CN113592163A - Method and equipment for predicting concentration of nitrogen oxide at inlet of SCR (Selective catalytic reduction) denitration reactor - Google Patents
Method and equipment for predicting concentration of nitrogen oxide at inlet of SCR (Selective catalytic reduction) denitration reactor Download PDFInfo
- Publication number
- CN113592163A CN113592163A CN202110829703.5A CN202110829703A CN113592163A CN 113592163 A CN113592163 A CN 113592163A CN 202110829703 A CN202110829703 A CN 202110829703A CN 113592163 A CN113592163 A CN 113592163A
- Authority
- CN
- China
- Prior art keywords
- prediction model
- inlet
- concentration
- scr denitration
- time
- 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
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 title claims abstract description 277
- 238000000034 method Methods 0.000 title claims abstract description 80
- 238000010531 catalytic reduction reaction Methods 0.000 title abstract description 6
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000007635 classification algorithm Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 64
- 239000013598 vector Substances 0.000 claims description 44
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 7
- 239000000126 substance Substances 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 abstract description 4
- 239000000243 solution Substances 0.000 description 16
- 238000004422 calculation algorithm Methods 0.000 description 10
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 229910021529 ammonia Inorganic materials 0.000 description 4
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 3
- 239000003546 flue gas Substances 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000003054 catalyst Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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"
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/74—General processes for purification of waste gases; Apparatus or devices specially adapted therefor
- B01D53/86—Catalytic processes
- B01D53/8621—Removing nitrogen compounds
- B01D53/8625—Nitrogen oxides
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/34—Chemical or biological purification of waste gases
- B01D53/74—General processes for purification of waste gases; Apparatus or devices specially adapted therefor
- B01D53/86—Catalytic processes
- B01D53/90—Injecting reactants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2251/00—Reactants
- B01D2251/20—Reductants
- B01D2251/206—Ammonium compounds
- B01D2251/2062—Ammonia
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D2258/00—Sources of waste gases
- B01D2258/02—Other waste gases
- B01D2258/0283—Flue gases
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Treating Waste Gases (AREA)
Abstract
The invention provides a method and equipment for predicting concentration of nitrogen oxides at an inlet of an SCR (selective catalytic reduction) denitration reactor. The method comprises the following steps: acquiring and preprocessing operation data of a plurality of boilers and SCR denitration reactors; determining input and output variables of a prediction model, constructing the prediction model by adopting a classification algorithm, adding a time-varying function in the prediction model to obtain the prediction results of the concentration of the nitric oxide under different lag time lengths, and updating the prediction model by adopting a sliding window by taking the time length corresponding to the minimum root-mean-square error in the prediction results as the lag time length; and training and testing the updated prediction model to obtain a final prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model. The method can accurately predict the concentration of the nitrogen oxides at the inlet of the SCR denitration reactor, avoids dependence on manual experience, and can update the prediction model in real time.
Description
Technical Field
The embodiment of the invention relates to the technical field of nitrogen oxide testing, in particular to a method and equipment for predicting the concentration of nitrogen oxide at an inlet of an SCR (selective catalytic reduction) denitration reactor.
Background
With the increasing upgrading of environmental requirements, the power industry has fully implemented ultra-low emission standards. In order to control the emission of pollutant nitrogen oxides, most of the existing coal-fired units generally adopt a solution scheme of increasing ammonia injection amount and increasing the number of catalyst layers, but the fluctuation of nitrogen oxides at the inlet of an SCR denitration reactor is severe, the representativeness of the measurement data of a continuous emission flue gas detection system (CEMS) is insufficient, and the measurement-control process of the SCR denitration system is delayed, so that the escape concentration of local ammonia is easily caused to exceed the design value, the aim of accurately injecting ammonia is difficult to achieve, and the safety, economy and stable operation of the denitration system are influenced, and even the equipment of a downstream system is damaged. At present, the artificial intelligence algorithm is used for predicting and optimizing the nitrogen oxide at the outlet of the boiler, in the denitration process of a large unit, because the section of a flue at a denitration inlet is large, a single boiler is matched with two SCR denitration reactors (namely, a selective catalytic reduction denitration reactor), the flow field of flue gas is not uniform, bias current possibly exists, the concentration of the nitrogen oxide at the inlet of each denitration reactor can also have difference, and the artificial intelligence algorithm is used for predicting the concentration of the nitrogen oxide at the outlet of the boiler and cannot be used for guiding the accurate ammonia spraying in the denitration process. Therefore, it is an urgent technical problem to be solved in the art to develop a method and an apparatus for predicting the concentration of nitrogen oxides at the inlet of an SCR denitration reactor, which can effectively overcome the above-mentioned drawbacks in the related art.
Disclosure of Invention
In order to solve the above problems in the prior art, embodiments of the present invention provide a method and an apparatus for predicting a concentration of nitrogen oxides at an inlet of an SCR denitration reactor.
In a first aspect, embodiments of the present invention provideA method for predicting the concentration of nitrogen oxides at an inlet of an SCR denitration reactor comprises the following steps: acquiring operation data of a plurality of boilers and SCR denitration reactors, removing abnormal values in the operation data, and combining parameters of the same type with consistent variation trend; determining input and output variables of a prediction model, constructing the prediction model by adopting a classification algorithm based on data driving, and adopting a regularization parameter which has a large influence on the performance of the model by adopting a queue competition algorithm
And kernel function width
Optimizing, determining the optimal values of the two parameters, minimizing the error of the model, and improving the prediction accuracy of the model; adding a time-varying function into the prediction model to obtain the nitrogen oxide concentration prediction results under different lag time lengths, and updating the prediction model by adopting a sliding window with the time length corresponding to the minimum root mean square error in the prediction results as the lag time length; and training and testing the updated prediction model to obtain a final prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model.
On the basis of the content of the embodiment of the method, the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor, which is provided by the embodiment of the invention, adopts a classification algorithm to construct a prediction model, and comprises the following steps:
wherein the content of the first and second substances,
is the minimum value of the objective function;
the vector coefficients of (a);
is a non-linear transformation;
is the nth element of the vector coefficient;
is the norm of the vector coefficient;
is a regularization parameter;
predicting an error vector for the ith training set; n is the number of prediction error vectors of the training set; b is a prediction model parameter;
is the ith Lagrangian multiplier; k is a kernel function; x is an input vector;
is the ith input vector;
is a prediction model;
is the ith output vector;
are constraints.
Based on the content of the foregoing method embodiment, in the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention, the time-varying function includes:
wherein z is a time-varying function;
is the parameter value at the time t;
the input vector at the K-th moment is taken as the input vector;
the time-varying function output quantity at the K time is obtained; f is a time-varying function expression.
On the basis of the content of the above method embodiment, in the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention, the minimum root mean square error includes:
wherein RMSE is the root mean square error; m is the number of samples;
is the ith predicted value;
is the ith true value.
On the basis of the content of the embodiment of the method, the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor, which is provided by the embodiment of the invention, adopts the sliding window to update the prediction model, and comprises the following steps: the method comprises the steps that a sliding window technology is used for updating a nitrogen oxide concentration prediction model at an SCR denitration inlet in real time, the prediction model is initialized at the starting stage, the prediction model adopts a self-contained historical database to establish an initial model for initial prediction, the self-contained historical database for initialization modeling of the prediction model is gradually replaced by latest actual operation data along with the operation of the prediction model, and the prediction model is updated after a time interval corresponding to a sliding window.
On the basis of the content of the foregoing method embodiment, the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention further includes, after the prediction model is updated: the size of the sliding window is adjusted according to the frequency of data acquired by the data acquisition system and the precision of the prediction model, and meanwhile, the operation duration of the prediction model is controlled to be millisecond level, so that the concentration of nitrogen oxides at the inlet of the SCR denitration reactor is predicted in real time.
On the basis of the content of the foregoing method embodiment, the method for predicting the concentration of nitrogen oxide at the inlet of the SCR denitration reactor provided in the embodiment of the present invention further includes, after predicting the concentration of nitrogen oxide at the inlet of the SCR denitration reactor in real time by using the final prediction model: updating a prediction model by taking real-time acquired data and an actual value of the concentration of nitrogen oxides at an inlet of the SCR denitration reactor calculated by adopting a time-varying function as latest historical data; the real-time data acquisition and the actual value of the concentration of nitrogen oxides at the inlet of the SCR denitration reactor calculated by adopting a time-varying function are stored in a database.
In a second aspect, an embodiment of the present invention provides an apparatus for predicting an inlet nox concentration of an SCR denitration reactor, including: the first main module is used for acquiring the operation data of a plurality of boilers and the SCR denitration reactor, eliminating abnormal values in the operation data and combining the change trendsConsistent parameters of the same type; the second main module is used for determining input and output variables of the prediction model, constructing the prediction model by adopting a classification algorithm based on data driving, and adopting a regularization parameter with a large influence on the performance of the model by adopting a queue competition algorithm
And kernel function width
Optimizing, determining the optimal values of the two parameters, minimizing the error of the model, and improving the prediction accuracy of the model; adding a time-varying function into the prediction model to obtain the nitrogen oxide concentration prediction results under different lag time lengths, and updating the prediction model by adopting a sliding window with the time length corresponding to the minimum root mean square error in the prediction results as the lag time length; and the third main module is used for training and testing the updated prediction model to obtain a final prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided by any one of the various implementation manners of the first aspect.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method for predicting SCR denitration reactor inlet nox concentration provided in any one of the various implementations of the first aspect.
According to the method and the device for predicting the concentration of the nitrogen oxide at the inlet of the SCR denitration reactor, provided by the embodiment of the invention, the operation data of a plurality of boilers and the SCR denitration reactor are obtained and preprocessed, the input and output variables of the prediction model are determined, the prediction model is constructed, the time-varying function is added into the prediction model, the prediction results of the concentration of the nitrogen oxide under different delay time lengths are obtained, the time length corresponding to the minimum root-mean-square error in the prediction results is taken as the delay time length, the prediction model is updated by adopting the sliding window, the final prediction model is obtained, the concentration of the nitrogen oxide at the inlet of the SCR denitration reactor can be accurately predicted, the dependence on the manual experience is avoided, and the prediction model can be updated in real time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below to the drawings required for the description of the embodiments or the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a method for predicting the concentration of nitrogen oxides at an inlet of an SCR denitration reactor according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a device for predicting concentration of nitrogen oxides at an inlet of an SCR denitration reactor according to an embodiment of the present invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. In addition, technical features of various embodiments or individual embodiments provided by the present invention may be arbitrarily combined with each other to form a feasible technical solution, and such combination is not limited by the sequence of steps and/or the structural composition mode, but must be realized by a person skilled in the art, and when the technical solution combination is contradictory or cannot be realized, such a technical solution combination should not be considered to exist and is not within the protection scope of the present invention.
The embodiment of the invention provides a method for predicting concentration of nitrogen oxides at an inlet of an SCR (selective catalytic reduction) denitration reactor, and referring to FIG. 1, the method comprises the following steps: acquiring operation data of a plurality of boilers and SCR denitration reactors, removing abnormal values in the operation data, and combining parameters of the same type with consistent variation trend; determining input and output variables of the prediction model, constructing the prediction model by adopting a classification algorithm, (adopting a regularization parameter which has great influence on the performance of the model by a queue competition algorithm)
And kernel function width
Optimizing, determining the optimal values of the two parameters, minimizing the model error, and improving the prediction accuracy of the model); adding a time-varying function into the prediction model to obtain the nitrogen oxide concentration prediction results under different lag time lengths, and updating the prediction model by adopting a sliding window with the time length corresponding to the minimum root mean square error in the prediction results as the lag time length; and training and testing the updated prediction model to obtain a final prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model. Wherein, obtaining the operating data of a plurality of boilers and SCR denitration reactors includes: the denitration system comprises a primary air quantity, a secondary air quantity, a coal feeding quantity, a main steam temperature, a main steam pressure, a flue gas quantity, a denitration reactor inlet temperature and the like. Analyzing and preprocessing the acquired data, analyzing the acquired historical operating data of the boiler and the SCR denitration reactor through a mechanism of generating nitrogen oxides, eliminating abnormal values in the data, and combining the parameters with the same type and consistent variation trend.
Based on the content of the above method embodiment, as an optional embodiment, the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention, which uses a classification algorithm to construct a prediction model, includes:
wherein the content of the first and second substances,
is the minimum value of the objective function;
the vector coefficients of (a);
is a non-linear transformation;
is the nth element of the vector coefficient;
is the norm of the vector coefficient;
is a regularization parameter;
predicting an error vector for the ith training set; n is the number of prediction error vectors of the training set; b is a prediction model parameter;
is the ith Lagrangian multiplier; k is a kernel function; x is an input vector;
is the ith input vector;
is a prediction model;
is the ith output vector;
are constraints.
Specifically, the input vector x and the output vector y in the prediction model are in a nonlinear relation, and nonlinear transformation exists
So that y is equal to
The classification objective function is expressed by the formulas (1) to (3) in a linear relationship. The optimization problem in the high-dimensional feature space generally converts the above formula into its dual problem, and introduces Lagrange multiplier to solve:
wherein L is a Lagrangian function;
is an objective function.
The partial derivative of equation (5) can be obtained:
(6) the formula is equivalent to the matrix form shown in formula (7):
eliminating in formula (7)
And e, obtaining a linear equation system as shown in the formula (9):
(8) in formulae (1) and (9)
Is a unit vector, I is a unit matrix,
is a kernel function matrix. And b and
to predict the model parameters, it is also known from Mercer's theorem:
wherein the content of the first and second substances,
is the jth input vector; k is a symmetric positive-definite kernel function, commonly of the form gaussian Radial Basis (RBF) kernel function:
wherein the content of the first and second substances,
is the kernel function width; the prediction expression from which the function estimate for the new sample x can be derived is shown in equation (4).
Based on the content of the foregoing method embodiment, as an optional embodiment, in the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention, the time-varying function includes:
wherein z is a time-varying function;
is the parameter value at the time t;
the input vector at the K-th moment is taken as the input vector;
the time-varying function output quantity at the K time is obtained; f is a time-varying function expression.
In particular, the amount of the solvent to be used,adding a time-varying function, wherein the nitrogen oxide concentration parameter in the prediction model is obtained from a CEMS (continuous emission monitoring system) which has hysteresis, adding the time-varying function into the nitrogen oxide concentration prediction model at the inlet of the SCR denitration reactor as shown in the formulas (12) to (13),
the sample numbers in (1) are in one-to-one correspondence, and for t =1, 2, …, N, are based on
Training algorithm f to obtain
. Time-varying, i.e., when data fitting is performed, often encounters output variables
The mapping relation with the output variable is changed continuously along with the time, and the time is called
And
is time-varying. At this time, the mapping relationship of the sum needs to be continuously updated based on the incremental data of the output variable x and the output variable y according to the time sequence. And establishing a denitration system time lag model by relying on historical operation data of the power plant DCS platform, testing the prediction effect under different lag time length conditions, and taking the time length corresponding to the minimum RMSE in the prediction result as the lag time length.
Based on the content of the foregoing method embodiment, as an optional embodiment, in the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention, the minimum root mean square error includes:
wherein RMSE is the root mean square error; m is the number of samples;
is the ith predicted value;
is the ith true value.
Specifically, the first 240 pieces of data of a sample are used as prediction model initialization data, and every 800 pieces of subsequent data are grouped into a group to be used as a test set for prediction model verification. And evaluating the prediction model, substituting the data of the test set into the prediction model, predicting the target value of the test set, namely the concentration of nitrogen oxides at the inlet of the SCR denitration reactor, and calculating the root mean square error as shown in the formula (15).
Based on the content of the foregoing method embodiment, as an optional embodiment, the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention, which updates the prediction model by using the sliding window, includes: the method comprises the steps that a sliding window technology is used for updating a nitrogen oxide concentration prediction model at an SCR denitration inlet in real time, the prediction model is initialized at the starting stage, the prediction model adopts a self-contained historical database to establish an initial model for initial prediction, the self-contained historical database for initialization modeling of the prediction model is gradually replaced by latest actual operation data along with the operation of the prediction model, and the prediction model is updated after a time interval corresponding to a sliding window.
Specifically, a sliding window technology is used for updating a nitrogen oxide concentration prediction model at the inlet of the SCR denitration reactor in real time, the prediction model undergoes an initialization process in a starting stage, the prediction model uses a self-contained historical database to establish an initial model for initial prediction in the process, the self-contained historical database for initialization modeling of the model is gradually replaced by latest actual operation data along with the operation of the prediction model, and the prediction model is completely updated after a time interval duration corresponding to a sliding window is elapsed; the size of the sliding window can be reasonably adjusted according to the frequency of data acquisition of a data acquisition system and the precision of the prediction model, and meanwhile, the running time of the prediction model is controlled to be at millisecond level, so that the purpose of real-time prediction is achieved.
Based on the content of the foregoing method embodiment, as an optional embodiment, the method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention further includes, after the prediction model is updated: the size of the sliding window is adjusted according to the frequency of data acquired by the data acquisition system and the precision of the prediction model, and meanwhile, the operation duration of the prediction model is controlled to be millisecond level, so that the concentration of nitrogen oxides at the inlet of the SCR denitration reactor is predicted in real time.
Based on the content of the foregoing method embodiment, as an optional embodiment, the method for predicting nitrogen oxide concentration at an inlet of an SCR denitration reactor provided in the embodiment of the present invention further includes, after predicting the nitrogen oxide concentration at the inlet of the SCR denitration reactor in real time by using a final prediction model: updating a prediction model by taking real-time acquired data and an actual value of the concentration of nitrogen oxides at an inlet of the SCR denitration reactor calculated by adopting a time-varying function as latest historical data; the real-time data acquisition and the actual value of the concentration of nitrogen oxides at the inlet of the SCR denitration reactor calculated by adopting a time-varying function are stored in a database.
The method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided by the embodiment of the invention comprises the steps of obtaining and preprocessing the operation data of a plurality of boilers and the SCR denitration reactor, determining the input and output variables of a prediction model, constructing the prediction model by adopting a classification algorithm based on data driving, and adopting a regularization parameter with a large influence on the performance of the model by adopting a queue competition algorithm
And kernel function width
Optimizing, determining the optimal values of the two parameters, minimizing the error of the model, and improving the prediction accuracy of the model; adding a time-varying function into the prediction model to obtain the nitrogen oxide concentration prediction results under different lag time lengths so as to predictThe time length corresponding to the minimum root mean square error in the result is the lag time length, the prediction model is updated by adopting the sliding window to obtain the final prediction model, the concentration of nitrogen oxides at the inlet of the SCR denitration reactor can be accurately predicted, the dependence on manual experience is avoided, and the prediction model can be updated in real time.
The method for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor, provided by the embodiment of the invention, collects the operating data of a coal fired power plant boiler and the SCR denitration reactor in a preset area, the total number of sample data is 9400, the size of a sliding window is set to 240, the first 240 data are taken as model initialization historical data according to the time sequence, each 800 data are taken as a group for prediction, the model is evaluated, the RMSE (root mean square error) value of the predicted value and the actual value of the sample data in a test set is within 20, and the method is verified to have higher precision.
The implementation basis of the various embodiments of the present invention is realized by programmed processing performed by a device having a processor function. Therefore, in engineering practice, the technical solutions and functions thereof of the embodiments of the present invention can be packaged into various modules. Based on this actual situation, on the basis of the above embodiments, embodiments of the present invention provide an SCR denitration reactor inlet nitrogen oxide concentration prediction apparatus for performing the SCR denitration reactor inlet nitrogen oxide concentration prediction method in the above method embodiments. Referring to fig. 2, the apparatus includes: the first main module is used for acquiring the operation data of a plurality of boilers and SCR denitration reactors, eliminating abnormal values in the operation data and combining the parameters with the same type and the consistent variation trend; the second main module is used for determining input and output variables of the prediction model, constructing the prediction model by adopting a classification algorithm based on data driving, and adopting a regularization parameter with a large influence on the performance of the model by adopting a queue competition algorithm
And kernel function width
Proceed optimization and confirmationDetermining the optimal values of the two parameters to minimize the model error and improve the prediction precision of the model; adding a time-varying function into the prediction model to obtain the nitrogen oxide concentration prediction results under different lag time lengths, and updating the prediction model by adopting a sliding window with the time length corresponding to the minimum root mean square error in the prediction results as the lag time length; and the third main module is used for training and testing the updated prediction model to obtain a final prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model.
The device for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor, provided by the embodiment of the invention, adopts a plurality of modules in FIG. 2, determines the input and output variables of a prediction model by acquiring and preprocessing the operation data of a plurality of boilers and the SCR denitration reactor, constructs the prediction model by adopting a classification algorithm based on data driving, and adopts a regularization parameter which has a large influence on the performance of the model by a queue competition algorithm
And kernel function width
Optimizing, determining the optimal values of the two parameters, minimizing the error of the model, and improving the prediction accuracy of the model; adding a time-varying function into the prediction model to obtain the nitrogen oxide concentration prediction results under different lag time lengths, taking the time length corresponding to the minimum root mean square error in the prediction results as the lag time length, updating the prediction model by adopting a sliding window to obtain a final prediction model, accurately predicting the nitrogen oxide concentration at the inlet of the SCR denitration reactor, avoiding dependence on manual experience, and updating the prediction model in real time.
It should be noted that, the apparatus in the apparatus embodiment provided by the present invention may be used for implementing methods in other method embodiments provided by the present invention, except that corresponding function modules are provided, and the principle of the apparatus embodiment provided by the present invention is basically the same as that of the apparatus embodiment provided by the present invention, so long as a person skilled in the art obtains corresponding technical means by combining technical features on the basis of the apparatus embodiment described above, and obtains a technical solution formed by these technical means, on the premise of ensuring that the technical solution has practicability, the apparatus in the apparatus embodiment described above may be modified, so as to obtain a corresponding apparatus class embodiment, which is used for implementing methods in other method class embodiments. For example:
based on the content of the foregoing device embodiment, as an optional embodiment, the device for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention further includes: the first sub-module is used for realizing the construction of the prediction model by adopting a data-driven-based classification algorithm and adopting a regularization parameter which has a great influence on the performance of the model by adopting a queue competition algorithm
And kernel function width
Performing optimization to determine the optimal values of the two parameters, including:
wherein the content of the first and second substances,
to the eyesMinimum value of scalar function;
the vector coefficients of (a);
is a non-linear transformation;
is the nth element of the vector coefficient;
is the norm of the vector coefficient;
is a regularization parameter;
predicting an error vector for the ith training set; n is the number of prediction error vectors of the training set; b is a prediction model parameter;
is the ith Lagrangian multiplier; k is a kernel function; x is an input vector;
is the ith input vector;
is a prediction model;
is the ith output vector;
are constraints.
Based on the content of the foregoing device embodiment, as an optional embodiment, the device for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention further includes: a second submodule, configured to implement the time-varying function, including:
wherein z is a time-varying function;
is the parameter value at the time t;
the input vector at the K-th moment is taken as the input vector;
the time-varying function output quantity at the K time is obtained; f is a time-varying function expression.
Based on the content of the foregoing device embodiment, as an optional embodiment, the device for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention further includes: a third sub-module for implementing the minimum root mean square error comprises:
wherein RMSE is the root mean square error; m is the number of samples;
is the ith predicted value;
is the ith true value.
Based on the content of the foregoing device embodiment, as an optional embodiment, the device for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention further includes: a fourth sub-module, configured to update the prediction model with a sliding window, where the updating includes: the method comprises the steps that a sliding window technology is used for updating a nitrogen oxide concentration prediction model at an SCR denitration inlet in real time, the prediction model is initialized at the starting stage, the prediction model adopts a self-contained historical database to establish an initial model for initial prediction, the self-contained historical database for initialization modeling of the prediction model is gradually replaced by latest actual operation data along with the operation of the prediction model, and the prediction model is updated after a time interval corresponding to a sliding window.
Based on the content of the foregoing device embodiment, as an optional embodiment, the device for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention further includes: a fifth sub-module, configured to implement, after the prediction model is updated, further comprising: the size of the sliding window is adjusted according to the frequency of data acquired by the data acquisition system and the precision of the prediction model, and meanwhile, the operation duration of the prediction model is controlled to be millisecond level, so that the concentration of nitrogen oxides at the inlet of the SCR denitration reactor is predicted in real time.
Based on the content of the foregoing device embodiment, as an optional embodiment, the device for predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor provided in the embodiment of the present invention further includes: the sixth sub-module is configured to realize that after the final prediction model is used to predict the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time, the method further includes: updating a prediction model by taking real-time acquired data and an actual value of the concentration of nitrogen oxides at an inlet of the SCR denitration reactor calculated by adopting a time-varying function as latest historical data; the real-time data acquisition and the actual value of the concentration of nitrogen oxides at the inlet of the SCR denitration reactor calculated by adopting a time-varying function are stored in a database.
The method of the embodiment of the invention is realized by depending on the electronic equipment, so that the related electronic equipment is necessarily introduced. To this end, an embodiment of the present invention provides an electronic apparatus, as shown in fig. 3, including: the system comprises at least one processor (processor), a communication Interface (communication Interface), at least one memory (memory) and a communication bus, wherein the at least one processor, the communication Interface and the at least one memory are communicated with each other through the communication bus. The at least one processor may invoke logic instructions in the at least one memory to perform all or a portion of the steps of the methods provided by the various method embodiments described above.
In addition, the logic instructions in the at least one memory may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the method embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed 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 modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. Based on this recognition, each block in the flowchart or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In this patent, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for predicting the concentration of nitrogen oxides at an inlet of an SCR denitration reactor is characterized by comprising the following steps: acquiring operation data of a plurality of boilers and SCR denitration reactors, removing abnormal values in the operation data, and combining parameters of the same type with consistent variation trend; determining input and output variables of a prediction model, constructing the prediction model by adopting a classification algorithm, adding a time-varying function in the prediction model to obtain the prediction results of the concentration of the nitric oxide under different lag time lengths, and updating the prediction model by adopting a sliding window by taking the time length corresponding to the minimum root-mean-square error in the prediction results as the lag time length; and training and testing the updated prediction model to obtain a final prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model.
2. The method for predicting the concentration of nitrogen oxides at the inlet of an SCR denitration reactor according to claim 1, wherein the constructing a prediction model by using a classification algorithm comprises the following steps:
wherein the content of the first and second substances,
is the minimum value of the objective function;
the vector coefficients of (a);
is a non-linear transformation;
is the nth element of the vector coefficient;
is the norm of the vector coefficient;
is a regularization parameter;
predicting an error vector for the ith training set; n is the number of prediction error vectors of the training set; b is a prediction model parameter;
is the ith Lagrangian multiplier; k is a kernel function; x is an input vector;
is the ith input vector;
is a prediction model;
is the ith output vector;
are constraints.
3. The SCR denitration reactor inlet nox concentration prediction method of claim 2, wherein the time-varying function comprises:
wherein z is a time-varying function;
is the parameter value at the time t;
the input vector at the K-th moment is taken as the input vector;
the time-varying function output quantity at the K time is obtained; f is a time-varying function expression.
4. The method of predicting the inlet nitrogen oxide concentration of an SCR denitration reactor of claim 3, wherein the minimum root mean square error comprises:
wherein RMSE is the root mean square error; m is the number of samples;
is the ith predicted value;
is the ith true value.
5. The method of predicting the inlet nitrogen oxide concentration of an SCR denitration reactor according to claim 4, wherein the updating the prediction model by using a sliding window comprises: the method comprises the steps that a sliding window technology is used for updating a nitrogen oxide concentration prediction model at an SCR denitration inlet in real time, the prediction model is initialized at the starting stage, the prediction model adopts a self-contained historical database to establish an initial model for initial prediction, the self-contained historical database for initialization modeling of the prediction model is gradually replaced by latest actual operation data along with the operation of the prediction model, and the prediction model is updated after a time interval corresponding to a sliding window.
6. The SCR denitration reactor inlet nox concentration prediction method of claim 5, further comprising, after the prediction model is updated: the size of the sliding window is adjusted according to the frequency of data acquired by the data acquisition system and the precision of the prediction model, and meanwhile, the operation duration of the prediction model is controlled to be millisecond level, so that the concentration of nitrogen oxides at the inlet of the SCR denitration reactor is predicted in real time.
7. The method of predicting the inlet nitrogen oxide concentration of an SCR denitration reactor according to claim 6, further comprising, after predicting the inlet nitrogen oxide concentration of the SCR denitration reactor in real time by using the final prediction model: updating a prediction model by taking real-time acquired data and an actual value of the concentration of nitrogen oxides at an inlet of the SCR denitration reactor calculated by adopting a time-varying function as latest historical data; the real-time data acquisition and the actual value of the concentration of nitrogen oxides at the inlet of the SCR denitration reactor calculated by adopting a time-varying function are stored in a database.
8. An apparatus for predicting concentration of nitrogen oxides at inlet of SCR denitration reactor, comprising: the first main module is used for acquiring the operation data of a plurality of boilers and SCR denitration reactors, eliminating abnormal values in the operation data and combining the parameters with the same type and the consistent variation trend; the second main module is used for determining input and output variables of the prediction model, constructing the prediction model by adopting a classification algorithm, adding time-varying functions into the prediction model to obtain the nitrogen oxide concentration prediction results under different lag time lengths, and updating the prediction model by adopting a sliding window by taking the time length corresponding to the minimum root mean square error in the prediction results as the lag time length; and the third main module is used for training and testing the updated prediction model to obtain a final prediction model, and predicting the concentration of nitrogen oxides at the inlet of the SCR denitration reactor in real time by adopting the final prediction model.
9. An electronic device, comprising:
at least one processor, at least one memory, and a communication interface; wherein the content of the first and second substances,
the processor, the memory and the communication interface are communicated with each other;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110829703.5A CN113592163A (en) | 2021-07-22 | 2021-07-22 | Method and equipment for predicting concentration of nitrogen oxide at inlet of SCR (Selective catalytic reduction) denitration reactor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110829703.5A CN113592163A (en) | 2021-07-22 | 2021-07-22 | Method and equipment for predicting concentration of nitrogen oxide at inlet of SCR (Selective catalytic reduction) denitration reactor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113592163A true CN113592163A (en) | 2021-11-02 |
Family
ID=78248910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110829703.5A Pending CN113592163A (en) | 2021-07-22 | 2021-07-22 | Method and equipment for predicting concentration of nitrogen oxide at inlet of SCR (Selective catalytic reduction) denitration reactor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592163A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114089636A (en) * | 2022-01-19 | 2022-02-25 | 汉谷云智(武汉)科技有限公司 | SCR denitration external hanging type intelligent ammonia spraying closed-loop control method and equipment |
| CN114360656A (en) * | 2021-11-30 | 2022-04-15 | 国家能源集团新能源技术研究院有限公司 | Modeling method, device and equipment for selective catalytic reduction denitration model |
| CN115146833A (en) * | 2022-06-14 | 2022-10-04 | 北京全应科技有限公司 | Method for predicting generation concentration of boiler nitrogen oxide |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106444428A (en) * | 2016-10-25 | 2017-02-22 | 中国石油化工股份有限公司 | Process simulation software based atmospheric and vacuum distillation unit optimization operation system and method |
| CN107609328A (en) * | 2017-08-30 | 2018-01-19 | 武汉理工大学 | A kind of Multipurpose Optimal Method of catalytic cracking unit model |
| CN108837699A (en) * | 2018-07-02 | 2018-11-20 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and PREDICTIVE CONTROL |
| CN109634117A (en) * | 2018-12-14 | 2019-04-16 | 华北电力大学（保定） | A kind of information physical emerging system and its control method for denitration control |
| CN111652414A (en) * | 2020-05-20 | 2020-09-11 | 浙江大学 | Sliding window PCA blast furnace abnormity monitoring method based on Gaussian mixture model |
| CN111833969A (en) * | 2020-04-21 | 2020-10-27 | 汉谷云智(武汉)科技有限公司 | Finished oil octane number prediction method, equipment and storage medium |
| CN112085277A (en) * | 2020-09-10 | 2020-12-15 | 南京工业大学 | SCR denitration system prediction model optimization method based on machine learning |
| CN112580250A (en) * | 2020-11-12 | 2021-03-30 | 山东纳鑫电力科技有限公司 | Thermal power generating unit denitration system based on deep learning and optimization control method |
| CN112651166A (en) * | 2020-11-24 | 2021-04-13 | 呼和浩特科林热电有限责任公司 | Denitration system inlet nitrogen oxide concentration prediction method and device and denitration system |
-
2021
- 2021-07-22 CN CN202110829703.5A patent/CN113592163A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106444428A (en) * | 2016-10-25 | 2017-02-22 | 中国石油化工股份有限公司 | Process simulation software based atmospheric and vacuum distillation unit optimization operation system and method |
| CN107609328A (en) * | 2017-08-30 | 2018-01-19 | 武汉理工大学 | A kind of Multipurpose Optimal Method of catalytic cracking unit model |
| CN108837699A (en) * | 2018-07-02 | 2018-11-20 | 大唐环境产业集团股份有限公司 | It is a kind of that ammonia optimization method and system are intelligently sprayed based on the SCR denitration of hard measurement and PREDICTIVE CONTROL |
| CN109634117A (en) * | 2018-12-14 | 2019-04-16 | 华北电力大学（保定） | A kind of information physical emerging system and its control method for denitration control |
| CN111833969A (en) * | 2020-04-21 | 2020-10-27 | 汉谷云智(武汉)科技有限公司 | Finished oil octane number prediction method, equipment and storage medium |
| CN111652414A (en) * | 2020-05-20 | 2020-09-11 | 浙江大学 | Sliding window PCA blast furnace abnormity monitoring method based on Gaussian mixture model |
| CN112085277A (en) * | 2020-09-10 | 2020-12-15 | 南京工业大学 | SCR denitration system prediction model optimization method based on machine learning |
| CN112580250A (en) * | 2020-11-12 | 2021-03-30 | 山东纳鑫电力科技有限公司 | Thermal power generating unit denitration system based on deep learning and optimization control method |
| CN112651166A (en) * | 2020-11-24 | 2021-04-13 | 呼和浩特科林热电有限责任公司 | Denitration system inlet nitrogen oxide concentration prediction method and device and denitration system |
Non-Patent Citations (6)
| Title |
|---|
| 丁刚;钟诗胜;: "具有时变输入输出函数的反馈过程神经网络及应用", 控制与决策, no. 01 * |
| 刘显德;刘立伟;许少华;周继；: "一种过程神经元网络模型及其在动态预测中的应用", 大庆石油学院学报, vol. 32, no. 4, pages 107 - 110 * |
| 张子阳;孙彦广;: "基于ARIMA-NN组合模型的钢铁企业氧气管网压力预测研究", 冶金自动化, no. 06 * |
| 湛腾西;郭观七;: "电厂烟气含氧量的智能混合预测方法", 仪器仪表学报, no. 08 * |
| 王春生;吴敏;佘锦华;: "基于PNN和IGS的铅锌烧结块成分智能集成预测模型", 控制理论与应用, no. 03 * |
| 王雅琳;黄凯华;伍铁斌;谢文平;阳春华;: "基于核偏最小二乘的砷盐净化除钴过程钴离子浓度软测量", 中南大学学报(自然科学版), no. 01 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114360656A (en) * | 2021-11-30 | 2022-04-15 | 国家能源集团新能源技术研究院有限公司 | Modeling method, device and equipment for selective catalytic reduction denitration model |
| CN114089636A (en) * | 2022-01-19 | 2022-02-25 | 汉谷云智(武汉)科技有限公司 | SCR denitration external hanging type intelligent ammonia spraying closed-loop control method and equipment |
| CN115146833A (en) * | 2022-06-14 | 2022-10-04 | 北京全应科技有限公司 | Method for predicting generation concentration of boiler nitrogen oxide |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113592163A (en) | Method and equipment for predicting concentration of nitrogen oxide at inlet of SCR (Selective catalytic reduction) denitration reactor | |
| CN111804146B (en) | Intelligent ammonia injection control method and intelligent ammonia injection control device | |
| US5386373A (en) | Virtual continuous emission monitoring system with sensor validation | |
| Bartolini et al. | Application of artificial neural networks to micro gas turbines | |
| US7536364B2 (en) | Method and system for performing model-based multi-objective asset optimization and decision-making | |
| AU2006201792A1 (en) | Method and system for performing multi-objective predictive modeling, monitoring, and update for an asset | |
| CN105955026B (en) | Fuzzy PID control method, device and system | |
| Arahal et al. | Neural identification applied to predictive control of a solar plant | |
| US11237551B2 (en) | Real-time automation for monitor and control of electro-mechanical system | |
| CN113175678B (en) | Garbage incineration monitoring method and device | |
| CN115034129A (en) | NOx emission concentration soft measurement method for thermal power plant denitration device | |
| CN104932274A (en) | A coordination control controlled object transfer function model identification method | |
| Blaud et al. | From multi‐physics models to neural network for predictive control synthesis | |
| CN112052496A (en) | Operation method of high arch dam valley amplitude deformation influence factor analysis system based on VAR model | |
| CN116484675A (en) | Crack propagation life prediction method and system for ship engine blade | |
| Fu et al. | Prediction model of desulfurization efficiency of coal-fired power plants based on long short-term memory neural network | |
| CN102967393A (en) | Supercritical unit boiler separator outlet temperature on-line calibration method | |
| CN116050643A (en) | Method for predicting emission concentration of process industrial pollutants based on integrated model | |
| Fast et al. | A novel approach for gas turbine condition monitoring combining CUSUM technique and artificial neural network | |
| Bakal et al. | Time Delay Neural Networks for NOx and CO Prediction in Fossil Fuel Plants | |
| US10521716B2 (en) | Computer-assisted analysis of a data record from observations | |
| Farber et al. | Using multiple-model adaptive estimation and system identification for fault detection in nuclear power plants | |
| Petruzzi et al. | Uncertainties in predictions by system thermal-hydraulic codes: the CASUALIDAD method | |
| Yang et al. | Identification of LTI Time‐Delay Systems with Missing Output Data Using GEM Algorithm | |
| Najar et al. | Comparative Machine Learning Study for Estimating Peak Cladding Temperature in AP1000 Under LOFW |
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 |