AI Prediction of Polymer Composite Properties from Material Recipes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting the properties of polymer composite materials are inefficient and costly, relying on trial and error and requiring extensive experimental data collection, and existing AI models struggle to account for the numerous variables and interactions in material compositions.
Innovation Solution
A method and device utilizing a property prediction model trained through deep learning algorithms to predict polymer composite material properties based on input recipes, including materials and mixing ratios, allowing for rapid assessment of material changes without full synthesis and measurement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If trial and error methods are used to predict polymer composite material properties, then property data can be collected through experiments, but the process requires extensive time and resources
Solution Approach 1:
The patent applies preliminary action by training an AI model in advance using comprehensive material data and synthesis conditions. This pre-trained model can then rapidly predict properties of new polymer composite materials without requiring time-consuming experimental trials, thus reducing development time while maintaining prediction accuracy
Solution Approach 2:
The patent creates a virtual copy of the material property prediction process through AI simulation. Instead of physically synthesizing and testing materials, the system uses machine learning models to copy and simulate the prediction process, eliminating the need for repeated experimental cycles while preserving measurement precision
2Productivity
If commercially available AI models are used for prediction, then property prediction can be performed, but it is difficult to consider numerous variables of materials and their interactions
Solution Approach 1:
The patent applies parameter changes by incorporating numerous material variables, composition ratios, and synthesis conditions as input parameters to the AI model. The system dynamically adjusts and considers multiple parameters simultaneously, enabling comprehensive analysis of material interactions while maintaining fast prediction speed through optimized model architecture
3Reliability
If extensive experimental data collection is performed, then training data can be obtained, but the cost and time requirements increase significantly
Solution Approach 1:
The patent applies universality by creating a multi-functional AI model that can handle various types of material data, synthesis conditions, and property predictions through a single unified system. This approach maximizes the utility of collected training data, reducing the need for extensive separate experiments for different material systems while maintaining model reliability
Data Source
AI summary
A method for predicting characteristics of a polymer composite material and a device thereof may be provided, wherein the method includes inputting a recipe including two or more materials containing at least one polymer and a mixing ratio for each of the two or more materials; predicting properties of the polymer composite material according to the recipe based on a recipe and property prediction model; and outputting the properties of the polymer composite material.