Method for rapidly predicating macromolecule energy gap
A technology of forbidden band width and polymer, applied in the field of rapid prediction of the forbidden band width of polymers, can solve the problems of high test cost and low accuracy, and achieve the effects of convenient calculation, simple model and simple prediction operation.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0088] Embodiment 1: Based on 228 first principles combined with the modeling results of the polymer bandgap quantitative prediction model established by the support vector machine, such as figure 2 shown.
[0089] The support vector machine regression algorithm was used to carry out regression modeling on 228 polymer sample data, and a support vector machine regression quantitative prediction model for the band gap width of polymer was established. The coefficient of determination of the predicted value of the polymer band gap model and the calculated value of the first principle is 0.9352.
Embodiment 2
[0090] Embodiment 2: Based on 228 first-principles combined with the support vector machine, the internal cross-validation results of the leave-one-out method of the quantitative prediction model of the polymer bandgap width established, such as image 3 shown.
[0091] The leave-one-out method was used to carry out internal cross-validation of the support vector machine quantitative prediction model of the polymer bandgap width established by 228 sample data, and the model prediction value and first-principle calculation value of the polymer bandgap width in the leave-one-out method The coefficient of determination is 0.759.
Embodiment 3
[0092] Embodiment 3: Based on 228 first-principles combined with the independent test set prediction results of the polymer bandgap quantitative prediction model established by the support vector machine, such as Figure 4 shown.
[0093] The 56 samples in the independent test set were predicted by using the support vector machine quantitative prediction model of the polymer bandgap width, and good results were obtained. The coefficient of determination of the model prediction value and the first-principle calculation value of the polymer band gap is 0.8503.
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com