Polymer Composite Recipe Prediction for Target Property Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting polymer composite materials with target properties are time-consuming and costly, requiring repeated trial and error, and struggle with numerous variables and interactions, especially when using artificial intelligence models.
Innovation Solution
A method and device using a recipe prediction model based on a deep learning algorithm to quickly generate recipes for polymer composite materials, incorporating recycled plastics, by calculating and modifying mixing ratios to achieve target properties, and utilizing an optimization algorithm to maximize or minimize specific properties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional trial and error methods are used to predict polymer composite material properties, then material composition data can be collected and analyzed, but the process requires repeated experiments and takes a lot of time
Solution Approach 1:
The patent applies preliminary action by pre-training an AI model with extensive material composition and property data before actual prediction. The model is prepared in advance with learned relationships between compositions and properties, enabling rapid predictions without repeated trial-and-error experiments during the actual material development process
Solution Approach 2:
The patent uses copying by creating a virtual model (AI-based prediction system) that replicates the complex relationships between material compositions and properties. This digital copy allows predictions to be made computationally instead of requiring physical experiments, dramatically reducing time while maintaining prediction accuracy
2Productivity
If AI models are trained to predict polymer composite material recipes, then prediction speed improves, but training the model is costly and time-consuming
Solution Approach 1:
The patent applies preliminary action by performing extensive model training and data processing in advance. The AI model is pre-trained on comprehensive datasets containing material compositions and properties before deployment, so that during actual use, predictions can be made rapidly without requiring additional training time
Solution Approach 2:
The patent transitions from the physical dimension of repeated experiments to the digital dimension of computational predictions. By moving the prediction process into the digital domain using AI models, the system achieves rapid predictions without being constrained by the time requirements of physical material synthesis and testing
3Adaptability or versatility
If commercially available AI models are used for material prediction, then some prediction capability is provided, but there are limitations in considering numerous variables and interactions between recipes and properties
Solution Approach 1:
The patent applies parameter changes by configuring the AI model to specifically consider multiple material composition parameters and their interactions. The system adjusts and optimizes model parameters to account for numerous variables including different polymer types, fillers, plasticizers, and their complex interactions, thereby improving both adaptability and reliability of predictions
Data Source
AI summary
A method and a device for generating recipes of a polymer composite material are provided which include acquiring a prediction recipe based on a preset target property of a target polymer composite material and a recipe prediction model; acquiring a result property of a polymer composite material generated based on the prediction recipe; calculating a difference value between the target property and the result property; and outputting or modifying the prediction recipe based on a result of comparing the difference value with a preset reference value.