CN115964968A - Multi-objective optimization method and system for ultra-low nitrogen combustor and storage medium - Google Patents
Multi-objective optimization method and system for ultra-low nitrogen combustor and storage medium Download PDFInfo
- Publication number
- CN115964968A CN115964968A CN202310077664.7A CN202310077664A CN115964968A CN 115964968 A CN115964968 A CN 115964968A CN 202310077664 A CN202310077664 A CN 202310077664A CN 115964968 A CN115964968 A CN 115964968A
- Authority
- CN
- China
- Prior art keywords
- model
- ultra
- low nitrogen
- objective optimization
- nitrogen combustor
- 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
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 title claims abstract description 159
- 238000005457 optimization Methods 0.000 title claims abstract description 121
- 229910052757 nitrogen Inorganic materials 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000002485 combustion reaction Methods 0.000 claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 41
- 238000005336 cracking Methods 0.000 claims abstract description 38
- VGGSQFUCUMXWEO-UHFFFAOYSA-N Ethene Chemical compound C=C VGGSQFUCUMXWEO-UHFFFAOYSA-N 0.000 claims abstract description 37
- 239000005977 Ethylene Substances 0.000 claims abstract description 37
- 230000004044 response Effects 0.000 claims abstract description 33
- 239000003795 chemical substances by application Substances 0.000 claims abstract description 12
- 238000013528 artificial neural network Methods 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 24
- 238000004088 simulation Methods 0.000 claims description 22
- 230000002068 genetic effect Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 239000012530 fluid Substances 0.000 claims description 7
- 230000035772 mutation Effects 0.000 claims description 7
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 239000003546 flue gas Substances 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 239000000779 smoke Substances 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims description 2
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 93
- 238000013461 design Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 230000009467 reduction Effects 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004134 energy conservation Methods 0.000 description 3
- 239000003344 environmental pollutant Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000012938 design process Methods 0.000 description 2
- 239000002737 fuel gas Substances 0.000 description 2
- 239000000383 hazardous chemical Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 238000003916 acid precipitation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 229910002091 carbon monoxide Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- FKLFBQCQQYDUAM-UHFFFAOYSA-N fenpiclonil Chemical compound ClC1=CC=CC(C=2C(=CNC=2)C#N)=C1Cl FKLFBQCQQYDUAM-UHFFFAOYSA-N 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 239000004071 soot Substances 0.000 description 1
- XTQHKBHJIVJGKJ-UHFFFAOYSA-N sulfur monoxide Chemical class S=O XTQHKBHJIVJGKJ-UHFFFAOYSA-N 0.000 description 1
- 229910052815 sulfur oxide Inorganic materials 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Abstract
The invention provides a multi-objective optimization method, an optimization system and a storage medium for an ultra-low nitrogen combustor. The multi-objective optimization method comprises the following steps: constructing a parameterized grid model; constructing an emission concentration prediction model of NOx and CO in the ultra-low nitrogen combustor; constructing a multi-feature quick response proxy model based on the parameterized grid model and the emission concentration prediction model; and performing multi-objective optimization solution on the multi-feature quick response agent model in the combustion process of the ethylene cracking furnace within the allowable range of the structural parameters by adopting an NSGA-II evolutionary algorithm to determine the optimized variable values of the structural parameters. By adopting the configuration, the invention can optimize each structural variable of the low-nitrogen combustor, reduce the NOx emission concentration and simultaneously realize the maximization of the combustion efficiency of the cracking furnace.
Description
Technical Field
The invention relates to the field of structural optimization of ultra-low nitrogen combustors, in particular to an ultra-low nitrogen combustor multi-target optimization method based on parametric modeling, an ultra-low nitrogen combustor multi-target optimization system and a computer readable storage medium.
Background
With the development of the economic level of China and the progress of the petrochemical industry technology, some large petrochemical design units in China have mastered the design technology of large ethylene complete equipment at present. Under the trend of large-scale ethylene devices, in order to meet the new requirements of energy conservation, consumption reduction and environmental protection, the ethylene process needs to be further optimized.
The ethylene cracking furnace is the main energy consumption equipment of an ethylene production device, and the consumed fuel gas accounts for more than 60 percent of the comprehensive energy consumption of the ethylene device. The burner is the source of heat for the ethylene cracking furnace and is therefore an extremely important component. The burner is a direct factor for determining the combustion performance of the ethylene cracking furnace, such as combustion efficiency, combustion stability, nitrogen oxide emission and the like. The good burner structure can realize uniform and stable combustion effect. With the environmental problems arousing more and more attention, energy conservation and emission reduction become problems which need to be solved urgently, and the limit on the emission of harmful environmental pollutants is more and more strict. Some secondary combustion products are major pollutants such as carbon monoxide, unburned hydrocarbons, soot, sulfur oxides, and nitrogen oxides (NOx). NOx not only causes toxic effects to the human body, but also causes photochemical smog, causes acid rain, causes depletion of the ozone layer, and thus causes health and environmental hazards.
Currently, the NOx emission of the ethylene cracking furnace can be controlled by modifying the structure of the burner. However, there is a contradiction between the NOx emission concentration and the combustion efficiency of the ethylene cracking furnace, and it is not possible to consider only how to reduce the emission concentration of nitrogen oxides without considering the actual combustion efficiency. In the prior art, the selection of the set value of the structural variable of the burner in the cracking furnace mainly refers to the scheme of the inherent cracking furnace provided by a patent manufacturer, the latest emission requirement is always not considered, and the combustion efficiency, the emission of nitrogen oxides and the like are greatly influenced.
In order to overcome the defects in the prior art, a multi-objective optimization technology of an ultra-low nitrogen burner is urgently needed in the field, and is used for solving the multi-objective optimization problems of combustion efficiency and nitrogen oxide emission in the combustion process of an ethylene cracking furnace, so that the combustion efficiency of the cracking furnace is maximized on the basis of reducing the emission concentration of NOx.
Disclosure of Invention
The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements of all aspects nor delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
In order to overcome the defects in the prior art, the invention provides a multi-objective optimization method of an ultra-low nitrogen burner, a multi-objective optimization system of the ultra-low nitrogen burner and a computer readable storage medium, which can solve the problem of multi-objective optimization of combustion efficiency and nitrogen oxide emission in the combustion process of an ethylene cracking furnace by optimizing various structural variables of the low nitrogen burner, thereby realizing the maximization of the combustion efficiency of the cracking furnace on the basis of reducing the NOx emission concentration.
Specifically, a method for multi-objective optimization of an ultra-low nitrogen combustor provided according to a first aspect of the present invention includes the steps of: constructing a parameterized grid model according to the geometric structure of the ultra-low nitrogen combustor; according to the parameterized grid model and the actual industrial principle of the ultra-low nitrogen combustor, constructing an emission concentration prediction model of NOx and CO in the ultra-low nitrogen combustor; taking the structural parameters of the ultra-low nitrogen combustor as optimization variables, taking the NOx and CO emission concentration of the ultra-low nitrogen combustor as an objective function, and constructing a multi-feature quick response proxy model based on the parameterized grid model and the emission concentration prediction model; and performing multi-objective optimization solution on the multi-feature quick response agent model in the combustion process of the ethylene cracking furnace within the allowable range of the structural parameters by adopting an NSGA-II evolutionary algorithm to determine the optimized variable values of the structural parameters.
Further, in some embodiments of the present invention, the step of constructing a parameterized grid model based on the geometry of the ultra low nitrogen combustor comprises: constructing a geometric model according to the geometric structure of the ultra-low nitrogen burner; extracting structural parameters characterizing the complete structure of the geometric model from the geometric model to construct a parameterized log; defining a mesh partitioning variable in the parameterized log to set a corresponding mesh size value; building a visual interface, inputting a grid size value corresponding to the grid division variable into the visual interface, and carrying out grid division on the geometric model to obtain an initial parameterized grid model; and performing fluid dynamics simulation on the initial parameterized grid model, and setting boundary conditions and fluid properties of the initial parameterized grid model to obtain the parameterized grid model.
Further, in some embodiments of the present invention, the step of constructing a prediction model of NOx and CO emission concentrations in the ultra-low nitrogen combustor based on the parameterized grid model and the actual industrial principles of the ultra-low nitrogen combustor comprises: constructing a coupling model reflecting turbulence-combustion interaction by adopting a standard k-epsilon turbulence model reflecting the actual industrial principle of the ultra-low nitrogen combustor, a DO radiation model and a finite rate/vortex dissipation-aftertreatment NOx combustion model; performing CFD numerical simulation on the coupling model to obtain a simulation result of the flame temperature and/or the content of the smoke components; comparing the simulation result of the flame temperature and/or the flue gas component content with actual data, and analyzing the reason of the result deviation so as to correct the structural parameters and the boundary conditions of the parameterized grid model; and based on the corrected structural parameters and boundary conditions, carrying out CFD numerical simulation again and correcting the structural parameters and boundary conditions of the parameterized grid model until the deviation of the simulation result and the actual data meets the simulation precision requirement.
Further, in some embodiments of the invention, the structural parameters include damper size, primary orifice diameter, secondary orifice diameter, and orifice inclination angle.
Further, in some embodiments of the present invention, the step of constructing a multi-feature fast response proxy model based on the parameterized grid model and the emission concentration prediction model with the structural parameters of the ultra-low nitrogen combustor as optimization variables and the NOx and CO emission concentrations of the ultra-low nitrogen combustor as objective functions comprises: constructing an objective function by taking the emission concentrations of NOx and CO as target values; establishing a constraint condition based on structural parameter variables according to the parameter ranges of the size of the air door, the diameter of the primary nozzle, the diameter of the secondary nozzle and the inclination angle of the nozzle of the ultra-low nitrogen burner; and establishing a multi-feature rapid response proxy model of the ultra-low nitrogen combustor in the ethylene cracking furnace by combining the objective function and based on a data regression prediction method for optimizing the BP neural network by a genetic algorithm.
Further, in some embodiments of the present invention, the step of establishing a multi-feature fast response proxy model of the ultra-low nitrogen burner in the ethylene cracking furnace based on a data regression prediction method for optimizing a BP neural network based on a genetic algorithm in combination with the objective function comprises: creating a BP neural network to determine a topological structure thereof; determining an initial weight value and a threshold value of the BP neural network, and coding the initial weight value and the threshold value to obtain an initial population; in response to the fact that the current iteration times are smaller than the preset maximum iteration times, taking each individual in the current population as an initial weight and a threshold of the BP neural network, training by using a training sample, and calculating a training error of the training sample to be used as the fitness of each individual; selecting the optimal individual of the current population according to the fitness of each individual; performing selection, crossover and mutation genetic algorithm operation based on the optimal individuals to obtain a new population; and selecting the final optimal individual in response to the current iteration times reaching the maximum iteration times so as to obtain the optimal BP neural network weight and threshold.
Further, in some embodiments of the invention, the expression of the objective function is as follows:
wherein, { a 1 ,a 2 ,…,a m Is m structural parameters obtained by screening,
is NOx emission concentration, <' > based on>
Is the CO emission concentration.
Further, in some embodiments of the invention, the constraints include:
L min ≤L≤L max
W min ≤W≤W max
wherein L is the length of the damper, W is the width of the damper, L min 、W min Is the minimum value of the length and width of the damper, L max 、W max The maximum values of the length and the width of the air door are respectively;
R fmin ≤R f ≤R fmax
wherein R is f Is the primary orifice diameter, R fmax 、R fmin The maximum value and the minimum value of the diameter of the primary nozzle are respectively;
R smin ≤R s ≤R smax
wherein R is s For the second-stage nozzle to be straightDiameter, R smax 、R smin The maximum value and the minimum value of the diameter of the secondary nozzle are respectively; and
N min ≤N≤N max
wherein N is the spout inclination angle, N max 、N min The maximum value and the minimum value of the spout inclination angle are respectively.
Further, in some embodiments of the present invention, the step of performing a multi-objective optimization solution on the multi-feature fast response surrogate model for the combustion process of the ethylene cracking furnace within the allowable range of the structural parameter by using the NSGA-II evolutionary algorithm to determine the optimized variable value of the structural parameter includes: performing multi-objective optimization solution of the combustion process of the ethylene cracking furnace through a multi-objective decision model, wherein the multi-objective decision model is as follows:
wherein,
further, in some embodiments of the present invention, the step of performing a multi-objective optimization solution on the multi-feature fast response surrogate model for the combustion process of the ethylene cracking furnace within the allowable range of the structural parameter by using the NSGA-II evolutionary algorithm to determine the optimized variable value of the structural parameter further includes: setting the number N of the initialized population, the maximum iteration number, the cross probability, the mutation probability, the cross distribution index and the mutation distribution index of the NSGA-II evolutionary algorithm to obtain a parent population P t Wherein t =1; for the parent population P t Each individual in (a) is subjected to non-dominance sorting to obtain a first non-dominance set; calculating the congestion of each individual in each non-dominating setExtruding degree, and obtaining offspring population Q through selection, crossing and variation t (ii) a The filial generation population Q t And the parent population P t Combined to form a population R t And applying said population R according to the elite strategy t Performing non-dominance ordering to generate a second non-dominance set; calculating the crowdedness of the second non-dominating set to generate a new offspring population Q t+1 (ii) a And judging whether the iteration times reach the maximum iteration times, if so, outputting the optimal solution of the decision variables, and terminating the algorithm, otherwise, if not, enabling t = t +1, and performing iteration calculation again.
Further, a multi-objective optimization system for an ultra-low nitrogen combustor is provided in accordance with a second aspect of the invention and includes a memory and a processor. The memory has stored thereon computer instructions. The processor is coupled to the memory and configured to execute computer instructions stored on the memory to implement the multi-objective optimization method for an ultra-low nitrogen combustor as described in any one of the above.
Further, according to a third aspect of the present invention, there is provided a computer readable storage medium having stored thereon computer instructions. The computer instructions, when executed by a processor, implement the multi-objective optimization method for an ultra-low nitrogen combustor as described in any one of the above.
Drawings
The above features and advantages of the present disclosure will be better understood upon reading the detailed description of embodiments of the disclosure in conjunction with the following drawings. In the drawings, components are not necessarily drawn to scale, and components having similar associated characteristics or features may have the same or similar reference numerals.
FIG. 1 illustrates a flow diagram of an ultra-low nitrogen combustor multi-objective optimization method based on parametric modeling provided in accordance with some embodiments of the present invention;
FIG. 2 illustrates a flow diagram of a parametric modeling method provided in accordance with some embodiments of the invention;
FIG. 3 illustrates a flow diagram of a data regression prediction method for optimizing BP neural networks based on genetic algorithms provided in accordance with some embodiments of the present invention;
FIG. 4 illustrates a flow diagram of an NSGA-II evolutionary algorithm provided in accordance with some embodiments of the present invention;
fig. 5 illustrates a schematic diagram of an approximate pareto front provided in accordance with some embodiments of the invention.
Detailed Description
The following description of the embodiments of the present invention is provided for illustrative purposes, and other advantages and effects of the present invention will become apparent to those skilled in the art from the present disclosure. While the invention will be described in connection with the preferred embodiments, there is no intent to limit its features to those embodiments. On the contrary, the invention is described in connection with the embodiments for the purpose of covering alternatives or modifications that may be extended based on the claims of the present invention. In the following description, numerous specific details are included to provide a thorough understanding of the invention. The invention may be practiced without these particulars. Moreover, some of the specific details have been left out of the description in order to avoid obscuring or obscuring the focus of the present invention.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Additionally, the terms "upper," "lower," "left," "right," "top," "bottom," "horizontal," "vertical" and the like as used in the following description are to be understood as referring to the segment and the associated drawings in the illustrated orientation. The relative terms are used for convenience of description only and do not imply that the described apparatus should be constructed or operated in a particular orientation and therefore should not be construed as limiting the invention.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, regions, layers and/or sections, these elements, regions, layers and/or sections should not be limited by these terms, but rather are used to distinguish one element, region, layer and/or section from another element, region, layer and/or section. Thus, a first component, region, layer or section discussed below could be termed a second component, region, layer or section without departing from some embodiments of the present invention.
As described above, in the trend of large-scale ethylene plants, the ethylene process needs to be further optimized to meet the new requirements of energy saving, consumption reduction and environmental protection. The ethylene cracking furnace is the main energy consumption equipment of an ethylene production device, and the consumed fuel gas accounts for more than 60 percent of the comprehensive energy consumption of the ethylene device. The burner is the source of heat for the ethylene cracking furnace and is therefore an extremely important component. With the environmental problems arousing more and more attention, energy conservation and emission reduction become problems which need to be solved urgently, and the limit on the emission of harmful environmental pollutants is more and more strict.
At present, NOx emission of the ethylene cracking furnace can be controlled by modifying the structure of the burner, however, the contradiction exists between the NOx emission concentration and the combustion efficiency of the ethylene cracking furnace, and the reduction of the emission concentration of nitrogen oxides can not be considered without considering the actual combustion efficiency. In the prior art, the selection of the set value of the structural variable of the burner in the cracking furnace mainly refers to the scheme of the inherent cracking furnace provided by a patent manufacturer, the latest emission requirement is always not considered, and the combustion efficiency, the emission of nitrogen oxides and the like are greatly influenced.
In order to overcome the defects in the prior art, the invention provides an ultra-low nitrogen combustor multi-objective optimization method based on parametric modeling, an ultra-low nitrogen combustor multi-objective optimization system and a computer readable storage medium, which can solve the problem of multi-objective optimization of combustion efficiency and nitrogen oxide emission in the combustion process of an ethylene cracking furnace by optimizing each structural variable of a low nitrogen combustor, thereby realizing the maximization of the combustion efficiency of the cracking furnace on the basis of reducing the NOx emission concentration.
In some non-limiting embodiments, the multi-objective optimization method for the ultra-low nitrogen combustor provided in the first aspect of the invention may be implemented based on the multi-objective optimization system for the ultra-low nitrogen combustor provided in the second aspect of the invention. Specifically, the multi-objective optimization system is provided with a memory and a processor. The memory includes, but is not limited to, the above-described computer-readable storage medium provided by the third aspect of the present invention having computer instructions stored thereon. The processor is coupled to the memory and configured to execute computer instructions stored on the memory to implement the multi-objective optimization method for ultra-low nitrogen burners as provided in the first aspect of the invention.
The working principle of the multi-objective optimization system will be described below in connection with some embodiments of the multi-objective optimization method. It will be appreciated by those skilled in the art that these examples of the multi-objective optimization method are only a few non-limiting embodiments provided by the present invention, which are intended to clearly illustrate the broad concepts of the present invention and to provide some detailed solutions which are convenient for the public to implement, and are not intended to limit the overall functionality or overall operation of the multi-objective optimization system. Similarly, the multi-objective optimization system is only a limited embodiment provided by the present invention, and does not limit the execution subject or execution sequence of the steps in the multi-objective optimization method.
Please refer to fig. 1 and fig. 2 first. FIG. 1 illustrates a flow diagram of an ultra-low nitrogen combustor multi-objective optimization method based on parametric modeling provided in accordance with some embodiments of the present invention. FIG. 2 illustrates a flow diagram of a parametric modeling method provided in accordance with some embodiments of the invention.
As shown in FIG. 1, in performing multiobjective optimization of ultra-low nitrogen combustors, the multiobjective optimization system may first perform step S1: and constructing a parameterized grid model according to the geometric structure of the ultra-low nitrogen combustor.
Specifically, as shown in fig. 2, in the process of constructing the parameterized mesh model, the multi-objective optimization system may first establish a geometric model according to the selected combustor structure, and then extract parameters that can represent the complete structure of the model from the established geometric model to construct the parameterized log. Here, the structural parameters include, but are not limited to, damper size, primary orifice diameter, secondary orifice diameter, and orifice inclination angle. The parameterized log may be implemented as a GAMBIT parameterized log file. When the size of the model is changed subsequently, the multi-objective optimization system only needs to change and replace the parameters by using a variable replacement method, and the set parameter values are changed to realize simple reconstruction and automatic modeling of the model.
And then, the multi-objective optimization system can define mesh division variables in the generated log file, set corresponding parameter variables for different line, surface and body mesh division, and input mesh division parameters in the set visual interface so as to automatically edit and generate the log file. Here, these meshing variables may be used to set the corresponding mesh size values. The multi-objective optimization system can drive the meshing software to realize meshing and quickly and efficiently generate meshing files with different parameters.
And then, the multi-objective optimization system can utilize FLUENT software to carry out fluid dynamics simulation on the initial parameterized grid model, generate and check the network model, and set boundary conditions and the fluid properties of the materials. And then, the multi-objective optimization system can select a calculation model through the setting of a solving method, control and monitoring, carry out initialization calculation and solving, and return a result after calculation convergence. Otherwise, if the calculation fails to converge, the multi-objective optimization system may return to the steps of material and boundary setting for adjustment. Furthermore, the multi-objective optimization system can adjust parameter setting and physical models, respectively perform CFD calculation on combustors with different structures, and acquire a large amount of data to construct a database.
As shown in FIG. 1, after constructing the parameterized mesh model, the multi-objective optimization system may perform step S2: and constructing an emission concentration prediction model of NOx and CO in the ultra-low nitrogen combustor according to the parameterized grid model and the actual industrial principle of the ultra-low nitrogen combustor.
Specifically, in the process of constructing the emission concentration prediction model, the multi-objective optimization system can firstly use a standard k-epsilon turbulence model reflecting the actual characteristics of the ultra-low nitrogen combustor, a DO radiation model and a finite rate/vortex dissipation-aftertreatment NOx combustion model to construct an ultra-low nitrogen combustor CFD model conforming to the industrial practice, and realize the accurate prediction of the NOx and CO concentration emission.
Further, based on the three-dimensional grid model of the ultra-low nitrogen combustor established in the GAMBIT software in the step S1 and the fluid calculation performed on the Fluent 19.2 platform, in order to ensure the accuracy of CFD simulation data, the multi-objective optimization system can adopt a turbulence model of a standard k-epsilon model, a DO radiation model and a finite rate/vortex dissipation-aftertreatment NOx combustion model to establish a turbulence-combustion interaction coupling model to perform CFD numerical simulation, compare simulation results of key combustion characteristic parameters (flame temperature, content of each component of flue gas and the like) with actual data, analyze the reasons of result deviation, correct model parameters, boundaries and initial conditions, and re-simulate precision until the simulation precision reaches the requirements. Furthermore, the multi-objective optimization system can research the NOx emission through numerical simulation to determine the influence rule of different structural parameters on the NOx and CO emission concentration of the combustor.
As shown in FIG. 1, after constructing the prediction model of the NOx and CO emission concentrations in the ultra-low nitrogen combustor, the multi-objective optimization system may perform step S3: and (3) constructing a multi-feature quick response proxy model based on a parameterized grid model and an emission concentration prediction model by taking the structural parameters of the ultra-low nitrogen combustor as optimization variables and the NOx and CO emission concentrations of the ultra-low nitrogen combustor as objective functions.
Specifically, in the process of constructing the multi-feature rapid response proxy model, the multi-objective optimization system can firstly construct an objective function by taking the emission concentration of NOx and CO as target values, establish a constraint condition based on structural parameter variables according to the parameter ranges of the size of a throttle of the ultra-low nitrogen combustor, the diameter of a primary nozzle, the diameter of a secondary nozzle and the inclination angle of the nozzle, and then establish the multi-feature rapid response proxy model of the ultra-low nitrogen combustor in the ethylene cracking furnace by combining the objective function and a data regression prediction method based on genetic algorithm optimization BP neural network.
Further, the constraint condition based on the structure parameter variable includes:
L min ≤L≤L max
W min ≤W≤W max
wherein L is the length of the air door, W is the width of the air door, and L min 、W min Respectively, the minimum of the length and width of the damper, L max 、W max The maximum values of the length and width of the damper, respectively.
In addition, the constraint condition based on the structure parameter variable further comprises:
R fmin ≤R f ≤R fmax
wherein R is f Is a primary orifice diameter, R fmax 、R fmin The maximum value and the minimum value of the primary nozzle diameter are respectively.
In addition, the constraint condition based on the structure parameter variable further comprises:
R smin ≤R s ≤R smax
wherein R is s Is a secondary orifice diameter, R smax 、R smin The maximum value and the minimum value of the diameter of the secondary nozzle are respectively.
In addition, the constraint condition based on the structure parameter variable further comprises:
N min ≤N≤N max
wherein N is the inclination angle of the nozzle, and N is max 、N min Respectively the maximum value and the minimum value of the spout inclination angle.
Based on the constraint conditions, the multi-objective optimization system can sequentially execute the steps of test design, sample point simulation calculation, function fitting, proxy model precision evaluation and the like so as to construct a multi-feature quick response proxy model.
Specifically, the multi-objective optimization system can select design variables and value ranges, generate sampling points by adopting Latin hypercube sampling, select the ultra-low nitrogen burner models with different structures automatically generated according to the sampling points in the step S1 each time, and perform CFD calculation on the models. Here, in the process of sampling the sample points by using the latin hypercube sampling method, the multi-objective optimization system may first divide each dimension into m non-overlapping intervals, so that each interval has the same probability (usually, a uniform distribution is considered, and thus the lengths of the intervals are the same). Thereafter, the multi-objective optimization system may randomly extract one point in each interval in each dimension, and then randomly extract the points selected in step S312 from each dimension to form them into a vector. And then, the multi-objective optimization system can count the analysis result of the numerical simulation.
The statistics uses an ultra-low nitrogen burner as a research object, the structural parameters of the statistics mainly comprise burner structures such as air door size, primary nozzle diameter, secondary nozzle diameter, nozzle inclination angle and the like, and the output variables of the statistics are NOx and CO concentrations of a flue gas outlet of a cracking furnace. The technician can perform a number of CFD calculations using the above-described configuration parameters as input variables to obtain raw input-output data sets and construct a database. Then, the technician can continuously train the data in the database as a training set and a test set to complete the establishment of the multi-feature quick response agent model, and finally obtain the expression of the objective function as follows:
wherein, { a 1 ,a 2 ,…,a m Is m structural parameters obtained by screening,
is the NOx emission concentration, <' > based>
Is the CO emission concentration.
Furthermore, the multi-feature quick response agent model can be established based on a data regression prediction method for optimizing the BP neural network by the genetic algorithm, and mainly comprises the steps of determining the structure of the BP neural network, determining the optimization weight and threshold of the genetic algorithm and training the BP neural network.
Here, the topology of the BP neural network is determined according to the number of input/output parameters of the sample. Thus, the number of optimization parameters of the genetic algorithm can be determined, and the encoding length of the population individuals can be determined. Because the genetic algorithm optimization parameters are the initial weight and the threshold of the BP neural network, the number of the weight and the threshold can be determined as long as the network structure is known. The weights and thresholds of the neural network are generally initialized randomly to random numbers in the range of [ -0.5,0.5], and the training results of the network are the same. And the optimal initial weight and threshold can be optimized by introducing a genetic algorithm.
In addition, the genetic algorithm optimizes the BP neural network to obtain better initial weight and threshold of the network through the genetic algorithm, and the basic idea is to use an individual to represent the initial weight and threshold of the network, take the norm of the test error of the BP neural network of a prediction sample as the output of an objective function, further calculate the fitness value of the individual, and then search for the optimal individual through selection, intersection and variation operations, namely the optimal initial weight and threshold of the BP neural network.
Referring further to fig. 3, fig. 3 illustrates a flow chart of a data regression prediction method for optimizing a BP neural network based on a genetic algorithm according to some embodiments of the present invention.
As shown in fig. 3, in the data regression prediction method for optimizing the BP neural network based on the genetic algorithm, in the process of establishing the multi-feature fast response agent model, the multi-objective optimization system may first create a network to determine the topology structure of the neural network.
In particular, the created neural network may comprise a three-layer network structure in which there is an approximate relationship between the number of hidden layer neural networks n2 and the number of input layer neurons n1 (e.g., n) 2 ＝2×n 1 +1). In this embodiment, since the sample has 4 input parameters and 2 output parameters, n here 2 Value takingIs 9, and the BP neural network structure is set to be 4-9-2, i.e. 4 nodes of the input layer, 9 nodes of the hidden layer, 2 nodes of the output layer, the number of weights is 4 × 9+9 × 2=54, the number of thresholds is 9+2=11, and the number of decision variables in the genetic algorithm is 65.
Here, the modular length of the test error vector of the test sample can be used to measure the generalization ability (i.e., fitness) of the network, and the smaller the fitness, the smaller the error, i.e., the better the individual.
Furthermore, the transfer function of the hidden layer neurons of the neural network may use an S-type tangent function, while the transfer function of the output layer neurons may use an S-type logarithmic function, to satisfy the output requirement that the network result is 0 or 1.
In some embodiments, the set number of training times may be set to 1000, the required accuracy of training may be set to 0.01, and the learning rate may be set to 0.1.
Then, as shown in fig. 3, the multi-objective optimization system may determine an initial weight value and a threshold value of the network, encode the initial weight value and the threshold value to obtain an initial population, perform iterative computation when the current iteration number (Gen) is less than the maximum iteration number (maxGen), and calculate a fitness to select an optimal individual. Here, for each individual in the population, the multi-objective optimization system may use the initial weight and the threshold of the network as well as a training sample for training, and the training error is regarded as fitness, and then a genetic algorithm operation of selection, crossing and variation is performed to obtain a new population. Then, the multi-objective optimization system can repeat iteration within the range below the maximum iteration times (maxGen) to obtain a new population and select the final optimal individual so as to obtain the optimal weight and threshold of the neural network.
Further, after the agent model is built, the multi-objective optimization system can perform error precision analysis and verification on the agent model to determine whether the built agent model is available. The multi-feature quick response proxy model achieving the precision requirement can be used for replacing complex and time-consuming CFD calculation in the optimization design process, and solving an objective function so as to optimize design parameters and achieve the purpose of controlling the calculation cost. Otherwise, for the multi-feature quick response agent model which does not reach the precision requirement, the multi-objective optimization system can continue to increase sample points for refitting or improve the model to improve the prediction precision until the precision requirement is reached.
As shown in FIG. 1, after constructing the multi-feature rapid response agent model, the multi-objective optimization system may perform step S4: and performing multi-objective optimization solution on the multi-characteristic quick response agent model in the allowable range of the structural parameters by adopting an NSGA-II evolutionary algorithm to determine the optimization variable values of the structural parameters, thereby obtaining the NOx emission which is as low as possible in the combustion process of the cracking furnace through multi-objective optimization and simultaneously ensuring the optimal structural parameter design scheme of the combustion efficiency in the combustor.
Specifically, in the multi-objective optimization design process of the ultra-low nitrogen combustor, the multi-objective optimization system can take the generation concentration of NOx and CO as an optimization target, and continuously optimize the structural parameters of the ultra-low nitrogen combustor by combining a multi-feature quick response proxy model of the combustor and a selected multi-objective optimization algorithm. When two targets of emission concentration of CO and NOx are optimized, the optimization targets are difficult to be respectively achieved, so that the pareto optimization system can achieve an ideal state of resource allocation by adopting pareto optimization.
Further, the objective function is to minimize the CO generation concentration while minimizing the NOx emission concentration, and then add constraints to improve the optimization. The constraint condition is used for controlling the value of each decision variable in a reasonable range. The decision variables are structural parameters selected for use in building the proxy model. Multiple iterations are carried out through the NSGA-II evolutionary algorithm to continuously approach the optimal solution, and the multi-objective optimization system can finally obtain the optimal design scheme of the structural parameters of the ultra-low nitrogen combustor.
Specifically, in the process of performing multi-objective optimization solution, the multi-objective optimization system may perform the multi-objective optimization solution of the combustion process of the ethylene cracking furnace through a multi-objective decision model, where the multi-objective decision model is:
with further reference to fig. 4, fig. 4 illustrates a flow diagram of the NSGA-II evolutionary algorithm provided in accordance with some embodiments of the present invention.
As shown in fig. 4, in the process of searching for and obtaining optimized structural parameters of the combustor by using the NSGA-II evolutionary algorithm, the multi-objective optimization system may first set parameters such as the number N of the initialized population, the maximum iteration number, the cross probability, the mutation probability, the cross distribution index, and the mutation distribution index of the NSGA-II evolutionary algorithm, to obtain the parent population Pt, where t =1. Thereafter, the multi-objective optimization system may target the parent population P t The individuals in the group are subjected to non-domination sorting to obtain a first non-domination set, the crowdedness of each individual in each non-domination set is calculated, and then the offspring population Qt is obtained through selection, crossing and variation. And then, the multi-objective optimization system can combine the child population Qt and the parent population Pt to form a population Rt with the size of 2N, perform non-dominated sorting on the population according to an elite strategy to generate a second non-dominating set, and then calculate the crowding degree to generate a new child population Qt +1. And then, the multi-objective optimization system can carry out evolution iteration of the population generation by generation, and judge whether the current iteration number (Gen) reaches the preset maximum iteration number (maxGen) or not. And if the current iteration times do not reach the preset maximum iteration times, the multi-target optimization system can return to the step of generating a new filial generation population, so that the current iteration times Gen = Gen +1, and the iterative calculation of selection, intersection and variation is continuously carried out. On the contrary, if the current iteration number reaches the preset maximum iteration number, the multi-objective optimization system can output the optimal solution of the decision variables and terminate the NSGA-II evolutionary algorithm.
Please refer to fig. 5 and table 1. Fig. 5 illustrates a schematic diagram of an approximate pareto front provided in accordance with some embodiments of the invention. Table 1 gives the values of the structural parameters corresponding to the optimized concentration boundaries.
TABLE 1 results of structural parameters corresponding to optimized boundaries
Thus, a decision maker can select a set of non-dominant solutions to guide the design of an actual desired industrial model of an ultra-low nitrogen combustor configuration based on needs and preferences.
In summary, the multi-objective optimization method, the multi-objective optimization system and the computer-readable storage medium for the ultra-low nitrogen combustor based on the parametric modeling provided by the invention have the following implementation optimization effects:
(1) An ultra-low nitrogen combustor is combined with a turbulence and combustion model to complete effective turbulence-combustion action mechanism coupling CFD calculation, so that the concentration of NOx and CO at an outlet can be accurately predicted;
(2) The method for modeling and dividing the grids in a multi-objective optimization mode is innovatively introduced, the work of automatically completing geometric modeling and dividing the grids is realized, the time and the workload for completing modeling and dividing the grids are greatly reduced, and the structural optimization of multi-objective optimization is assisted to be completed;
(3) Establishing an ultra-low nitrogen combustor multi-feature quick response proxy model scheme based on a data regression prediction method for optimizing a BP neural network by a genetic algorithm, and reducing the time and workload of frequently performing CFD calculation;
(4) The NOx and CO emission concentration is used as a target value, an NSGA-II evolutionary algorithm is adopted to search in a structure variable allowable range of the combustor, a multi-objective optimization problem model of the ethylene cracking furnace in the combustion process is solved, and a structure optimization design scheme of the ultra-low nitrogen combustor is provided, so that a decision maker can select a corresponding dominant solution according to requirements and preferences to guide actual production design.
While, for purposes of simplicity of explanation, the methodologies are shown and described as a series of acts, it is to be understood and appreciated that the methodologies are not limited by the order of acts, as some acts may, in accordance with one or more embodiments, occur in different orders and/or concurrently with other acts from that shown and described herein or not shown and described herein, as would be understood by one skilled in the art.
Those of skill in the art would understand that information, signals, and data may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits (bits), symbols, and chips that may be referenced throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (12)
1. A multi-objective optimization method for an ultra-low nitrogen combustor is characterized by comprising the following steps:
constructing a parameterized grid model according to the geometric structure of the ultra-low nitrogen combustor;
according to the parameterized grid model and the actual industrial principle of the ultra-low nitrogen combustor, constructing an emission concentration prediction model of NOx and CO in the ultra-low nitrogen combustor;
taking the structural parameters of the ultra-low nitrogen combustor as optimization variables, taking the NOx and CO emission concentration of the ultra-low nitrogen combustor as an objective function, and constructing a multi-feature quick response proxy model based on the parameterized grid model and the emission concentration prediction model; and
and performing multi-objective optimization solution on the multi-feature quick response agent model in the combustion process of the ethylene cracking furnace within the allowable range of the structural parameters by adopting an NSGA-II evolutionary algorithm to determine the optimized variable values of the structural parameters.
2. The multi-objective optimization method of claim 1, wherein the step of constructing a parameterized grid model based on the ultra-low nitrogen combustor geometry comprises:
constructing a geometric model according to the geometric structure of the ultra-low nitrogen burner;
extracting structural parameters characterizing the complete structure of the geometric model from the geometric model to construct a parameterized log;
defining a mesh partitioning variable in the parameterized log to set a corresponding mesh size value;
building a visual interface, inputting a grid size value corresponding to the grid division variable into the visual interface, and carrying out grid division on the geometric model to obtain an initial parameterized grid model; and
and performing fluid dynamics simulation on the initial parameterized grid model, and setting boundary conditions and fluid properties of the initial parameterized grid model to obtain the parameterized grid model.
3. The multi-objective optimization method of claim 2, wherein the step of constructing a prediction model of NOx and CO emission concentrations in the ultra-low nitrogen combustor based on the parameterized grid model and actual industrial principles of the ultra-low nitrogen combustor comprises:
constructing a coupling model reflecting turbulence-combustion interaction by adopting a standard k-epsilon turbulence model reflecting the actual industrial principle of the ultra-low nitrogen combustor, a DO radiation model and a finite rate/vortex dissipation-aftertreatment NOx combustion model;
performing CFD numerical simulation on the coupling model to obtain a simulation result of the flame temperature and/or the content of the smoke components;
comparing the simulation result of the flame temperature and/or the flue gas component content with actual data, and analyzing the reason of the result deviation so as to correct the structural parameters and the boundary conditions of the parameterized grid model; and
and based on the corrected structural parameters and boundary conditions, carrying out CFD numerical simulation again and correcting the structural parameters and the boundary conditions of the parameterized grid model until the deviation of the simulation result and the actual data meets the simulation precision requirement.
4. The multi-objective optimization method of claim 2, wherein the configuration parameters include damper size, primary orifice diameter, secondary orifice diameter, and orifice inclination angle.
5. The multi-objective optimization method of claim 4, wherein the step of constructing a multi-feature fast response proxy model based on the parameterized grid model and the emission concentration prediction model using the ultra-low nitrogen combustor configuration parameters as optimization variables and the ultra-low nitrogen combustor NOx and CO emission concentrations as objective functions comprises:
constructing an objective function by taking the emission concentrations of NOx and CO as target values;
establishing a constraint condition based on structural parameter variables according to the parameter ranges of the size of the air door, the diameter of the primary nozzle, the diameter of the secondary nozzle and the inclination angle of the nozzle of the ultra-low nitrogen burner; and
and establishing a multi-feature quick response proxy model of the ultra-low nitrogen combustor in the ethylene cracking furnace by combining the objective function and a data regression prediction method for optimizing the BP neural network based on a genetic algorithm.
6. The multi-objective optimization method of claim 5, wherein the step of building a multi-feature fast response proxy model for the ultra-low nitrogen combustor in an ethylene cracking furnace based on a data regression prediction method for genetic algorithm optimized BP neural network in combination with the objective function comprises:
creating a BP neural network to determine a topological structure of the BP neural network;
determining an initial weight value and a threshold value of the BP neural network, and coding the initial weight value and the threshold value to obtain an initial population;
in response to the fact that the current iteration times are smaller than the preset maximum iteration times, taking each individual in the current population as an initial weight and a threshold of the BP neural network, training by using a training sample, and calculating a training error of the training sample to be used as the fitness of each individual;
selecting the optimal individual of the current population according to the fitness of each individual;
performing selection, crossing and variation genetic algorithm operation based on the optimal individual to obtain a new population; and
and selecting the final optimal individual in response to the fact that the current iteration times reach the maximum iteration times so as to obtain the optimal BP neural network weight and threshold.
7. The multi-objective optimization method of claim 5, wherein the objective function is expressed as follows:
wherein, { a 1 ,a 2 ,…,a m Is m structural parameters obtained by screening,
is the NOx emission concentration, <' > based>
Is the CO emission concentration.
8. The multi-objective optimization method of claim 5, wherein the constraints comprise:
L min ≤L≤L max
W mim ≤W≤W max
wherein L is the length of the damper, W is the width of the damper, L min 、W min Is the minimum value of the length and width of the damper, L max 、W max The maximum values of the length and the width of the air door are respectively;
R fmin ≤R f ≤R fmax
wherein R is f Is the primary orifice diameter, R fmax 、R fmin The maximum value and the minimum value of the diameter of the primary nozzle are respectively;
R smin ≤R s ≤R smax
wherein R is s Is the secondary orifice diameter, R smax 、R smin The maximum value and the minimum value of the diameter of the secondary nozzle are respectively; and
N min ≤N≤N max
wherein N is the spout inclination angle, N max 、N min The maximum value and the minimum value of the spout inclination angle are respectively.
9. The multi-objective optimization method of claim 8, wherein the step of performing multi-objective optimization solution of the ethylene cracking furnace combustion process on the multi-feature fast response proxy model within the allowable range of the structural parameters by using the NSGA-II evolutionary algorithm to determine the optimized variable values of the structural parameters comprises:
performing multi-objective optimization solution of the combustion process of the ethylene cracking furnace through a multi-objective decision model, wherein the multi-objective decision model is as follows:
wherein,
10. the multi-objective optimization method of claim 8, wherein the step of performing the multi-objective optimization solution of the ethylene cracking furnace combustion process on the multi-feature fast response proxy model within the allowable range of the structural parameters by using the NSGA-II evolutionary algorithm to determine the optimized variable values of the structural parameters further comprises:
setting the number N of the initialized population, the maximum iteration number, the cross probability, the mutation probability, the cross distribution index and the mutation distribution index of the NSGA-II evolutionary algorithm to obtain a parent population P t Wherein t =1;
for the parent population P t Each individual in (a) is subjected to non-dominance sorting to obtain a first non-dominance set;
calculating the crowdedness of each individual in each non-dominating set, and obtaining a child population Q through selection, crossing and variation t ；
The filial generation population Q t And the parent population P t Combined to form population R t And applying said population R according to the elite strategy t Performing non-dominance ordering to generate a second non-dominance set;
calculating the crowdedness of the second non-dominating set to generate a new offspring population Q t+1 (ii) a And
and judging whether the iteration times reach the maximum iteration times, if so, outputting the optimal solution of the decision variables, and terminating the algorithm, otherwise, if not, enabling t = t +1, and performing iteration calculation again.
11. A multi-objective optimization system for ultra-low nitrogen combustors, comprising:
a memory having computer instructions stored thereon; and
a processor coupled to the memory and configured to execute computer instructions stored on the memory to implement the multi-objective optimization method for an ultra-low nitrogen combustor as recited in any one of claims 1-10.
12. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the method of multi-objective optimization of ultra-low nitrogen burners as claimed in any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310077664.7A CN115964968A (en) | 2023-01-19 | 2023-01-19 | Multi-objective optimization method and system for ultra-low nitrogen combustor and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310077664.7A CN115964968A (en) | 2023-01-19 | 2023-01-19 | Multi-objective optimization method and system for ultra-low nitrogen combustor and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115964968A true CN115964968A (en) | 2023-04-14 |
Family
ID=87360049
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310077664.7A Pending CN115964968A (en) | 2023-01-19 | 2023-01-19 | Multi-objective optimization method and system for ultra-low nitrogen combustor and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115964968A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116467817A (en) * | 2023-06-01 | 2023-07-21 | 广东合胜厨电科技有限公司 | Air duct design method based on upper air inlet burner |
-
2023
- 2023-01-19 CN CN202310077664.7A patent/CN115964968A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116467817A (en) * | 2023-06-01 | 2023-07-21 | 广东合胜厨电科技有限公司 | Air duct design method based on upper air inlet burner |
| CN116467817B (en) * | 2023-06-01 | 2023-11-17 | 广东合胜厨电科技有限公司 | Air duct design method based on upper air inlet burner |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106931453B (en) | The forecasting system and method for circulating fluid bed domestic garbage burning emission of NOx of boiler | |
| Sha et al. | Overview of computational intelligence for building energy system design | |
| CN105020705A (en) | Method and system for optimizing and controlling combustion performance of circulating fluidized bed boiler in real time | |
| Rahat et al. | Data-driven multi-objective optimisation of coal-fired boiler combustion systems | |
| Reca et al. | Application of several meta-heuristic techniques to the optimization of real looped water distribution networks | |
| Mattiussi et al. | A decision support system for sustainable energy supply combining multi-objective and multi-attribute analysis: An Australian case study | |
| CN109932903A (en) | The air-blower control Multipurpose Optimal Method of more parent optimization networks and genetic algorithm | |
| CN109634121A (en) | More parent genetic algorithm air source heat pump multiobjective optimization control methods based on radial basis function neural network | |
| NL2030102B1 (en) | Computer system and method based on evaluation of a regional air pollution regulation plan | |
| Mariani et al. | Separation efficiency and heat exchange optimization in a cyclone | |
| Piao et al. | Development of a stochastic simulation–optimization model for planning electric power systems–A case study of Shanghai, China | |
| CN114969953B (en) | Optimized shield underpass tunnel design method and equipment based on Catboost-NSGA-III | |
| CN115964968A (en) | Multi-objective optimization method and system for ultra-low nitrogen combustor and storage medium | |
| WO2024060488A1 (en) | Method based on deep recurrent neural network and evolutionary computation for optimizing combustion of industrial boiler | |
| Dong et al. | Intelligent optimization: A novel framework to automatize multi-objective optimization of building daylighting and energy performances | |
| CN109886448A (en) | Using learning rate changing BP neural network and the heat pump multiobjective optimization control method of NSGA-II algorithm | |
| CN108564205A (en) | A kind of load model and parameter identification optimization method based on measured data | |
| CN112016244A (en) | Durable concrete multi-target mix proportion optimization method based on SVM and intelligent algorithm | |
| CN113095556A (en) | Medium-and-long-term load prediction method and system considering carbon neutralization tendency | |
| CN114302418A (en) | Method and device for detecting network element equipment performance and computer readable medium | |
| Son et al. | Evolutionary multi-objective optimization in building retrofit planning problem | |
| Faulkner et al. | Fast prediction of indoor airflow distribution inspired by synthetic image generation artificial intelligence | |
| Büche | Multi-objective evolutionary optimization of gas turbine components | |
| CN115755624A (en) | Coal-fired boiler multi-objective optimization method based on evolutionary algorithm | |
| Gao et al. | Shape optimization of bi-directional flow passage components based on a genetic algorithm and computational fluid dynamics |
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 |