Material Composition Optimization Through Phase Fraction Backpropagation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing models require a significant amount of time to predict phase fractions due to a large number of parameters, making it impractical to search for a material composition corresponding to a target phase fraction within a realistic time frame.
Innovation Solution
A composition optimization device that uses a trained model to predict phase fractions and updates the material composition through backpropagation of errors until a predetermined condition is met, employing architectures like RNN, bidirectional RNN, Seq2Seq, Seq2Seq with attention mechanism, GRU, LSTM, or Transformer, and incorporates constraints and loss function calculations to refine the composition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a trained model with a large number of parameters is used to predict phase fraction, then prediction accuracy is improved, but prediction time increases significantly
Solution Approach 1:
The model is trained in advance using a large number of parameters to achieve high prediction accuracy. The training process pre-computes the relationships between material composition and phase fraction, storing these patterns in the model parameters. During actual use, the pre-trained model can quickly predict phase fractions without requiring extensive computation, thus resolving the contradiction between accuracy and speed.
2Measurement precision
If exhaustive search of material composition is performed to find target phase fraction, then composition optimization accuracy is improved, but search time becomes unrealistic
Solution Approach 1:
The system uses backpropagation to calculate the error between predicted and target phase fractions, then feeds this error information back to update the material composition. This iterative feedback mechanism guides the search process efficiently toward the optimal composition without requiring exhaustive exploration of all possible compositions, thus improving both accuracy and efficiency.
Solution Approach 2:
The material composition is dynamically updated based on the calculated error through backpropagation. Instead of static exhaustive search, the system adaptively adjusts the composition parameters in each iteration, moving toward the target phase fraction efficiently. This dynamic adjustment process resolves the contradiction by making the search both accurate and time-efficient.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A material composition corresponding to a target phase fraction is efficiently searched for. A composition optimization device includes a prediction unit configured to predict, by inputting a predetermined material composition into a trained model, a phase fraction of a material having the predetermined material composition at each temperature within a predetermined temperature range, the trained model being trained using training data in which a material composition of a training target material and a phase fraction of the training target material at each temperature within the predetermined temperature range are associated with each other; and an update unit configured to update the predetermined material composition input into the trained model by performing backpropagation of an error calculated based on a target phase fraction and the predicted phase fraction. A process of the prediction unit predicting a phase fraction based on the updated material composition and a process of the update unit updating a predetermined material composition by performing backpropagation of a calculated error are repeated until a calculated error satisfies a predetermined condition.