CN113627036A - Method and device for predicting dielectric constant of material, computer equipment and storage medium - Google Patents
Method and device for predicting dielectric constant of material, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113627036A CN113627036A CN202111080423.5A CN202111080423A CN113627036A CN 113627036 A CN113627036 A CN 113627036A CN 202111080423 A CN202111080423 A CN 202111080423A CN 113627036 A CN113627036 A CN 113627036A
- Authority
- CN
- China
- Prior art keywords
- dielectric constant
- prediction
- model
- random forest
- training
- 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
- 239000000463 material Substances 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000007637 random forest analysis Methods 0.000 claims abstract description 80
- 238000012549 training Methods 0.000 claims abstract description 54
- 229910010293 ceramic material Inorganic materials 0.000 claims abstract description 46
- 239000002994 raw material Substances 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 50
- 239000002131 composite material Substances 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 22
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000007689 inspection Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 20
- 238000010801 machine learning Methods 0.000 abstract description 11
- 238000011161 development Methods 0.000 abstract description 10
- 238000004422 calculation algorithm Methods 0.000 abstract description 5
- 238000012360 testing method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 239000000919 ceramic Substances 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000003066 decision tree Methods 0.000 description 6
- 238000010200 validation analysis Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 229910052681 coesite Inorganic materials 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 229910052906 cristobalite Inorganic materials 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000000704 physical effect Effects 0.000 description 2
- 239000000377 silicon dioxide Substances 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 2
- 229910052682 stishovite Inorganic materials 0.000 description 2
- 229910052905 tridymite Inorganic materials 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 229910008572 Li2O—B2O3-SiO2 Inorganic materials 0.000 description 1
- 229910008585 Li2O—B2O3—SiO2 Inorganic materials 0.000 description 1
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 150000002739 metals Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000005245 sintering Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 230000009466 transformation Effects 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/26—Composites
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
Abstract
The embodiment of the invention discloses a method and a device for predicting a dielectric constant of a material, computer equipment and a storage medium. The method comprises the steps of obtaining a formula of a low-temperature co-fired ceramic material to be predicted to obtain a material to be predicted; inputting the material to be predicted into a prediction model to predict the dielectric constant so as to obtain a prediction result; the prediction model is obtained by training a random forest model by using a low-temperature co-fired ceramic material with known dielectric constant as a sample set. According to the embodiment of the invention, the disclosed data set of the formula of the low-temperature co-fired ceramic material of various systems is extracted, the machine learning model based on the random forest algorithm is trained through three parameters of the dielectric constant, the volume percentage and the density of the raw materials, and the dielectric constant of the formula of the low-temperature co-fired ceramic material to be tested is predicted through the trained prediction model, so that the prediction accuracy and the generalization effect are improved, and the development period and the cost of the new material are shortened.
Description
Technical Field
The invention relates to a computer, in particular to a method and a device for predicting the dielectric constant of a material of a low-temperature co-fired ceramic material, computer equipment and a storage medium.
Background
LTCC (Low Temperature Co-fired Ceramic) is a new material technology developed by Houss corporation of America in 1982. Initially, LTCC was mainly used in military field, but at present, LTCC has been widely used in fields of automotive electronics, communications, and medical equipment. LTCC is a technology developed by using application drivers and process technologies as a lead. The LTCC can embed four passive devices such as inductors, resistors, transformers and capacitors into a multilayer ceramic plate, then the four passive devices are laminated together, the inner electrode and the outer electrode can be made into a three-dimensional high-density circuit without mutual interference by respectively using metals such as silver, copper, gold and the like and integrally sintering at 900 ℃, and also can be made into a three-dimensional circuit substrate with built-in passive elements.
The development process of the traditional low-temperature co-fired ceramic material adopts a trial-and-error method, various physical properties of the sample are measured on the basis of successfully preparing an experimental sample, so that various physical properties of the sample are known, the material is analyzed and classified through different performance parameters, experimental research has great dependence on the experimental sample, experimental steps are complicated, a 15-25 year or even longer period is needed from research and development to application, and expected effects cannot be achieved. If the material performance can be predicted in advance by calculation or simulation before the experiment, or the range is narrowed, the development period and the development cost can be effectively reduced. At present, the calculation of the composite effective dielectric constant of the multi-term ceramic generally adopts LICHTERECKER generalized mixed logarithm equation or MAXWELL-WAGNER model and deformation model thereof. However, these models are only effective in predicting two-phase composite or partially specific material systems. The adaptability of the multi-system and multi-phase composite ceramic, low-temperature co-fired ceramic, is poor.
In summary, the existing modeling method and prediction model cannot effectively predict the dielectric constant of the low-temperature co-fired ceramic material.
Therefore, it is necessary to design a new method to effectively predict the dielectric constant of the low-temperature co-fired ceramic material, and to reduce the development cost and cycle to some extent.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a material dielectric constant prediction method, a device, computer equipment and a storage medium.
In order to achieve the purpose, the invention adopts the following technical scheme: the method for predicting the dielectric constant of the material comprises the following steps:
obtaining a formula of a low-temperature co-fired ceramic material to be predicted to obtain a material to be predicted;
inputting the material to be predicted into a prediction model to predict the dielectric constant so as to obtain a prediction result;
wherein the prediction model is obtained by training a random forest model by using a low-temperature co-fired ceramic material with a known dielectric constant as a sample set.
The further technical scheme is as follows: the prediction model is obtained by training a random forest model by taking a low-temperature co-fired ceramic material with a known dielectric constant as a sample set, and comprises the following steps:
obtaining a low-temperature co-fired ceramic material with a known dielectric constant to obtain a sample set;
preprocessing the sample set to obtain a processing result;
constructing a random forest model;
training the random forest model by using the processing result;
predicting the trained random forest model to obtain a prediction result;
and determining parameters of the random forest model according to the prediction result to obtain a prediction model.
The further technical scheme is as follows: the pre-processing the sample set to obtain a processing result, comprising:
extracting characteristic parameters from the sample set;
and converting the characteristic parameters to obtain a processing result.
The further technical scheme is as follows: the characteristic parameters include the dielectric constant of the composite material, the dielectric constant, the content and the density of raw materials constituting the composite material.
The further technical scheme is as follows: the converting the characteristic parameters to obtain a processing result comprises:
and converting the content of the raw materials for forming the composite material in the characteristic parameters into volume percentage to obtain a processing result.
The further technical scheme is as follows: the training of the random forest model by using the processing result comprises the following steps:
and training the random forest model by using the processing result by adopting a five-fold cross inspection method.
The further technical scheme is as follows: determining parameters of a random forest model according to the prediction result to obtain a prediction model, wherein the parameters comprise:
judging whether the prediction result is smaller than a set threshold value or not;
if the prediction result is smaller than the set threshold value, taking the parameters of the random forest model obtained by training as the parameters of the prediction model to obtain the prediction model;
and if the prediction result is not smaller than the set threshold value, adjusting the parameters of the random forest model, and executing the training of the random forest model by using the processing result.
The invention also provides a material dielectric constant prediction device, which comprises:
the material obtaining unit is used for obtaining a formula of the low-temperature co-fired ceramic material to be predicted so as to obtain a material to be predicted;
and the prediction unit is used for inputting the material to be predicted into a prediction model to perform dielectric constant prediction so as to obtain a prediction result.
The invention also provides computer equipment, which is characterized by comprising a memory and a processor, wherein the memory stores a computer program, and the processor realizes the method when executing the computer program.
The invention also provides a storage medium storing a computer program which, when executed by a processor, is operable to carry out the method as described above.
Compared with the prior art, the invention has the beneficial effects that: according to the method, the disclosed data set of the formula of the low-temperature co-fired ceramic material of various systems is extracted, the machine learning model based on the random forest algorithm is trained through three parameters of the dielectric constant, the volume percentage and the density of the raw materials, and the dielectric constant of the formula of the low-temperature co-fired ceramic material to be tested is predicted through the trained prediction model, so that the prediction accuracy and the generalization effect are improved, and the development period and the cost of the new material are shortened.
The invention is further described below with reference to the accompanying drawings and specific embodiments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario of a method for predicting a dielectric constant of a material according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a method for predicting dielectric constant of a material according to an embodiment of the present invention;
FIG. 3 is a sub-flow diagram illustrating a method for predicting dielectric constant of a material according to an embodiment of the present invention;
FIG. 4 is a sub-flow diagram illustrating a method for predicting dielectric constant of a material according to an embodiment of the present invention;
FIG. 5 is a sub-flow diagram illustrating a method for predicting dielectric constant of a material according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating the predicted effect of the prediction model according to the embodiment of the present invention;
FIG. 7 is a schematic block diagram of a material dielectric constant prediction apparatus provided in an embodiment of the present invention;
FIG. 8 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1 and fig. 2, fig. 1 is a schematic view of an application scenario of a method for predicting a dielectric constant of a material according to an embodiment of the present invention. Fig. 2 is a schematic flow chart of a method for predicting a dielectric constant of a material according to an embodiment of the present invention. The material dielectric constant prediction method is applied to a server. The server and the terminal carry out data interaction, the formula of the low-temperature co-fired ceramic material to be predicted is input through the terminal, the dielectric constant of the low-temperature co-fired ceramic material is predicted through a prediction model in the server, and the prediction result is fed back to the terminal.
Fig. 2 is a schematic flow chart of a method for predicting dielectric constant of a material according to an embodiment of the present invention. As shown in fig. 2, the method includes the following steps S110 to S120.
And S110, obtaining a formula of the low-temperature co-fired ceramic material to be predicted to obtain the material to be predicted.
In this embodiment, the material to be predicted refers to a formula of a low-temperature co-fired ceramic material for which the dielectric constant of the material needs to be predicted.
And S120, inputting the material to be predicted into a prediction model for dielectric constant prediction to obtain a prediction result.
In this embodiment, the prediction result refers to the dielectric constant of the material obtained by machine learning prediction through a prediction model.
The dielectric constant of the new formula is predicted, namely the formula which is not in the training set and the test set, the tested formula material can be processed through experiments, and the actually tested dielectric constant is compared with the predicted result, so that the accuracy of the prediction model in the actual use process is ensured.
Specifically, the prediction model is obtained by training a random forest model by using a low-temperature co-fired ceramic material with a known dielectric constant as a sample set.
In one embodiment, referring to fig. 3, the prediction model is obtained by training a random forest model using a low-temperature co-fired ceramic material with a known dielectric constant as a sample set, and may include steps S121 to S126.
And S121, obtaining a low-temperature co-fired ceramic material with known dielectric constant to obtain a sample set.
In the present embodiment, the sample set refers to a formula of the low-temperature co-fired ceramic material obtained from published literature and experiments for predicting the dielectric constant of the low-temperature co-fired ceramic material.
The sample sets include but are not limited to glass/ceramic composite systems, amorphous glass systems and microcrystalline glass systems, and the number of the extracted sample sets is more than 150 groups, so as to ensure the accuracy of the model training process.
And S122, preprocessing the sample set to obtain a processing result.
In the present embodiment, the processing result refers to the dielectric constant of the composite material, the dielectric constant, the content and the density of the raw materials constituting the composite material, wherein the content of the raw materials constituting the composite material is expressed in terms of volume percentage.
In one embodiment, referring to fig. 4, the step S122 may include steps S1221 to S1222.
S1221, extracting characteristic parameters from the sample set;
and S1222, converting the characteristic parameters to obtain a processing result.
Specifically, the content of the raw materials constituting the composite material in the characteristic parameters is converted into a percentage by volume to obtain a processing result.
The method comprises the steps of manually extracting LTCC material formula data in documents to form a sample set, wherein the sample set comprises dielectric constants of composite materials, names and proportions of raw material components, then querying two parameters of the dielectric constants and the densities of the raw materials through a material database and the like, and forming characteristic parameters of the dielectric constants and the densities of the extracted composite materials, the dielectric constants of the raw materials, the volume percentages of the raw materials and the densities, wherein the query process can be executed in a keyword query mode, and all the raw material contents in the extracted characteristic parameters are converted into the volume percentages, so that a processing result is obtained.
S123, constructing a random forest model;
and S124, training the random forest model by using the processing result.
In this embodiment, the random forest model is trained using the processing result by using a five-fold cross-checking method.
When the data is grouped, random grouping is adopted. That is, the extracted sample set is randomly divided into 5 groups, 4 groups of the 5 groups are used for training the model, and the remaining 1 group is used for testing the trained model. This repeats the training and testing multiple times. Specifically, the feature sample set is randomly divided into 5 groups, wherein 4 groups are training sets and are used for training a model, and one group is a test set and is used for testing the prediction effect of the model to calculate the average absolute error; repeating the above process for 5 times to obtain 5 average absolute errors; and 5 times of random grouping avoids overfitting to a certain extent, and improves the generalization effect.
And S125, predicting the trained random forest model to obtain a prediction result.
In this embodiment, the prediction result is an average absolute error of the prediction result output by the trained random forest model during testing.
After the model after each training is tested by using the test set, an average absolute error can be obtained, and the average absolute error of the whole model is calculated to evaluate the prediction effect of machine learning. When the mean absolute error value is less than 1.5, the training is stopped.
The mean absolute error is calculated by
Wherein, yiThe real value of the ith composite dielectric constant of the random forest model during testing is obtained;
the method comprises the steps of outputting an ith predicted value when a random forest model is tested; n is the total number of tests.
In addition, two terms are added to the evaluation parameter, one term is mean square error, and the mean value is represented by the sum of squares of differences between predicted values and actual values of the samples in the test set. The average pair error is further corrected by the parameter, the size can reflect the discrete degree of the difference value of the test set, and the smaller the value, the better the stability of the model. In an embodiment, the threshold value of this value is set to<4.0, the calculation formula is
The other term is a decision coefficient R2, which represents the fitting degree of the prediction model, and is between 0-1The closer to 1 the value therebetween is, the better the fitting degree is, and generally the threshold value of the value is set to>0.9. In this embodiment of the present invention,
wherein: y isiRepresenting the true value of the ith composite permittivity to be predicted in the test set,
represents the mean of the true values of all composite dielectric constants to be predicted.
In this embodiment, the values of the evaluation parameters of the model after training and parameter tuning are: MAE 1.04, MSE 3.56, R2 0.99.
And S126, determining parameters of the random forest model according to the prediction result to obtain a prediction model.
In an embodiment, referring to fig. 5, the step S126 may include steps S1261 to S1263.
S1261, judging whether the prediction result is smaller than a set threshold value;
s1262, if the prediction result is smaller than a set threshold value, taking parameters of the random forest model obtained through training as parameters of the prediction model to obtain the prediction model;
s1263, if the prediction result is not smaller than the set threshold, adjusting the parameter of the random forest model, and executing the step S124.
In this embodiment, the threshold set as described above is not limited to 1.5, and different thresholds may be selected according to actual situations.
In this embodiment, the parameters of the random forest model are as follows: the number of trees n _ estimators is 100; the deepest depth max _ depth of the tree is 10; random _ state is 0.
The parameters are parameters of the random forest model and only have different values. The above values are values in this invention.
The method is characterized in that the average absolute error is used for evaluation, if the average absolute error is less than 1.5, the prediction model is good in performance, the machine learning model is trained according to a low-temperature co-fired ceramic material with a known dielectric constant as a sample set, in the embodiment, the machine learning model adopts a random forest model, so that the prediction model can effectively predict the dielectric constant of the low-temperature co-fired ceramic material, the development cost and the development period can be reduced to a certain extent, a large number of data sets are obtained by means of published experimental data, the machine learning model is established by using a random forest algorithm, and the prediction progress and the generalization effect are improved by training the model. The method solves the problem of predicting the dielectric constant of the low-temperature co-fired ceramic material.
For example: a formula data 160 group of low-temperature co-fired ceramic materials comprising a plurality of systems such as CaO-B2O3-SiO2 system, Li2O-B2O3-SiO2, MgO-Al2O3-SiO2 and the like is extracted from the literature, and after the acquired data are preprocessed, a training set and a test set are formed. The machine learning model was built using Python programming. The average absolute error is calculated after training is completed. As a proof, 6 low temperature co-fired ceramic formulations containing three of these systems were process tested. The recipe data for the validation set is shown in table 1.
TABLE 1 formulation data for the validation set
The prediction results of different models for the validation set are shown in table 2. Table 2 shows only the prediction model and LICHTERECKER generalized mixed logarithm equation comparisons. In addition, the system for machine learning prediction is a system which is learned in a training set, is not the same formula, but is the type of the contained system.
TABLE 2 prediction of validation set by different models
From table 2, it can be known that the prediction accuracy and generalization effect of the prediction model formed by the random forest model are improved, and the development period and cost of the new material are shortened, which can be specifically shown in fig. 6.
In this embodiment, the frame parameters of the random forest model are mainly three: n _ estimators are the number of decision trees, if the parameter is too small, under-fitting easily occurs, generally, the larger the parameter value is, the better the fitting effect is, but the calculation amount can also be increased, after reaching a certain value, the value of the parameter is continuously increased, the calculation amount and time can be continuously increased, but the improvement on the fitting degree is very small, the effect cannot be obviously improved, and therefore, when the parameter is adjusted, a value which takes the calculation amount and the fitting effect into consideration can be preferably selected. Bootstp, namely whether the sample is subjected to the sample with put back sampling or not to construct a decision tree; true indicates a default value True. oob _ score is whether to use out-of-bag samples to evaluate the model's quality, True represents the default value False. The latter two parameters are determined according to actual conditions, and there is no absolute preference, and in the embodiment, default values, boottrp (true), oob _ score (false), are adopted, so that two frame parameters are not explained and optimized.
Random forest decision tree parameters: the max _ features is the maximum feature number, the default value is auto, the larger the parameter effect max _ features value is, the more information the model can learn, and the easier the overfitting is. max _ depth is the maximum depth of the tree, the default value may not be input, and the common values are: 10-100, the larger the parameter effect is, the more complex the decision tree is, and the easier it is to overfit. min _ samples _ split, which is the minimum number of samples required for internal node subdivision, default: 2; the larger the parameter effect is, the simpler the decision tree is, and the less the overfitting is easy. min _ weight _ fraction _ leaf, which is the minimum number of samples of a leaf node, the default value: 1; the larger the parameter effect is, the easier the leaf nodes are pruned, the simpler the decision tree is, the less fitting is easy. min _ weight _ fraction _ leaf, which is the minimum sample weight sum of leaf nodes, is a default value of 0; the parameter effect is that if more samples have missing values or the distribution class deviation of the classification tree samples is large, the parameters are changed. max _ leaf _ nodes is the maximum leaf node number, and the default value is None; the smaller the parameter effect is, the fewer the number of leaf nodes is, and overfitting can be prevented. min _ impurity _ split, i.e. minimum impure degree of node partitioning, default value 1e-7, parameter effect is that no change is generally recommended. random _ state, which is a random state, is a model parameter for machine learning, because we need to use the model to predict after training the model. Therefore, it is necessary to ensure that the trained model and the prediction model are the same model, and the model is not random, so the value set is random _ state equal to 0.
Parameter tuning is required to be performed according to the sample condition, the set threshold value and the cross validation effect. In this embodiment, three parameters are adjusted, and other parameters are all default values, and have been optimized to the set threshold value. All parameters are not readjusted.
According to the method for predicting the dielectric constant of the material, the disclosed data set of the formula of the low-temperature co-fired ceramic material of various systems is extracted, the machine learning model based on the random forest algorithm is trained through three parameters of the dielectric constant, the volume percentage and the density of the raw materials, and the dielectric constant of the formula of the low-temperature co-fired ceramic material to be tested is predicted through the trained prediction model, so that the prediction accuracy and the generalization effect are improved, and the development period and the cost of a new material are shortened.
Fig. 7 is a schematic block diagram of a material dielectric constant prediction apparatus 300 according to an embodiment of the present invention. As shown in fig. 7, the present invention also provides a material dielectric constant predicting apparatus 300 corresponding to the above material dielectric constant predicting method. The material dielectric constant prediction apparatus 300 includes a unit for performing the above-described material dielectric constant prediction method, and the apparatus may be configured in a server. Specifically, referring to fig. 7, the material permittivity prediction apparatus 300 includes a material obtaining unit 301 and a prediction unit 302.
The material obtaining unit 301 is configured to obtain a formula of a low-temperature co-fired ceramic material to be predicted, so as to obtain a material to be predicted; the prediction unit 302 is configured to input the material to be predicted into a prediction model for dielectric constant prediction, so as to obtain a prediction result.
In one embodiment, the material dielectric constant prediction apparatus 300 includes a prediction model obtaining unit.
The prediction model obtaining unit is used for training a random forest model by taking a low-temperature co-fired ceramic material with a known dielectric constant as a sample set so as to obtain a prediction model.
In an embodiment, the prediction model obtaining unit includes a sample set obtaining subunit, a preprocessing subunit, a model constructing subunit, a training subunit, a prediction subunit, and a parameter determining subunit.
The sample set acquisition subunit is used for acquiring a low-temperature co-fired ceramic material with a known dielectric constant to obtain a sample set; a preprocessing subunit, configured to preprocess the sample set to obtain a processing result; the model building subunit is used for building a random forest model; the training subunit is used for training the random forest model by using the processing result; the prediction subunit is used for predicting the trained random forest model to obtain a prediction result; and the parameter determining subunit is used for determining the parameters of the random forest model according to the prediction result so as to obtain the prediction model.
In one embodiment, the preprocessing subunit includes a parameter extraction module and a transformation module.
The parameter extraction module is used for extracting characteristic parameters from the sample set; and the conversion module is used for converting the characteristic parameters to obtain a processing result.
Specifically, the conversion module is used for converting the content of the raw materials composing the composite material in the characteristic parameters into volume percentage so as to obtain a processing result.
Specifically, the training subunit is configured to train the random forest model by using the processing result through a five-fold cross-checking method.
In an embodiment, the parameter determining subunit is configured to determine whether the prediction result is smaller than a set threshold; if the prediction result is smaller than the set threshold value, taking the parameters of the random forest model obtained by training as the parameters of the prediction model to obtain the prediction model; and if the prediction result is not smaller than the set threshold value, adjusting the parameters of the random forest model, and executing the training of the random forest model by using the processing result.
It should be noted that, as can be clearly understood by those skilled in the art, the specific implementation processes of the material dielectric constant prediction apparatus 300 and each unit may refer to the corresponding descriptions in the foregoing method embodiments, and for convenience and brevity of description, no further description is provided herein.
The material dielectric constant prediction apparatus 300 may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 8.
Referring to fig. 8, fig. 8 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of a plurality of servers.
Referring to fig. 8, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 comprises program instructions that, when executed, cause the processor 502 to perform a material dielectric constant prediction method.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 may be enabled to perform a material dielectric constant prediction method.
The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 8 is a block diagram of only a portion of the configuration relevant to the present teachings and does not constitute a limitation on the computer device 500 to which the present teachings may be applied, and that a particular computer device 500 may include more or less components than those shown, or combine certain components, or have a different arrangement of components.
Wherein the processor 502 is configured to run the computer program 5032 stored in the memory to implement the following steps:
obtaining a formula of a low-temperature co-fired ceramic material to be predicted to obtain a material to be predicted; inputting the material to be predicted into a prediction model to predict the dielectric constant so as to obtain a prediction result;
wherein the prediction model is obtained by training a random forest model by using a low-temperature co-fired ceramic material with a known dielectric constant as a sample set.
In one embodiment, the processor 502 implements the following steps when implementing the step of training the random forest model by using the low-temperature co-fired ceramic material with known dielectric constant as the sample set:
obtaining a low-temperature co-fired ceramic material with a known dielectric constant to obtain a sample set; preprocessing the sample set to obtain a processing result; constructing a random forest model; training the random forest model by using the processing result; predicting the trained random forest model to obtain a prediction result; and determining parameters of the random forest model according to the prediction result to obtain a prediction model.
In an embodiment, when the processor 502 implements the step of preprocessing the sample set to obtain the processing result, the following steps are specifically implemented:
extracting characteristic parameters from the sample set; and converting the characteristic parameters to obtain a processing result.
Wherein the characteristic parameters comprise the dielectric constant of the composite material, the dielectric constant, the content and the density of raw materials for forming the composite material.
In an embodiment, when the processor 502 implements the step of converting the characteristic parameter to obtain the processing result, the following steps are specifically implemented:
and converting the content of the raw materials for forming the composite material in the characteristic parameters into volume percentage to obtain a processing result.
In an embodiment, when the processor 502 implements the step of training the random forest model by using the processing result, the following steps are specifically implemented:
and training the random forest model by using the processing result by adopting a five-fold cross inspection method.
In an embodiment, when the processor 502 implements the step of determining the parameters of the random forest model according to the prediction result to obtain the prediction model, the following steps are specifically implemented:
judging whether the prediction result is smaller than a set threshold value or not; if the prediction result is smaller than the set threshold value, taking the parameters of the random forest model obtained by training as the parameters of the prediction model to obtain the prediction model; and if the prediction result is not smaller than the set threshold value, adjusting the parameters of the random forest model, and executing the training of the random forest model by using the processing result.
It should be understood that in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program includes program instructions, and the computer program may be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program, when executed by a processor, causes the processor to perform the steps of:
obtaining a formula of a low-temperature co-fired ceramic material to be predicted to obtain a material to be predicted; inputting the material to be predicted into a prediction model to predict the dielectric constant so as to obtain a prediction result;
wherein the prediction model is obtained by training a random forest model by using a low-temperature co-fired ceramic material with a known dielectric constant as a sample set.
In an embodiment, when the computer program is executed to implement the step of training the random forest model by using a low-temperature co-fired ceramic material with a known dielectric constant as a sample set, the processor specifically implements the following steps:
obtaining a low-temperature co-fired ceramic material with a known dielectric constant to obtain a sample set; preprocessing the sample set to obtain a processing result; constructing a random forest model; training the random forest model by using the processing result; predicting the trained random forest model to obtain a prediction result; and determining parameters of the random forest model according to the prediction result to obtain a prediction model.
In an embodiment, when the processor executes the computer program to implement the step of preprocessing the sample set to obtain a processing result, the processor specifically implements the following steps:
extracting characteristic parameters from the sample set; and converting the characteristic parameters to obtain a processing result.
Wherein the characteristic parameters comprise the dielectric constant of the composite material, the dielectric constant, the content and the density of raw materials for forming the composite material.
In an embodiment, when the processor executes the computer program to implement the step of converting the characteristic parameter to obtain the processing result, the following steps are specifically implemented:
and converting the content of the raw materials for forming the composite material in the characteristic parameters into volume percentage to obtain a processing result.
In an embodiment, when the processor executes the computer program to implement the step of training the random forest model by using the processing result, the following steps are specifically implemented:
and training the random forest model by using the processing result by adopting a five-fold cross inspection method.
In an embodiment, when the processor executes the computer program to implement the step of determining parameters of the random forest model according to the prediction result to obtain the prediction model, the following steps are specifically implemented:
judging whether the prediction result is smaller than a set threshold value or not; if the prediction result is smaller than the set threshold value, taking the parameters of the random forest model obtained by training as the parameters of the prediction model to obtain the prediction model; and if the prediction result is not smaller than the set threshold value, adjusting the parameters of the random forest model, and executing the training of the random forest model by using the processing result.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The method for predicting the dielectric constant of the material is characterized by comprising the following steps:
obtaining a formula of a low-temperature co-fired ceramic material to be predicted to obtain a material to be predicted;
inputting the material to be predicted into a prediction model to predict the dielectric constant so as to obtain a prediction result;
wherein the prediction model is obtained by training a random forest model by using a low-temperature co-fired ceramic material with a known dielectric constant as a sample set.
2. The method for predicting the dielectric constant of the material as claimed in claim 1, wherein the prediction model is obtained by training a random forest model by using a low-temperature co-fired ceramic material with a known dielectric constant as a sample set, and comprises the following steps:
obtaining a low-temperature co-fired ceramic material with a known dielectric constant to obtain a sample set;
preprocessing the sample set to obtain a processing result;
constructing a random forest model;
training the random forest model by using the processing result;
predicting the trained random forest model to obtain a prediction result;
and determining parameters of the random forest model according to the prediction result to obtain a prediction model.
3. The method of claim 2, wherein the pre-processing the sample set to obtain a processed result comprises:
extracting characteristic parameters from the sample set;
and converting the characteristic parameters to obtain a processing result.
4. The method of claim 3, wherein the characteristic parameters include a dielectric constant of the composite material, a dielectric constant, a content and a density of raw materials constituting the composite material.
5. The method for predicting the dielectric constant of the material as claimed in claim 4, wherein said converting the characteristic parameters to obtain the processing result comprises:
and converting the content of the raw materials for forming the composite material in the characteristic parameters into volume percentage to obtain a processing result.
6. The method for predicting the dielectric constant of the material as claimed in claim 2, wherein the training the random forest model by using the processing result comprises:
and training the random forest model by using the processing result by adopting a five-fold cross inspection method.
7. The method for predicting the dielectric constant of the material as claimed in claim 2, wherein the determining parameters of the random forest model according to the prediction result to obtain a prediction model comprises the following steps:
judging whether the prediction result is smaller than a set threshold value or not;
if the prediction result is smaller than the set threshold value, taking the parameters of the random forest model obtained by training as the parameters of the prediction model to obtain the prediction model;
and if the prediction result is not smaller than the set threshold value, adjusting the parameters of the random forest model, and executing the training of the random forest model by using the processing result.
8. A material dielectric constant prediction apparatus, comprising:
the material obtaining unit is used for obtaining a formula of the low-temperature co-fired ceramic material to be predicted so as to obtain a material to be predicted;
and the prediction unit is used for inputting the material to be predicted into a prediction model to perform dielectric constant prediction so as to obtain a prediction result.
9. A computer device, characterized in that the computer device comprises a memory, on which a computer program is stored, and a processor, which when executing the computer program implements the method according to any of claims 1 to 7.
10. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111080423.5A CN113627036A (en) | 2021-09-15 | 2021-09-15 | Method and device for predicting dielectric constant of material, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111080423.5A CN113627036A (en) | 2021-09-15 | 2021-09-15 | Method and device for predicting dielectric constant of material, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113627036A true CN113627036A (en) | 2021-11-09 |
Family
ID=78390128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111080423.5A Pending CN113627036A (en) | 2021-09-15 | 2021-09-15 | Method and device for predicting dielectric constant of material, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627036A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091878A (en) * | 2019-11-07 | 2020-05-01 | 上海大学 | Method for rapidly predicting perovskite dielectric constant |
| CN111833970A (en) * | 2020-06-18 | 2020-10-27 | 湖北博华自动化系统工程有限公司 | Construction method and application of cement clinker quality characterization parameter prediction model |
| CN112085157A (en) * | 2020-07-20 | 2020-12-15 | 西安电子科技大学 | Prediction model establishing method and device based on neural network and tree model |
| WO2021054026A1 (en) * | 2019-09-18 | 2021-03-25 | 株式会社日立製作所 | Material property prediction system and material property prediction method |
| CN113326664A (en) * | 2021-06-28 | 2021-08-31 | 南京玻璃纤维研究设计院有限公司 | Method for predicting dielectric constant of glass based on M5P algorithm |
-
2021
- 2021-09-15 CN CN202111080423.5A patent/CN113627036A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021054026A1 (en) * | 2019-09-18 | 2021-03-25 | 株式会社日立製作所 | Material property prediction system and material property prediction method |
| CN111091878A (en) * | 2019-11-07 | 2020-05-01 | 上海大学 | Method for rapidly predicting perovskite dielectric constant |
| CN111833970A (en) * | 2020-06-18 | 2020-10-27 | 湖北博华自动化系统工程有限公司 | Construction method and application of cement clinker quality characterization parameter prediction model |
| CN112085157A (en) * | 2020-07-20 | 2020-12-15 | 西安电子科技大学 | Prediction model establishing method and device based on neural network and tree model |
| CN113326664A (en) * | 2021-06-28 | 2021-08-31 | 南京玻璃纤维研究设计院有限公司 | Method for predicting dielectric constant of glass based on M5P algorithm |
Non-Patent Citations (2)
| Title |
|---|
| ANINDITA DAS等: "An automation approach in dielectric constant prediction using machine learning", 《2017 INTERNATIONAL CONFERENCE ON ENERGY, COMMUNICATION, DATA ANALYTICS AND SOFT COMPUTING (ICECDS)》, 2 August 2017 (2017-08-02), pages 3084 - 3086, XP033360337, DOI: 10.1109/ICECDS.2017.8390023 * |
| 冯宇等: "基于机器学习的PVDF基复合介质储能特性数据分析与预测", 《高电压技术》, vol. 48, no. 05, 29 June 2021 (2021-06-29), pages 1997 - 2004 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109597968B (en) | SMT big data-based solder paste printing performance influence factor analysis method | |
| CN110636445B (en) | WIFI-based indoor positioning method, device, equipment and medium | |
| TWI731459B (en) | Image recognition device and method | |
| CN112163637B (en) | Image classification model training method and device based on unbalanced data | |
| CN113255832B (en) | Method for identifying long tail distribution of double-branch multi-center | |
| CN113935535A (en) | Principal component analysis method for medium-and-long-term prediction model | |
| Jin et al. | An overview of neural network techniques for microwave inverse modeling | |
| CN113128612B (en) | Processing method of abnormal value in power data and terminal equipment | |
| CN107077617B (en) | Fingerprint extraction method and device | |
| CN113627036A (en) | Method and device for predicting dielectric constant of material, computer equipment and storage medium | |
| CN114464152B (en) | Music genre classification method and system based on visual transformation network | |
| CN110968835A (en) | Approximate quantile calculation method and device | |
| CN115206455A (en) | Deep neural network-based rare earth element component content prediction method and system | |
| CN112765521B (en) | Website user classification method based on improved K neighbor | |
| CN115271045A (en) | Neural network model optimization method and system based on machine learning | |
| CN112149351B (en) | Microwave circuit physical dimension estimation method based on deep learning | |
| CN114067169A (en) | Raman spectrum analysis method based on convolutional neural network | |
| CN109359694B (en) | Image classification method and device based on mixed collaborative representation classifier | |
| CN113743593A (en) | Neural network quantization method, system, storage medium and terminal | |
| TW202312030A (en) | Recipe construction system, recipe construction method, computer readable recording media with stored programs, and non-transitory computer program product | |
| CN113850523A (en) | ESG index determining method based on data completion and related product | |
| CN111863136A (en) | Integrated system and method for correlation analysis among multiple sets of chemical data | |
| CN115795225B (en) | Screening method and device for near infrared spectrum correction set | |
| JP2020177287A (en) | Specimen evaluation system and method for constructing the same | |
| CN115879513B (en) | Hierarchical standardization method and device for data and electronic 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 |