Summary of the invention
The present invention provides a kind of finned heat exchanger parameter optimization method and device, and carrying out mathematics by establishing neural network buildsMould, then optimizing is carried out based on optimizing algorithm, optimal structure is obtained, workload is reduced, it is more convincing to obtain optimum structure.
In a first aspect, the present invention provides a kind of finned heat exchanger parameter optimization methods, which comprises
According to the structural parameters of the finned heat exchanger determine the flow resistance factor under each structural parameters and heat transfer becauseSon, to establish the corresponding relationship of any structure parameter corresponding flow resistance factor and heat transfer factor；With structure ginsengThe corresponding relationship of number corresponding the flow resistance factor and heat transfer factor is training sample, establishes neural network model, whereinThe neural network model is input with any structure parameter, and the corresponding flow resistance factor and heat transfer factor are output；It is rightThe neural network model is solved, to obtain the optimal solution of the comprehensive parameters of the flow resistance factor and heat transfer factor；The corresponding structural parameters of the optimal solution of the comprehensive parameters are determined, to optimize to the finned heat exchanger parameter.
Preferably,
The structural parameters according to the finned heat exchanger determine the flow resistance factor and biography under each structural parametersThe hot factor includes:
The fin dog-ear that obtains the finned heat exchanger, folding are away from, fin inclination angle, fin thickness and spacing of fin；According to instituteState the fin dog-ear of finned heat exchanger, folding calculated away from, fin inclination angle, fin thickness and spacing of fin corresponding flow resistance becauseSon and heat transfer factor.
Preferably,
It is described to be counted according to the fin dog-ear of the finned heat exchanger, folding away from, fin inclination angle, fin thickness and spacing of finIt calculates the corresponding flow resistance factor and heat transfer factor includes:
By fin dog-ear to the finned heat exchanger, folding away from appointing in, fin inclination angle, fin thickness and spacing of finOne structural parameters carries out parameter single argument；Determine under the structural parameters single argument the corresponding flow resistance factor and heat transfer becauseSon.
Preferably,
The corresponding relationship of the flow resistance factor and heat transfer factor corresponding with the structural parameters is training sampleThis, establishing neural network model includes:
The flowing corresponding from the structural parameters in the corresponding relationship for selecting predetermined number in all corresponding relationshipsResistance factor and heat transfer factor are as training sample, to establish neural network model.
Preferably,
It is described that the neural network model is solved, to obtain the synthesis of the flow resistance factor and heat transfer factorThe optimal solution of parameter includes:
Optimizing solution is carried out to the neural network model by optimizing algorithm, to obtain the flow resistance factor and biographyThe optimal solution of the comprehensive parameters of the hot factor.
Preferably, the method also includes:
Test sample is determined from the corresponding relationship；Based on the test sample to the pre- of the neural network modelIt surveys performance to be tested, wherein the test sample is the knot in the corresponding relationship other than as the training sampleThe corresponding flow resistance factor of structure parameter and heat transfer factor.
Another aspect of the present invention also provides a kind of finned heat exchanger parameter optimization device, and described device includes:
Computing module, for determining the flow resistance under each structural parameters according to the structural parameters of the finned heat exchangerThe factor and heat transfer factor, to establish the corresponding relationship of any structure parameter corresponding flow resistance factor and heat transfer factor；
Model building module, for the correspondence of the structural parameters corresponding flow resistance factor and heat transfer factorRelationship is training sample, establishes neural network model, wherein the neural network model is input with any structure parameter,The corresponding flow resistance factor and heat transfer factor are output；
Model solution module, for being solved to the neural network model, with obtain the flow resistance factor andThe optimal solution of the comprehensive parameters of heat transfer factor；
Optimization module, the corresponding structural parameters of optimal solution for determining the comprehensive parameters, to exchange heat to the finDevice parameter optimizes.
Preferably,
The computing module includes:
Acquiring unit, the fin dog-ear, folding for obtaining the finned heat exchanger are away from, fin inclination angle, fin thickness and wingPiece spacing；Computing unit, according to the fin dog-ear of the finned heat exchanger, folding away from, fin inclination angle, fin thickness and spacing of finTo calculate the corresponding flow resistance factor and heat transfer factor.
Preferably,
The model building module includes:
Model foundation unit, for joining from the structure in the corresponding relationship for selecting predetermined number in all corresponding relationshipsNumber corresponding the flow resistance factor and heat transfer factor are as training sample, to establish neural network model.
Preferably,
The model solution model includes:
Unit is solved, for carrying out optimizing solution to the neural network model by optimizing algorithm, to obtain the streamThe optimal solution of the comprehensive parameters of the dynamic resistance factor and heat transfer factor.
A kind of finned heat exchanger parameter optimization method and device provided by the invention, according to the structural parameters of finned heat exchangerThe flow resistance factor being calculated under relevant parameter and heat transfer factor are carried out, establishes nerve net in this, as training sample trainingNetwork model, the neural network model using the structural parameters of finned heat exchanger as input, with the flow resistance under relevant parameter becauseSon and heat transfer factor are solved to obtain optimal solution as output to the model, to obtain the optimal of finned heat exchangerStructure, reduce workload, obtain optimum structure it is more convincing.
Specific embodiment
To keep the purposes, technical schemes and advantages of this specification clearer, below in conjunction with specific embodiment and accordinglyAttached drawing the technical solution of this specification is clearly and completely described.Obviously, described embodiment is only this specificationA part of the embodiment, instead of all the embodiments.The embodiment of base in this manual, those of ordinary skill in the art are not havingEvery other embodiment obtained under the premise of creative work is made, the range of this specification protection is belonged to.
A kind of finned heat exchanger parameter optimization method provided by the invention and device are carried out below in conjunction with attached drawing detailedDescription so that those skilled in the art can clearly, accurately understand technical solution of the present invention.
Fig. 1 is a kind of flow diagram for finned heat exchanger parameter optimization method that one embodiment of the invention provides.
As shown in Figure 1, a kind of finned heat exchanger parameter provided in an embodiment of the present invention may include steps of:
Step 110, the flow resistance factor under each structural parameters is determined according to the structural parameters of the finned heat exchangerAnd heat transfer factor, to establish the corresponding relationship of any structure parameter corresponding flow resistance factor and heat transfer factor.
In embodiments of the present invention, step 110 can be realized in the following way, illustratively, obtain finned heat exchangerFin dog-ear, folding away from, fin inclination angle, fin thickness and spacing of fin, according to the fin dog-ear of finned heat exchanger, folding away from, wingPiece inclination angle, fin thickness and spacing of fin calculate the corresponding flow resistance factor and heat transfer factor.
Further, by fin dog-ear to the finned heat exchanger, folding away from, fin inclination angle, fin thickness and finAny structure parameter in spacing carries out parameter single argument；Determine under the structural parameters single argument the corresponding flow resistance factor andHeat transfer factor.Illustratively, fin dog-ear, folding are constant away from, fin inclination angle, fin thickness, change spacing of fin, obtain group ginsengThe corresponding flow resistance factor and heat transfer factor under several.Again for example, fin folding is away from, fin inclination angle, fin thickness and finSpacing is constant, changes fin dog-ear angle, obtains the corresponding flow resistance factor and heat transfer factor under this group of parameter.Herein no longerIt is illustrated one by one.
In some embodiment of the invention, one fin structure parameter can be emulated with certain step-length, and with itHis one or more structural parameters are that variable carries out computer sim- ulation, to obtain the corresponding flow resistance factor and heat transfer spySex factor.
In further embodiments, flow resistance factor f and heat transfer factor j can be converted into comprehensive parametersOutput.
It step 120, is training sample with the corresponding relationship of the corresponding flow resistance factor of structural parameters and heat transfer factorThis, establish neural network model, wherein neural network model with any structure parameter be input, corresponding flow resistance becauseSon and heat transfer factor are output.
In embodiments of the present invention, based on the corresponding flow resistance of one group of structural parameters determined in step 110 becauseThe corresponding relationship of son and heat transfer factor establishes neural network model as training sample or training data.The nerve netNetwork model can be BP neural network model.
Step 130, neural network model is solved, to obtain the flow resistance factor and heat transfer factor comprehensive parametersOptimal solution.
Illustratively, this step, which can be, carries out optimizing solution to the neural network model by optimizing algorithm, withTo the optimal solution of the flow resistance factor and the comprehensive parameters of heat transfer factor.Wherein, shown optimizing algorithm illustratively can be withIt is gradient descent method, Newton method etc., the present invention is without limitation.
Step 140, the corresponding structural parameters of the optimal solution of comprehensive parameters are determined, it is excellent to be carried out to finned heat exchanger parameterChange.
In embodiments of the present invention, neural network model is using the structural parameters of finned heat exchanger as input, to flow resistanceThe power factor and heat transfer factor are output, and the flow resistance factor and heat transfer factor that export or its comprehensive parameters are optimalSolution, optimal solution correspond to optimum structure parameter.Optimal design is carried out to finned heat exchanger based on these structural parameters.
Illustratively, the embodiment of the present invention can also include the following steps: to determine test specimens from the corresponding relationshipThis；Tested based on estimated performance of the test sample to the neural network model, wherein the test sample be exceptStructural parameters in the corresponding relationship outside as the training sample corresponding the flow resistance factor and heat transfer becauseSon.In some embodiments, it is also possible to by whole corresponding relationships structural parameters, the corresponding flow resistance factor and heat transfer becauseSon is used as test sample.The present invention is without limitation.
In conclusion a kind of finned heat exchanger parameter optimization method provided by the invention, according to the structure of finned heat exchangerParameter carries out the flow resistance factor and heat transfer factor being calculated under relevant parameter, establishes mind in this, as training sample trainingThrough network model, the neural network model is using the structural parameters of finned heat exchanger as input, with the flowing resistance under relevant parameterThe power factor and heat transfer factor are solved to obtain optimal solution as output to the model, to obtain finned heat exchangerOptimal structure reduces workload, and it is more convincing to obtain optimum structure.
Fig. 2 is a kind of structural schematic diagram for finned heat exchanger parameter optimization device that one embodiment of the invention provides.
As shown in Fig. 2, one of embodiment of the present invention finned heat exchanger parameter optimization device 200 can be with computing module210, model building module 220, model solution module 230 and optimization module 240.
Computing module 210 can be used for determining the stream under each structural parameters according to the structural parameters of the finned heat exchangerThe dynamic resistance factor and heat transfer factor, to establish the correspondence of any structure parameter corresponding flow resistance factor and heat transfer factorRelationship.
In some embodiments, computing module 210 may include acquiring unit and computing unit.Acquiring unit can be used forObtain the fin dog-ear of the finned heat exchanger, folding can root away from, fin inclination angle, fin thickness and spacing of fin, computing unitCorresponding flowing is calculated away from, fin inclination angle, fin thickness and spacing of fin according to the fin dog-ear of the finned heat exchanger, folding to hinderThe power factor and heat transfer factor.
Model building module 220 can be used for the corresponding flow resistance factor of the structural parameters and heat transfer factorCorresponding relationship be training sample, establish neural network model, wherein the neural network model with any structure parameter be it is defeatedEnter, the corresponding flow resistance factor and heat transfer factor are output.
In embodiments of the present invention, model building module 220 may include model foundation unit, and model foundation unit can be withFor the flow resistance corresponding from the structural parameters in the corresponding relationship for selecting predetermined number in all corresponding relationshipsThe factor and heat transfer factor are as training sample, to establish neural network model.
Model solution module 230 can be used for solving the neural network model, to obtain the flow resistanceThe optimal solution of the comprehensive parameters of the factor and heat transfer factor.
Model solution module 230 may include solve unit, for by optimizing algorithm to the neural network model intoRow optimizing solves, to obtain the optimal solution of the comprehensive parameters of the flow resistance factor and heat transfer factor.
Optimization module 240 is determined for the corresponding structural parameters of optimal solution of the comprehensive parameters, to the wingPiece heat exchanger parameter optimizes.
A kind of finned heat exchanger parameter optimization device provided by the invention, is counted according to the structural parameters of finned heat exchangerCalculation obtains the flow resistance factor and the heat transfer factor under relevant parameter, establishes neural network mould in this, as training sample trainingType, the neural network model using the structural parameters of finned heat exchanger as input, under relevant parameter the flow resistance factor andHeat transfer factor is solved to obtain optimal solution as output to the model, to obtain the optimal knot of finned heat exchangerStructure reduces workload, and it is more convincing to obtain optimum structure.
For convenience of description, it describes to be divided into various units when system above with function or module describes respectively.Certainly, existImplement to realize the function of each unit or module in the same or multiple software and or hardware when this specification.
It should be understood by those skilled in the art that, the embodiment of this specification can provide as method, system or computer journeySequence product.Therefore, in terms of this specification can be used complete hardware embodiment, complete software embodiment or combine software and hardwareEmbodiment form.Moreover, it wherein includes computer usable program code that this specification, which can be used in one or more,The computer implemented in computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)The form of program product.
This specification is referring to the method, equipment (system) and computer program product according to this specification embodimentFlowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagramThe combination of process and/or box in one process and/or box and flowchart and/or the block diagram.It can provide these computersProcessor of the program instruction to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devicesTo generate a machine, so that generating use by the instruction that computer or the processor of other programmable data processing devices executeIt is in realize the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagramSystem.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spyDetermine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,Enable the manufacture of system, the instruction system realize in one box of one or more flows of the flowchart and/or block diagram orThe function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that countingSeries of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer orThe instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram oneThe step of function of being specified in a box or multiple boxes.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludabilityIt include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrapInclude other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic wantElement.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described wantThere is also other identical elements in the process, method of element, commodity or equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodimentDividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system realityFor applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the methodPart explanation.
The foregoing is merely the embodiments of this specification, are not limited to this specification.For art technologyFor personnel, this specification can have various modifications and variations.It is all made any within the spirit and principle of this specificationModification, equivalent replacement, improvement etc., should be included within the scope of the claims of this specification.