes better than the two values. The replacement means that the particles are replaced by a better result in iteration, the particle position is replaced by a better result, and the whole population is further better.
And seventh, judging whether the requirements of precision and evolution algebra are met, if so, jumping out of the loop, and if not, jumping to the fourth step to continue execution until the requirements are met, thereby realizing the optimization of the adjustable parameters of the boiler.
According to the embodiment of the invention, the data samples are obtained by processing the historical data, the data samples are clustered according to the input parameters of the data samples, a plurality of subsets are obtained, the sample load change in each subset is small, the preset model is trained through each subset to obtain one model corresponding to each working condition, the target model is determined through the non-adjustable parameters under the given working condition, and the adjustable parameters under the given working condition are optimized through the target model, so that the optimization of the boiler operation parameters under the scene with frequent load change is realized.
With reference to fig. 2, the embodiment of the invention further provides a method for controlling the emission amount of nitrogen oxides from a boiler, which comprises the following steps:
in step 201, a plurality of data samples are obtained according to the historical data, wherein the input parameter of each data sample is an operating state parameter of the boiler, including an adjustable parameter and an non-adjustable parameter, and the output parameter is a value of NO x emission.
In step 202, the plurality of data samples are clustered according to the input parameters of each data sample to obtain t subsets, and training is performed on the preset model through each subset to obtain t sub-models.
In step 203, a target model is determined among t sub-models according to non-adjustable parameters of the boiler under a given operating condition.
In step 204, the objective function is determined with the lowest emission of the outlet NO x of the boiler, and the adjustable parameters of the boiler are optimized according to the objective function and the objective model, so as to obtain the optimized values of the adjustable parameters of the boiler.
The specific implementation process of the above steps 201 to 204 may refer to steps 101 to 104, which are not repeated in the embodiments of the present invention.
In step 205, according to the non-adjustable parameters of the boiler under the given working condition, sequentially calculating the membership value of the clustering center corresponding to each sub-model under the given working condition, obtaining a sub-model with the largest membership as a target model, and according to the input parameters of the boiler under the given working condition and the target model, obtaining the predicted value of the NO x emission under the given working condition; or obtaining the predicted value of the NO x emission under the given working condition according to the input parameters of the boiler under the given working condition, the membership value of the clustering center corresponding to each sub-model under the given working condition and each sub-model.
In some embodiments, the input parameters of the boiler under the given working condition may be directly input into the target model to obtain the predicted value of NO x.
In some embodiments, the predicted value of the NO x emission under the given working condition may be obtained according to the input parameter of the boiler under the given working condition, the value of the membership degree of the clustering center corresponding to each sub-model under the given working condition, and each sub-model, for example:
Obtaining a predicted value of NO x emission under a given working condition according to a first formula, wherein the first formula is as follows (21)
Wherein g (-) represents an integrated model, f k (-) represents a kth submodel, a value of membership degree of a clustering center corresponding to the kth submodel under a given working condition is represented, and x represents an input parameter of a data sample under the given working condition.
In some embodiments, if the membership value of the clustering center of the given working condition and the target model is greater than or equal to the preset threshold, the input parameters of the boiler under the given working condition may be directly input into the target model, so as to obtain the predicted value of NO x.
In some embodiments, if the membership of the cluster center corresponding to the given working condition and the target model is smaller than or equal to a preset threshold, that is, the membership of the cluster center corresponding to each sub-model in the given working condition is smaller than a preset threshold, that is, the preset threshold is 0.7, and the membership of the cluster center corresponding to each sub-model in the given working condition is smaller than 0.7, the predicted value of the NO x emission in the given working condition can be obtained according to the input parameters of the boiler in the given working condition, the membership of the cluster center corresponding to each sub-model in the given working condition, and each sub-model.
The embodiment of the invention provides a control method for the emission of nitrogen oxides of a boiler, which predicts the emission of NO x under a given working condition through a sub-model with the highest membership degree with the given working condition, or predicts the emission of NO x under the given working condition through each sub-model and the membership degree of a clustering center corresponding to the given working condition and each sub-model and an integrated model, thereby improving the accuracy of the prediction of the emission of NO x
With reference to fig. 3, the embodiment of the invention further provides a method for controlling the emission amount of nitrogen oxides from a boiler, which comprises the following steps:
in step 301, the variation of the discharge amount from the current time to the next time NO x of the boiler outlet is obtained according to the actual discharge amount of the current time NO x of the boiler and the predicted discharge amount of the next time NO x of the boiler.
The process of obtaining the predicted value of the emission amount of NO x at the next time can refer to the embodiment corresponding to fig. 2, and the embodiment of the present invention will not be described again.
In step 302, the amount of change in the ammonia injection amount of the denitration system is determined according to the amount of change in the NO x emission amount, the denitration efficiency of the denitration system, and the flue gas flow of the boiler.
Optionally, the variation of the ammonia injection amount of the denitration system is obtained according to a second formula (22) as follows
Wherein Deltay is the variation of ammonia spraying amount of the denitration system, deltac NOx is the variation of NO x emission amount from the current moment to the next moment of a boiler outlet, deltac NOx is mg/Nm 3, eta is denitration efficiency of the denitration system, Q is flue gas flow of the boiler, Q is m 3/h,Is NH 3 molar mass,/>Is the molar mass of NO x.
In step 303, the amount of change in the valve opening of the ammonia injection valve is obtained from the amount of change in the ammonia injection amount of the denitration system.
In some embodiments, the variation of the valve opening is obtained according to a third formula, wherein the third formula is formula (23)
Wherein delta n is the variation of the valve opening, and b and k are preset fitting coefficients.
Further, the method further comprises: obtaining a target value of ammonia spraying amount according to a predicted value of NO x emission amount of the boiler at the next moment, denitration efficiency of a denitration system and flue gas flow of the boiler; obtaining a target value of the valve opening according to the target value of the ammonia injection amount; and performing PID control on the valve opening according to the target value of the valve opening and the value of the valve opening at the current moment so as to enable the valve opening of the ammonia injection valve at the next moment to be the target value.
According to the embodiment of the invention, the accurate prediction of the emission amount at the next moment is used for controlling the ammonia injection amount, namely the opening degree of the ammonia injection valve, so that the real-time processing capability of the denitration system on NO x is improved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
The following are device embodiments of the invention, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 4 shows a schematic structural diagram of a boiler nitrogen oxide emission control device 4 according to an embodiment of the present invention, and for convenience of explanation, only the portions related to the embodiment of the present invention are shown, and the details are as follows:
As shown in fig. 4, the boiler nitrogen oxide emission control device 4 includes: a data sample acquisition unit 41, a clustering and training unit 42, a target model determination unit 43 and an adjustable parameter optimizing unit 44;
A data sample obtaining unit 41, configured to obtain a plurality of data samples according to historical data, where an input parameter of each data sample is an operating state parameter of the boiler, including an adjustable parameter and an non-adjustable parameter, and an output parameter is a value of NO x emission;
the clustering and training unit 42 is configured to cluster a plurality of data samples according to the input parameters of each data sample to obtain t subsets, and train the preset model through each subset to obtain t sub-models;
a target model determining unit 43, configured to determine a target model from t sub-models according to an unadjustable parameter of the boiler under a given working condition;
And the adjustable parameter optimizing unit 44 is configured to determine an objective function with the lowest emission amount of the outlet NO x of the boiler, and optimize the adjustable parameter of the boiler according to the objective function and the objective model, so as to obtain an optimized value of the adjustable parameter of the boiler.
According to the method, the historical data are processed to obtain the data samples, the data samples are clustered according to the input parameters of the data samples to obtain a plurality of subsets, the sample load in each subset is small in change, the preset model is trained through each subset to obtain a model corresponding to each sub-working condition, the target model is determined through the non-adjustable parameters under the given working condition, the adjustable parameters under the given working condition are optimized through the target model, and therefore optimization of the boiler operation parameters under the scene with frequent load change is achieved.
In one possible implementation, the adjustable parameters of the boiler include the opening degree of each layer of overgrate air baffle and each layer of exhaust air door of the boiler, and the non-adjustable parameters of the boiler include the coal feeding amount of each layer of coal feeder of the boiler, the total air quantity of the boiler and the load of the boiler.
In one possible implementation manner, the target model determining unit 43 is configured to sequentially calculate, according to the non-adjustable parameters of the boiler under the given working condition, a value of a membership degree of a clustering center corresponding to each sub-model under the given working condition, and obtain, as the target model, a sub-model with the largest membership degree.
In a possible implementation manner, the device further comprises a prediction unit 45, configured to obtain a predicted value of NO x emission under a given working condition according to an input parameter of the boiler under the given working condition and a target model;
Or obtaining the predicted value of the NO x emission under the given working condition according to the input parameters of the boiler under the given working condition, the membership value of the clustering center corresponding to each sub-model under the given working condition and each sub-model.
In one possible implementation, the prediction unit 45 is configured to obtain the predicted value of the NO x emission under the given working condition according to a first formula, where the first formula is
Wherein g (-) represents an integrated model, f k (-) represents a kth submodel, a value of membership degree of a clustering center corresponding to the kth submodel under a given working condition is represented, and x represents an input parameter of a data sample under the given working condition.
In a possible implementation manner, the device further comprises an ammonia injection control unit 46, configured to obtain a variation of the emission amount of NO x from the current moment to the next moment of the boiler outlet according to the actual emission amount of NO x at the current moment of the boiler and the predicted emission amount of NO x at the next moment;
Determining the variation of the ammonia spraying amount of the denitration system according to the variation of the NO x emission amount, the denitration efficiency of the denitration system and the flue gas flow of the boiler;
and obtaining the variable quantity of the valve opening of the ammonia spraying valve according to the variable quantity of the ammonia spraying quantity of the denitration system.
The ammonia injection control unit 46 is further configured to obtain the variation of the ammonia injection amount of the denitration system according to a second formula, where the second formula is
Wherein Deltay is the variation of ammonia spraying amount of the denitration system, deltac NOx is the variation of NO x emission amount from the current moment to the next moment of a boiler outlet, deltac NOx is mg/Nm 3, eta is denitration efficiency of the denitration system, Q is flue gas flow of the boiler, Q is m 3/h,Is NH 3 molar mass,/>Is the molar mass of NO x;
obtaining the variation of the valve opening according to a third formula, wherein the third formula is that
Wherein delta n is the variation of the valve opening, and b and k are preset fitting coefficients.
In a possible implementation manner, the ammonia injection control unit 46 is further configured to obtain a target value of the ammonia injection amount according to a predicted value of the NO x emission amount of the boiler at a next moment, the denitration efficiency of the denitration system, and the flue gas flow of the boiler;
obtaining a target value of the valve opening according to the target value of the ammonia injection amount;
And performing PID control on the valve opening according to the target value of the valve opening and the value of the valve opening at the current moment so as to enable the valve opening of the ammonia injection valve at the next moment to be the target value.
The device for controlling the emission of nitrogen oxides in the boiler provided in this embodiment may be used to implement the embodiment of the method for controlling the emission of nitrogen oxides in the boiler, and its implementation principle and technical effects are similar, and this embodiment will not be described here again.
Fig. 5 is a schematic diagram of a terminal according to an embodiment of the present invention. As shown in fig. 5, the terminal 5 of this embodiment includes: a processor 50, a memory 51 and a computer program 52 stored in said memory 51 and executable on said processor 50. The processor 50, when executing the computer program 52, performs the steps of the various boiler nox emission control method embodiments described above, such as steps 101 through 104 shown in fig. 1. Or the processor 50, when executing the computer program 52, performs the functions of the modules/units of the device embodiments described above, such as the functions of the units 41 to 46 shown in fig. 4.
By way of example, the computer program 52 may be partitioned into one or more modules/units that are stored in the memory 51 and executed by the processor 50 to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions describing the execution of the computer program 52 in the terminal 5.
The terminal 5 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The terminal 5 may include, but is not limited to, a processor 50, a memory 51. It will be appreciated by those skilled in the art that fig. 5 is merely an example of the terminal 5 and is not limiting of the terminal 5, and may include more or fewer components than shown, or may combine some components, or different components, e.g., the terminal may further include input and output devices, network access devices, buses, etc.
The Processor 50 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 51 may be an internal storage unit of the terminal 5, such as a hard disk or a memory of the terminal 5. The memory 51 may also be an external storage device of the terminal 5, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the terminal 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the terminal 5. The memory 51 is used for storing the computer program as well as other programs and data required by the terminal. The memory 51 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other manners. For example, the apparatus/terminal embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may also be implemented by implementing all or part of the flow of the method of the above embodiment, or by instructing the relevant hardware by a computer program, where the computer program may be stored in a computer readable storage medium, and the computer program may be executed by a processor, where the steps of the method embodiment of controlling the emission amount of nitrogen oxides from each boiler are implemented. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium may include content that is subject to appropriate increases and decreases as required by jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is not included as electrical carrier signals and telecommunication signals.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (10)
1. A method for controlling nitrogen oxide emissions from a boiler, comprising:
Acquiring a plurality of data samples according to historical data, wherein the input parameter of each data sample is a working state parameter of a boiler, the working state parameter comprises an adjustable parameter and an unadjustable parameter, and the output parameter is a value of NO x emission;
clustering the plurality of data samples according to the input parameters of each data sample to obtain t subsets, and training a preset model through each subset to obtain t sub-models;
Determining a target model in the t sub-models according to the non-adjustable parameters of the boiler under the given working condition;
And determining an objective function according to the lowest emission of the NO x at the outlet of the boiler, and optimizing the adjustable parameters of the boiler according to the objective function and the objective model to obtain the optimized value of the adjustable parameters of the boiler.
2. The method of claim 1, wherein the adjustable parameters of the boiler comprise secondary air baffles and a full air door opening of each layer of the boiler, and the non-adjustable parameters of the boiler comprise a coal feeding amount of each layer of coal feeders of the boiler, a total air quantity of the boiler and a load of the boiler.
3. The method of claim 1, wherein determining at least one sub-model as a target model based on non-adjustable parameters of the boiler for a given operating condition comprises:
And according to the non-adjustable parameters of the boiler under the given working condition, sequentially calculating the membership value of the clustering center corresponding to each sub-model under the given working condition, and obtaining one sub-model with the largest membership as the target model.
4. A method according to claim 3, characterized in that the method further comprises:
Obtaining a predicted value of NO x emission under the given working condition according to the input parameters of the boiler under the given working condition and the target model;
Or obtaining the predicted value of the NO x emission under the given working condition according to the input parameters of the boiler under the given working condition, the membership value of the clustering center corresponding to each sub-model under the given working condition and each sub-model.
5. The method of claim 4, wherein the obtaining the predicted value of the NO x emission under the given condition according to the input parameter of the boiler under the given condition, the value of the membership degree of the cluster center corresponding to each sub-model under the given condition, and each sub-model includes:
obtaining a predicted value of NO x emission under the given working condition according to a first formula, wherein the first formula is that
Wherein g (-) represents an integrated model, f k (-) represents a kth submodel, a value representing membership degree of a clustering center corresponding to the kth submodel under the given working condition, and x represents an input parameter of a data sample under the given working condition.
6. The method of claim 4, further comprising:
Obtaining the variation of the discharge amount from the current moment to the next moment NO x of the boiler outlet according to the actual value of the discharge amount of the boiler at the current moment NO x and the predicted value of the discharge amount of the boiler at the next moment NO x;
Determining the variation of the ammonia spraying amount of the denitration system according to the variation of the NO x emission amount, the denitration efficiency of the denitration system and the flue gas flow of the boiler;
and obtaining the variation of the valve opening of the ammonia spraying valve according to the variation of the ammonia spraying amount of the denitration system.
7. The method of claim 6, wherein the determining the amount of change in the ammonia injection amount of the denitration system based on the amount of change in the NO x discharge amount from the boiler outlet, the denitration efficiency of the denitration system, and the flue gas flow amount from the boiler comprises:
Obtaining the variation of the ammonia spraying amount of the denitration system according to a second formula, wherein the second formula is that
Wherein Deltay is the variation of ammonia spraying amount of the denitration system, deltac NOx is the variation of NO x emission amount from the current moment to the next moment of the boiler outlet, deltac NOx is mg/Nm 3, eta is the denitration efficiency of the denitration system, Q is the flue gas flow of the boiler, Q is m 3/h,Is NH 3 molar mass,/>Is the molar mass of NO x;
the obtaining the variation of the valve opening of the ammonia spraying valve according to the variation of the ammonia spraying amount of the denitration system comprises the following steps: obtaining the variation of the valve opening according to a third formula, wherein the third formula is that
Wherein delta n is the variation of the valve opening, and b and k are preset fitting coefficients.
8. The method of claim 6, wherein the method further comprises:
Obtaining a target value of ammonia spraying amount according to a predicted value of NO x emission of the boiler at the next moment, denitration efficiency of the denitration system and flue gas flow of the boiler;
Obtaining a target value of the valve opening according to the target value of the ammonia injection amount;
And performing PID control on the valve opening according to the target value of the valve opening and the valve opening value at the current moment so that the valve opening of the ammonia injection valve at the next moment is the target value.
9. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of the preceding claims 1 to 8 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any of the preceding claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111334994.7A CN114065100B (en) | 2021-11-11 | 2021-11-11 | Boiler nitrogen oxide emission control method, terminal and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111334994.7A CN114065100B (en) | 2021-11-11 | 2021-11-11 | Boiler nitrogen oxide emission control method, terminal and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114065100A CN114065100A (en) | 2022-02-18 |
CN114065100B true CN114065100B (en) | 2024-06-14 |
Family
ID=80275618
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111334994.7A Active CN114065100B (en) | 2021-11-11 | 2021-11-11 | Boiler nitrogen oxide emission control method, terminal and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114065100B (en) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108985381A (en) * | 2018-07-25 | 2018-12-11 | 广东工业大学 | The determination method, device and equipment of nitrogen oxide emission prediction model |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111596548B (en) * | 2020-05-29 | 2023-04-07 | 华润电力技术研究院有限公司 | Boiler secondary air regulating and controlling method, device, equipment and medium |
CN111765445B (en) * | 2020-07-01 | 2021-10-15 | 河北工业大学 | Boiler on-line combustion optimization control method and system and computer equipment |
CN112651568A (en) * | 2020-12-31 | 2021-04-13 | 新奥数能科技有限公司 | Boiler load dynamic adjustment method and device, control terminal and storage medium |
CN113628694A (en) * | 2021-07-05 | 2021-11-09 | 国能国华(北京)电力研究院有限公司 | Method for predicting discharge amount of nitrogen oxides of boiler |
-
2021
- 2021-11-11 CN CN202111334994.7A patent/CN114065100B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108985381A (en) * | 2018-07-25 | 2018-12-11 | 广东工业大学 | The determination method, device and equipment of nitrogen oxide emission prediction model |
Non-Patent Citations (1)
Title |
---|
四角切圆燃煤锅炉低NO_x燃烧优化研究;周建新;仇晓智;司风琪;徐治皋;;热能动力工程;20090320(第02期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114065100A (en) | 2022-02-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106600059B (en) | Intelligent power grid short-term load prediction method based on improved RBF neural network | |
CN111027772A (en) | Multi-factor short-term load prediction method based on PCA-DBILSTM | |
CN112884236B (en) | Short-term load prediction method and system based on VDM decomposition and LSTM improvement | |
CN110708318A (en) | Network abnormal flow prediction method based on improved radial basis function neural network algorithm | |
CN113469426A (en) | Photovoltaic output power prediction method and system based on improved BP neural network | |
CN111709454B (en) | Multi-wind-field output clustering evaluation method based on optimal copula model | |
CN111860701B (en) | Denitration system working condition discrimination preprocessing method based on clustering method | |
CN108985381A (en) | The determination method, device and equipment of nitrogen oxide emission prediction model | |
CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
CN114399032A (en) | Method and system for predicting metering error of electric energy meter | |
CN110020712A (en) | A kind of optimization population BP neural network forecast method and system based on cluster | |
CN113722980A (en) | Ocean wave height prediction method, system, computer equipment, storage medium and terminal | |
US20230351180A1 (en) | Quantization recognition training method of neural network that supplements limitations of gradient-based learning by adding gradient-indipendent update | |
CN111709585A (en) | Air conditioner load prediction method and device and storage medium | |
CN114065100B (en) | Boiler nitrogen oxide emission control method, terminal and storage medium | |
CN116722541A (en) | Power system load prediction method and device based on convolutional neural network | |
CN116205135A (en) | SO based on data decomposition and neural network 2 Emission prediction method and system | |
CN116108975A (en) | Method for establishing short-term load prediction model of power distribution network based on BR-SOM clustering algorithm | |
CN115423149A (en) | Incremental iterative clustering method for energy internet load prediction and noise level estimation | |
CN111709578A (en) | Short-time ship traffic flow prediction method and device and storage medium | |
CN116432507A (en) | Method and device for predicting oxygen content of boiler flue gas and computing equipment | |
CN113919871A (en) | Carbon transaction price prediction method based on improved LSTM model | |
CN110543724A (en) | Satellite structure performance prediction method for overall design | |
Ivakhnenko | Short-Term Process Forecasting by Analogues Complexing GMDH Algorithm | |
CN114943360A (en) | Neural network prediction photovoltaic short-term power generation method based on improved particle swarm |
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 |