Solid electrolyte ion conductivity prediction method based on a BP neural network
A BP neural network and ionic conductivity technology, applied in the field of artificial intelligence, can solve the problems of low classification accuracy, easy underfitting of logistic regression models, and inability to meet the needs of new materials, saving time and cost, and reducing blindness. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0038] Such as figure 2 Shown, a kind of BP neural network-based solid electrolyte ionic conductivity prediction method of the present invention comprises the following steps:
[0039] Step 1: Collect 643 sets of material data from the material database, each set of data contains 10 features and 1 label; after normalizing and preprocessing the 643 sets of material data, 643 sets of total sample sets are obtained, and the 624 sets of total sample sets Randomly divided into test set samples and training set samples at a ratio of 2:8;
[0040] Specifically, the preprocessing of the collected material data includes extracting the chemical formula, atomic coordinates, lattice length, and volume fields in each set of data as input parameters, and calculating 10 features of each set of data according to the input parameters; The 10 features include the average atomic volume, the standard deviation of the number of adjacent atoms of lithium ions, the standard deviation of lithium io...
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