CN116665808A - NOx emission prediction method and device based on neighborhood rough set and fuzzy neural network - Google Patents
NOx emission prediction method and device based on neighborhood rough set and fuzzy neural network Download PDFInfo
- Publication number
- CN116665808A CN116665808A CN202310572071.8A CN202310572071A CN116665808A CN 116665808 A CN116665808 A CN 116665808A CN 202310572071 A CN202310572071 A CN 202310572071A CN 116665808 A CN116665808 A CN 116665808A
- Authority
- CN
- China
- Prior art keywords
- nox
- fuzzy
- neural network
- attribute
- data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000013507 mapping Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 23
- 230000015654 memory Effects 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 12
- 239000003245 coal Substances 0.000 claims description 10
- 230000007812 deficiency Effects 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 6
- 239000000779 smoke Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 238000011946 reduction process Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims 1
- 238000002485 combustion reaction Methods 0.000 abstract description 6
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 4
- 229910021529 ammonia Inorganic materials 0.000 abstract description 2
- 238000013499 data model Methods 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract description 2
- 238000002347 injection Methods 0.000 abstract description 2
- 239000007924 injection Substances 0.000 abstract description 2
- 239000007789 gas Substances 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000003344 environmental pollutant Substances 0.000 description 3
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 231100000719 pollutant Toxicity 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 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
- 239000013307 optical fiber Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
- G01N33/0037—NOx
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
- G01N33/0068—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a computer specifically programmed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Analytical Chemistry (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Combustion & Propulsion (AREA)
- Biochemistry (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Mathematical Physics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Fuzzy Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Automation & Control Theory (AREA)
- Databases & Information Systems (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
Abstract
The invention provides a NOx emission prediction method and equipment based on a neighborhood rough set and a fuzzy neural network, wherein the method selects parameters affecting NOx generation by using operation data acquired by a DCS (distributed control system) of a circulating fluidized bed power plant by adopting a neighborhood rough set method, extracts an input parameter set of data modeling, removes redundant information in the input parameter set by adopting characteristic selection of an algorithm, retains important characteristic relation in original information, further reduces the input quantity number of a data model and reduces the number of fuzzy rules; the nonlinear mapping relation between the input parameters and the NOx generation amount is established through the fuzzy neural network, fuzzy reasoning is fully combined, the regulation law affecting the NOx generation is intuitively known, the regulation experience for controlling the NOx emission is accumulated, and the method can be further used as a reference basis for boiler combustion optimization and precise ammonia injection optimization of an SCR denitration system.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to a NOx emission prediction method, device, equipment and storage medium based on a neighborhood rough set and a fuzzy neural network.
Background
The circulating fluidized bed unit is used as a main emission source of pollutant gas, and has important significance of energy conservation and emission reduction for establishing an accurate pollutant gas emission prediction model. Nitrogen oxides NOx must be further appreciated as the most hazardous pollutant in combustion emissions.
The complex combustion process of the circulating fluidized bed causes factors influencing the generation of NOx to also show strong coupling, so that an accurate mechanism model is difficult to build, and a data modeling method is adopted nowadays. A neural network model, a support vector machine model, a long-term and short-term memory neural network model and the like for predicting NOx emission are established by combining field measurement data with an artificial intelligence method. Although each prediction model shows good prediction effect, the data driving model is a black box model, so that the operation rule affecting the NOx emission is not easy to learn, and the operator is not facilitated to obtain more instructive regulation measures for preventing the NOx gas emission. In addition, when facing high-dimensional data, the modeling process and the model training time can be continuously increased, and the demand of timely prediction of the model is affected.
Disclosure of Invention
The invention provides a NOx emission prediction method, device, equipment and storage medium based on a neighborhood rough set and a fuzzy neural network, and aims to realize accurate prediction of NOx generation amount of a circulating fluidized bed unit under different running conditions.
To this end, a first object of the present invention is to propose a method for predicting NOx emissions based on a neighborhood rough set and a fuzzy neural network, comprising:
collecting NOx concentration historical data in a specified time period and corresponding historical operating parameters related to NOx generation from a DCS (distributed control system) of a circulating fluidized bed boiler unit; wherein, the historical data of the NOx concentration is marked as a target parameter, and the corresponding historical operation parameter related to the generation of NOx is marked as a characteristic parameter;
screening the characteristic parameters through a neighborhood rough set algorithm, and removing the characteristic parameters with low importance; taking the target parameters and the screened characteristic parameters as model training set data;
establishing a NOx emission prediction model based on a fuzzy neural network of Takagi-Sugeno, and training the NOx emission prediction model through model training set data;
and inputting the screened characteristic parameters acquired in the period to be predicted into a trained NOx emission prediction model, and outputting a result, namely, predicting the corresponding NOx generation concentration.
Wherein the types of the corresponding historical operating parameters related to the generation of NOx at least include: coal quality, unit load, smoke quantity, smoke temperature, main steam flow, opening degree of a secondary air door baffle, secondary air pressure, secondary air quantity, rotating speed of each coal feeder, coal feeding quantity and air distribution mode.
Wherein, after the step of collecting the data, the method further comprises the step of preprocessing the data; the method specifically comprises the following steps:
deficiency value complement; the method comprises the steps of carrying out mean value complementation by utilizing data before and after a single point when the single point is in a deficiency state, and carrying out complementation by utilizing an interpolation method when the continuous multipoint is in a deficiency state;
removing bad values;
normalizing the data; the data normalization method comprises the following formula:
x in the formula represents a characteristic parameter.
Wherein, the characteristic parameters are screened by a neighborhood rough set algorithm, in the step of removing the characteristic parameters with lower importance,
an information system IS= < U, A, V, f >; wherein A represents a set of attributes; v represents a range of values and,f, U is multiplied by A to V as a function, and represents the mapping relation between the sample and the attribute value; c is a conditional attribute; d is a decision attribute; and a=c u D; then for any x i E, U, defining the neighborhood as:
δ(x)={y∣Δ(x,y),,δ,y∈U}
wherein delta is the neighborhood radius; delta (x) is a neighborhood particle of x; delta employs a P-norm distance function:
based on the calculation result, obtaining the upper approximation, the lower approximation and the boundary of the neighborhood rough set of the characteristic parameters:
the attribute reduction process based on the neighborhood rough set algorithm is realized by judging the necessity of the attribute in a decision system, and the importance degree of the attribute needs to be calculated in a specific realization way. Assume thatIf meeting gamma B (D)≠γ B-{a} (D) It is indicated that attribute a is necessary in set B to decide attribute D. If any of the attributes a in set B have such a relationship, set B is independent from D. Wherein, gamma B (D) The attribute dependence can be calculated by the following formula:
when (when)a ε C-B, then the attribute importance of a with respect to B and D is:
SIG(a,B,D)=γ B (D)-γ B-(a) (D)
combining the definition of the neighborhood rough set and the attribute of the attribute Jian Suanfa, and obtaining a characteristic parameter reduction set influencing NOx emission by adopting a mode of adding the condition attribute forward according to the attribute importance information.
In the process of establishing a NOx emission prediction model based on a Takagi-Sugeno fuzzy neural network, an input vector is set as X= [ X ] 1 ,x 2 ,...,x n ] T Wherein each component x i Are all fuzzy linguistic variables and have Represents x i A j-th language variable value of (a); the value is defined in the field +.>A fuzzy set on the corresponding membership function is +.>Also for the output y, the fuzzy linguistic variable T (y) = { B 1 ,B 2 ,...,B m },B j The j-th linguistic variable representing y, which is defined in the discourse domain U y Fuzzy set of the above, its membership function is +.>
The output of the fuzzy rule in this model is a linear combination of input variables, expressed as follows:
R j :if x 1 isand x 2 is/>and…and x n is/>then B j =p j0 +p j1 x 1 +...+p jn x n
in the above
Wherein the NOx emission prediction model is of a 5-layer structure, wherein,
the first layer is an input layer and is used for transmitting input parameters of the fuzzy neural network to a next fuzzy layer; the formula is:
wherein i=1, 2, n; n is the number of input parameters;
the second layer is a fuzzification layer for fuzzifying the input parameters and calculating the membership value of each input parameter; the formula is:
where i=1, 2, n, j=1, 2, m; c ij And delta ij The center and width of the gaussian function are shown, respectively;
the third layer is a fuzzy reasoning layer and is used for generating fuzzy rules and calculating the fitness value of each rule; the formula is:
where w=1, 2, the first and second parameters, m,
the fourth layer is a normalization layer and is used for carrying out normalization operation on the fitness of each rule; the formula is:
wherein j=1, 2, …, m;
the fifth layer is an output layer and is used for calculating the weighted sum of all outputs of the normalization layer; the formula is:
wherein i=1, 2, …, r, w ij Representing y i The j-th language value of (c) is the central value of the membership function.
In the step of training the NOx emission prediction model through the model training set data, a mixed learning algorithm is adopted to optimize and adjust parameters in the NOx emission prediction model.
A second object of the present invention is to provide a NOx emission prediction apparatus based on a neighborhood rough set and a fuzzy neural network, comprising:
the data acquisition module is used for acquiring NOx concentration historical data and corresponding historical operating parameters related to NOx generation in a specified time period from a DCS (distributed control system) system of the circulating fluidized bed boiler unit; wherein, the historical data of the NOx concentration is marked as a target parameter, and the corresponding historical operation parameter related to the generation of NOx is marked as a characteristic parameter;
the data screening module screens the characteristic parameters through a neighborhood rough set algorithm and removes the characteristic parameters with lower importance; taking the target parameters and the screened characteristic parameters as model training set data;
the model building module is used for building a NOx emission prediction model based on a Takagi-Sugeno fuzzy neural network and training the NOx emission prediction model through model training set data;
the prediction module is used for inputting the screened characteristic parameters acquired in the period to be predicted into the NOx emission prediction model after training, and outputting the result, namely, the corresponding NOx generation concentration prediction.
A third object of the present invention is to propose an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of the preceding claims.
A fourth object of the invention is to propose a non-transitory computer-readable storage medium storing computer instructions for causing a computer to carry out the steps of the method according to the preceding claims.
Compared with the prior art, the NOx emission prediction method based on the neighborhood rough set and the fuzzy neural network provided by the invention utilizes the operation data acquired by the DCS system of the circulating fluidized bed power plant, adopts the neighborhood rough set method to select parameters affecting the generation of NOx, extracts the input parameter set of data modeling, removes redundant information in the input parameter set through the feature selection of the algorithm, retains important feature relation in original information, further reduces the input quantity number of a data model, and reduces the number of fuzzy rules; the nonlinear mapping relation between the input parameters and the NOx generation amount is established through the fuzzy neural network, fuzzy reasoning is fully combined, the regulation law affecting the NOx generation is intuitively known, the regulation experience for controlling the NOx emission is accumulated, and the method can be further used as a reference basis for boiler combustion optimization and precise ammonia injection optimization of an SCR denitration system.
Drawings
The invention and/or additional aspects and advantages will be apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flow chart of a NOx emission prediction method based on a neighborhood rough set and a fuzzy neural network.
Fig. 2 is a schematic flow chart of an attribute reduction algorithm based on a neighborhood rough set in a NOx emission prediction method based on the neighborhood rough set and a fuzzy neural network.
FIG. 3 is a schematic diagram of a structure of a NOx emission prediction model constructed in a NOx emission prediction method based on a neighborhood rough set and a fuzzy neural network.
FIG. 4 is a schematic diagram of a structure of a NOx emission prediction device based on a neighborhood rough set and a fuzzy neural network.
Fig. 5 is a schematic diagram of a non-transitory computer readable storage medium storing computer instructions according to the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
Referring to fig. 1, a processing logic of a method for predicting NOx emission based on a neighborhood rough set and a fuzzy neural network according to an embodiment of the present invention is shown in fig. 2. The method comprises the following steps:
s110: and collecting NOx concentration historical data and corresponding historical operating parameters related to NOx generation in a specified time period from a DCS (distributed control system) of the circulating fluidized bed boiler unit.
The invention also includes the step of determining a set of parameters affecting NOx gas production by theoretical analysis of the NOx production mechanism prior to data collection. Specifically, factors influencing the generation of NOx gas include the content of nitrogen element and the environmental condition of combustion reaction, and can be specifically classified into coal quality, excess air ratio, bed temperature and combustion mode.
And collecting the NOx concentration and the determined operating parameter values related to the NOx generation in a specified time period from a DCS system of the circulating fluidized bed boiler unit, and taking the NOx concentration and the determined operating parameter values related to the NOx generation as NOx concentration historical data and corresponding historical operating parameters related to the NOx generation in the specified time period.
The acquired parameters include: coal quality, unit load, smoke quantity, smoke temperature, main steam flow, opening degree of a secondary air door baffle, secondary air pressure, secondary air quantity, rotating speed of each coal feeder, coal feeding quantity, air distribution mode and NOx concentration. Wherein the NOx concentration is marked as a target parameter and the remaining marks as characteristic parameters.
S120: screening the characteristic parameters through a neighborhood rough set algorithm, and removing the characteristic parameters with low importance; and taking the target parameters and the screened characteristic parameters as model training set data.
After the step of collecting the data, the method further comprises the step of preprocessing the data; the method specifically comprises the following steps:
deficiency value complement; the method comprises the steps of carrying out mean value complementation by utilizing data before and after a single point when the single point is in a deficiency state, and carrying out complementation by utilizing an interpolation method when the continuous multipoint is in a deficiency state;
removing bad values;
normalizing the data; the data normalization method comprises the following formula:
x in the formula represents a characteristic parameter.
Aiming at the characteristics of large data sample size and numerical data of the circulating fluidized bed unit, the invention provides a neighborhood rough set reduction method for carrying out attribute reduction on characteristic parameters influencing NOx gas generation. Wherein the distance is calculated using the P-norm.
The correlation of the neighborhood rough set is defined as follows:
an information system IS= < U, A, V, f >; wherein A represents a set of attributes; v represents a value range, and f is U multiplied by A to V which is a function and represents the mapping relation between the sample and the attribute value; c is a conditional attribute; d is a decision attribute; and a=c u D; then for any x i E, U, defining the neighborhood as:
δ(x)={y∣Δ(x,y),,δ,y∈U}
wherein delta is the neighborhood radius; delta (x) is a neighborhood particle of x; delta employs a P-norm distance function:
based on the calculation result, obtaining the upper approximation, the lower approximation and the boundary of the neighborhood rough set of the characteristic parameters:
the attribute reduction process based on the neighborhood rough set algorithm is realized by judging the necessity of the attribute in a decision system, and the importance degree of the attribute needs to be calculated in a specific realization way. Assume thatIf meeting gamma B (D)≠γ B-{a} (D) It is indicated that attribute a is necessary in set B to decide attribute D. If any of the attributes a in set B have such a relationship, set B is independent from D. Wherein, gamma B (D) The attribute dependence can be calculated by the following formula:
when (when)a E C-B, thenThe attribute importance of a with respect to B and D is:
SIG(a,B,D)=γ B (D)-γ B-(a) (D)
combining the definition of the neighborhood rough set and the attribute of the attribute Jian Suanfa, and obtaining a characteristic parameter reduction set influencing NOx emission by adopting a mode of adding the condition attribute forward according to the attribute importance information. The flow chart of the attribute reduction algorithm based on the neighborhood rough set is shown in fig. 2.
S130: a NOx emission prediction model is established based on a Takagi-Sugeno fuzzy neural network, and the NOx emission prediction model is trained through model training set data.
In the establishment of a NOx emission prediction model based on a Takagi-Sugeno fuzzy neural network, an input vector is set as X= [ X ] 1 ,x 2 ,...,x n ] T Wherein each component x i Are all fuzzy linguistic variables and have Represents x i A j-th language variable value of (a); the value is defined in the field +.>A fuzzy set on the corresponding membership function is +.>Also for the output y, the fuzzy linguistic variable T (y) = { B 1 ,B 2 ,...,B m },B j The j-th linguistic variable representing y, which is defined in the discourse domain U y Fuzzy set of the above, its membership function is +.>
The output of the fuzzy rule in this model is a linear combination of input variables, expressed as follows:
R j :if x 1 isand x 2 is/>and…and x n is/>then B j =p j0 +p j1 x 1 +...+p jn x n
in the above
As shown in fig. 3, the NOx emission prediction model is a 5-layer structure, in which,
the first layer is an input layer and is used for transmitting input parameters of the fuzzy neural network to a next fuzzy layer; the formula is:
wherein i=1, 2, n; n is the number of input parameters;
the second layer is a fuzzification layer for fuzzifying the input parameters and calculating the membership value of each input parameter; the formula is:
where i=1, 2, n, j=1, 2, m; c ij And delta ij The center and width of the gaussian function are shown, respectively;
the third layer is a fuzzy reasoning layer and is used for generating fuzzy rules and calculating the fitness value of each rule; the formula is:
where w=1, 2, …, m,
the fourth layer is a normalization layer and is used for carrying out normalization operation on the fitness of each rule; the formula is:
wherein j=1, 2, …, m;
the fifth layer is an output layer and is used for calculating the weighted sum of all outputs of the normalization layer; the formula is:
wherein i=1, 2, …, r, w ij Representing y i The j-th language value of (c) is the central value of the membership function.
And optimizing and adjusting parameters in the network model by adopting a hybrid learning algorithm to finish training the model.
S140: and inputting the screened characteristic parameters acquired in the period to be predicted into a trained NOx emission prediction model, and outputting a result, namely, predicting the corresponding NOx generation concentration.
And after preprocessing the characteristic parameters acquired in the time period to be predicted, inputting the characteristic parameters into a trained NOx prediction model, and outputting the model to obtain a predicted NOx generation concentration result in the time period.
As shown in fig. 4, the present invention provides a NOx emission prediction apparatus 300 based on a neighborhood rough set and a fuzzy neural network, comprising:
the data acquisition module 310 is used for acquiring NOx concentration historical data and corresponding historical operation parameters related to NOx generation in a specified time period from a DCS (distributed control system) system of the circulating fluidized bed boiler unit; wherein, the historical data of the NOx concentration is marked as a target parameter, and the corresponding historical operation parameter related to the generation of NOx is marked as a characteristic parameter;
the data screening module 320 screens the feature parameters through a neighborhood rough set algorithm to remove the feature parameters with low importance; taking the target parameters and the screened characteristic parameters as model training set data;
the model construction module 330 is configured to establish a NOx emission prediction model based on a Takagi-Sugeno fuzzy neural network, and train the NOx emission prediction model through model training set data;
the prediction module 340 is configured to input the filtered characteristic parameters collected in the period to be predicted into the trained NOx emission prediction model, and output the result as the corresponding NOx generation concentration prediction.
In order to implement the embodiment, the invention further provides an electronic device, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the NOx emission prediction method of the preceding aspect.
As shown in fig. 5, non-transitory computer-readable storage medium 800 includes memory 810 of instructions executable by processor 820 to perform a method according to NOx emission prediction. Alternatively, the storage medium may be a non-transitory computer readable storage medium, for example, a ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
To achieve the embodiments, the present invention also proposes a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements NOx emission prediction as in the embodiments of the present invention.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In such embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the described embodiments may be implemented by a program that instructs associated hardware to perform, and that the program may be stored on a computer readable storage medium that when executed includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The mentioned storage medium may be a read-only memory, a magnetic or optical disk or the like. Although embodiments of the present invention have been shown and described above, it will be understood that the embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (10)
1. A method for predicting NOx emissions based on a neighborhood rough set and a fuzzy neural network, comprising:
collecting NOx concentration historical data in a specified time period and corresponding historical operating parameters related to NOx generation from a DCS (distributed control system) of a circulating fluidized bed boiler unit; wherein, the historical data of the NOx concentration is marked as a target parameter, and the corresponding historical operation parameter related to the generation of NOx is marked as a characteristic parameter;
screening the characteristic parameters through a neighborhood rough set algorithm, and removing the characteristic parameters with low importance; taking the target parameters and the screened characteristic parameters as model training set data;
establishing a NOx emission prediction model based on a Takagi-Sugeno fuzzy neural network, and training the NOx emission prediction model through model training set data;
and inputting the screened characteristic parameters acquired in the period to be predicted into the NOx emission prediction model after training is completed, and outputting a result to be the corresponding NOx generation concentration prediction.
2. The method for predicting NOx emissions based on a neighbor matte set and fuzzy neural network of claim 1, wherein the types of corresponding historical operating parameters related to NOx generation include at least: coal quality, unit load, smoke quantity, smoke temperature, main steam flow, opening degree of a secondary air door baffle, secondary air pressure, secondary air quantity, rotating speed of each coal feeder, coal feeding quantity and air distribution mode.
3. The method for predicting NOx emissions based on a neighbor matte set and fuzzy neural network of claim 1, further comprising the step of preprocessing the data after the step of collecting the data; the method specifically comprises the following steps:
deficiency value complement; the method comprises the steps of carrying out mean value complementation by utilizing data before and after a single point when the single point is in a deficiency state, and carrying out complementation by utilizing an interpolation method when the continuous multipoint is in a deficiency state;
removing bad values;
normalizing the data; the data normalization method comprises the following formula:
x in the formula represents a characteristic parameter.
4. The method for predicting NOx emission based on a neighbor matte set and fuzzy neural network of claim 3, wherein in the step of removing the feature parameters having low importance by filtering the feature parameters through a neighbor matte set algorithm,
an information system IS= < U, A, V, f >; wherein A represents a set of attributes; v represents a value range, and f is U multiplied by A to V which is a function and represents the mapping relation between the sample and the attribute value; c is a conditional attribute; d is a decision attribute; and a=c u D; then for any x i E, U, defining the neighborhood as:
δ(x)={y∣Δ(x,y),,δ,y∈U}
wherein delta is the neighborhood radius; delta (x) is a neighborhood particle of x; delta employs a P-norm distance function:
based on the calculation result, obtaining the upper approximation, the lower approximation and the boundary of the neighborhood rough set of the characteristic parameters:
the attribute reduction process based on the neighborhood rough set algorithm is realized by judging the necessity of the attribute in a decision system, and the importance degree of the attribute needs to be calculated in a specific realization way. Assume thatIf meeting gamma B (D)≠γ B-{a} (D) It is indicated that attribute a is necessary in set B to decide attribute D. If any of the attributes a in set B have such a relationship, set B is independent from D. Wherein, gamma B (D) The attribute dependence can be calculated by the following formula:
when (when)a ε C-B, then the attribute importance of a with respect to B and D is:
SIG(a,B,D)=γ B (D)-γ B-(a) (D)
combining the definition of the neighborhood rough set and the attribute of the attribute Jian Suanfa, and obtaining a characteristic parameter reduction set influencing NOx emission by adopting a mode of adding the condition attribute forward according to the attribute importance information.
5. The method for predicting NOx emission based on a neighbor matte set and a fuzzy neural network according to claim 1, wherein in the step of establishing a NOx emission prediction model based on a fuzzy neural network of Takagi-Sugeno, an input vector is set as X= [ X ] 1 ,x 2 ,...,x n ] T Wherein each component x i Are all fuzzy linguistic variables and have Represents x i A j-th language variable value of (a); the value is defined in the field +.>A fuzzy set on the corresponding membership function is +.>Also for the output y, the fuzzy linguistic variable T (y) = { B 1 ,B 2 ,...,B m },B j The j-th linguistic variable representing y, which is defined in the discourse domain U y Fuzzy set of the above, its membership function is +.>
The output of the fuzzy rule in this model is a linear combination of input variables, expressed as follows:
R j :then B j =p j0 +p j1 x 1 +...+p jn x n
where j=1, 2,..m,
6. the method for predicting NOx emissions based on a neighbor matte set and fuzzy neural network of claim 5, wherein the NOx emissions prediction model is a 5-layer structure, wherein,
the first layer is an input layer and is used for transmitting input parameters of the fuzzy neural network to a next fuzzy layer; the formula is:
wherein i=1, 2, n; n is the number of input parameters;
the second layer is a fuzzification layer for fuzzifying the input parameters and calculating the membership value of each input parameter; the formula is:
where i=1, 2, n, j=1, 2, m; c ij And delta ij The center and width of the gaussian function are shown, respectively;
the third layer is a fuzzy reasoning layer and is used for generating fuzzy rules and calculating the fitness value of each rule; the formula is:
where w=1, 2, …, m,
the fourth layer is a normalization layer and is used for carrying out normalization operation on the fitness of each rule; the formula is:
wherein j=1, 2, …, m;
the fifth layer is an output layer and is used for calculating the weighted sum of all outputs of the normalization layer; the formula is:
wherein i=1, 2, …, r, w ij Representing y i The j-th language value of (c) is the central value of the membership function.
7. The method for predicting the NOx emission based on the neighborhood rough set and the fuzzy neural network according to claim 1, wherein in the step of training the NOx emission prediction model through the model training set data, a mixed learning algorithm is adopted to perform optimizing adjustment on parameters in the NOx emission prediction model.
8. A device for predicting NOx emissions based on a neighborhood rough set and a fuzzy neural network, comprising:
the data acquisition module is used for acquiring NOx concentration historical data and corresponding historical operating parameters related to NOx generation in a specified time period from a DCS (distributed control system) system of the circulating fluidized bed boiler unit; wherein, the historical data of the NOx concentration is marked as a target parameter, and the corresponding historical operation parameter related to the generation of NOx is marked as a characteristic parameter;
the data screening module screens the characteristic parameters through a neighborhood rough set algorithm and removes the characteristic parameters with low importance; taking the target parameters and the screened characteristic parameters as model training set data;
the model building module is used for building a NOx emission prediction model based on a Takagi-Sugeno fuzzy neural network, and training the NOx emission prediction model through the model training set data;
the prediction module is used for inputting the screened characteristic parameters acquired in the period to be predicted into the NOx emission prediction model after training is completed, and the output result is the corresponding NOx generation concentration prediction.
9. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any one of claims 1-7.
10. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the steps of the method according to any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310572071.8A CN116665808A (en) | 2023-05-19 | 2023-05-19 | NOx emission prediction method and device based on neighborhood rough set and fuzzy neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310572071.8A CN116665808A (en) | 2023-05-19 | 2023-05-19 | NOx emission prediction method and device based on neighborhood rough set and fuzzy neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116665808A true CN116665808A (en) | 2023-08-29 |
Family
ID=87716400
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310572071.8A Pending CN116665808A (en) | 2023-05-19 | 2023-05-19 | NOx emission prediction method and device based on neighborhood rough set and fuzzy neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116665808A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117272233A (en) * | 2023-11-21 | 2023-12-22 | 中国汽车技术研究中心有限公司 | Diesel engine emission prediction method, apparatus, and storage medium |
-
2023
- 2023-05-19 CN CN202310572071.8A patent/CN116665808A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117272233A (en) * | 2023-11-21 | 2023-12-22 | 中国汽车技术研究中心有限公司 | Diesel engine emission prediction method, apparatus, and storage medium |
CN117272233B (en) * | 2023-11-21 | 2024-05-31 | 中国汽车技术研究中心有限公司 | Diesel engine emission prediction method, apparatus, and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8554706B2 (en) | Power plant control device which uses a model, a learning signal, a correction signal, and a manipulation signal | |
CN116665808A (en) | NOx emission prediction method and device based on neighborhood rough set and fuzzy neural network | |
DE102019126310A1 (en) | System and method for optimizing the combustion of a boiler | |
DE102004052433A1 (en) | A gas turbine control apparatus, gas turbine system and gas turbine control method | |
CN113469449B (en) | Optimization control method and system for desulfurization system | |
CN112712189B (en) | Heat supply demand load prediction method | |
CN105137762A (en) | Fuzzy control method and system for automatic combustion of incinerator | |
DE102009003200A1 (en) | Method for determining an oil wear in an internal combustion engine, electrical device for controlling and / or regulating an internal combustion engine, internal combustion engine | |
CN107203687A (en) | Absorption tower sweetening process multiple target cooperative intelligent optimal control method | |
WO2020002447A1 (en) | Controller for controlling a technical system, and method for configuring the controller | |
CN111522290A (en) | Denitration control method and system based on deep learning method | |
WO2009080282A2 (en) | Optimizing the operation of a power plant | |
CN112232373A (en) | Method and system for predicting carbon content of boiler fly ash | |
CN115587433A (en) | State condition based unit consumption difference analysis optimization method and system | |
DE102019126293B4 (en) | System and method for regulating the operation of a boiler | |
CN114019846A (en) | Intelligent ventilation control design method and system for long road tunnel | |
CN113759709A (en) | Method and device for training strategy model, electronic equipment and storage medium | |
Sahab et al. | An adaptive type-2 input based nonsingleton type-2 fuzzy logic system for real world applications | |
CN117470300B (en) | Environment monitoring method and system for finished copper pipe storage workshop | |
JP2644941B2 (en) | Process control method and apparatus | |
CN112699600B (en) | Thermal power operating parameters and NOxMethod for analyzing partial return between emission concentrations | |
CN115330044A (en) | Nitrogen oxide emission prediction method and equipment based on genetic algorithm and convolution network | |
CN117890440B (en) | Semiconductor gas sensor temperature control voltage optimization method based on information entropy | |
CN115111601B (en) | Multi-target boiler combustion optimization control method based on embedded algorithm fusion under variable load | |
Annunziato et al. | A Nature-inspired-Modeling-Optimization-Control system applied to a waste incinerator plant |
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 |