Dual AI Models for Battery Material Feature Extraction
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 for effective research using artificial intelligence, particularly deep learning, due to insufficient material data availability, making it difficult to analyze battery materials accurately.
Innovation Solution
A system utilizing two AI models, one for composition information and one for structure information, with a processor that learns and adjusts feature data to enhance similarity, enabling accurate feature data extraction even with limited structural data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If artificial intelligence (particularly deep learning) is used to research positive electrode materials, then research speed and efficiency are improved, but the method cannot be effectively applied due to insufficient material data availability
Solution Approach 1:
The patent introduces structure information as an intermediary to bridge the gap between composition information and AI model training. By incorporating structure information into the training data, the system enables effective AI-based research even when direct material performance data is scarce, thus resolving the contradiction between research speed and data availability
Solution Approach 2:
The patent performs preliminary action by pre-processing and organizing structure information from databases before AI model training. This advance preparation of structural data creates a foundation that enables subsequent AI research to proceed efficiently without requiring extensive experimental data collection
2Measurement precision
If structure information is used to train AI models, then prediction accuracy is improved, but the complexity of data acquisition and processing increases due to limited structural data availability
Solution Approach 1:
The patent makes the AI model universal by enabling it to process both composition information and structure information through a unified training framework. This multi-functionality allows the model to achieve high prediction accuracy while handling limited structural data efficiently, reducing the complexity of specialized processing procedures
Solution Approach 2:
The patent changes the parameters of the training data by incorporating structure information alongside composition information. This parameter change enables the AI model to achieve higher prediction accuracy while the systematic approach to data integration keeps the processing complexity manageable
Data Source
Figure 1~2
Figure 3~4
Figure 5
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.