Polymer Composite Recipe Prediction for Faster Material Development
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting materials of polymer composite materials with target properties require extensive trial and error, are costly, and struggle with considering numerous variables and interactions, making them inefficient and time-consuming.
Innovation Solution
A method and device using a recipe prediction model based on machine learning algorithms to quickly determine the materials and mixing ratios for polymer composite materials by inputting desired properties, incorporating pure and recycled polymers, and verifying the predicted recipes against target properties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If trial and error methods are used to predict polymer composite material properties, then material composition can be optimized, but development time and costs increase significantly
Solution Approach 1:
The patent applies preliminary action by pre-training an AI model with extensive material composition data and property relationships before actual recipe prediction. This pre-prepared knowledge base enables rapid prediction without requiring trial-and-error experiments during the actual material development process, thus optimizing composition quickly while reducing development time
Solution Approach 2:
The patent replaces the mechanical trial-and-error experimentation system with an AI-based computational prediction system. The AI model processes material composition inputs and predicts properties through algorithms rather than physical experiments, eliminating the need for repeated laboratory testing and significantly reducing both time and resource consumption
2Ease of operation
If commercially available AI models are used for material prediction, then prediction capability is provided, but training costs and time requirements increase
Solution Approach 1:
The patent extracts and utilizes pre-trained AI model capabilities from commercially available sources, taking out the core prediction functionality without requiring users to perform extensive training themselves. The system leverages existing model knowledge while allowing customization for specific polymer composite applications, thus providing prediction capability while minimizing training time and costs
Solution Approach 2:
The patent introduces an intermediary layer that adapts pre-trained AI models to specific polymer composite material applications. This intermediary adaptation layer allows the system to leverage general AI prediction capabilities while customizing them for specific material types, avoiding the need for complete retraining while maintaining prediction accuracy
3Measurement precision
If extensive variables and interactions are considered in material prediction, then prediction accuracy improves, but model complexity and training requirements increase
Solution Approach 1:
The patent applies parameter changes by dynamically adjusting the level of detail and number of variables considered based on the specific prediction task. The AI model can adaptively select which material parameters and interactions to prioritize, maintaining high prediction accuracy for critical properties while avoiding unnecessary complexity from less relevant variables, thus balancing accuracy with model simplicity
Data Source
AI summary
A method for predicting recipes of a polymer composite material and a device thereof may be provided, wherein the method includes: obtaining at least one property for a target polymer composite material; predicting a recipe including at least two materials including at least one polymer for synthesizing the target polymer composite material and a mixing ratio for each of the at least two materials based on at least one property and recipe prediction model; and outputting the recipe.