CN117933062A - Training and particulate matter sedimentation simulation prediction method and equipment for mixed flow field model - Google Patents
Training and particulate matter sedimentation simulation prediction method and equipment for mixed flow field model Download PDFInfo
- Publication number
- CN117933062A CN117933062A CN202311728126.6A CN202311728126A CN117933062A CN 117933062 A CN117933062 A CN 117933062A CN 202311728126 A CN202311728126 A CN 202311728126A CN 117933062 A CN117933062 A CN 117933062A
- Authority
- CN
- China
- Prior art keywords
- flow field
- mixed flow
- sedimentation
- field model
- preset
- 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
- 238000004062 sedimentation Methods 0.000 title claims abstract description 280
- 239000013618 particulate matter Substances 0.000 title claims abstract description 109
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000004088 simulation Methods 0.000 title claims abstract description 56
- 238000012549 training Methods 0.000 title claims abstract description 49
- 239000002245 particle Substances 0.000 claims description 30
- 230000003746 surface roughness Effects 0.000 claims description 16
- 238000002474 experimental method Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 4
- 235000019592 roughness Nutrition 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 238000005399 mechanical ventilation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a training and particulate matter sedimentation simulation prediction method and equipment for a mixed flow field model, and relates to the technical field of automobiles. According to the method, according to the experimental parameters of a preset laboratory mixed flow field, an initial mixed flow field model is adopted for simulation, and simulated particulate matter sedimentation data are obtained; acquiring actual particulate matter sedimentation data of a preset laboratory mixed flow field; calculating loss parameters of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data; and according to the loss parameters, carrying out parameter adjustment on the initial mixed flow field model until the preset iteration stopping condition is met, and obtaining the target mixed flow field model. Therefore, the target mixed flow field model is accurately obtained, and the simulation of the real laboratory mixed flow field by adopting the target mixed flow field model is facilitated.
Description
Technical Field
The invention relates to the technical field of automobiles, in particular to a method and equipment for training a mixed flow field model and simulating and predicting particulate matter sedimentation.
Background
In recent years, due to the rapid development of urban areas, the problem of particulate pollution is becoming serious. Automobiles are one of the important transportation means in daily life, so that the pollution of the particulate matters in the automobiles cannot be ignored. The sedimentation phenomenon of the particles not only can reduce the concentration of the particles in the environment in the vehicle, but also can influence the distribution of the particles on various surfaces in the vehicle.
At present, the traditional particulate matter sedimentation model is concentrated in a mechanical ventilation space provided with an inlet and an outlet, but the spatial distribution of particulate matters in a mechanical ventilation flow field is generally uneven, the simulation precision is low, and the sedimentation amount is greatly influenced. Therefore, an instructive strategy for optimizing and improving the in-vehicle environment cannot be proposed based on the results obtained by the conventional settlement prediction model.
Disclosure of Invention
The application aims to overcome the defects in the prior art, and provides a training method, device, equipment and storage medium for a mixed flow field model, so as to solve the problems of low accuracy and the like of a sedimentation prediction model in the prior art.
In order to achieve the above purpose, the technical scheme adopted by the embodiment of the application is as follows:
In a first aspect, an embodiment of the present application provides a method for training a hybrid flow field model, where the method includes:
According to the experimental parameters of a preset laboratory mixed flow field, an initial mixed flow field model is adopted for simulation, and simulated particulate matter sedimentation data are obtained;
acquiring actual particulate matter sedimentation data of the preset laboratory mixed flow field;
calculating loss parameters of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data;
And according to the loss parameters, carrying out parameter adjustment on the initial mixed flow field model until a preset iteration stopping condition is met, and obtaining a target mixed flow field model.
Optionally, the simulated particulate matter sedimentation data comprises: sedimentation fraction; the experimental parameters include: presetting an experiment speed;
According to the experimental parameters of the preset laboratory mixed flow field, an initial mixed flow field model is adopted for simulation to obtain simulated particulate matter sedimentation data, and the method comprises the following steps:
Injecting simulated particles into the initial mixed flow field model at a preset experimental speed at a plurality of emission positions respectively to obtain simulated sedimentation fractions corresponding to the emission positions;
The obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field comprises the following steps:
Acquiring actual sedimentation fractions corresponding to a plurality of emission positions of the preset laboratory mixed flow field;
and calculating the loss parameter of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data, wherein the loss parameter comprises the following components:
calculating a first loss parameter of the initial mixed flow field model according to the simulated sedimentation fraction and the actual sedimentation fraction;
Calculating a second loss parameter of the initial mixed flow field model according to a plurality of the simulated sedimentation fractions;
And according to the loss parameter, performing parameter adjustment on the initial mixed flow field model until a preset iteration stopping condition is met, so as to obtain a target mixed flow field model, which comprises the following steps:
And carrying out parameter adjustment on the initial mixed flow field model according to the first loss parameter and the second loss parameter until the first loss parameter meets a first preset iteration stopping condition and the second loss parameter meets a second preset iteration stopping condition to obtain the target mixed flow field model.
Optionally, the simulating with the initial mixed flow field model according to the experimental parameters of the preset laboratory mixed flow field to obtain simulated particulate matter sedimentation data further includes:
Respectively injecting simulated particulate matters with a plurality of sizes into the initial mixed flow field model at the preset emission position at the preset experimental speed to obtain simulated sedimentation fractions corresponding to the plurality of sizes;
the obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field further comprises:
And acquiring actual sedimentation fractions corresponding to the multiple sizes of the preset laboratory mixed flow field.
Optionally, the simulating with the initial mixed flow field model according to the experimental parameters of the preset laboratory mixed flow field to obtain simulated particulate matter sedimentation data further includes:
Setting a plurality of wall temperatures for the initial mixed flow field model respectively, and injecting simulated particles into the initial mixed flow field model at a preset emission position at the preset experimental speed to obtain simulated sedimentation fractions corresponding to the plurality of wall temperatures;
the obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field further comprises:
and acquiring actual sedimentation fractions corresponding to the wall temperatures of the preset laboratory mixed flow field.
Optionally, the simulating with the initial mixed flow field model according to the experimental parameters of the preset laboratory mixed flow field to obtain simulated particulate matter sedimentation data further includes:
respectively setting a plurality of wall surface roughness for the initial mixed flow field model, and injecting simulated particles into the initial mixed flow field model at a preset emission position at the preset experimental speed to obtain simulated sedimentation fractions corresponding to the plurality of wall surface roughness;
the obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field further comprises:
And acquiring actual sedimentation fractions corresponding to the plurality of wall surface roughness of the preset laboratory mixed flow field.
Optionally, the calculating a first loss parameter of the initial hybrid flow field model according to the simulated sedimentation fraction and the actual sedimentation fraction includes:
Calculating the fitting degree between the simulated sedimentation fraction and the actual sedimentation fraction;
And taking the fitting degree between the simulated sedimentation fraction and the actual sedimentation fraction as a first loss parameter of the initial mixed flow field model.
Optionally, the calculating a second loss parameter of the initial hybrid flow field model according to a plurality of the simulated sedimentation fractions includes:
calculating a relative error between a plurality of the simulated sedimentation fractions;
And taking the relative error among a plurality of the simulated sedimentation fractions as a second loss parameter of the initial mixed flow field model.
Optionally, the simulated particulate matter sedimentation data comprises: sedimentation wind speed; the experimental parameters include: presetting an experiment speed;
according to the experimental parameters of the preset laboratory mixed flow field, an initial mixed flow field model is adopted for simulation to obtain simulated particulate matter sedimentation data, and the method further comprises the following steps:
Injecting the simulated particulate matters into the initial mixed flow field model at a preset emission position at a preset experimental speed to obtain a simulated sedimentation wind speed at the preset position;
the obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field further comprises:
Acquiring an actual sedimentation wind speed of the preset position of the preset laboratory mixed flow field;
The calculating the loss parameter of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data, further comprises:
calculating a third loss parameter of the initial mixed flow field model according to the simulated sedimentation wind speed and the actual sedimentation wind speed;
And performing parameter adjustment on the initial mixed flow field model according to the loss parameter until a preset iteration stopping condition is met, so as to obtain a target mixed flow field model, and further comprising:
And carrying out parameter adjustment on the initial mixed flow field model according to the third loss parameter until the third loss parameter meets a third preset iteration stopping condition, so as to obtain the target mixed flow field model.
In a second aspect, an embodiment of the present application provides a method for simulating and predicting particulate matter sedimentation based on a mixed flow field, including:
Acquiring operation parameters of a mixed flow field;
Performing simulation prediction according to the operation parameters and a preset mixed flow field model to obtain a simulation operation result of the mixed flow field; the mixed flow field model is a target mixed flow field model obtained by training the mixed flow field model training method according to any one of the first aspect.
In a third aspect, an embodiment of the present application provides an electronic device, including: the device comprises a processor and a storage medium, wherein the processor is in communication connection with the storage medium through a bus, the storage medium stores program instructions executable by the processor, and the processor calls a program stored in the storage medium to execute the steps of the training method of the hybrid flow field model according to any one of the first aspect or the steps of the particulate matter sedimentation simulation prediction method based on the hybrid flow field according to the second aspect.
Compared with the prior art, the application has the following beneficial effects:
The application provides a training and particulate matter sedimentation simulation prediction method and equipment of a mixed flow field model, wherein the method adopts an initial mixed flow field model to simulate according to experimental parameters of a preset laboratory mixed flow field to obtain simulated particulate matter sedimentation data; acquiring actual particulate matter sedimentation data of a preset laboratory mixed flow field; calculating loss parameters of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data; and according to the loss parameters, carrying out parameter adjustment on the initial mixed flow field model until the preset iteration stopping condition is met, and obtaining the target mixed flow field model. Therefore, the target mixed flow field model is accurately obtained, and the simulation of the real laboratory mixed flow field by adopting the target mixed flow field model is facilitated.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a training method of a hybrid flow field model provided by the application;
FIG. 2 is a schematic diagram of a hybrid flow field model provided by the present application;
FIG. 3 is a flow chart of a method for training a hybrid flow field model according to a sedimentation fraction according to an embodiment of the present application;
FIG. 4 is a flow chart of another method for training a hybrid flow field model based on a sedimentation fraction according to an embodiment of the present application;
FIG. 5 is a flow chart of yet another method for training a hybrid flow field model based on a sedimentation fraction according to an embodiment of the present application;
FIG. 6 is a flow chart of yet another method for training a hybrid flow field model based on a sedimentation fraction according to an embodiment of the present application;
FIG. 7 is a flow chart of a method for calculating a first loss parameter of an initial hybrid flow field model according to an embodiment of the present application;
FIG. 8 is a flow chart of a method for calculating a second loss parameter of an initial hybrid flow field model according to an embodiment of the present application;
FIG. 9 is a flow chart of a method for training a hybrid flow field model according to a sediment wind speed according to an embodiment of the present application;
FIG. 10 is a schematic flow chart of a method for simulating and predicting the sedimentation of particulate matters based on a mixed flow field;
FIG. 11 is a schematic diagram of a training device for a hybrid flow field model according to an embodiment of the present application;
fig. 12 is a schematic diagram of a particulate matter sedimentation simulation prediction device based on a mixed flow field according to an embodiment of the present application;
fig. 13 is a schematic diagram of an electronic device according to an embodiment of the present application.
Icon: 1101-simulation module, 1102-first acquisition module, 1103-calculation module, 1104-training module, 1201-second acquisition module, 1202-prediction module, 1301-processor, 1302-storage medium.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
Furthermore, the terms "first," "second," and the like, if any, are used merely for distinguishing between descriptions and not for indicating or implying a relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
In order to improve the accuracy of a mixed flow field model, the application provides a training method, a training device, training equipment and a storage medium of the mixed flow field model.
The training method of the hybrid flow field model provided by the application is explained by a specific example. Fig. 1 is a schematic flow chart of a training method of a hybrid flow field model according to the present application, where an execution subject of the method may be an electronic device, and the electronic device may be a device with a computing function, such as a desktop computer, a notebook computer, or the like. As shown in fig. 1, the method includes:
S101, according to experimental parameters of a preset laboratory mixed flow field, adopting an initial mixed flow field model to simulate, and obtaining simulated particulate matter sedimentation data.
It should be noted that, in order to train and verify the accuracy of the mixed flow field model, modeling software is used to build an initial mixed flow field model, and a preset laboratory mixed flow field is built in a real laboratory environment. And the initial mixed flow field model and the preset laboratory mixed flow field are set to adopt the same experimental parameters. Therefore, a mixed flow field model similar to a preset laboratory mixed flow field is obtained through multiple training. The experimental parameters are structural parameters of the mixed flow field, such as length, width, height and fan position of the mixed flow field.
For example, the flow field cells were first mixed in a realistic experimental environment, the fan position was set, and the fan speed. And then, according to the structural parameters of the mixed flow field cell, establishing a physical model of the mixed flow field by adopting Solidworks mechanical drawing software, and carrying out grid division on the model by adopting Fluent meshing, and setting the position of the fan and the rotating speed of the fan.
After the initial mixed flow field model is established, blowing is carried out by adopting a preset experimental speed as the rotating speed of the fan, and the particulate matters are injected into the particulate matter injection port, so that a mixed flow field is formed in the initial mixed flow field model. And then collecting and obtaining the simulated particulate matter sedimentation data in the initial mixed flow field model.
S102, acquiring actual particulate matter sedimentation data of a preset laboratory mixed flow field.
For comparative training, actual particulate matter sedimentation data of a preset laboratory mixed flow field is acquired simultaneously.
S103, calculating loss parameters of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data.
There is a difference between the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data. And calculating the loss parameter of the initial mixed flow field model according to the difference between the simulated particle sedimentation data and the actual particle sedimentation data.
And S104, carrying out parameter adjustment on the initial mixed flow field model according to the loss parameters until the preset iteration stopping condition is met, and obtaining the target mixed flow field model.
For example, the preset stop iteration condition may be that the loss parameter is smaller than a preset loss threshold, or that the number of iterations is greater than or equal to a preset number.
If the preset iteration stopping condition is not met, the difference between the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data is large, and the actual laboratory mixed flow field cannot be simulated by using the mixed flow field model.
If the preset iteration stopping condition is met, the difference between the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data meets the training requirement, and a mixed flow field model can be adopted to simulate a real laboratory mixed flow field. Therefore, the target mixed flow field model is accurately obtained, and the simulation of the real laboratory mixed flow field by adopting the target mixed flow field model is facilitated.
The application also provides a schematic diagram of the hybrid flow field model based on the embodiment corresponding to fig. 1. Fig. 2 is a schematic diagram of a hybrid flow field model according to the present application. As shown in fig. 2, the length, width, and height dimensions of the hybrid flow field model are shown, as well as the different locations of the particulate injection ports and the hybrid flow field.
To sum up, in this embodiment, according to the experimental parameters of the preset laboratory mixed flow field, an initial mixed flow field model is adopted to perform simulation, so as to obtain simulated particulate matter sedimentation data; acquiring actual particulate matter sedimentation data of a preset laboratory mixed flow field; calculating loss parameters of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data; and according to the loss parameters, carrying out parameter adjustment on the initial mixed flow field model until the preset iteration stopping condition is met, and obtaining the target mixed flow field model. Therefore, the target mixed flow field model is accurately obtained, and the simulation of the real laboratory mixed flow field by adopting the target mixed flow field model is facilitated.
On the basis of the embodiment corresponding to fig. 1, the embodiment of the application also provides a method for training the mixed flow field model according to the sedimentation fraction. Fig. 3 is a flow chart of a method for training a hybrid flow field model according to a sedimentation fraction according to an embodiment of the present application. As shown in fig. 3, the simulated particulate matter sedimentation data includes: sedimentation fraction; the experimental parameters include: the experimental speed is preset.
In S101, according to the experimental parameters of the preset laboratory mixed flow field, performing simulation by using an initial mixed flow field model to obtain simulated particulate matter sedimentation data, including:
S201, injecting the simulated particulate matters into the initial mixed flow field model at a preset experimental speed at a plurality of emission positions respectively to obtain simulated sedimentation fractions corresponding to the emission positions.
And operating the initial mixed flow field model at a preset experimental speed. And selecting 9 emission positions which are uniformly distributed on a certain wall surface in the initial mixed flow field model, and injecting particles from the 9 emission positions. The sedimentation fraction obtained when particles were injected from different positions was calculated from the number of settled particles and the total number of particles when particles were injected from each emission position.
Illustratively, the sedimentation fraction is the ratio of the number of settled particles to the total number of particles.
The step of acquiring actual particulate matter sedimentation data of a preset laboratory mixed flow field in S102 includes:
s202, acquiring actual sedimentation fractions corresponding to a plurality of emission positions of a preset laboratory mixed flow field.
It should be noted that the plurality of emission positions of the preset laboratory hybrid flow field are the same as the plurality of emission positions of the initial hybrid flow field model.
And calculating the sedimentation fraction obtained when the particles are injected from different positions according to the number of settled particles and the total number of particles when the particles are injected from each emission position of the preset laboratory mixed flow field.
Calculating loss parameters of the initial hybrid flow field model from the simulated particulate matter settling data and the actual particulate matter settling data in S103, comprising:
s203, calculating a first loss parameter of the initial mixed flow field model according to the simulated sedimentation fraction and the actual sedimentation fraction.
There is a difference between the simulated sedimentation fraction and the actual sedimentation fraction. And calculating the loss parameter of the initial mixed flow field model according to the difference between the simulated sedimentation fraction and the actual sedimentation fraction.
The first loss parameter characterizes the difference between the simulation and the actual.
S204, calculating a second loss parameter of the initial mixed flow field model according to the plurality of simulated sedimentation fractions.
The second loss parameter characterizes whether the initial hybrid flow field model is a hybrid flow field.
In S104, according to the loss parameter, performing parameter adjustment on the initial mixed flow field model until a preset stop iteration condition is satisfied, to obtain a target mixed flow field model, including:
And S205, carrying out parameter adjustment on the initial mixed flow field model according to the first loss parameter and the second loss parameter until the first loss parameter meets a first preset iteration stopping condition and the second loss parameter meets a second preset iteration stopping condition, so as to obtain the target mixed flow field model.
For example, the first preset stop iteration condition may be that the first loss parameter is less than a first preset loss threshold, or that the first number of iterations is greater than or equal to a first preset number. The second preset stop iteration condition may be that the second loss parameter is smaller than a second preset loss threshold, or the second iteration number is greater than or equal to a second preset number.
If the first preset iteration stopping condition is not met, the difference between the simulated sedimentation fraction and the actual sedimentation fraction is larger, and the actual laboratory mixed flow field cannot be simulated by using the mixed flow field model. And if the second preset iteration stopping condition is not met, indicating that the mixed flow field model is not the mixed flow field.
If the first preset stopping iteration condition is met and the second preset stopping iteration condition is met, a target mixed flow field model can be used for simulating a real laboratory mixed flow field, and the target mixed flow field model is a mixed flow field. Therefore, the target mixed flow field model is accurately obtained, the simulation of a real laboratory mixed flow field by adopting the target mixed flow field model is facilitated, and the mixed flow field is obtained.
To sum up, in the present embodiment, the simulated particulate matter sedimentation data includes: sedimentation fraction; the experimental parameters include: presetting an experiment speed; injecting the simulated particulate matters into the initial mixed flow field model at a preset experimental speed at a plurality of emission positions respectively to obtain simulated sedimentation fractions corresponding to the emission positions; acquiring actual sedimentation fractions corresponding to a plurality of emission positions of a preset laboratory mixed flow field; calculating a first loss parameter of the initial mixed flow field model according to the simulated sedimentation fraction and the actual sedimentation fraction; calculating a second loss parameter of the initial mixed flow field model according to the plurality of simulated sedimentation fractions; and carrying out parameter adjustment on the initial mixed flow field model according to the first loss parameter and the second loss parameter until the first loss parameter meets a first preset iteration stopping condition and the second loss parameter meets a second preset iteration stopping condition, so as to obtain the target mixed flow field model. Therefore, the target mixed flow field model is accurately obtained, the simulation of a real laboratory mixed flow field by adopting the target mixed flow field model is facilitated, and the mixed flow field is obtained.
On the basis of the embodiment corresponding to fig. 3, the embodiment of the application also provides another method for training the mixed flow field model according to the sedimentation fraction. Fig. 4 is a flow chart of another method for training a hybrid flow field model according to a sedimentation fraction according to an embodiment of the present application. As shown in fig. 4, in S101, according to the experimental parameters of the preset laboratory mixed flow field, an initial mixed flow field model is adopted to perform simulation, so as to obtain simulated particulate matter sedimentation data, and the method further includes:
S301, respectively injecting simulated particulate matters with a plurality of sizes into an initial mixed flow field model at a preset emission position at a preset experimental speed to obtain simulated sedimentation fractions corresponding to the plurality of sizes.
Exemplary of the plurality of sizes of simulated particulate matter are particulate matter having a radius of 0.01 μm, 0.03 μm, 0.1 μm, 0.3 μm, 1 μm, 3 μm, 10 μm.
For example, the simulated particulate matter with multiple sizes may be injected into the initial mixed flow field model at the preset experimental speed at the multiple emission positions, so as to obtain the multiple emission positions and the simulated sedimentation fractions corresponding to the multiple sizes.
The step of acquiring actual particulate matter sedimentation data of the preset laboratory mixed flow field in S102 further comprises:
S302, acquiring actual sedimentation fractions corresponding to a plurality of sizes of a preset laboratory mixed flow field.
And respectively injecting real particulate matters with a plurality of sizes into the preset laboratory mixed flow field of the initial mixed flow field model at a preset experimental speed at preset emission positions in the preset laboratory mixed flow field to obtain actual sedimentation fractions corresponding to the plurality of sizes.
Further, steps S203 to S205 are continued.
To sum up, in this embodiment, at a preset emission position, respectively injecting a plurality of sizes of simulated particulate matters into an initial mixed flow field model at a preset experimental speed to obtain a plurality of sizes of simulated sedimentation fractions corresponding to each other; and obtaining actual sedimentation fractions corresponding to a plurality of sizes of a preset laboratory mixed flow field. Therefore, the target mixed flow field model is accurately obtained, the simulation of a real laboratory mixed flow field by adopting the target mixed flow field model is facilitated, and the mixed flow field is obtained.
On the basis of the embodiment corresponding to fig. 3, the embodiment of the application also provides a method for training the mixed flow field model according to the sedimentation fraction. Fig. 5 is a flow chart of a method for training a hybrid flow field model according to a sedimentation fraction according to an embodiment of the present application. As shown in fig. 5, in S101, according to the experimental parameters of the preset laboratory mixed flow field, an initial mixed flow field model is adopted to perform simulation, so as to obtain simulated particulate matter sedimentation data, and the method further includes:
s401, respectively setting a plurality of wall temperatures for the initial mixed flow field model, and injecting simulated particles into the initial mixed flow field model at a preset emission position at a preset experimental speed to obtain simulated sedimentation fractions corresponding to the plurality of wall temperatures.
By way of example, a wall temperature is set for the initial mixed flow field model, and simulated particulate matters are injected into the initial mixed flow field model at a preset emission position at a preset experimental speed, so as to obtain a simulated sedimentation fraction corresponding to the wall temperature. And sequentially obtaining simulated sedimentation fractions corresponding to the wall temperatures.
The step of acquiring actual particulate matter sedimentation data of the preset laboratory mixed flow field in S102 further comprises:
S402, obtaining actual sedimentation fractions corresponding to a plurality of wall temperatures of a preset laboratory mixed flow field.
And respectively setting a plurality of same wall temperatures for a preset laboratory mixed flow field, and injecting particles into the preset laboratory mixed flow field at a preset emission position at a preset experiment speed to obtain actual sedimentation fractions corresponding to the plurality of wall temperatures.
Further, steps S203 to S205 are continued.
To sum up, in this embodiment, a plurality of wall temperatures are respectively set for an initial mixed flow field model, and simulated particulate matters are injected into the initial mixed flow field model at a preset emission position at a preset experimental speed, so as to obtain simulated sedimentation fractions corresponding to the plurality of wall temperatures; and obtaining actual sedimentation fractions corresponding to a plurality of wall temperatures of a preset laboratory mixed flow field. Therefore, the target mixed flow field model is accurately obtained, the simulation of a real laboratory mixed flow field by adopting the target mixed flow field model is facilitated, and the mixed flow field is obtained.
On the basis of the embodiment corresponding to fig. 3, the embodiment of the application also provides a method for training the mixed flow field model according to the sedimentation fraction. Fig. 6 is a flow chart of yet another method for training a hybrid flow field model based on a sedimentation fraction according to an embodiment of the present application. As shown in fig. 6, in S101, according to the experimental parameters of the preset laboratory mixed flow field, an initial mixed flow field model is adopted to perform simulation, so as to obtain simulated particulate matter sedimentation data, and the method further includes:
S501, respectively setting a plurality of wall surface roughness on the initial mixed flow field model, and injecting the simulated particles into the initial mixed flow field model at a preset emission position at a preset experimental speed to obtain simulated sedimentation fractions corresponding to the plurality of wall surface roughness.
For example, a wall roughness is set for the initial mixed flow field model, and simulated particulate matters are injected into the initial mixed flow field model at a preset emission position at a preset experimental speed, so as to obtain a simulated sedimentation fraction corresponding to the wall roughness. And sequentially obtaining simulated sedimentation fractions corresponding to the wall surface roughness.
The step of acquiring actual particulate matter sedimentation data of the preset laboratory mixed flow field in S102 further comprises:
S502, obtaining actual sedimentation fractions corresponding to the roughness of a plurality of walls of a preset laboratory mixed flow field.
And respectively setting a plurality of same wall surface roughness for a preset laboratory mixed flow field, and injecting particles into the preset laboratory mixed flow field at a preset emission position at a preset experiment speed to obtain actual sedimentation fractions corresponding to the plurality of wall surface roughness.
Further, steps S203 to S205 are continued.
To sum up, in this embodiment, a plurality of wall surface roughness is set for an initial mixed flow field model, and simulated particulate matters are injected into the initial mixed flow field model at a preset emission position at a preset experimental speed, so as to obtain simulated sedimentation fractions corresponding to the plurality of wall surface roughness; and obtaining actual sedimentation fractions corresponding to the roughness of a plurality of walls of the preset laboratory mixed flow field. Therefore, the target mixed flow field model is accurately obtained, the simulation of a real laboratory mixed flow field by adopting the target mixed flow field model is facilitated, and the mixed flow field is obtained.
On the basis of the embodiment corresponding to fig. 3, the embodiment of the application further provides a method for calculating the first loss parameter of the initial mixed flow field model. Fig. 7 is a flowchart of a method for calculating a first loss parameter of an initial hybrid flow field model according to an embodiment of the present application. As shown in fig. 7, calculating a first loss parameter of the initial hybrid flow field model from the simulated sedimentation fraction and the actual sedimentation fraction in S203 includes:
S601, calculating the fitting degree between the simulated sedimentation fraction and the actual sedimentation fraction.
Illustratively, a fitness calculation formula for calculating the simulated sedimentation fraction and the actual sedimentation fraction is shown in the following formula (1):
wherein R is the fitting degree, A is the simulated sedimentation fraction, and B is the actual sedimentation fraction.
The higher the fitting degree is, the closer the simulated sedimentation fraction is to the actual sedimentation fraction; the lower the fit, the more the simulated sedimentation fraction differs from the actual sedimentation fraction.
S602, using the fitting degree between the simulated sedimentation fraction and the actual sedimentation fraction as a first loss parameter of the initial mixed flow field model.
For example, the first preset loss threshold may be 80%.
To sum up, in the present embodiment, a fitting degree between the simulated sedimentation fraction and the actual sedimentation fraction is calculated; and taking the fitting degree between the simulated sedimentation fraction and the actual sedimentation fraction as a first loss parameter of the initial mixed flow field model. Thus, the first loss parameter is calculated accurately.
On the basis of the embodiment corresponding to fig. 3, the embodiment of the application further provides a method for calculating the second loss parameter of the initial mixed flow field model. Fig. 8 is a flowchart of a method for calculating a second loss parameter of an initial hybrid flow field model according to an embodiment of the present application. As shown in fig. 8, calculating a second loss parameter of the initial hybrid flow field model from the plurality of simulated sedimentation fractions in S204 includes:
s701, calculating relative errors among a plurality of simulated sedimentation fractions.
Determining the maximum simulated sedimentation fraction and the minimum simulated sedimentation fraction in the simulated sedimentation fractions, and taking the relative error between the maximum simulated sedimentation fraction and the minimum simulated sedimentation fraction as the relative error between the simulated sedimentation fractions.
S702, taking the relative error among a plurality of simulated sedimentation fractions as a second loss parameter of the initial mixed flow field model.
For example, the second preset loss threshold may be 95%. The relative error is greater than or equal to 95%, the mixed flow field model is a mixed flow field; the relative error is less than 95% indicating that the hybrid flow field model is not a hybrid flow field.
To sum up, in the present embodiment, the relative error between the plurality of simulated sedimentation scores is calculated; and taking the relative error among the plurality of simulated sedimentation fractions as a second loss parameter of the initial mixed flow field model. Thus, the second loss parameter is accurately calculated.
On the basis of the embodiment corresponding to fig. 1, the embodiment of the application also provides a method for training the mixed flow field model according to the sedimentation wind speed. Fig. 9 is a schematic flow chart of a method for training a hybrid flow field model according to a sedimentation wind speed according to an embodiment of the present application.
As shown in fig. 9, the simulated particulate matter sedimentation data includes: sedimentation wind speed; the experimental parameters include: the experimental speed is preset.
In S101, according to the experimental parameters of the preset laboratory mixed flow field, an initial mixed flow field model is adopted to perform simulation, so as to obtain simulated particulate matter sedimentation data, and the method further includes:
S801, injecting simulated particles into an initial mixed flow field model at a preset emission position at a preset experimental speed to obtain simulated sedimentation wind speed at the preset position.
The predetermined position is, for example, two curves of 0.25m and 0.5m from the wall surface on the predetermined section. And in the operation process of the initial mixed flow field model, acquiring the wind speed at a preset position as the simulated sedimentation wind speed.
The step of acquiring actual particulate matter sedimentation data of the preset laboratory mixed flow field in S102 further comprises:
s802, acquiring an actual sedimentation wind speed at a preset position of a preset laboratory mixed flow field.
And injecting the simulated particles into a preset laboratory mixed flow field at a preset emission position at a preset experimental speed to obtain the actual sedimentation wind speed at the preset position. The preset position of the preset laboratory mixed flow field is the same as the preset position of the initial mixed flow field model.
In S103, calculating a loss parameter of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data, and further including:
s803, calculating a third loss parameter of the initial mixed flow field model according to the simulated sedimentation wind speed and the actual sedimentation wind speed.
There is a difference between the simulated sedimentation wind speed and the actual sedimentation wind speed. And calculating a third loss parameter of the initial mixed flow field model according to the difference between the simulated sedimentation wind speed and the actual sedimentation wind speed.
In S104, according to the loss parameter, performing parameter adjustment on the initial mixed flow field model until a preset iteration stopping condition is satisfied, to obtain a target mixed flow field model, and further including:
And S804, carrying out parameter adjustment on the initial mixed flow field model according to the third loss parameter until the third loss parameter meets a third preset iteration stopping condition, and obtaining the target mixed flow field model.
For example, the preset stop iteration condition may be that the third loss parameter is smaller than a third preset loss threshold, or that the number of iterations is greater than or equal to a preset number.
To sum up, in the present embodiment, the simulated particulate matter sedimentation data includes: sedimentation wind speed; the experimental parameters include: presetting an experiment speed; injecting the simulated particles into the initial mixed flow field model at a preset emission position at a preset experimental speed to obtain a simulated sedimentation wind speed at the preset position; acquiring an actual sedimentation wind speed at a preset position of a preset laboratory mixed flow field; calculating a third loss parameter of the initial mixed flow field model according to the simulated sedimentation wind speed and the actual sedimentation wind speed; and according to the third loss parameter, carrying out parameter adjustment on the initial mixed flow field model until the third loss parameter meets a third preset iteration stopping condition, and obtaining the target mixed flow field model. Therefore, the target mixed flow field model is accurately obtained, the simulation of a real laboratory mixed flow field by adopting the target mixed flow field model is facilitated, and the mixed flow field is obtained.
The particulate matter sedimentation simulation prediction method based on the mixed flow field provided by the application is explained by a specific example. Fig. 10 is a schematic flow chart of a particulate matter sedimentation simulation prediction method based on a mixed flow field, where an execution subject of the method may be an electronic device, and the electronic device may be a device with a computing function, such as a desktop computer, a notebook computer, and the like.
As shown in fig. 10, the method includes:
S901, acquiring operation parameters of a mixed flow field.
The operating parameter is, for example, an operating wind speed.
S902, performing simulation prediction according to the operation parameters and a preset mixed flow field model to obtain a simulation operation result of the mixed flow field.
The mixed flow field model is a target mixed flow field model obtained by training the mixed flow field model training method according to any one of the above embodiments.
To sum up, in the present embodiment, the operation parameters of the hybrid flow field are obtained; and performing simulation prediction according to the operation parameters and a preset mixed flow field model to obtain a simulation operation result of the mixed flow field. Thus, the simulation operation result of the mixed flow field is accurately obtained.
The following describes training of a hybrid flow field model, a particulate matter sedimentation simulation prediction device, equipment, a storage medium and the like based on a hybrid flow field, and specific implementation processes and technical effects thereof are referred to above and are not described in detail.
Fig. 11 is a schematic diagram of a training device for a hybrid flow field model according to an embodiment of the present application, as shown in fig. 11, where the device includes:
The simulation module 1101 is configured to perform simulation by using an initial mixed flow field model according to experimental parameters of a preset laboratory mixed flow field, so as to obtain simulated particulate matter sedimentation data.
The first obtaining module 1102 is configured to obtain actual particulate matter sedimentation data of a preset laboratory mixed flow field.
The calculating module 1103 is configured to calculate a loss parameter of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data.
And the training module 1104 is used for carrying out parameter adjustment on the initial mixed flow field model according to the loss parameter until the preset iteration stopping condition is met, so as to obtain the target mixed flow field model.
Further, the simulation module 1101 specifically configured to simulate the particulate matter sedimentation data includes: sedimentation fraction; the experimental parameters include: presetting an experiment speed; and injecting the simulated particulate matters into the initial mixed flow field model at a preset experimental speed at a plurality of emission positions respectively to obtain simulated sedimentation fractions corresponding to the emission positions.
Further, the first obtaining module 1102 is specifically configured to obtain actual sedimentation fractions corresponding to a plurality of emission positions of the preset laboratory mixed flow field.
Further, the calculating module 1103 is specifically configured to calculate a first loss parameter of the initial mixed flow field model according to the simulated sedimentation fraction and the actual sedimentation fraction; and calculating a second loss parameter of the initial mixed flow field model according to the plurality of simulated sedimentation fractions.
Further, the training module 1104 is specifically configured to perform parameter adjustment on the initial hybrid flow field model according to the first loss parameter and the second loss parameter until the first loss parameter meets a first preset stop iteration condition, and the second loss parameter meets a second preset stop iteration condition, so as to obtain the target hybrid flow field model.
Further, the simulation module 1101 is specifically further configured to inject, at a preset emission position, a plurality of sizes of simulated particulate matters into the initial mixed flow field model at a preset experimental speed, so as to obtain a plurality of simulated sedimentation fractions corresponding to the sizes.
Further, the first obtaining module 1102 is specifically further configured to obtain actual sedimentation fractions corresponding to a plurality of sizes of the preset laboratory mixed flow field.
Further, the simulation module 1101 is specifically further configured to set a plurality of wall temperatures for the initial mixed flow field model, and inject the simulated particulate matter into the initial mixed flow field model at a preset emission position at a preset experimental speed, so as to obtain simulated sedimentation fractions corresponding to the plurality of wall temperatures.
Further, the first obtaining module 1102 is specifically further configured to obtain actual sedimentation fractions corresponding to a plurality of wall temperatures of the preset laboratory mixed flow field.
Further, the simulation module 1101 is specifically further configured to set a plurality of wall surface roughness for the initial mixed flow field model, and inject the simulated particulate matter into the initial mixed flow field model at a preset emission position at a preset experimental speed, so as to obtain simulated sedimentation fractions corresponding to the plurality of wall surface roughness.
Further, the first obtaining module 1102 is specifically further configured to obtain actual sedimentation fractions corresponding to the plurality of wall surface roughnesses of the preset laboratory mixed flow field.
Further, the calculating module 1103 is specifically further configured to calculate a fitting degree between the simulated sedimentation score and the actual sedimentation score; and taking the fitting degree between the simulated sedimentation fraction and the actual sedimentation fraction as a first loss parameter of the initial mixed flow field model.
Further, the calculating module 1103 is specifically configured to calculate a relative error between the plurality of simulated sedimentation scores; and taking the relative error among the plurality of simulated sedimentation fractions as a second loss parameter of the initial mixed flow field model.
Further, the simulation module 1101, specifically further for simulating particulate matter sedimentation data, includes: sedimentation wind speed; the experimental parameters include: presetting an experiment speed; and injecting the simulated particles into the initial mixed flow field model at a preset emission position at a preset experimental speed to obtain a simulated sedimentation wind speed at the preset position.
Further, the first obtaining module 1102 is specifically further configured to obtain an actual sedimentation wind speed at a preset position of a preset laboratory mixed flow field.
Further, the calculating module 1103 is specifically further configured to calculate a third loss parameter of the initial hybrid flow field model according to the simulated sedimentation wind speed and the actual sedimentation wind speed.
Further, the training module 1104 is specifically further configured to perform parameter adjustment on the initial hybrid flow field model according to the third loss parameter until the third loss parameter meets a third preset stop iteration condition, thereby obtaining the target hybrid flow field model.
Fig. 12 is a schematic diagram of a particulate matter sedimentation simulation prediction apparatus based on a mixed flow field according to an embodiment of the present application, as shown in fig. 12, the apparatus includes:
A second acquisition module 1201 is configured to acquire an operation parameter of the hybrid flow field.
The prediction module 1202 is configured to perform simulation prediction according to the operation parameters and a preset mixed flow field model, so as to obtain a simulation operation result of the mixed flow field; the mixed flow field model is a target mixed flow field model obtained by training the mixed flow field model by the training method of any one of the above embodiments.
Fig. 13 is a schematic diagram of an electronic device according to an embodiment of the present application, where the electronic device may be a device with a computing function.
The electronic device includes: processor 1301, storage medium 1302. The processor 1301 and the storage medium 1302 are connected by a bus.
The storage medium 1302 is used to store a program, and the processor 1301 calls the program stored in the storage medium 1302 to execute the above-described method embodiment. The specific implementation manner and the technical effect are similar, and are not repeated here.
Optionally, the present invention further provides a storage medium comprising a program, which when executed by a processor is adapted to carry out the above-described method embodiments. In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.
The integrated units implemented in the form of software functional units described above may be stored in a storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (english: processor) to perform some of the steps of the methods according to the embodiments of the invention. And the aforementioned storage medium includes: u disk, mobile hard disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk, etc.
Claims (10)
1. A method of training a hybrid flow field model, the method comprising:
According to the experimental parameters of a preset laboratory mixed flow field, an initial mixed flow field model is adopted for simulation, and simulated particulate matter sedimentation data are obtained;
acquiring actual particulate matter sedimentation data of the preset laboratory mixed flow field;
calculating loss parameters of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data;
And according to the loss parameters, carrying out parameter adjustment on the initial mixed flow field model until a preset iteration stopping condition is met, and obtaining a target mixed flow field model.
2. The method of claim 1, wherein the simulated particulate matter settling data comprises: sedimentation fraction; the experimental parameters include: presetting an experiment speed;
According to the experimental parameters of the preset laboratory mixed flow field, an initial mixed flow field model is adopted for simulation to obtain simulated particulate matter sedimentation data, and the method comprises the following steps:
Injecting simulated particles into the initial mixed flow field model at a preset experimental speed at a plurality of emission positions respectively to obtain simulated sedimentation fractions corresponding to the emission positions;
The obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field comprises the following steps:
Acquiring actual sedimentation fractions corresponding to a plurality of emission positions of the preset laboratory mixed flow field;
and calculating the loss parameter of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data, wherein the loss parameter comprises the following components:
calculating a first loss parameter of the initial mixed flow field model according to the simulated sedimentation fraction and the actual sedimentation fraction;
Calculating a second loss parameter of the initial mixed flow field model according to a plurality of the simulated sedimentation fractions;
And according to the loss parameter, performing parameter adjustment on the initial mixed flow field model until a preset iteration stopping condition is met, so as to obtain a target mixed flow field model, which comprises the following steps:
And carrying out parameter adjustment on the initial mixed flow field model according to the first loss parameter and the second loss parameter until the first loss parameter meets a first preset iteration stopping condition and the second loss parameter meets a second preset iteration stopping condition to obtain the target mixed flow field model.
3. The method of claim 2, wherein the simulating with the initial mixed flow field model according to the experimental parameters of the preset laboratory mixed flow field to obtain simulated particulate matter sedimentation data, further comprises:
Respectively injecting simulated particulate matters with a plurality of sizes into the initial mixed flow field model at the preset emission position at the preset experimental speed to obtain simulated sedimentation fractions corresponding to the plurality of sizes;
the obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field further comprises:
And acquiring actual sedimentation fractions corresponding to the multiple sizes of the preset laboratory mixed flow field.
4. The method of claim 2, wherein the simulating with the initial mixed flow field model according to the experimental parameters of the preset laboratory mixed flow field to obtain simulated particulate matter sedimentation data, further comprises:
Setting a plurality of wall temperatures for the initial mixed flow field model respectively, and injecting simulated particles into the initial mixed flow field model at a preset emission position at the preset experimental speed to obtain simulated sedimentation fractions corresponding to the plurality of wall temperatures;
the obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field further comprises:
and acquiring actual sedimentation fractions corresponding to the wall temperatures of the preset laboratory mixed flow field.
5. The method of claim 2, wherein the simulating with the initial mixed flow field model according to the experimental parameters of the preset laboratory mixed flow field to obtain simulated particulate matter sedimentation data, further comprises:
respectively setting a plurality of wall surface roughness for the initial mixed flow field model, and injecting simulated particles into the initial mixed flow field model at a preset emission position at the preset experimental speed to obtain simulated sedimentation fractions corresponding to the plurality of wall surface roughness;
the obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field further comprises:
And acquiring actual sedimentation fractions corresponding to the plurality of wall surface roughness of the preset laboratory mixed flow field.
6. The method of claim 2, wherein said calculating a first loss parameter of the initial hybrid flow field model from the simulated sedimentation fraction and the actual sedimentation fraction comprises:
Calculating the fitting degree between the simulated sedimentation fraction and the actual sedimentation fraction;
And taking the fitting degree between the simulated sedimentation fraction and the actual sedimentation fraction as a first loss parameter of the initial mixed flow field model.
7. The method of claim 2, wherein said calculating a second loss parameter of said initial hybrid flow field model from a plurality of said simulated sedimentation fractions comprises:
calculating a relative error between a plurality of the simulated sedimentation fractions;
And taking the relative error among a plurality of the simulated sedimentation fractions as a second loss parameter of the initial mixed flow field model.
8. The method of claim 1, wherein the simulated particulate matter settling data comprises: sedimentation wind speed; the experimental parameters include: presetting an experiment speed;
according to the experimental parameters of the preset laboratory mixed flow field, an initial mixed flow field model is adopted for simulation to obtain simulated particulate matter sedimentation data, and the method further comprises the following steps:
Injecting the simulated particulate matters into the initial mixed flow field model at a preset emission position at a preset experimental speed to obtain a simulated sedimentation wind speed at the preset position;
the obtaining the actual particulate matter sedimentation data of the preset laboratory mixed flow field further comprises:
Acquiring an actual sedimentation wind speed of the preset position of the preset laboratory mixed flow field;
The calculating the loss parameter of the initial mixed flow field model according to the simulated particulate matter sedimentation data and the actual particulate matter sedimentation data, further comprises:
calculating a third loss parameter of the initial mixed flow field model according to the simulated sedimentation wind speed and the actual sedimentation wind speed;
And performing parameter adjustment on the initial mixed flow field model according to the loss parameter until a preset iteration stopping condition is met, so as to obtain a target mixed flow field model, and further comprising:
And carrying out parameter adjustment on the initial mixed flow field model according to the third loss parameter until the third loss parameter meets a third preset iteration stopping condition, so as to obtain the target mixed flow field model.
9. The particulate matter sedimentation simulation prediction method based on the mixed flow field is characterized by comprising the following steps of:
Acquiring operation parameters of a mixed flow field;
performing simulation prediction according to the operation parameters and a preset mixed flow field model to obtain a simulation operation result of the mixed flow field; the mixed flow field model is a target mixed flow field model obtained by training the mixed flow field model training method according to any one of claims 1-8.
10. An electronic device, comprising: the device comprises a processor and a storage medium, wherein the processor is in communication connection with the storage medium through a bus, the storage medium stores program instructions executable by the processor, and the processor calls a program stored in the storage medium to execute the steps of the training method of the hybrid flow field model according to any one of claims 1 to 8 or the steps of the particulate matter sedimentation simulation prediction method based on the hybrid flow field according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311728126.6A CN117933062A (en) | 2023-12-14 | 2023-12-14 | Training and particulate matter sedimentation simulation prediction method and equipment for mixed flow field model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311728126.6A CN117933062A (en) | 2023-12-14 | 2023-12-14 | Training and particulate matter sedimentation simulation prediction method and equipment for mixed flow field model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117933062A true CN117933062A (en) | 2024-04-26 |
Family
ID=90758287
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311728126.6A Pending CN117933062A (en) | 2023-12-14 | 2023-12-14 | Training and particulate matter sedimentation simulation prediction method and equipment for mixed flow field model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117933062A (en) |
-
2023
- 2023-12-14 CN CN202311728126.6A patent/CN117933062A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170212974A1 (en) | Method for simulating a vehicle driving through water | |
| CN111079226B (en) | CFD-based automobile transmission lubricating oil liquid level simulation method | |
| CN116564421A (en) | Method for constructing prognosis model related to copper death of acute myelogenous leukemia patient | |
| CN117933062A (en) | Training and particulate matter sedimentation simulation prediction method and equipment for mixed flow field model | |
| CN111159828A (en) | Battery box heat dissipation optimization design method and device, equipment and storage medium thereof | |
| CN112163384A (en) | Solid boundary extraction method for free surface flow | |
| CN109885877B (en) | Constraint domain optimization Latin hypercube design method based on clustering algorithm | |
| Braun et al. | HPC predictions of primary atomization with SPH: challenges and lessons learned | |
| CN114818539B (en) | Underwater structure viscous drag resistance prediction method and system based on exponential function | |
| CN114925627B (en) | Helicopter flow field numerical simulation system and method based on graphic processor | |
| CN116384313A (en) | Global layout method of integrated circuit, electronic equipment and storage medium | |
| Helluy et al. | OpenCL numerical simulations of two-fluid compressible flows with a 2D random choice method | |
| Khapane et al. | Wading simulation-challenges and solutions | |
| Lin et al. | An effective approach to solve design optimization problems with arbitrarily distributed uncertainties in the original design space using ensemble of Gaussian reliability analyses | |
| Ruiz‐Gironés et al. | Insertion of triangulated surfaces into a meccano tetrahedral discretization by means of mesh refinement and optimization procedures | |
| Cao et al. | Efficient optimization design of flue deflectors through parametric surrogate modeling with physics-informed neural networks | |
| CN109686400A (en) | A kind of enrichment degree method of inspection, device and readable medium, storage control | |
| CN113177373B (en) | Fluid distribution calculation method based on VOF principle | |
| Khapane et al. | State of the Art Water Wading Simulation Method to Design Under-Body Components | |
| CN115388893B (en) | Mobile robot mapping method based on genetic filtering SLAM algorithm | |
| Chen et al. | Quantification of Meta-model and Parameter Uncertainties in Robust Design | |
| Diwakar et al. | Objective based modelling and simulation within a context of an electric vehicle development program | |
| Krajnovic | Aerodynamic optimization of vehicles using computational fluid dynamics and response surface methodology | |
| CN116822059A (en) | Aircraft performance parameter prediction method and device based on deviation classification | |
| CN115688454A (en) | Thin-wall part strain measuring point positioning method and device and thin-wall part machining equipment |
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 |