AI Material Feature Modeling for Composition-Only Battery Research
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The development of positive electrode materials for lithium-ion batteries is hindered by the lack of sufficient data, particularly in acquiring structure information, which limits the application of artificial intelligence in this field.
Innovation Solution
A device, method, and program that utilize two AI models to acquire feature data for material composition and structure information. The first AI model outputs feature data for composition information, while the second AI model outputs feature data for structure information, with the processor configured to learn and adjust these models based on each other's output to enhance their association and similarity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If artificial intelligence is used to analyze battery materials, then research speed and efficiency are improved, but the application is limited by insufficient data availability
Solution Approach 1:
The patent creates a virtual copy of structural information through AI-generated feature data. The first AI model learns to output feature data that replicates the characteristics of the second AI model's structural feature data, enabling composition-based prediction without requiring actual structural information or extensive experimental data
Solution Approach 2:
The first AI model acts as an intermediary that translates composition information into structural feature representations. It learns the mapping between composition and structure through training on the second AI model's outputs, bridging the gap between available composition data and required structural information for material analysis
2Measurement precision
If structure information is used for material analysis, then prediction accuracy is improved, but data acquisition difficulty increases
Solution Approach 1:
Instead of directly using difficult-to-acquire structural information, the system creates a copy of its essential features through the first AI model's output. The learned feature data replicates the predictive power of structural information while being derived from easily obtainable composition data
Solution Approach 2:
The patent replaces the mechanical/experimental process of obtaining structural information with an AI-based computational approach. The first AI model substitutes physical measurement and analysis with learned patterns from training data, eliminating the need for complex structural characterization experiments
Data Source
AI summary
A system, device, method, and program for acquiring feature data for material composition information based on artificial intelligence are disclosed. The system may include a memory configured to store a first artificial intelligence (AI) model configured to output first feature data for composition information of a material and a second AI model configured to output second feature data for structure information of the material; and a processor configured to learn the first AI model and the second AI model. The processor may be configured to learn the first AI model based on the second feature data for the structure information of the material output by the second AI model, and/or to learn the second AI model based on the first feature data for the composition information of the material output by the first AI model.