CN116306316A - Method for predicting micro-heat pipe structure and technological parameters of composite liquid suction core - Google Patents
Method for predicting micro-heat pipe structure and technological parameters of composite liquid suction core Download PDFInfo
- Publication number
- CN116306316A CN116306316A CN202310438159.0A CN202310438159A CN116306316A CN 116306316 A CN116306316 A CN 116306316A CN 202310438159 A CN202310438159 A CN 202310438159A CN 116306316 A CN116306316 A CN 116306316A
- Authority
- CN
- China
- Prior art keywords
- micro
- heat pipe
- parameters
- data
- data set
- 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
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000002131 composite material Substances 0.000 title claims abstract description 43
- 239000007788 liquid Substances 0.000 title claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 35
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims abstract description 31
- 230000008569 process Effects 0.000 claims abstract description 30
- 230000001419 dependent effect Effects 0.000 claims abstract description 16
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 15
- 238000002474 experimental method Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000011176 pooling Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 9
- 238000009826 distribution Methods 0.000 description 14
- 238000012938 design process Methods 0.000 description 6
- 238000005452 bending Methods 0.000 description 5
- 238000010438 heat treatment Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000007789 sealing Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007872 degassing Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000005245 sintering Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/20—Design reuse, reusability analysis or reusability optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a composite wick micro-heat pipe structure and a prediction method of technological parameters, which are characterized in that dependent variable parameters to be predicted and independent variable parameters to be used as input are determined according to the current micro-heat pipe wick structure, a micro-heat pipe parameter data set is obtained through a micro-heat pipe experiment, after data preprocessing is carried out on data in the data set, the determined independent variable parameters are used as input parameters, and a one-dimensional convolutional neural network is adopted for training, so that a parameter prediction model is formed. And (3) expanding the groove and annular copper powder composite wick micro-heat pipe parameter data set by adopting a WGAN-GP algorithm, and changing input parameters according to a parameter prediction model to obtain corresponding micro-heat pipe structure and process parameters. The method solves the problems that the traditional design of the groove and annular copper powder composite liquid suction core micro-heat pipe depends on expert design experience, repeated experiments are needed, and the micro-heat pipe structure and the technological parameters are not easy to obtain quickly, and realizes the quick active design of the groove and annular copper powder composite liquid suction core micro-heat pipe structure and the technological parameters.
Description
Technical Field
The invention belongs to the technical field of micro-heat tube design and data analysis and processing, and particularly relates to a method for predicting a composite liquid suction core micro-heat tube structure and process parameters.
Background
The groove and annular copper powder composite liquid suction core structure can avoid the problems of small capillary force of the groove liquid suction core structure, low permeability of the copper powder sintered liquid suction core structure, large thermal resistance of the woven net liquid suction core structure and the like. Therefore, the groove and annular composite wick structure is widely applied to flattening micro heat pipes with flattening thickness of 2.0mm-3.0 mm. However, the micro heat pipe has complex parameters and the performance is influenced by the structure and the technological parameters. The micro heat pipe structure parameters include micro heat pipe wall thickness, micro heat pipe diameter, micro heat pipe bending, groove depth, groove width, groove quantity, copper powder type and the like. The micro heat pipe process can be divided into five parts, namely pipe blank manufacturing, degassing process, heat treatment process, forming process and test process. Wherein the micro heat pipe process parameters comprise core rod size, sintering temperature, vacuum degree, working medium sealing quantity and the like. The current groove and annular copper powder composite micro-heat pipe structure and technological parameters are designed and tested by a designer according to the micro-heat pipe requirement, and are selected through multiple experimental verification, and the whole design process depends on the experience knowledge of the designer. However, due to the numerous parameters, the design process of the micro heat pipe is difficult to integrate multi-parameter consideration, so that the performance of the micro heat pipe cannot meet the requirements, and the requirements of the micro heat pipe are more and more complicated along with the diversification of the use scenes of the micro heat pipe. In the traditional production and manufacturing process of the micro heat pipe, engineering personnel also need to determine the structure and the technological parameters of the groove and annular copper powder composite micro heat pipe through multiple experiments, so that the cost is high and the efficiency is low.
In recent years, the combination of machine learning and industrial production processes is becoming more and more intimate, and the automation and intelligence level of industrial production is further improved. The wide application of machine learning provides a new idea for the design process of the groove and annular copper powder composite wick micro-heat pipe structure and technological parameters. Therefore, the technical problem to be solved by the invention is to overcome the defect that the traditional design process of the groove and annular copper powder composite liquid suction core micro-heat pipe seriously depends on expert experience, time consuming and resource consuming of multiple experiments are required, and the traditional design process of the groove and annular copper powder composite liquid suction core micro-heat pipe is replaced by prediction based on a machine learning model, so that the rapid active design is realized by a prediction method based on the structure and technological parameters of the groove and annular copper powder composite liquid suction core micro-heat pipe.
Disclosure of Invention
The invention aims to solve the technical problems in the background technology and provides a method for predicting a micro heat pipe structure and technological parameters of a composite liquid suction core.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a groove and annular copper powder composite wick micro-heat pipe structure and a technological parameter prediction method. The micro-heating tube liquid suction core to be subjected to parameter prediction is of a groove and annular copper powder composite liquid suction core structure, and comprises the following steps:
and step S1, determining the dependent variable parameters to be predicted and the independent variable parameters to be used as input. The dependent variable parameters to be predicted and the independent variable parameters to be used as input are related parameters of the micro heat pipe with the groove and annular copper powder composite wick structure. The dependent variable parameters comprise the wall thickness of the micro heat pipe, the depth of the groove, the width of the groove, the number of the groove, the type of copper powder, the diameter of the core rod and the water sealing and storing quantity; the independent variable parameters comprise the length of the micro heat pipe, the diameter of the micro heat pipe, the flattening thickness, the bending angle and the bending R angle. And designing a micro heat pipe experiment of the groove and annular copper powder composite wick structure to form a micro heat pipe parameter data set.
And S2, carrying out data preprocessing on the micro heat pipe parameter data obtained in the step S1.
Step S3, taking the micro-heat pipe parameter data set subjected to data preprocessing in the step S2 as a basis, taking the independent variables divided in the step S1 as a model input, taking the dependent variables divided in the step S1 as a model output, training by adopting a machine learning algorithm to form a parameter prediction model, wherein the machine learning method is a one-dimensional convolutional neural network, and the step of forming the parameter prediction model comprises the following steps:
(1) And (3) dividing the micro-heat pipe parameter data collected in the step (S2) into a training set and a testing set. The micro-heat pipe parameter data set is processed according to 8:2, dividing the training set and the testing set in proportion, and distributing the training set and the testing set in each model training process by adopting a k-fold cross validation method.
(2) Taking the independent variables divided in the S1 as model input, taking the dependent variables divided in the S1 as model output, and training a one-dimensional convolutional neural network model, wherein the model training process adopts a mean square error function as an optimization target, and the model training process is specifically shown as the following formula:
where J (θ) is a loss function,the predicted value of the ith variable, N is the dependent variable number.
(3) Training a one-dimensional convolutional neural network model until the final mean square value is less than a set value.
Further, the data preprocessing operation performed on the micro heat pipe parameter in S2 includes data dimensionality, missing value processing and encoding operation.
Further, the dimensionless method includes, 1) a normalization method of scaling data to fall within a small specific interval; 2) The normalization method maps the result value between [0-1] for linear transformation of the original data.
Furthermore, the encoding operation is to encode text and label data into high-dimension vectors in a one-hot mode.
Further, training a one-dimensional convolutional neural network model based on a pytorch framework obtains model weights.
Further, to ensure the integrity of the extracted features in the convolution layer, a convolution operation is performed on the convolution layer using eight convolution kernels and the result after the convolution is taken to be the relu activation function value thereof, so as to introduce a nonlinear factor into the convolution layer.
Further, in the pooling layer, the maximum pooling operation is adopted to further extract the advanced features obtained from the convolution layer, reject unnecessary features of the advanced features, and keep the larger-influence features.
Further, flattening the advanced features subjected to the maximum pooling, flattening the original two-dimensional feature matrix into a one-dimensional vector, and inputting the one-dimensional vector into a feature regressor.
Furthermore, in order to avoid the situations that original features of the micro-heat pipe demand parameter sequence are lost in the convolution process or the original features are fuzzy after the model layer number is gradually deep, a residual network is adopted, and the convolved advanced micro-heat pipe features and the initial micro-heat features are fused and input into a feature regressor.
Furthermore, a WGAN-GP algorithm is adopted to expand the data set of the groove and annular copper powder composite wick micro-heat pipe. The WGAN-GP algorithm is an extension of the GAN algorithm and consists of a generator and a discriminator, wherein the input of the generator is random noise data conforming to a certain rule, the output of the generator is a false sample, the generator can be expected to be continuously fitted with the data distribution of a real sample through training, and finally the data for the discriminator to judge as true can be generated; the input data of the discriminator is a false sample generated by the generator and a true sample contained in the original data set, and the two data mixed together are subjected to true and false discrimination. In the training process, the fake making capability of the generator is gradually enhanced, the resolution capability of the discriminator is also improved, and finally, as the training times are increased, the two networks achieve dynamic balance, namely, the generator generates data basically consistent with the real data distribution.
Furthermore, the data volume generated by adopting the WGAN-GP algorithm is not more than 20% of the real data set, so that the larger deviation of the predicted result is avoided.
Further, the generated data is checked again through the generator, and the data with the check result between 0.4 and 0.6 is used as final expansion data.
Further, the MMD algorithm is adopted to calculate the high latitude distance between the generated data set and the real data set so as to measure the data quality of the generated data set. The basic idea of MMD is that two distributions are identical if any order of the two distributions is the same. And when the two distributions are not identical, the moment that makes the difference between the two distributions the greatest should be used as a criterion for measuring the two distributions.
Compared with the prior art, the invention has the advantages that:
the invention focuses on the design process of the groove and annular copper powder composite liquid suction core micro-heat pipe, establishes a micro-heat pipe parameter data set through a design micro-heat pipe experiment, adopts a one-dimensional convolution neural network model, establishes the mapping relation between the requirement parameters of the groove and annular copper powder composite liquid suction core micro-heat pipe and the structure and process parameters thereof, solves the problems that the traditional design of the groove and annular copper powder composite liquid suction core micro-heat pipe depends on expert design experience, needs repeated experiments for many times and is not easy to obtain the micro-heat pipe structure and process parameters rapidly, and realizes the rapid and active design of the groove and annular copper powder composite liquid suction core micro-heat pipe structure and process parameters.
Drawings
FIG. 1 is a schematic flow chart of a one-dimensional convolutional neural network model employed in the present invention;
FIG. 2 is a schematic diagram of a one-dimensional convolutional neural network model employed in the present invention;
FIG. 3 is a schematic diagram of the WGAN-GP algorithm employed in the present invention.
Detailed Description
The following describes specific embodiments of the present invention with reference to examples:
it should be noted that the structures, proportions, sizes and the like illustrated in the present specification are used for being understood and read by those skilled in the art in combination with the disclosure of the present invention, and are not intended to limit the applicable limitations of the present invention, and any structural modifications, proportional changes or size adjustments should still fall within the scope of the disclosure of the present invention without affecting the efficacy and achievement of the present invention.
Also, the terms such as "upper," "lower," "left," "right," "middle," and "a" and the like recited in the present specification are merely for descriptive purposes and are not intended to limit the scope of the invention, but are intended to provide relative positional changes or modifications without materially altering the technical context in which the invention may be practiced.
Example 1
As shown in figure 1, a method for predicting the structure and process parameters of a composite wick micro-heat pipe. The micro-heating tube liquid suction core to be subjected to parameter prediction is of a groove and annular copper powder composite liquid suction core structure, and comprises the following steps:
and step S1, determining the dependent variable parameters to be predicted and the independent variable parameters to be used as input. The dependent variable parameters to be predicted and the independent variable parameters to be used as input are related parameters of the micro heat pipe with the groove and annular copper powder composite wick structure. The dependent variable parameters comprise the wall thickness of the micro heat pipe, the depth of the groove, the width of the groove, the number of the groove, the type of copper powder, the diameter of the core rod and the water sealing and storing quantity; the independent variable parameters comprise the length of the micro heat pipe, the diameter of the micro heat pipe, the flattening thickness, the bending angle and the bending R angle. And designing a micro heat pipe experiment of the groove and annular copper powder composite wick structure to form a micro heat pipe parameter data set.
And S2, carrying out data preprocessing on the micro heat pipe parameter data obtained in the step S1.
Step S3, taking the micro-heat pipe parameter data set subjected to data preprocessing in the step S2 as a basis, taking the independent variables divided in the step S1 as a model input, taking the dependent variables divided in the step S1 as a model output, training by adopting a machine learning algorithm to form a parameter prediction model, wherein the machine learning method is a one-dimensional convolutional neural network, and the step of forming the parameter prediction model comprises the following steps of:
(1) And (3) dividing the micro-heat pipe parameter data collected in the step (S2) into a training set and a testing set. The micro-heat pipe parameter data set is processed according to 8:2, dividing the training set and the testing set in proportion, and distributing the training set and the testing set in each model training process by adopting a k-fold cross validation method.
(2) Taking the independent variables divided in the S1 as model input, taking the dependent variables divided in the S1 as model output, and training a one-dimensional convolutional neural network model, wherein the model training process adopts a mean square error function as an optimization target, and the model training process is specifically shown as the following formula:
where J (θ) is a loss function,the predicted value of the ith variable, N is the dependent variable number.
(3) Training a one-dimensional convolutional neural network model until the final mean square value is less than a set value.
Further, the data preprocessing operation performed on the micro heat pipe parameter in S2 includes data dimensionality, missing value processing and encoding operation.
Further, the dimensionless method includes, 1) a normalization method of scaling data to fall within a small specific interval; 2) The normalization method maps the result value between [0-1] for linear transformation of the original data.
Furthermore, the encoding operation is to encode text and label data into high-dimension vectors in a one-hot mode.
Further, training a one-dimensional convolutional neural network model based on a pytorch framework obtains model weights.
Further, to ensure the integrity of the extracted features in the convolution layer, a convolution operation is performed on the convolution layer using eight convolution kernels and the result after the convolution is taken to be the relu activation function value thereof, so as to introduce a nonlinear factor into the convolution layer.
Further, in the pooling layer, the maximum pooling operation is adopted to further extract the advanced features obtained from the convolution layer, reject unnecessary features of the advanced features, and keep the larger-influence features.
Further, flattening the advanced features subjected to the maximum pooling, flattening the original two-dimensional feature matrix into a one-dimensional vector, and inputting the one-dimensional vector into a feature regressor.
Furthermore, in order to avoid the situations that original features of the micro-heat pipe demand parameter sequence are lost in the convolution process or the original features are fuzzy after the model layer number is gradually deep, a residual network is adopted, and the convolved advanced micro-heat pipe features and the initial micro-heat features are fused and input into a feature regressor.
Further, as shown in fig. 3, the WGAN-GP algorithm was used to extend the data of the groove and annular copper powder composite wick micro-heat pipe dataset. The WGAN-GP algorithm is an extension of the GAN algorithm and consists of a generator and a discriminator, wherein the input of the generator is random noise data conforming to a certain rule, the output of the generator is a false sample, the generator can be expected to be continuously fitted with the data distribution of a real sample through training, and finally the data for the discriminator to judge as true can be generated; the input data of the discriminator is a false sample generated by the generator and a true sample contained in the original data set, and the two data mixed together are subjected to true and false discrimination. In the training process, the fake making capability of the generator is gradually enhanced, the resolution capability of the discriminator is also improved, and finally, as the training times are increased, the two networks achieve dynamic balance, namely, the generator generates data basically consistent with the real data distribution.
Furthermore, the data volume generated by adopting the WGAN-GP algorithm is not more than 20% of the real data set, so that the larger deviation of the predicted result is avoided.
Further, the generated data is checked again through the generator, and the data with the check result between 0.4 and 0.6 is used as final expansion data.
Further, the MMD algorithm is adopted to calculate the high latitude distance between the generated data set and the real data set so as to measure the data quality of the generated data set. The basic idea of MMD is that two distributions are identical if any order of the two distributions is the same. And when the two distributions are not identical, the moment that makes the difference between the two distributions the greatest should be used as a criterion for measuring the two distributions.
While the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the above embodiments, and various changes may be made without departing from the spirit of the present invention within the knowledge of those skilled in the art.
Many other changes and modifications may be made without departing from the spirit and scope of the invention. It is to be understood that the invention is not to be limited to the specific embodiments, but only by the scope of the appended claims.
Claims (10)
1. The method for predicting the micro-thermal tube structure and the technological parameters of the composite liquid suction core is characterized in that the micro-thermal tube liquid suction core for parameter prediction is based on a groove and annular copper powder composite liquid suction core structure, and the method comprises the following steps:
s1: determining dependent variable parameters to be predicted and independent variable parameters to be used as input;
s2: and designing a micro heat pipe experiment of a groove and annular copper powder composite wick structure, and obtaining a micro heat pipe parameter data set.
S3: performing data preprocessing on the micro heat pipe parameter data set acquired in the step S2 to obtain a preprocessed data set;
s4: based on the preprocessed data set, the independent variable parameters divided in the S1 are used as model input, the independent variable parameters divided in the S1 are used as model output, a machine learning algorithm is adopted for training, a parameter prediction model is obtained, and the parameter prediction is carried out by using the obtained parameter prediction model.
2. The method for predicting the structure and process parameters of a composite wick micro-thermal tube according to claim 1, wherein the machine learning algorithm is a one-dimensional convolutional neural network, and the step of forming a parameter prediction model comprises:
dividing the preprocessed data set into a training set and a testing set according to different proportions; distributing a training set and a testing set in each model training process by adopting a k-fold cross validation method;
taking the independent variable parameters divided in the S1 as model input, taking the dependent variable parameters divided in the S1 as model output, and training a one-dimensional convolutional neural network model, wherein the model training process takes a mean square error function as an optimization target, and the specific formula is as follows:
where J (θ) is a loss function,the predicted value of the ith variable, N is the number of dependent variables;
training the one-dimensional convolutional neural network model until the final mean square difference value is smaller than a set value to obtain a parameter prediction model.
3. The method for predicting a micro heat pipe structure and process parameters of a composite wick according to claim 1, wherein the data preprocessing operation performed on the micro heat pipe parameters in S3 comprises: data dimensionless, missing value processing and encoding operations;
the dimensionless method comprises the following steps: a normalization method, namely scaling data to fall into a small specific interval; the normalization method is used for linearly transforming the original data to map the result value between 0 and 1;
the coding operation is to code text and label data into a high-dimension vector in a one-hot mode.
4. The method for predicting composite wick micro-thermal tube structure and process parameters of claim 1, wherein model weights are obtained by training a one-dimensional convolutional neural network model based on a pytorch framework.
5. The method for predicting the structure and the process parameters of the composite wick micro-thermal pipe according to claim 1, wherein eight convolution kernels are used for convolution operation in a convolution layer in the process of constructing a one-dimensional convolution neural network model, and a relu activation function value is taken for a result after the convolution.
6. The method for predicting the structure and process parameters of a composite wick micro-heat pipe according to claim 5, wherein a maximum pooling operation is adopted in the pooling layer;
flattening the advanced features subjected to the maximum pooling operation, flattening the original two-dimensional feature matrix into a one-dimensional vector, and inputting the one-dimensional vector into a feature regressor;
and adopting a residual network, and fusing the convolved advanced micro heat pipe characteristics with the initial micro heat characteristics and inputting the fused characteristics into a characteristic regressor.
7. The method for predicting the structure and process parameters of a composite wick micro-heat pipe according to claim 1, wherein the data expansion is performed on the groove and copper powder composite wick micro-heat pipe data set by adopting a WGAN-GP algorithm.
8. The method for predicting the structure and the technological parameters of the composite wick micro-thermal pipe according to claim 7, wherein the data volume generated by adopting the WGAN-GP algorithm is not more than 20% of the real data set, so that the prediction result is prevented from being greatly deviated.
9. The method for predicting the structure and the technological parameters of the composite wick micro-thermal pipe according to claim 8, wherein the generated data is checked again by the generator, and the data with the checking result between 0.4 and 0.6 is used as final expansion data.
10. The method for predicting the micro heat pipe structure and the working parameters of the composite wick of the groove and the annular copper powder according to claim 9, wherein the MMD algorithm is adopted to calculate the high latitude distance between the generated data set and the real data set so as to measure the data quality of the generated data set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310438159.0A CN116306316A (en) | 2023-04-23 | 2023-04-23 | Method for predicting micro-heat pipe structure and technological parameters of composite liquid suction core |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310438159.0A CN116306316A (en) | 2023-04-23 | 2023-04-23 | Method for predicting micro-heat pipe structure and technological parameters of composite liquid suction core |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116306316A true CN116306316A (en) | 2023-06-23 |
Family
ID=86838076
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310438159.0A Pending CN116306316A (en) | 2023-04-23 | 2023-04-23 | Method for predicting micro-heat pipe structure and technological parameters of composite liquid suction core |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116306316A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104635789A (en) * | 2013-11-11 | 2015-05-20 | 联发科技股份有限公司 | Thermal management method using micro-throttle and wireless device thereof |
US20220223494A1 (en) * | 2021-01-08 | 2022-07-14 | iCometrue Company Ltd. | Micro heat pipe for use in semiconductor ic chip package |
CN115048874A (en) * | 2022-08-16 | 2022-09-13 | 北京航空航天大学 | Aircraft design parameter estimation method based on machine learning |
CN115640515A (en) * | 2022-08-03 | 2023-01-24 | 山东天蓝信息科技有限责任公司 | RWDCGAN-based aeroengine assembly vibration sample expansion method |
-
2023
- 2023-04-23 CN CN202310438159.0A patent/CN116306316A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104635789A (en) * | 2013-11-11 | 2015-05-20 | 联发科技股份有限公司 | Thermal management method using micro-throttle and wireless device thereof |
US20220223494A1 (en) * | 2021-01-08 | 2022-07-14 | iCometrue Company Ltd. | Micro heat pipe for use in semiconductor ic chip package |
CN115640515A (en) * | 2022-08-03 | 2023-01-24 | 山东天蓝信息科技有限责任公司 | RWDCGAN-based aeroengine assembly vibration sample expansion method |
CN115048874A (en) * | 2022-08-16 | 2022-09-13 | 北京航空航天大学 | Aircraft design parameter estimation method based on machine learning |
Non-Patent Citations (1)
Title |
---|
张娴;朱月仙;许轶;许海云;李姝影;房俊民;方曙;: "芯片微冷却关键技术专利分析", 科学观察, no. 04, pages 11 - 23 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115564203B (en) | Equipment real-time performance evaluation system and method based on multidimensional data collaboration | |
US8510242B2 (en) | Artificial neural network models for determining relative permeability of hydrocarbon reservoirs | |
CN108563906B (en) | Short fiber reinforced composite material macroscopic performance prediction method based on deep learning | |
CN109063234B (en) | High-speed press force application part reliability design method considering multiple types of uncertainty | |
Knust et al. | Preform optimization for hot forging processes using genetic algorithms | |
CN109635763B (en) | Crowd density estimation method | |
CN106022352A (en) | Submersible piston pump fault diagnosis method based on support vector machine | |
CN115147655A (en) | Oil gas gathering and transportation monitoring system and method thereof | |
CN100349135C (en) | Test vector generation method | |
Radha et al. | Simplifying the powder metallurgy manufacturing process using soft computing tools | |
CN109242150A (en) | A kind of electric network reliability prediction technique | |
CN116306316A (en) | Method for predicting micro-heat pipe structure and technological parameters of composite liquid suction core | |
CN115758891A (en) | Wing profile flow field prediction method based on Transformer decoder network | |
CN110362861A (en) | A kind of mold structure parameter Multipurpose Optimal Method considering efficiency | |
CN111832951A (en) | Method and system for evaluating oil reservoir development value of small fault block ultra-low permeability reservoir | |
CN106909747B (en) | Fuzzy parameter membership function identification method in heat convection diffusion system | |
CN116305574A (en) | Test design method based on neural network model | |
CN115295098A (en) | Method and system for predicting permeability characteristics of spherical particle system based on machine learning | |
CN113051735B (en) | Electromagnetic force linear characteristic optimization method for proportional electromagnet | |
CN116467947B (en) | Prediction method of micro heat pipe structure and technological parameters | |
CN116720288B (en) | Micro-heating pipe automatic design system based on machine learning | |
CN113723649A (en) | Chemical process abnormity monitoring method based on semi-supervised model and model optimization method | |
Jannoud et al. | Genetic Algorithm for Image Recognition in Smart Systems Applications | |
Naeimi et al. | Optimum designing of forging preform die for the H-shaped parts using backward deformation method and neural networks algorithm | |
CN117058443B (en) | Pipeline magnetic flux leakage image identification method based on improved residual error shrinkage network |
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 |