CN116776773A - Tube type optimization system and method for straight fin tube type heat exchanger - Google Patents
Tube type optimization system and method for straight fin tube type heat exchanger Download PDFInfo
- Publication number
- CN116776773A CN116776773A CN202310757141.7A CN202310757141A CN116776773A CN 116776773 A CN116776773 A CN 116776773A CN 202310757141 A CN202310757141 A CN 202310757141A CN 116776773 A CN116776773 A CN 116776773A
- Authority
- CN
- China
- Prior art keywords
- design
- heat exchanger
- module
- optimization
- optimizing
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000005457 optimization Methods 0.000 title claims abstract description 40
- 238000013461 design Methods 0.000 claims abstract description 126
- 238000004088 simulation Methods 0.000 claims abstract description 36
- 230000006870 function Effects 0.000 claims abstract description 21
- 238000010801 machine learning Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000003062 neural network model Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000035772 mutation Effects 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000010206 sensitivity analysis Methods 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a tubular optimization system and method for a straight fin tubular heat exchanger, wherein the system comprises the following components: the system comprises a mathematic module, an optimization simulation module, a decision module and a forward and reverse design module; the mathematical module is used for abstracting the tubular design of the heat exchanger to be optimized into mathematical problems, the optimization simulation module is used for establishing an NSGA-II multi-objective optimization model, and optimizing design variables by taking heat exchange efficiency and pressure drop indexes as optimization objective functions to obtain a Pareto optimal design scheme set; the decision module is used for selecting a scheme meeting the design requirement from a Pareto non-inferior design scheme set in the cloud database by utilizing a multi-attribute decision method according to the user requirement; the positive and negative design module is used for constructing a machine learning rapid design model by utilizing the data of the cloud database Pareto non-inferior design scheme set, capturing the nonlinear relation between design variables and heat exchanger performance indexes, and assisting a user in rapid design; the invention has the advantages of small calculated amount and design time saving.
Description
Technical Field
The invention relates to the technical field of artificial intelligence auxiliary heat exchanger design, in particular to a tubular optimization system and method for a straight fin tubular heat exchanger.
Background
The finned tube type heat exchanger is widely applied to the fields of chemical industry, petroleum, power, food and other industries, and has the advantages of flexible structure, strong adaptability, high space utilization rate and the like. Under the industrial background of deep pushing green energy conservation, the improvement of the heat transfer performance of the heat exchanger is widely focused. The performance of the heat exchanger is affected by various structural parameters, one of which is the tube shape, and the research of the structural parameters is important to the improvement of the overall performance of the heat exchanger. The research of the structural parameters of the traditional heat exchanger mainly adopts an experimental analysis method, the research period is long, the experimental cost is high, and the performance of the heat exchanger is often evaluated by a single evaluation index, so that the research result is not comprehensive.
Although numerical simulation is successful to replace experimental analysis along with the improvement of computer performance, the calculated amount of numerical simulation is large, unified numerical simulation software does not exist at home at present, most of design workers mainly depend on commercial software, simulation, data analysis, result processing and the like related to the tubular optimal design process of the heat exchanger are required to span multiple software, data structures required by different software are quite different, and the method is very unfriendly to users/designers.
Disclosure of Invention
The invention aims to: the invention aims to provide a tubular optimization system and method for a straight fin tubular heat exchanger, which are used for solving the problems in the background technology.
The technical scheme is as follows: the invention relates to a tubular optimizing system of a straight fin tubular heat exchanger, which comprises the following components: the system comprises a mathematic module, an optimization simulation module, a decision module and a forward and reverse design module; the mathematical module is used for abstracting the tubular design of the heat exchanger to be optimized into mathematical problems, determining basic structural parameters and working environments of the fin tubular heat exchanger, selecting design variables of the tubular heat exchanger to be optimized, determining the change range of the design variables according to expert experience and national standards, and transmitting the data to the simulation optimizing module; the optimization simulation module is used for establishing an NSGA-II multi-objective optimization model, optimizing design variables by taking heat exchange efficiency and pressure drop indexes as optimization objective functions, and obtaining a Pareto optimal design scheme set; wherein, different heat exchange efficiency and pressure drop indexes are obtained by CFD simulation; the decision module is used for selecting a scheme meeting the design requirement from a Pareto non-inferior design scheme set in the cloud database by utilizing a multi-attribute decision method according to the user requirement; the positive and negative design module is used for constructing a machine learning rapid design model by utilizing Pareto non-inferior design scheme set data in the cloud database, capturing a nonlinear relation between design variables and heat exchanger performance indexes and assisting a user in rapid design.
Further, the connection relationship between the modules is specifically set as follows: the mathematical module is connected with the optimization simulation module; the optimization simulation module is respectively connected with the decision module and the positive and negative design module.
The invention relates to a method for optimizing a tube type optimizing system of a straight fin tube type heat exchanger, which comprises the following steps:
(1) Abstracting a physical problem of tubular design of a heat exchanger to be optimized into a two-dimensional mathematical optimization problem, determining the sizes of long and wide basic structures, arranging the tubes, selecting a design variable affecting tubular heat exchange performance as the variable to be optimized, and determining the change range of the design variable by combining expert experience and national standard;
(2) Carrying out parent population random initialization on an optimization algorithm NSGA-II within the variable range of the design variable; wherein the parent population is denoted as P k (k＝1,2,…,N)；
(3) Calculation and evaluation of P from CFD simulation k Is a target function of (2);
(4) Generating a child population Q through selection, crossing and mutation operations k ；
(5) Computing population Q from CFD simulation k Is a target function of (2);
(6) Pareto non-dominant ordering is performed on each target;
(7) Calculating the crowding distance of the individual;
(8) Selecting a design scheme of a composite requirement from the Pareto non-inferior solution set according to user preference by utilizing a multi-attribute decision method;
(9) And capturing the nonlinear relation between the design variables and the heat exchange performance indexes of the Pareto non-inferior design scheme set in the cloud database by using the machine learning model, constructing a forward design machine learning model and a reverse design machine learning model, and mining implicit relation between the forward design and the reverse design to assist a user in rapid design.
Further, the steps (3) and (5) are specifically as follows: the Nu number representing the heat exchange efficiency and the pressure drop representing the flow field are adopted, and the calculation formula is as follows:
obj 2 ＝min(Δp)＝min(p out -p in )
further, the step (7) specifically includes the following steps: and calculating the crowding distance of the individuals, selecting the optimal first N individuals as new parents according to an elite selection strategy, and iterating until the iteration times are over to obtain a Pareto non-inferior solution set.
Further, the multi-attribute decision method in step (8) includes: TOPSIS, MOORA, CODAS, COPRAS.
Further, the design scheme meeting the user requirement is obtained by utilizing TOPSIS to make multi-attribute decision, specifically: constructing a decision matrix according to the Pareto non-inferior solution set to obtain a normalized decision matrix; calculating a distance decision matrix to obtain a closeness decision matrix, and determining a final design scheme according to the principle of larger closeness.
Further, the machine learning model of step (9) includes: BP neural network model, RBF neural network model, ELM neural network model, GRNN neural network model, GPR model.
Further, the input data of the forward design machine learning model in the step (9) is a design variable, and the output data is a heat exchanger performance index; the input data of the reverse design machine learning model is a heat exchanger performance index, and the output data is a design variable.
The device comprises a memory, a processor and a program stored on the memory and capable of running on the processor, wherein the processor realizes the steps in the tube type optimizing system and the method of the straight fin tube type heat exchanger when executing the program.
The beneficial effects are that: compared with the prior art, the invention has the following remarkable advantages: according to the invention, the CFD simulation, the multi-objective optimization algorithm, the prediction model and the multi-attribute decision method are combined, and the OpenMP is utilized to easily realize parallel optimization calculation; the invention has the advantages of small calculated amount and design time saving.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a schematic view of a straight fin cross oval tube heat exchanger in accordance with one embodiment of the present invention;
fig. 3 shows the best compromise design of TOPSIS selected from Pareto non-inferior designs under different weights of the present invention.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present invention provides a tube-type optimizing system of a flat fin tube heat exchanger, including: the system comprises a mathematic module, an optimization simulation module, a decision module and a forward and reverse design module; the mathematical module is used for abstracting the tubular design of the heat exchanger to be optimized into mathematical problems, determining basic structural parameters and working environments of the fin tubular heat exchanger, selecting design variables of the tubular heat exchanger to be optimized, determining the change range of the design variables according to expert experience and national standards, and transmitting the data to the simulation optimizing module; the optimization simulation module is used for establishing an NSGA-II multi-objective optimization model, optimizing design variables by taking heat exchange efficiency and pressure drop indexes as optimization objective functions, and obtaining a Pareto optimal design scheme set; the method comprises the steps that different heat exchange efficiency and pressure drop indexes are obtained through CFD simulation, a series of non-inferior Pareto solutions, namely design scheme combinations, are obtained through calculation of a simulation optimization module, and are stored in a cloud database; the decision module is used for selecting a scheme meeting the design requirement from a Pareto non-inferior design scheme set in the cloud database by utilizing a multi-attribute decision method according to the user requirement; the positive and negative design module is used for constructing a machine learning rapid design model by utilizing Pareto non-inferior design scheme set data in the cloud database, capturing a nonlinear relation between design variables and heat exchanger performance indexes and assisting a user in rapid design. The connection relation among the modules is specifically set as follows: the mathematical module is connected with the optimization simulation module; the optimization simulation module is respectively connected with the decision module and the positive and negative design module.
The embodiment of the invention also provides a method for optimizing the tubular optimizing system of the straight fin tubular heat exchanger, taking cross elliptical tubular design as an example, comprising the following steps:
(1) The physical problem of the tube design of the heat exchanger to be optimized is abstracted into a two-dimensional mathematical optimization problem, as shown in fig. 2, and a plurality of staggered elliptical tubes extend along the horizontal direction in order to simplify the research area. And determining the basic structure dimensions such as length, width and the like according to the research area, arranging the pipes, selecting the design variables influencing the pipe heat exchange performance as variables to be optimized, and determining the variation range of the design variables by combining expert experience and national standards. Wherein the length x=65 mm and the width y=80 mm are staggered, and 6 variables to be designed are determined because the tube is elliptical, namely the reference diameter phi of the ellipse, the ratio L of the length of the long axis to the reference diameter fac Ratio S of short axis length to reference diameter fac And angles theta between the major axes of the three ellipses and the horizontal direction in the research area 1 ，θ 2 ，θ 3 . The variation ranges of the 6 variables to be optimized are respectively as follows:L fac ∈[1.0,1.4]；S fac ∈[0.6,1.0]；θ 1 ,θ 2 ,θ 3 ∈[-90°,90°]。
(2) Father optimization algorithm NSGA-II in design variable variation rangeRandomly initializing a generation population, and marking a father population as P k (k=1, 2, …, N); the population size is set to 100 and the maximum number of iterations is 250.
(3) Calculation and evaluation of P from CFD simulation k Is a target function of (2); the method comprises the following steps: the method is completed by adopting an MHT framework independently developed by the Sian digital peak information technology limited company, and the framework has the characteristics of stable and reliable calculation. The method mainly comprises the following steps:
(31) Generating geometry and network according to the design variables; the appropriate number of grids is determined using sensitivity analysis.
(32) Setting boundary conditions, setting an inlet boundary as a speed inlet, setting an outlet boundary as a pressure outlet, adopting periodic boundaries for the speed inlet and the pressure outlet, adopting symmetrical boundaries up and down, and setting the wall surface as non-slip. The inlet parameters are: the temperature is 37 ℃, the turbulence intensity is 5%, the turbulence viscosity ratio is 10, and the speed is 0.6m/s.
(33) Setting fluid parameters, wherein the working medium is air, and the physical parameters are as follows: density 1.225kg/m 3 Specific heat capacity 1006.43J/(kg.K), dynamic viscosity 1.7894 ×10 -5 kg/mS, and the heat conductivity coefficient is 0.025W/mK.
(34) The method comprises the steps of setting a solver, adopting a SIMPLE algorithm for speed and pressure coupling, adopting a green Gaussian algorithm based on units for gradient calculation, adopting a standard wall function for a wall function, and adopting a high-order format for space dispersion for momentum and energy equations.
(35): CFD simulation;
(36): and (3) post-processing, namely calculating heat exchange efficiency and pressure loss according to CFD simulation, and obtaining the objective function value under the current design variable scheme. The heat exchange efficiency is represented by Nu number, the pressure loss is the pressure drop of the flow field, and the calculation formula is as follows:
obj 2 ＝min(Δp)＝min(p out -p in )
(4) Generating a child population Q through selection, crossing and mutation operations k The method comprises the steps of carrying out a first treatment on the surface of the Wherein, the crossover rate is set to 0.8 and the mutation rate is set to 0.17.
(5) Computing population Q from CFD simulation k Is a target function of (2); the method comprises the steps of carrying out a first treatment on the surface of the The method comprises the following steps: the method is completed by adopting an MHT framework independently developed by the Sian digital peak information technology limited company, and the framework has the characteristics of stable and reliable calculation. The method mainly comprises the following steps:
(51) Generating geometry and network according to the design variables; the appropriate number of grids is determined using sensitivity analysis.
(52) Setting boundary conditions, setting an inlet boundary as a speed inlet, setting an outlet boundary as a pressure outlet, adopting periodic boundaries for the speed inlet and the pressure outlet, adopting symmetrical boundaries up and down, and setting the wall surface as non-slip. The inlet parameters are: the temperature is 37 ℃, the turbulence intensity is 5%, the turbulence viscosity ratio is 10, and the speed is 0.6m/s.
(53) Setting fluid parameters, wherein the working medium is air, and the physical parameters are as follows: density 1.225kg/m 3 Specific heat capacity 1006.43J/(kg.K), dynamic viscosity 1.7894 ×10 -5 kg/mS, and the heat conductivity coefficient is 0.025W/mK.
(54) The method comprises the steps of setting a solver, adopting a SIMPLE algorithm for speed and pressure coupling, adopting a green Gaussian algorithm based on units for gradient calculation, adopting a standard wall function for a wall function, and adopting a high-order format for space dispersion for momentum and energy equations.
(55): CFD simulation;
(56): and (3) post-processing, namely calculating heat exchange efficiency and pressure loss according to CFD simulation, and obtaining the objective function value under the current design variable scheme. The heat exchange efficiency is represented by Nu number, the pressure loss is the pressure drop of the flow field, and the calculation formula is as follows:
obj 2 ＝min(Δp)＝min(p out -p in )
(6) Pareto non-dominant ordering is performed on each target;
(7) Calculating a Pareto non-inferior solution set; the method comprises the following steps: and calculating the crowding distance of the individuals, selecting the optimal first N individuals as new parents according to an elite selection strategy, iterating until the iteration times are over, obtaining a Pareto non-inferior solution set, and outputting the result to a cloud database.
(8) Selecting a design scheme of a composite requirement from the Pareto non-inferior solution set according to user preference by utilizing a multi-attribute decision method; the multi-attribute decision method comprises the following steps: TOPSIS, MOORA, CODAS, COPRAS and other common multi-attribute decision methods; the steps are described herein with TOPSIS as an example:
(81): pareto design scheme S= { S generated according to simulation optimization module 1 ,S 2 ,S 3 ,...,S n Objective function value a= { a } 1 ,A 2 ,A 3 ,...,A m Construction of decision matrix x= [ X ] ij ] n×m As can be seen from the above technical solution, where n=100, m=2.
(82) Normalizing the X matrix to obtain a matrix R= [ R ] ij ] n×m The calculation formula is as follows:
(83) Weighting the matrix R to obtain a matrix Y:
y ij ＝ω j *r ij ,(i＝1,2,...,n；j＝1,2,...,m)
weights ω of different objective functions j Can be determined using analytic hierarchy process, entropy method, and the like.
(84) Determining an ideal solutionAnd negative ideal solution->
Wherein A is + The larger the target function value is, the better the target function value is; a is that - The smaller the objective function value, the better the cost class index is.
(85) The Euler distance from each design scheme to positive and negative ideal solutions is calculated:
(86) Calculating relative closeness:
(87) All design schemes are ordered according to relative closeness, and the scheme with the largest relative closeness is the best compromise. Fig. 3 is the best compromise under different weights. The combination of the CFD simulated flow field and the temperature distribution can confirm that the comprehensive performance of the three schemes is superior to that of a circular pipe with equivalent hydraulic diameter.
(9) And capturing the nonlinear relation between the design variables and the heat exchange performance indexes of the Pareto non-inferior design scheme set in the cloud database by using the machine learning model, constructing a forward design machine learning model and a reverse design machine learning model, and mining implicit relation between the forward design and the reverse design to assist a user in rapid design. The machine learning model includes: BP neural network model, RBF neural network model, ELM neural network model, GRNN neural network model, GPR model. In this embodiment, a BP neural network is used, and the steps are:
(91) Judging whether forward design or reverse design is to be carried out subsequently according to the user requirements; if the user selects the forward design, the model is input as a design variable, and the model is output as a heat exchange performance index, and the following steps are continued; and otherwise, the model is input into a heat exchange performance index, and output is a design variable.
(92) Preparing input and output data, preprocessing, wherein the preprocessing comprises normalization and data set division, and if the input variables are too many, the input dimension reduction can be performed by adopting a feature extraction method such as principal component analysis;
(93) Constructing a BP neural network by using a training sample, and capturing a nonlinear relation between a design variable and heat exchange performance; parameters of the neural network are optimized;
(94) Verifying the optimized BP neural network by using verification period data, wherein the verification index adopts R 2 RMSE, MAE, MAPE, etc.; determining whether model optimization is needed according to the verification result, and storing the model without needing to be performed;
(95) The user inputs a new design scheme into the optimized BP model, and then the heat exchange performance index corresponding to the design scheme can be obtained; the user inputs new requirements into the optimized BP model, and then different design variable values can be obtained. Table 1 shows the results of the heat exchange efficiency and pressure loss forecast for the 6 design variables. As can be seen from the table, the accuracy of the training period and the inspection period model is very high, and the training period and inspection period model can be used for auxiliary design.
TABLE 1
The embodiment of the invention also provides equipment, which comprises a memory, a processor and a program stored on the memory and capable of running on the processor, wherein the processor realizes the steps in the tube type optimizing system and the method of the straight fin tube type heat exchanger when executing the program.
Claims (10)
1. A tube-type optimization system for a straight fin tube heat exchanger, comprising: the system comprises a mathematic module, an optimization simulation module, a decision module and a forward and reverse design module; the mathematical module is used for abstracting the tubular design of the heat exchanger to be optimized into mathematical problems, determining basic structural parameters and working environments of the fin tubular heat exchanger, selecting design variables of the tubular heat exchanger to be optimized, determining the change range of the design variables according to expert experience and national standards, and transmitting the data to the simulation optimizing module; the optimization simulation module is used for establishing an NSGA-II multi-objective optimization model, optimizing design variables by taking heat exchange efficiency and pressure drop indexes as optimization objective functions, and obtaining a Pareto optimal design scheme set; wherein, different heat exchange efficiency and pressure drop indexes are obtained by CFD simulation; the decision module is used for selecting a scheme meeting the design requirement from a Pareto non-inferior design scheme set in the cloud database by utilizing a multi-attribute decision method according to the user requirement; the positive and negative design module is used for constructing a machine learning rapid design model by utilizing Pareto non-inferior design scheme set data in the cloud database, capturing a nonlinear relation between design variables and heat exchanger performance indexes and assisting a user in rapid design.
2. A tube-type optimizing system for a straight fin tube heat exchanger according to claim 1, wherein the connection relationship between the modules is specifically set as: the mathematical module is connected with the optimization simulation module; the optimization simulation module is respectively connected with the decision module and the positive and negative design module.
3. A method of optimizing a tube-in-tube system for a straight fin tube heat exchanger, comprising the steps of:
(1) Abstracting a physical problem of tubular design of a heat exchanger to be optimized into a two-dimensional mathematical optimization problem, determining the sizes of long and wide basic structures, arranging the tubes, selecting a design variable affecting tubular heat exchange performance as the variable to be optimized, and determining the change range of the design variable by combining expert experience and national standard;
(2) Carrying out parent population random initialization on an optimization algorithm NSGA-II within the variable range of the design variable; wherein the parent population is denoted as P k (k＝1,2,…,N)；
(3) Calculation and evaluation of P from CFD simulation k Is a target function of (2);
(4) Generating a child population Q through selection, crossing and mutation operations k ；
(5) Computing population Q from CFD simulation k Is a target function of (2);
(6) Pareto non-dominant ordering is performed on each target;
(7) Calculating a Pareto non-inferior solution set;
(8) Selecting a design scheme of a composite requirement from the Pareto non-inferior solution set according to user preference by utilizing a multi-attribute decision method;
(9) And capturing the nonlinear relation between the design variables and the heat exchange performance indexes of the Pareto non-inferior design scheme set in the cloud database by using the machine learning model, constructing a forward design machine learning model and a reverse design machine learning model, and mining implicit relation between the forward design and the reverse design to assist a user in rapid design.
4. A method of optimizing a tube-type optimizing system of a straight fin tube heat exchanger according to claim 3, wherein said steps (3), (5) are specifically as follows: the Nu number representing the heat exchange efficiency and the pressure drop representing the flow field are adopted, and the calculation formula is as follows:
obj 2 ＝min(Δp)＝min(p out -p in )
5. a method of optimizing a tube-type optimizing system of a straight fin tube heat exchanger according to claim 3, wherein said step (7) is specifically as follows: and calculating the crowding distance of the individuals, selecting the optimal first N individuals as new parents according to an elite selection strategy, and iterating until the iteration times are over to obtain a Pareto non-inferior solution set.
6. A method of optimizing a tube-type optimizing system for a straight fin tube heat exchanger according to claim 3, wherein said step (8) multi-attribute decision method comprises: TOPSIS, MOORA, CODAS, COPRAS.
7. The method for optimizing the tubular optimizing system of the straight fin tubular heat exchanger according to claim 6, wherein the design scheme meeting the user requirement is obtained by utilizing TOPSIS to make multi-attribute decisions, specifically: constructing a decision matrix according to the Pareto non-inferior solution set to obtain a normalized decision matrix; calculating a distance decision matrix to obtain a closeness decision matrix, and determining a final design scheme according to the principle of larger closeness.
8. A method of optimizing a tube-type optimizing system for a straight fin tube heat exchanger as claimed in claim 3, wherein said step (9) machine learning model comprises: BP neural network model, RBF neural network model, ELM neural network model, GRNN neural network model, GPR model.
9. A method for optimizing a tube-type optimizing system of a straight fin tube heat exchanger as claimed in claim 3, wherein the input data of the forward-designed machine learning model in step (9) is a design variable, and the output data is a heat exchanger performance index; the input data of the reverse design machine learning model is a heat exchanger performance index, and the output data is a design variable.
10. An apparatus comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor performs the steps in a method of a tube-type optimization system of a straight fin tube heat exchanger according to any one of claims 3-9 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310757141.7A CN116776773B (en) | 2023-06-26 | 2023-06-26 | Tube type optimization system and method for straight fin tube type heat exchanger |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310757141.7A CN116776773B (en) | 2023-06-26 | 2023-06-26 | Tube type optimization system and method for straight fin tube type heat exchanger |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116776773A true CN116776773A (en) | 2023-09-19 |
| CN116776773B CN116776773B (en) | 2024-06-07 |
Family
ID=87994305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310757141.7A Active CN116776773B (en) | 2023-06-26 | 2023-06-26 | Tube type optimization system and method for straight fin tube type heat exchanger |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116776773B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117709168A (en) * | 2024-02-02 | 2024-03-15 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Optimal design method and device for forced air cooling heat dissipation system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7996344B1 (en) * | 2010-03-08 | 2011-08-09 | Livermore Software Technology Corporation | Multi-objective evolutionary algorithm based engineering design optimization |
| CN110059372A (en) * | 2019-03-29 | 2019-07-26 | 上海理工大学 | A kind of objective design method of the shell-and-tube heat exchanger based on differential evolution algorithm |
| CN110414114A (en) * | 2019-07-22 | 2019-11-05 | 西安建筑科技大学 | A kind of optimum design method of the multi-target multi-parameter of U-shaped ground heat exchanger |
| CN113505502A (en) * | 2021-09-10 | 2021-10-15 | 中国人民解放军国防科技大学 | Method for designing special-shaped microchannel heat exchange tube, computer equipment and storage medium |
| CN113591299A (en) * | 2021-07-28 | 2021-11-02 | 清华大学 | Method and system for judging comprehensive performance of different types of microchannel radiators |
| CN113591365A (en) * | 2021-06-22 | 2021-11-02 | 武汉科技大学 | Multi-objective optimization method for self-oscillation heat exchange tube |
| CN115525997A (en) * | 2022-09-21 | 2022-12-27 | 中国人民解放军国防科技大学 | Special-shaped microchannel heat exchange tube type design method and system based on arc line |
| CN115859496A (en) * | 2022-11-09 | 2023-03-28 | 浙江陆特能源科技股份有限公司 | Method for constructing annular hydraulic loss calculation model of double-pipe heat exchanger |
-
2023
- 2023-06-26 CN CN202310757141.7A patent/CN116776773B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7996344B1 (en) * | 2010-03-08 | 2011-08-09 | Livermore Software Technology Corporation | Multi-objective evolutionary algorithm based engineering design optimization |
| CN110059372A (en) * | 2019-03-29 | 2019-07-26 | 上海理工大学 | A kind of objective design method of the shell-and-tube heat exchanger based on differential evolution algorithm |
| CN110414114A (en) * | 2019-07-22 | 2019-11-05 | 西安建筑科技大学 | A kind of optimum design method of the multi-target multi-parameter of U-shaped ground heat exchanger |
| CN113591365A (en) * | 2021-06-22 | 2021-11-02 | 武汉科技大学 | Multi-objective optimization method for self-oscillation heat exchange tube |
| CN113591299A (en) * | 2021-07-28 | 2021-11-02 | 清华大学 | Method and system for judging comprehensive performance of different types of microchannel radiators |
| CN113505502A (en) * | 2021-09-10 | 2021-10-15 | 中国人民解放军国防科技大学 | Method for designing special-shaped microchannel heat exchange tube, computer equipment and storage medium |
| CN115525997A (en) * | 2022-09-21 | 2022-12-27 | 中国人民解放军国防科技大学 | Special-shaped microchannel heat exchange tube type design method and system based on arc line |
| CN115859496A (en) * | 2022-11-09 | 2023-03-28 | 浙江陆特能源科技股份有限公司 | Method for constructing annular hydraulic loss calculation model of double-pipe heat exchanger |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117709168A (en) * | 2024-02-02 | 2024-03-15 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Optimal design method and device for forced air cooling heat dissipation system |
| CN117709168B (en) * | 2024-02-02 | 2024-04-30 | 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) | Optimal design method and device for forced air cooling heat dissipation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116776773B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lemouedda et al. | Optimization of the angle of attack of delta-winglet vortex generators in a plate-fin-and-tube heat exchanger | |
| Peng et al. | Optimal design approach for the plate-fin heat exchangers using neural networks cooperated with genetic algorithms | |
| Varun et al. | Thermal performance optimization of a flat plate solar air heater using genetic algorithm | |
| Sharma | A particle swarm optimization algorithm for optimization of thermal performance of a smooth flat plate solar air heater | |
| CN111881505B (en) | Multi-objective optimization transformation decision method for existing building based on GA-RBF algorithm | |
| Zhang et al. | Multi-objective optimization of elliptical tube fin heat exchangers based on neural networks and genetic algorithm | |
| CN116776773B (en) | Tube type optimization system and method for straight fin tube type heat exchanger | |
| CN107622307A (en) | A kind of Undirected networks based on deep learning connect side right weight Forecasting Methodology | |
| CN110414114B (en) | Multi-objective multi-parameter optimization design method for U-shaped ground heat exchanger | |
| CN112084727A (en) | Transition prediction method based on neural network | |
| CN110601185B (en) | Unified power flow model-based comprehensive energy system weak point identification method | |
| Dezan et al. | Heat transfer enhancement and optimization of flat-tube multilouvered fin compact heat exchangers with delta-winglet vortex generators | |
| CN105425583A (en) | Control method of penicillin production process based on cooperative training local weighted partial least squares (LWPLS) | |
| Sun et al. | An intelligent plate fin-and-tube heat exchanger design system through integration of CFD, NSGA-II, ANN and TOPSIS | |
| Bagheri-Esfeh et al. | Multi-objective optimisation of drag and lift coefficients of a car integrated with canards | |
| CN109840335A (en) | Based on the radial forging pit prediction optimization method for strengthening T-S fuzzy neural network | |
| CN116717839A (en) | Heating control method, control device and heating system | |
| CN105447256A (en) | Excitation enhancement simulation genetic optimization method | |
| CN104318008A (en) | Loose constraint genetic simplex algorithm based optimal design method for condenser | |
| CN116595845A (en) | Structure optimization method of spiral fin tube type heat exchanger | |
| Zhuang et al. | Accurately predicting heat transfer performance of ground heat exchanger for ground-coupled heat pump systems using data mining methods | |
| Abdollahi et al. | Combining artificial intelligence and computational fluid dynamics for optimal design of laterally perforated finned heat sinks | |
| CN109885880B (en) | Method, system, device and medium for optimizing set extension type reliability | |
| Rahimi et al. | GMDH-type neural network modeling and genetic algorithm-based multi-objective optimization of thermal and friction characteristics in heat exchanger tubes with wire-rod bundles | |
| Joseph et al. | Optimisation framework for distinctive vertical AxisWind turbine blade generation using hybrid multi-objective genetic algorithms and deep neural networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |