CN114492727A - Intelligent prediction and control method for inlet smoke concentration of dust removal system - Google Patents
Intelligent prediction and control method for inlet smoke concentration of dust removal system Download PDFInfo
- Publication number
- CN114492727A CN114492727A CN202111516885.7A CN202111516885A CN114492727A CN 114492727 A CN114492727 A CN 114492727A CN 202111516885 A CN202111516885 A CN 202111516885A CN 114492727 A CN114492727 A CN 114492727A
- Authority
- CN
- China
- Prior art keywords
- dust
- concentration
- prediction
- inlet
- neural network
- 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
Classifications
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- B01D53/32—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 by electrical effects other than those provided for in group B01D61/00
- B01D53/323—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 by electrical effects other than those provided for in group B01D61/00 by electrostatic effects or by high-voltage electric fields
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses an intelligent prediction and control method for the concentration of smoke dust at the inlet of a dust removal system, which belongs to the technical field of dust removal systems, and comprises the following steps: s1: establishing a training sample N group of an SA-RBF mixed neural network model predictor; s2: optimizing the number of hidden layer neurons of the RBF mixed neural network by a particle swarm parameter optimization algorithm, selecting parameters of the neural network, and initializing weights of the neural network; s3: training the prediction model and the controller by using a DPSO training algorithm to obtain a neural network weight parameter; s4: determining the lag time of the system, taking the input parameters and the actual output parameters as initial values of the controller, calculating a prediction error, and adjusting the parameters of the controller through the error; s5: the output of the neural network prediction model is calculated, the obtained prediction output is used as control output to act on a controlled object, accurate prediction of dust concentration at the inlet of the dust remover and optimization of operation parameters under different working conditions are achieved, and reliability and economical efficiency of system operation are improved.
Description
Technical Field
The invention relates to the technical field of dust removal systems, in particular to an intelligent prediction and control method for the concentration of smoke dust at an inlet of a dust removal system.
Background
A large amount of coal can be combusted in the production flow of a thermal power plant, the coal often contains a large amount of ash, smoke and dust particles can be formed after the combustion, and if the smoke and dust particles are not treated, the environment can be greatly harmed. Therefore, controlling and reducing soot pollutants in coal-fired power plants is critical to environmental remediation.
At present, the dust removal of a thermal power plant mainly adopts an electrostatic dust removal mode, and because the smoke concentration at the inlet of the electrostatic dust remover is higher, a measuring instrument often breaks down, so that a smoke measuring device is not additionally arranged at the inlet of the electrostatic dust remover in many power plants, and the smoke concentration at the inlet of the dust remover cannot be fed back in real time.
At present, due to the shortage of the coal market, the coal quality fluctuation of the as-fired coal in a power plant is large, and due to the fact that the accurate smoke concentration is not available, when the smoke concentration at the inlet of the dust remover rises, due to the fact that the electric dust remover is not timely controlled, the smoke is easily discharged in an over-standard mode, or when the smoke concentration at the inlet of the dust remover is low, the voltage and current control of the dust remover is too high, the operation energy consumption is high, and the waste of the energy consumption of a system is caused.
Aiming at the related technologies, the inventor provides an intelligent prediction and control method for the concentration of smoke dust at the inlet of a dust removal system.
Disclosure of Invention
The invention provides an intelligent prediction and control method for the concentration of smoke dust at an inlet of a dust removal system, aiming at improving the problem that the concentration of the smoke dust at the inlet of a dust remover is not accurate, when the concentration of the smoke dust at the inlet of the dust remover is increased, the smoke dust is easily discharged beyond the standard due to untimely control of an electric dust remover, or when the concentration of the smoke dust at the inlet of the dust remover is low, the voltage and current control of the dust remover is overhigh, the operation energy consumption is higher, and the waste of the energy consumption of the system is caused.
The invention provides an intelligent prediction and control method for the concentration of smoke dust at an inlet of a dust removal system, which adopts the following technical scheme and comprises the following steps:
s1: establishing a training sample N group of an SA-RBF mixed neural network model predictor;
s2: optimizing the number of hidden layer neurons of the RBF mixed neural network by a particle swarm parameter optimization algorithm, selecting parameters of the neural network, and initializing a weight of the neural network;
s3: training a prediction model and a controller of an SA-RBF (neural network-radial basis function) hybrid neural network model predictor by using a DPSO (distributed data acquisition) training algorithm to obtain a neural network weight parameter;
s4: determining the lag time of the system, taking the input parameters and the actual output parameters as initial values of the controller, calculating a prediction error, and adjusting the parameters of the controller through the error;
s5: and calculating the output of the established smoke concentration intelligent SOA-SOFNN prediction model to obtain the prediction output of the controlled object at the future moment, and taking the prediction output as the control output to act on the controlled object.
Optionally, the training sample of S1 includes a unit load, a main steam flow, a total air volume, a total coal supply amount, a primary air fan valve opening, secondary air fan valve openings a to E mill coal supply amount, and a to E mill secondary air opening.
Optionally, the principal component analysis method for determining the training sample includes calculating a covariance matrix, then calculating an eigenvalue and an eigenvector of the covariance matrix, then sorting the eigenvalue and the eigenvector of the covariance matrix and calculating a contribution rate, calculating a load matrix of the eigenvector with the contribution rate greater than 85% and the original eigenvector, and performing dimension reduction on the input parameter according to the load matrix.
Optionally, in the S2, the particle group parameter optimization algorithm randomly initializes the position and speed of the particle, defines a fitness function, tracks the individual optimal solution and the global optimal solution, and updates the position and speed of the individual optimal solution and the global optimal solution each time, in this process, the fitness value is calculated for each iteration, and a set target fitness value is reached after multiple iterations, so as to obtain the optimal solution.
Optionally, for each sample Xi in each set of training samples X, training the training samples except Xi by the DPSO training algorithm in S3 to obtain a model Mi; calculating gradient estimation of the sample Xi by adopting a sequencing lifting method and utilizing the model Mi; re-scoring the samples Xi by using the new model to form a weak learner; and performing weighting processing on all weak learners to obtain a final strong classifier.
Optionally, in S4, based on the extracted input parameters, the related operation data formed by the smoke dust of the boiler of the coal-fired unit is continuously collected and analyzed for 30d, and collected for 1 time per minute, the unit load, the main steam flow, the total air quantity, the total coal supply quantity, the primary air fan valve opening, the secondary air fan valve opening, the a-E mill coal supply quantity and the a-E mill secondary air opening, which are input by each burner, are collated and used as input parameters of the SOA-SOFNN prediction model, and meanwhile, the smoke dust concentration correspondingly measured at each time point is used as an output parameter for model training.
Optionally, in S5, real-time operation data of the dust concentration influencing factors at the dust collector inlet is input into the established intelligent SOA-SOFNN prediction model of the dust concentration, so as to obtain the dust concentration at the dust collector inlet, and the voltage and the current of the dust collector are adjusted according to the dust concentration at the inlet.
Optionally, the method for adjusting the voltage and the current of the dust remover according to the concentration of the inlet smoke includes: when the predicted smoke concentration is higher than the designed concentration, the voltage and current should be adjusted to the maximum input and output current, and when the smoke concentration is lower than the designed concentration, the input and output current of the dust remover should be reduced.
Optionally, the intelligent prediction and control method for the smoke concentration at the inlet of the dust removal system adopts an independent plug-in platform and is connected with the DCS in a communication manner.
In summary, the present invention includes at least one of the following advantages: the method realizes accurate prediction of the concentration of the smoke dust at the inlet of the dust remover and optimization of the operation parameters under different working conditions, improves the reliability and economy of system operation, can effectively improve the stability of the dust removal system, improves the automatic operation level and the system economy of the dust removal system of the thermal power unit, and has good technical and application values.
Detailed Description
The present invention will be described in further detail below.
The invention provides a dust collector inlet smoke prediction and control method, which is mainly realized by a self-organizing fuzzy neural network (SOA-SOFNN) prediction model, an SA-RBF mixed neural network model realization requirement (SOA-SOFNN) prediction model and an RBF mixed neural network, and the method not only considers the self-organization of the structure, but also improves the parameter regulation mode, has high training speed, meets the requirement of on-line prediction, and has the following main analysis process:
s1: establishing a training sample N group of an SA-RBF mixed neural network model predictor;
determining the influence factors of the inlet concentration of the dust remover and the input variables of the (SOA-SOFNN) prediction model according to the combustion principle of the coal-fired unit and the mechanism of the dust removal system; the system mainly comprises parameters such as unit load, main steam flow, total air quantity, total coal feeding quantity, primary fan valve opening, secondary fan valve opening, A-E mill coal feeding quantity, A-E mill secondary air opening and the like. Selecting a common network topological structure: and performing simulation calculation on the three-layer neural network, wherein 18 input nodes correspond to 18 input parameters related to boiler combustion.
The principal component analysis method for determining the training sample comprises the steps of calculating a covariance matrix, calculating an eigenvalue and an eigenvector of the covariance matrix, sequencing the eigenvalue and the eigenvector of the covariance matrix, solving a contribution rate, solving a load matrix of the eigenvector with the contribution rate larger than 85% and the original eigenvector, and reducing the dimension of the input parameter according to the load matrix.
S2: optimizing the number of hidden layer neurons of the RBF mixed neural network by a particle swarm parameter optimization algorithm, selecting parameters of the neural network, and initializing weights of the neural network;
the particle swarm parameter optimization algorithm firstly randomly initializes the position and the speed of particles, then defines a fitness function, tracks an individual optimal solution and a global optimal solution, updates the position and the speed of the individual optimal solution and the global optimal solution every time, calculates a fitness value every time iteration in the process, and reaches a set target fitness value after multiple iterations, thereby obtaining the optimal solution.
S3: training a prediction model and a controller of an SA-RBF (neural network-radial basis function) hybrid neural network model predictor by using a DPSO (distributed data acquisition) training algorithm to obtain a neural network weight parameter;
training samples except Xi to obtain a model Mi for each sample Xi in each training sample set X by the DPSO training algorithm; calculating gradient estimation of the sample Xi by adopting a sequencing lifting method and utilizing the model Mi; re-scoring the samples Xi by using the new model to form a weak learner; and performing weighting processing on all weak learners to obtain a final strong classifier.
S4: determining the lag time of the system, taking the input parameters and the actual output parameters as initial values of the controller, calculating a prediction error, and adjusting the parameters of the controller through the error;
on the basis of the extracted input parameters, related operation data formed by the smoke dust of the boiler of the coal-fired unit are continuously collected and analyzed for 30d, the operation data are collected for 1 time per minute, the unit load, the main steam flow, the total air quantity, the total coal feeding quantity, the opening of a primary air fan valve, the opening of secondary air fan valves from A mill to E mill, the opening of secondary air from A mill to E mill and other parameters input by each combustor are collated to be used as input parameters of an SOA-SOFNN prediction model, and meanwhile, the smoke dust concentration correspondingly measured at each moment is used as an output parameter to conduct model training.
S5: and calculating the output of the neural network prediction model to obtain the prediction output of the controlled object at the future moment, and acting the obtained prediction output on the controlled object as the control output.
Inputting real-time operation data of dust concentration influence factors of the dust collector inlet into the established intelligent SOA-SOFNN prediction model of the dust concentration to obtain the dust concentration of the dust collector inlet, and adjusting the voltage and the current of the dust collector according to the dust concentration of the inlet. Said basis is enteredThe method for regulating the voltage and the current of the dust remover by the concentration of the smoke dust comprises the following steps: when the concentration of the smoke dust is predicted to be higher than the designed concentration, the voltage and the current should be adjusted to the maximum input value, and when the concentration of the smoke dust is lower than the designed concentration, the voltage and the current should be reduced by the input value. According to the practical operation example of a certain power plant and the SOA-SOFNN prediction model, the dust concentration at the inlet of the dust remover is 25.2g/Nm332g/Nm below the design concentration3At this time, the input voltage and the input current of the dust remover are adjusted from 70kV, 539.82mA to 58kV, 420 mA.
The intelligent prediction and control method for the dust concentration at the inlet of the dust removal system adopts an independent external hanging platform and is connected with the DCS in a communication mode, so that the dust removal system can be accurately and reliably controlled.
In the embodiment of the invention, the method is applied to the control of a dust removal system of a certain power plant to verify the effect of the method, the deviation between the actual deviation of the dust removal system and the predicted dust removal system is 2.3 percent, and the inlet of the actual test dust removal system is 25.2g/Nm3Predicting the inlet smoke concentration of the dust removal system to be 24.6g/Nm3At the moment, the input voltage and the input current of the dust remover are adjusted to 58kV and 420mA from 70kV and 539.82mA, and the overall energy consumption is reduced by 20 percent, so that the method can effectively improve the stability of a dust removal system and simultaneously improve the automatic operation level and the system economy of the dust removal system of the thermal power generating unit.
The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, so: all equivalent changes made according to the structure, shape and principle of the invention are covered by the protection scope of the invention.
Claims (9)
1. The intelligent prediction and control method for the concentration of the smoke dust at the inlet of the dust removal system is characterized by comprising the following steps of: the method comprises the following steps:
s1: establishing a training sample N group of an SA-RBF mixed neural network model predictor;
s2: optimizing the number of hidden layer neurons of the RBF mixed neural network by a particle swarm parameter optimization algorithm, selecting parameters of the neural network, and initializing weights of the neural network;
s3: training a prediction model and a controller of an SA-RBF (neural network-radial basis function) hybrid neural network model predictor by using a DPSO (distributed data acquisition) training algorithm to obtain a neural network weight parameter;
s4: determining the lag time of the system, taking the input parameters and the actual output parameters as initial values of the controller, calculating a prediction error, and adjusting the parameters of the controller through the error;
s5: and calculating the output of the established smoke concentration intelligent SOA-SOFNN prediction model to obtain the prediction output of the controlled object at the future moment, and taking the prediction output as the control output to act on the controlled object.
2. The intelligent prediction and control method for the inlet smoke concentration of the dust removal system according to claim 1, characterized in that: the training sample of S1 comprises unit load, main steam flow, total air quantity, total coal feeding quantity, primary fan valve opening, secondary fan valve opening A-E grinding coal feeding quantity and A-E grinding secondary air opening.
3. The intelligent prediction and control method for the inlet smoke concentration of the dust removal system according to claim 2, characterized in that: the principal component analysis method for determining the training sample comprises the steps of calculating a covariance matrix, calculating an eigenvalue and an eigenvector of the covariance matrix, sequencing the eigenvalue and the eigenvector of the covariance matrix, solving a contribution rate, solving a load matrix of the eigenvector with the contribution rate larger than 85% and the original eigenvector, and reducing the dimension of the input parameter according to the load matrix.
4. The intelligent prediction and control method for the inlet smoke concentration of the dust removal system according to claim 1, characterized in that: in the S2, the particle group parameter optimization algorithm randomly initializes the position and speed of the particle, defines a fitness function, tracks the individual optimal solution and the global optimal solution, and updates the position and speed of the individual optimal solution and the global optimal solution each time.
5. The intelligent prediction and control method for the inlet smoke concentration of the dust removal system according to claim 1, characterized in that: training samples except for Xi to obtain a model Mi for each sample Xi in each training sample set X by the DPSO training algorithm in S3; calculating gradient estimation of the sample Xi by adopting a sequencing lifting method and utilizing the model Mi; re-scoring the samples Xi by using the new model to form a weak learner; and performing weighting processing on all weak learners to obtain a final strong classifier.
6. The intelligent prediction and control method for the inlet smoke concentration of the dust removal system according to claim 1, characterized in that: in the step S4, on the basis of the extracted input parameters, related operation data formed by the smoke dust of the boiler of the coal-fired unit are continuously collected and analyzed for 30d, the collection is performed for 1 time per minute, the unit load, the main steam flow, the total air quantity, the total coal supply quantity, the primary air fan valve opening, the secondary air fan valve opening, the grinding coal supply quantity from A to E and the grinding secondary air opening input by each combustor are arranged to be used as input parameters of an SOA-SOFNN prediction model, and meanwhile, the smoke dust concentration correspondingly measured at each moment is used as an output parameter to perform model training.
7. The intelligent prediction and control method for the inlet smoke concentration of the dust removal system according to claim 1, characterized in that: and in S5, inputting the real-time operation data of the dust concentration influence factors of the dust collector inlet into the established intelligent SOA-SOFNN prediction model of the dust concentration to obtain the dust concentration of the dust collector inlet, and adjusting the voltage and the current of the dust collector according to the dust concentration of the inlet.
8. The intelligent prediction and control method for the inlet smoke concentration of the dust removal system according to claim 7, wherein the method comprises the following steps: the method for adjusting the voltage and the current of the dust remover according to the concentration of the inlet smoke dust comprises the following steps: when the predicted smoke concentration is higher than the designed concentration, the voltage and current should be adjusted to the maximum input and output current, and when the smoke concentration is lower than the designed concentration, the input and output current of the dust remover should be reduced.
9. The intelligent prediction and control method for the inlet smoke concentration of the dust removal system according to claim 1, characterized in that: the intelligent prediction and control method for the smoke concentration at the inlet of the dust removal system adopts an independent external hanging platform and is connected with the DCS in a communication mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111516885.7A CN114492727A (en) | 2021-12-13 | 2021-12-13 | Intelligent prediction and control method for inlet smoke concentration of dust removal system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111516885.7A CN114492727A (en) | 2021-12-13 | 2021-12-13 | Intelligent prediction and control method for inlet smoke concentration of dust removal system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114492727A true CN114492727A (en) | 2022-05-13 |
Family
ID=81492893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111516885.7A Pending CN114492727A (en) | 2021-12-13 | 2021-12-13 | Intelligent prediction and control method for inlet smoke concentration of dust removal system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114492727A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115167321A (en) * | 2022-08-09 | 2022-10-11 | 绿能碳投(北京)科技有限公司 | Power plant electrostatic dust collection optimization control method and system |
-
2021
- 2021-12-13 CN CN202111516885.7A patent/CN114492727A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115167321A (en) * | 2022-08-09 | 2022-10-11 | 绿能碳投(北京)科技有限公司 | Power plant electrostatic dust collection optimization control method and system |
| CN115167321B (en) * | 2022-08-09 | 2023-11-21 | 绿能碳投(北京)科技有限公司 | Power plant electrostatic dust removal optimization control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105864797B (en) | Real-time prediction system and method for boiler entering heat value of circulating fluidized bed household garbage incineration boiler | |
| CN109420424A (en) | A kind of wet desulfurization of flue gas by limestone-gypsum method energy saving of system optimization method | |
| US7584024B2 (en) | Method and apparatus for optimizing operation of a power generating plant using artificial intelligence techniques | |
| CN102778538B (en) | Soft measuring method based on improved SVM (Support Vector Machine) for measuring boiler unburned carbon content in fly ash | |
| US8135653B2 (en) | Power plant control device which uses a model, a learning signal, a correction signal, and a manipulation signal | |
| CN107726358A (en) | Boiler Combustion Optimization System and method based on CFD numerical simulations and intelligent modeling | |
| CN106224939B (en) | Circulating fluid bed domestic garbage burning boiler bed temperature Forecasting Methodology and system | |
| CN109541168B (en) | Coal powder economic fineness on-line monitoring and adjusting method | |
| CN110263395A (en) | The power plant's denitration running optimizatin method and system analyzed based on numerical simulation and data | |
| WO2020192166A1 (en) | Method for soft measurement of dioxin emission concentration in municipal solid waste incineration process | |
| CN106202946A (en) | Clinker free calcium levels Forecasting Methodology based on degree of depth belief network model | |
| CN110597070B (en) | Method for identifying model parameters of thermal power generating unit system | |
| CN111754093A (en) | Fly ash carbon content prediction method based on coal quality prediction and PSO-SVM | |
| CN113440990A (en) | EMD-LSTM based outlet SO2Concentration prediction method | |
| Cass et al. | Adaptive process optimization using functional-link networks and evolutionary optimization | |
| CN114492727A (en) | Intelligent prediction and control method for inlet smoke concentration of dust removal system | |
| CN110400018A (en) | Progress control method, system and device for coal-fired firepower electrical plant pulverized coal preparation system | |
| CN114632624B (en) | Electric dust removal operation optimization system and optimization method | |
| CN115437245A (en) | Boiler optimization control method based on combustion state prediction model | |
| CN111199304B (en) | Multi-target combustion optimization method based on data-driven fusion strategy | |
| CN116085823A (en) | Boiler combustion control method and system | |
| CN115526433A (en) | Power plant reheat flue gas baffle operation prediction method based on integrated hybrid model | |
| CN115809744A (en) | Fly ash carbon content prediction method based on genetic simulated annealing parameter optimization | |
| CN115656439A (en) | Online monitoring method for nitrogen oxide emission concentration of coal-fired unit based on transfer learning | |
| CN117851767A (en) | Building carbon emission measuring and calculating method based on electric power big data and machine learning |
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 |