CN112116091A - On-line forecasting method for rapidly forecasting band gap of organic-inorganic hybrid perovskite based on machine learning - Google Patents
On-line forecasting method for rapidly forecasting band gap of organic-inorganic hybrid perovskite based on machine learning Download PDFInfo
- Publication number
- CN112116091A CN112116091A CN202010859424.9A CN202010859424A CN112116091A CN 112116091 A CN112116091 A CN 112116091A CN 202010859424 A CN202010859424 A CN 202010859424A CN 112116091 A CN112116091 A CN 112116091A
- Authority
- CN
- China
- Prior art keywords
- forecasting
- band gap
- organic
- inorganic hybrid
- hybrid perovskite
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an online forecasting method for rapidly forecasting band gap of organic and inorganic hybrid perovskite based on machine learning, which comprises the steps of establishing a sample set, generating descriptors, dividing a training set and a testing set, selecting an optimal characteristic subset for modeling, constructing a rapid forecasting model, forecasting the band gap of a sample of the testing set, developing and completing an online forecasting application program, and rapidly forecasting the band gap value of the organic and inorganic hybrid perovskite. According to the method, an efficient and rapid forecasting model is established through sample data from a database, an online forecasting application program for rapidly forecasting the organic-inorganic hybrid perovskite is developed, the online forecasting application program can be accessed and used through a website and a mobile phone WeChat two-dimensional code, and the method has the advantages of simplicity, convenience, low cost, environmental friendliness and the like. The application program disclosed by the invention is used for online forecasting of the band gap of the organic-inorganic hybrid perovskite, so that experimental researchers can be helped to avoid the blindness of an experimental trial-and-error method, the experimental time and cost are saved, and the research and development efficiency of materials is improved.
Description
Technical Field
The invention relates to application of organic-inorganic hybrid perovskite in the optical field, in particular to an on-line forecasting method for forecasting the band gap of organic-inorganic hybrid perovskite based on machine learning, which is applied to design a new organic-inorganic hybrid perovskite material with a specific band gap and high-throughput screening.
Background
Perovskite gradually becomes a hot point of new material development and research due to the stable crystal structure and the unique physicochemical property. The organic-inorganic hybrid perovskite is an important material with promising magnetic, optical and electrical properties due to low price, good adaptability and stability and adjustable electronic structure. In recent years, the photoelectric conversion efficiency of organic-inorganic hybrid perovskite solar cells is rapidly increased to more than 23%, and the organic-inorganic hybrid perovskite solar cells are widely used as efficient solar sensitizers and show great development potential in the photovoltaic field. In addition, the compounds also have the potential advantages of limiting photoinduced carrier recombination and further improving the photocatalytic performance under the irradiation of visible light, and have good application prospects in the aspects of photocatalytic water splitting hydrogen production and photocatalytic organic pollutant degradation.
The band gap (BandGap), also called energy gap, is the difference in energy between the lowest point of the conduction band and the highest point of the valence band and is denoted by the symbol Eg. In the photoelectric conversion process, the organic-inorganic hybrid perovskite is used as a solar sensitizer, the band gap of the organic-inorganic hybrid perovskite is one of important influence factors of photoelectric conversion efficiency, and therefore, the selection of a semiconductor with a proper band gap is an important step. At present, the numerical value of the band gap needs to be obtained through experiments and deduction calculation or calculation by utilizing quantification, and the problems of long time consumption and high cost exist. Therefore, a method for rapidly and accurately predicting the band gap value of the organic-inorganic hybrid perovskite is needed.
The genetic algorithm is based on natural selection and evolution mechanism of natural organisms, is a random and self-adaptive search algorithm, is an efficient, parallel and global search method essentially, can automatically acquire and accumulate knowledge about a search space in the search process, and can adaptively control the search process to obtain the optimal subset characteristics. Compared with other optimization algorithms, the genetic algorithm has the capability of moving from the local optimality existing on the response surface, and various optimizations can be carried out according to the requirements on the unknown gradient of the response surface.
The support vector machine algorithm is based on an insensitive function and a kernel function algorithm. If the fitted mathematical model is expressed as a curve in a multidimensional space, the result from the insensitive function is a "pipe" that envelopes the curve and the training points. Of all the sample points, only the portion of the points distributed on the "wall" determines the position of the pipe. This portion of the training sample becomes the "support vector".
Disclosure of Invention
The invention aims to overcome the blindness of a trial and error method in an experiment and provide an online forecasting method for quickly forecasting the band gap of an organic-inorganic hybrid perovskite based on machine learning. According to the invention, the band gap prediction model of the organic-inorganic hybrid perovskite material is established through a support vector machine regression algorithm, so that the accuracy is high and the effect is good. The organic-inorganic hybrid perovskite material band gap online forecasting application program developed by the invention can obtain a forecasting result only in a few seconds, and the operation is simple and rapid.
In order to achieve the purpose of the invention, the invention adopts the following technical scheme:
an online forecasting method for rapidly forecasting band gap of organic-inorganic hybrid perovskite based on machine learning comprises the following steps:
1) establishing a sample set:
collecting the chemical formula and the corresponding band gap value of the organic-inorganic hybrid perovskite material from a database as a data set sample for machine learning;
2) and generating a descriptor:
calculating physicochemical properties of A-site organic cations according to a chemical formula by using the collected data, generating a descriptor by combining atomic parameters, and deleting the sample with the defect value;
3) dividing a training set and a testing set:
randomly dividing the data set samples obtained in the step 1) into a training set and a testing set;
4) selecting an optimal feature subset for modeling:
taking the band gap collected in the step 1) as a target variable, nesting a support vector machine algorithm by using a genetic algorithm, and performing feature screening on a training set to select an optimal feature subset for modeling;
5) constructing a rapid forecasting model:
modeling by using a support vector machine regression algorithm and the characteristic variables screened in the step 4), then carrying out hyper-parameter optimization, and finally establishing an optimal rapid prediction model of the organic-inorganic hybrid perovskite material band gap;
6) forecasting the band gap of the test set sample:
forecasting the band gap of the test set sample obtained in the step 3) according to the forecasting model of the band gap of the organic-inorganic hybrid perovskite material established in the step 5);
7) and (3) developing and completing an online forecasting application program, and realizing rapid prediction of the band gap value of the organic-inorganic hybrid perovskite:
and 5) developing the forecasting model established in the step 5) into an application program of an online forecasting method capable of quickly forecasting the band gap of the organic-inorganic hybrid perovskite material, and quickly forecasting the band gap value of the organic-inorganic hybrid perovskite.
Preferably, in the step 4), the steps of supporting the vector machine algorithm are as follows:
the support vector machine algorithm is based on an insensitive function and a kernel function algorithm; if the fitted mathematical model is expressed as a certain curve of a multidimensional space, the result obtained according to the insensitive function is a 'pipeline' enveloping the curve and the training points; of all the sample points, only the part of the points distributed on the "wall" determines the position of the pipe; this portion of the training sample becomes the "support vector".
Compared with the prior art, the invention has the following obvious substantive characteristics and obvious advantages:
1. the online forecasting method provided by the invention designs an application program to overcome the defects of a trial and error method adopted in the traditional experiment, saves resources and time, establishes a rapid forecasting model of the organic-inorganic hybrid perovskite material band gap based on machine learning, imports data into the model, and can obtain a calculation result only in seconds; the developed online forecasting application program can quickly forecast the band gap by inputting the A, B, X-bit corresponding chemical formula of the required organic-inorganic hybrid perovskite and clicking the 'Predict' button, and is very convenient to use;
2. the application program of the online forecasting method can be accessed and used through the website, and can also be used by scanning the two-dimensional code through the mobile phone WeChat, so that the operation is simple, quick and convenient;
3. the online forecasting method does not relate to experiments and use chemical products in the whole process, does not generate chemical pollution, and accords with the green environmental protection concept; the method is easy to realize and is suitable for popularization and application;
4. the online forecasting method can forecast the band gap of the organic-inorganic hybrid perovskite material in advance through online forecasting, help experiment researchers select samples meeting requirements, save experiment and calculation time and resources, improve experiment efficiency, play a guiding role and avoid blindness.
Drawings
FIG. 1 is a block diagram of the process of the present invention.
FIG. 2 is a graph of the modeling result of the support vector regression model of the band gap of the three-organic-inorganic hybrid perovskite in the embodiment of the invention.
FIG. 3 is a graph of the leave-one-out cross validation result of the support vector regression model of the band gap of the three organic-inorganic hybrid perovskites in the embodiment of the invention.
FIG. 4 is a graph of the results of an independent test set of a support vector regression model of the band gap of the three organic-inorganic hybrid perovskites of the example of the invention.
FIG. 5 is a page diagram of an online forecasting application of the band gap of four inorganic-organic hybrid perovskites according to an embodiment of the present invention.
Detailed Description
The above-described solution is further explained below with reference to the accompanying drawings and preferred embodiments, which are detailed below:
the first embodiment is as follows:
referring to fig. 1, an online forecasting method for fast forecasting organic-inorganic hybrid perovskite band gap based on machine learning includes the following steps:
1) establishing a sample set:
collecting the chemical formula and the corresponding band gap value of the organic-inorganic hybrid perovskite material from a database as a data set sample for machine learning;
2) and generating a descriptor:
calculating physicochemical properties of A-site organic cations according to a chemical formula by using the collected data, generating a descriptor by combining atomic parameters, and deleting the sample with the defect value;
3) dividing a training set and a testing set:
randomly dividing the data set samples obtained in the step 1) into a training set and a testing set;
4) selecting an optimal feature subset for modeling:
taking the band gap collected in the step 1) as a target variable, nesting a support vector machine algorithm by using a genetic algorithm, and performing feature screening on a training set to select an optimal feature subset for modeling;
5) constructing a rapid forecasting model:
modeling by using a support vector machine regression algorithm and the characteristic variables screened in the step 4), then carrying out hyper-parameter optimization, and finally establishing an optimal rapid prediction model of the organic-inorganic hybrid perovskite material band gap;
6) forecasting the band gap of the test set sample:
forecasting the band gap of the test set sample obtained in the step 3) according to the forecasting model of the band gap of the organic-inorganic hybrid perovskite material established in the step 5);
7) and (3) developing and completing an online forecasting application program, and realizing rapid prediction of the band gap value of the organic-inorganic hybrid perovskite:
and 5) developing the forecasting model established in the step 5) into an application program of an online forecasting method capable of quickly forecasting the band gap of the organic-inorganic hybrid perovskite material, and quickly forecasting the band gap value of the organic-inorganic hybrid perovskite.
In the embodiment, an efficient and rapid forecasting model is established through experimental sample data from documents, and an online forecasting method for rapidly forecasting organic-inorganic hybrid perovskites and an application program thereof are developed. The application program of the method is used for online forecasting of the band gap of the organic-inorganic hybrid perovskite, so that experimental researchers can be helped to avoid blindness of an experimental trial-and-error method, experimental time and cost are saved, and material research and development efficiency is improved.
Example two:
this embodiment is substantially the same as the first embodiment, and is characterized in that:
in the online forecasting method for rapidly forecasting the band gap of the organic-inorganic hybrid perovskite based on machine learning, in the step 4), a method supporting a vector machine algorithm is as follows:
the support vector machine algorithm is based on an insensitive function and a kernel function algorithm; if the fitted mathematical model is expressed as a certain curve of a multidimensional space, the result obtained according to the insensitive function is a 'pipeline' enveloping the curve and the training points; of all the sample points, only the part of the points distributed on the "wall" determines the position of the pipe; this portion of the training sample becomes the "support vector".
The method establishes the band gap prediction model of the organic-inorganic hybrid perovskite material through a support vector machine regression algorithm, and has high accuracy and good effect. The application program for online prediction of the band gap of the organic-inorganic hybrid perovskite material developed by the embodiment can obtain a prediction result only within seconds, and is simple and rapid to operate.
Example three:
this embodiment is substantially the same as the above embodiment, and is characterized in that:
an online forecasting application program for rapidly forecasting band gap of organic-inorganic hybrid perovskite based on machine learning comprises the following steps:
1) collecting a chemical formula of the organic-inorganic hybrid perovskite material and a corresponding band gap value from a database as a data set sample; the band gap values of the partially organic-inorganic hybrid perovskite materials are shown in table 1:
TABLE 1 data sample set of chemical formulas and band gap values of partially organic-inorganic hybrid perovskites
| Chemical formula (II) | EgeV | Chemical formula (II) | EgeV |
| CH5N2SnF3 | 3.52 | H4NOGeF3 | 4.67 |
| CH3(CH2)2NH3PbBr3 | 3.08 | CH6N3PbI3 | 2.08 |
| CH3(CH2)3NH3GeCl3 | 3.59 | (CH3)4NSnI3 | 2.33 |
| CH6NCaCl3 | 5.67 | CH6NPbCl3 | 3.4 |
| (CH3)2CHNH3GeBr3 | 3.23 | CH3CH2NH3PbBr3 | 3.03 |
| (CH3)2CHNH3PbCl3 | 3.69 | CH6NMgCl3 | 3.95 |
| CH6NPbF3 | 4.36 | CH3(CH2)2NH3PbF3 | 4.83 |
| CH6NGeBr3 | 2.8 | H5N2PbBr3 | 2.93 |
| CH5N2PbI3 | 2.3 | C2H7N2SnF3 | 3.56 |
| CH5N2CaI3 | 3.57 | CH3NH2CH3PbI3 | 2.29 |
2) Calculating physicochemical properties of A-site organic cations according to a chemical formula by using the collected data, generating a descriptor by combining atomic parameters, and deleting samples with defect values, wherein the number of the samples with complete data is 332;
3) randomly dividing 332 data set samples obtained in the step 2) into a training set and a testing set according to the proportion of 10:1, wherein the sample amount of the training set and the sample amount of the testing set are 299 and 33 respectively;
TABLE 2 partial feature variable List
4) Taking the band gap collected in the step 1) as a target variable and the descriptor generated in the step 2) as a characteristic variable, wherein the total number of the generated characteristic variables is 113, and the part is shown in table 2; screening variables by utilizing the Pearson correlation, nesting a support vector machine algorithm by utilizing a genetic algorithm, and performing feature screening on a training set to select 22 features as an optimal feature subset for modeling;
the support vector machine algorithm comprises the following specific steps:
given a data set: (y)1，x1),…,(yn，xn) Defining a linear function f (x):
where n is the number of samples, w is the normal vector of the hyperplane, χ is the input mode space, b is the intercept, χ is the input space，
Is a set of real numbers, and is,<w，x>is a dot product of the vectors w and x; changing the support vector regression problem into a convex optimization problem;
minimization
So that
Where i is 1, …, n is the number of sample points, yiIs a dependent variable, xiIs an independent variable, | · | | non-conducting phosphor2Is the 2-norm, is the error.
The core idea of the optimization problem is to construct a Lagrangian function from an objective function and corresponding constraint conditions by introducing a dual variable set; taking a partial derivative of the Lagrangian function to the original variable; the optimization problem can be transformed into the following dual problem:
minimization
So that
And alphai,αi *∈[0，C]
Where j is 1, …, N is the number of samples, αi≥0,αi *More than or equal to 0 is Lagrangian multiplier, and parameter C is regularization constant; the solution of the support vector machine can be easily given as follows:
therefore, the temperature of the molten metal is controlled,
the selected optimal characteristics are shown in table 3:
TABLE 3 partial optimal descriptor list selected by genetic algorithm nested support vector machine
In the step, the characteristic variables with high noise and high repeatability are deleted, and the optimal characteristic subset for modeling is selected, so that the data noise is reduced, and the screening precision is improved;
5) modeling by using a support vector machine regression algorithm and the characteristic variables screened in the step 4), then carrying out hyper-parameter optimization, and finally establishing an optimal rapid prediction model of the organic-inorganic hybrid perovskite material band gap;
6) forecasting the band gap of the test set sample obtained in the step 3) according to the forecasting model of the band gap of the organic-inorganic hybrid perovskite material established in the step 5);
7) developing the forecasting model established in the step 5) into an online forecasting application program capable of quickly forecasting the band gap of the organic-inorganic hybrid perovskite material, and quickly forecasting the band gap value of the organic-inorganic hybrid perovskite by using the application program.
The embodiment is based on a modeling result of a band gap quantitative prediction model established by combining 332 organic-inorganic hybrid perovskite samples with a support vector machine regression algorithm, as shown in fig. 2.
In this embodiment, a support vector regression algorithm is used to perform regression modeling on 332 perovskite sample data, and a support vector regression quantitative model of the organic-inorganic hybrid perovskite band gap is established. The correlation coefficient (R) of the prediction value of the organic-inorganic hybrid perovskite band gap model and the database value is 0.9882, and the root mean square error (RSME) is 0.4051. According to the method, the efficient and rapid forecasting model is established through the sample data from the database, and the method has the advantages of simplicity, convenience, low cost, greenness and environmental friendliness.
In an embodiment, 332 samples in the training set are numbered a1，A2……A332. First step with A1，A2……A331For the training set, the same optimal feature subset as in the first embodiment is used, model 1 is established and model 1 is used to predict A99The band gap of (a). The second step is with A1，A2……A330，A332For the training set, the same optimal feature subset as in the first embodiment is used, model 2 is established and model 2 is used to predict A331The band gap of (a). By analogy, after 332 models are established, the stability and reliability of the data modeling method are judged through the error of the forecast value and the experimental value.
The leave-one-out internal cross validation result of the organic-inorganic hybrid perovskite band gap quantitative prediction model established based on 332 perovskite samples in combination with support vector regression is shown in fig. 3.
In the method, a leave-one-out method is adopted to carry out leave-one-out internal cross validation on the support vector regression quantitative prediction model of the organic-inorganic hybrid perovskite band gap established by 332 sample data, the correlation coefficient (R) of the model prediction value of the perovskite band gap and the database value in the leave-one-out method is 0.9793, and the root mean square error (RSME) is 0.4698. According to the method, the forecasting model of the one-out-of-one-training-set cross validation is established by data from the database, and the stability and reliability of the data modeling method can be evaluated.
The method of the embodiment utilizes the established support vector regression quantitative prediction model of the band gap of the organic-inorganic hybrid perovskite to predict 33 samples in an independent test set, and a better result is obtained. The correlation coefficient (R) of the model predicted value of the perovskite bandgap and the database value was 0.9811, and the root mean square error (RSME) was 0.4852. The independent test set forecasts, as shown in FIG. 4.
Example four:
this embodiment is substantially the same as the previous embodiment, and is characterized in that:
in this example, referring to fig. 5, a user only needs to open a website of an online forecasting application program or use a WeChat scan to generate a two-dimensional code on the internet, and only needs to input a corresponding A, B, X-bit chemical formula of the required organic-inorganic hybrid perovskite at a corresponding position of a program page, and then click a "Predict" button, the user can quickly access the website to obtain a band gap forecast value of the perovskite on the internet. The online forecasting application program is convenient and quick, and is very helpful for experimental researchers to design new organic-inorganic hybrid perovskites with targeted band gaps.
In summary, the online prediction method for rapidly predicting the band gap of the organic-inorganic hybrid perovskite based on machine learning comprises the following steps: 1) collecting the chemical formula and the corresponding band gap value of the organic-inorganic hybrid perovskite material from a database as a data set sample for machine learning; 2) generating corresponding descriptors according to the chemical formula; 3) randomly dividing a data set into a training set and a testing set; 4) screening the characteristic variables by using a genetic algorithm nested support vector machine; 5) establishing a rapid prediction model of the band gap of the organic-inorganic hybrid perovskite material by using a support vector regression algorithm and the characteristic variables screened in the step 4); 6) and forecasting the band gap of the test set sample according to the established model. 7) Developing the forecasting model established in the step 5) into an online forecasting application program capable of quickly forecasting the band gap of the organic-inorganic hybrid perovskite material, and quickly forecasting the band gap value of the organic-inorganic hybrid perovskite by using the application program. According to the embodiment, an efficient and rapid forecasting model is established through experimental sample data from documents, and an online forecasting application program capable of rapidly forecasting the organic-inorganic hybrid perovskite is developed. The application program can be used by accessing through a website or not, can be used by scanning the two-dimensional code through the mobile phone WeChat, and has the advantages of simplicity, convenience, low cost and environmental friendliness. The application program of the embodiment is used for online forecasting of the band gap of the organic-inorganic hybrid perovskite, so that experimental researchers can be helped to avoid blindness of an experimental trial-and-error method, experimental time and cost are saved, and material research and development efficiency is improved.
The embodiments of the present invention have been described with reference to the accompanying drawings, but the present invention is not limited to the embodiments, and various changes and modifications can be made according to the purpose of the invention, and any changes, modifications, substitutions, combinations or simplifications made according to the spirit and principle of the technical solution of the present invention shall be equivalent substitutions, as long as the purpose of the present invention is met, and the present invention shall fall within the protection scope of the present invention without departing from the technical principle and inventive concept of the present invention.
Claims (2)
1. An online forecasting method for rapidly forecasting band gap of organic-inorganic hybrid perovskite based on machine learning is characterized by comprising the following steps:
1) establishing a sample set:
collecting the chemical formula and the corresponding band gap value of the organic-inorganic hybrid perovskite material from a database as a data set sample for machine learning;
2) and generating a descriptor:
calculating physicochemical properties of A-site organic cations according to a chemical formula by using the collected data, generating a descriptor by combining atomic parameters, and deleting the sample with the defect value;
3) dividing a training set and a testing set:
randomly dividing the data set samples obtained in the step 1) into a training set and a testing set;
4) selecting an optimal feature subset for modeling:
taking the band gap collected in the step 1) as a target variable, nesting a support vector machine algorithm by using a genetic algorithm, and performing feature screening on a training set to select an optimal feature subset for modeling;
5) constructing a rapid forecasting model:
modeling by using a support vector machine regression algorithm and the characteristic variables screened in the step 4), then carrying out hyper-parameter optimization, and finally establishing an optimal rapid prediction model of the organic-inorganic hybrid perovskite material band gap;
6) forecasting the band gap of the test set sample:
forecasting the band gap of the test set sample obtained in the step 3) according to the forecasting model of the band gap of the organic-inorganic hybrid perovskite material established in the step 5);
7) and (3) developing and completing an online forecasting application program, and realizing rapid prediction of the band gap value of the organic-inorganic hybrid perovskite:
and 5) developing the forecasting model established in the step 5) into an application program of an online forecasting method capable of quickly forecasting the band gap of the organic-inorganic hybrid perovskite material, and quickly forecasting the band gap value of the organic-inorganic hybrid perovskite.
2. The on-line forecasting method for fast predicting the band gap of the organic-inorganic hybrid perovskite based on machine learning according to claim 1, in the step 4), the steps of supporting a vector machine algorithm are as follows:
the support vector machine algorithm is based on an insensitive function and a kernel function algorithm; if the fitted mathematical model is expressed as a certain curve of a multidimensional space, the result obtained according to the insensitive function is a 'pipeline' enveloping the curve and the training points; of all the sample points, only the part of the points distributed on the "wall" determines the position of the pipe; this portion of the training sample becomes the "support vector".
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010859424.9A CN112116091B (en) | 2020-08-24 | 2020-08-24 | Online forecasting method for rapidly forecasting organic-inorganic hybrid perovskite band gap based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010859424.9A CN112116091B (en) | 2020-08-24 | 2020-08-24 | Online forecasting method for rapidly forecasting organic-inorganic hybrid perovskite band gap based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112116091A true CN112116091A (en) | 2020-12-22 |
| CN112116091B CN112116091B (en) | 2023-07-18 |
Family
ID=73804375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010859424.9A Active CN112116091B (en) | 2020-08-24 | 2020-08-24 | Online forecasting method for rapidly forecasting organic-inorganic hybrid perovskite band gap based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116091B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327648A (en) * | 2021-06-01 | 2021-08-31 | 上海大学 | CsPbI under finite temperature based on electroacoustic reforming calculation3Method of bandgap |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104409636A (en) * | 2014-11-18 | 2015-03-11 | 天津理工大学 | Perovskite thin-film solar cell with three-dimensional ordered mesopore support layer |
| CN110516701A (en) * | 2019-07-12 | 2019-11-29 | 上海大学 | Method based on data mining quick predict perovskite Curie temperature |
-
2020
- 2020-08-24 CN CN202010859424.9A patent/CN112116091B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104409636A (en) * | 2014-11-18 | 2015-03-11 | 天津理工大学 | Perovskite thin-film solar cell with three-dimensional ordered mesopore support layer |
| CN110516701A (en) * | 2019-07-12 | 2019-11-29 | 上海大学 | Method based on data mining quick predict perovskite Curie temperature |
Non-Patent Citations (2)
| Title |
|---|
| ZHAIXIUYUN ET AL.: "Toxicity prediction of metal oxide nanoparticles with the assistance of machine learning", 《COMPUTERS AND APPLIED CHEMISTRY》 * |
| 郑伟达等: "基于不同机器学习算法的钙钛矿材料性能预测", 《中国有色金属学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113327648A (en) * | 2021-06-01 | 2021-08-31 | 上海大学 | CsPbI under finite temperature based on electroacoustic reforming calculation3Method of bandgap |
| CN113327648B (en) * | 2021-06-01 | 2022-04-15 | 上海大学 | CsPbI under finite temperature based on electroacoustic reforming calculation3Method of bandgap |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112116091B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Forecasting iron ore import and consumption of China using grey model optimized by particle swarm optimization algorithm | |
| CN112132177B (en) | Machine learning based fast prediction of ABO 3 On-line forecasting method of perovskite band gap | |
| Chuentawat et al. | The comparison of PM2. 5 forecasting methods in the form of multivariate and univariate time series based on support vector machine and genetic algorithm | |
| Castelli et al. | An evolutionary system for ozone concentration forecasting | |
| Zhou et al. | Accurate prediction of photovoltaic power output based on long short‐term memory network | |
| Jin et al. | Optimization and analysis of bioenergy production using machine learning modeling: Multi-layer perceptron, Gaussian processes regression, K-nearest neighbors, and Artificial neural network models | |
| CN110807490A (en) | Intelligent prediction method for construction cost of power transmission line based on single-base tower | |
| CN112116091B (en) | Online forecasting method for rapidly forecasting organic-inorganic hybrid perovskite band gap based on machine learning | |
| Salah et al. | Selecting an appropriate machine-learning model for perovskite solar cell datasets | |
| CN113808681A (en) | ABO (abnormal noise) rapid prediction based on SHAP-Catboost3Method and system for specific surface area of perovskite material | |
| Wolday et al. | Optimisation of methanol distillation using GA and neural network hybrid | |
| CN114581141A (en) | Short-term load prediction method based on feature selection and LSSVR | |
| Braconi | Bayesian optimization as a valuable tool for sustainable chemical reaction development | |
| CN117831685A (en) | Material design optimization method, system and medium | |
| Salman et al. | Hybrid deep learning models for time series forecasting of solar power | |
| CN109521001A (en) | A kind of flying marking measuring method based on PSO and ε-SVR | |
| Zheng et al. | TCN-GAT multivariate load forecasting model based on SHAP value selection strategy in integrated energy system | |
| SubLaban et al. | Artificial neural network models for octane number and octane sensitivity: a quantitative structure property relationship approach to fuel design | |
| Symeonidis et al. | Wind Energy Prediction Guided by Multiple-Location Weather Forecasts | |
| Mazumdar et al. | Optimized machine learning model for predicting groundwater contamination | |
| CN112132185B (en) | Method for rapidly predicting double perovskite oxide band gap based on data mining | |
| Sartini et al. | Optimization of random forest prediction for industrial energy consumption using genetic algorithms | |
| Sankari et al. | A Review of Deep Transfer Learning Strategy for Energy Forecasting | |
| Li et al. | Robust Optimization of Industrial Process Operation Parameters Based on Data‐Driven Model and Parameter Fluctuation Analysis | |
| CN112132182A (en) | Method for rapidly predicting resistivity of ternary gold alloy based on machine learning |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhang Shilin Inventor after: Zhang Wenbing Inventor after: Chen Huimin Inventor after: Li Minjie Inventor after: Peng Jubo Inventor after: Lu Wencong Inventor after: Fu Zewei Inventor after: Lu Tian Inventor after: Zhao Hui Inventor after: Tao Qiuling Inventor after: Liu Xiujuan Inventor before: Zhang Shilin Inventor before: Li Minjie Inventor before: Lu Wencong Inventor before: Lu Tian Inventor before: Tao Qiuling Inventor before: Liu Xiujuan Inventor before: Chen Huimin |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230118 Address after: 200444 No. 99, upper road, Shanghai, Baoshan District Applicant after: Shanghai University Applicant after: R & D Center of Yunnan Tin Industry Group (Holdings) Co.,Ltd. Address before: No.99 SHANGDA Road, Baoshan District, Baoshan District, Shanghai 200444 Applicant before: Shanghai University |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |