Materials Design Space Metrics for Faster Candidate Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for identifying materials that satisfy manufacturing parameters are inefficient and costly due to the lack of predictive indicators for candidate materials, leading to extensive experimentation with no viable results.
Innovation Solution
A system using machine learning models to evaluate design spaces by calculating Predicted Fraction of Improved Candidates (PFIC) and Cumulative Maximum Likelihood of Improvement (CMLI) scores to determine the likelihood of finding materials with improved properties, recommending high-quality design spaces for further iteration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional trial-and-error experimentation is used for materials discovery, then researchers can explore material properties empirically, but the process requires extensive time and computational resources
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing materials properties and synthesis feasibility in a database before actual experimentation. The system performs virtual screening and predictive calculations in advance, allowing researchers to identify promising candidates before physical synthesis, thereby reducing the time required for materials discovery while maintaining prediction accuracy.
Solution Approach 2:
The patent uses copying by creating virtual representations of materials and their properties through computational models. Instead of physically synthesizing and testing every possible material combination, the system creates digital copies and simulations to predict material behavior, significantly reducing the time and resources needed for materials exploration while maintaining accurate property prediction.
2Reliability
If comprehensive materials screening is performed to ensure high-quality discoveries, then reliable materials can be identified, but the computational cost and time requirements increase significantly
Solution Approach 1:
The patent applies segmentation by dividing the comprehensive materials screening process into distinct modules: materials property prediction, synthesis feasibility assessment, and integrated ranking. This modular approach allows the system to efficiently process large numbers of materials by evaluating them through separate, optimized computational routines, thereby maintaining high discovery reliability while improving overall development efficiency.
Solution Approach 2:
The patent uses parameter changes by dynamically adjusting the screening criteria and computational parameters based on the specific research objectives and available resources. The system can modify prediction accuracy thresholds, synthesis feasibility parameters, and ranking weights to balance reliability and productivity according to different project requirements, enabling flexible optimization of the materials discovery process.
3Adaptability or versatility
If complex synthesis pathways are considered to achieve desired material compositions, then target materials can be synthesized, but the number of required reactions and process complexity increase
Solution Approach 1:
The patent applies the intermediary principle by introducing a computational framework that acts as a mediator between target material specifications and synthesis pathways. The system uses predictive models to identify optimal intermediate steps and reaction sequences, translating desired material compositions into feasible synthesis routes while minimizing process complexity. This intermediary computational layer enables flexible materials design without proportionally increasing synthesis complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system and a method are disclosed for predicting design space quality for materials development and manufacture. In an embodiment, a processor receives input of a material property and a design space. The processor identifies a best data point. For each respective candidate material of the design space, the processor receives, as output from a model, a respective property value. The processor determines respective property values that exceed the property value of the best data point adds them to a subset of candidate materials. The processor determines a PFIC score for candidates in the subset. The processor generates a plurality of curves, each reflecting a respective probability distribution of property values. The processor determines a CMLI score based on the plurality of respective curves. The processor determines that the design space is high quality based on the PFIC and CMLI scores, and outputs a recommendation to proceed.