Online forecasting method for quickly forecasting organic-inorganic hybrid perovskite band gap based on machine learning
A machine learning and perovskite technology, applied in nuclear methods, genetic models, genetic rules, etc., can solve problems such as high cost and long time consumption, and achieve the effects of improving efficiency, avoiding blindness, and saving time and resources
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0036] Example 1:
[0037] see figure 1 , an online prediction method based on machine learning to rapidly predict the band gap of organic-inorganic hybrid perovskites, including the following steps:
[0038] 1) Create a sample set:
[0039] Collect chemical formulas and corresponding band gap values of organic-inorganic hybrid perovskite materials from the database as dataset samples for machine learning;
[0040] 2) Generate descriptor:
[0041] Using the collected data, calculate the physicochemical properties of the A-position organic cations according to the chemical formula and generate descriptors combined with atomic parameters, and delete the samples with missing values;
[0042] 3) Divide training set and test set:
[0043] The data set sample obtained in the step 1) is randomly divided into a training set and a test set;
[0044] 4) Select the optimal feature subset for modeling:
[0045] Taking the band gap collected in the described step 1) as the target v...
Example Embodiment
[0053] Embodiment 2:
[0054] This embodiment is basically the same as the first embodiment, and the special features are as follows:
[0055] In the online prediction method for rapidly predicting the band gap of organic-inorganic hybrid perovskite based on machine learning, in the step 4), the method of the support vector machine algorithm is as follows:
[0056] The support vector machine algorithm is based on the ε-insensitive function and the kernel function algorithm; if the fitted mathematical model is expressed as a certain curve in a multi-dimensional space, the result obtained according to the ε-insensitive function is the "envelope" of the curve and the training point. ε pipeline"; among all the sample points, only that part of the points distributed on the "pipe wall" determines the position of the pipeline; this part of the training samples becomes the "support vector".
[0057] In this embodiment, a support vector machine regression algorithm is used to establish ...
Example Embodiment
[0058] Embodiment three:
[0059] This embodiment is basically the same as the above-mentioned embodiment, and the special features are as follows:
[0060] An online prediction application based on machine learning to rapidly predict the band gap of organic-inorganic hybrid perovskite, including the following steps:
[0061] 1) Collect the chemical formulas and corresponding band gap values of organic-inorganic hybrid perovskite materials from the database as data set samples; the band gap values of some organic-inorganic hybrid perovskite materials are shown in Table 1:
[0062] Table 1. Data sample set of chemical formulas and band gap values of some organic-inorganic hybrid perovskites
[0063] chemical formula EgeV chemical formula EgeV CH 5 N 2 SnF 3
[0064] 2) Using the collected data, calculate the physicochemical properties of the A-position organic cations according to the chemical formula and generate descriptors combined with atom...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap