Genetic Algorithm Binder Composition Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for developing binder materials for powder molding, such as powder injection molding and powder extrusion molding, rely on inefficient trial-and-error approaches, making it impractical to find suitable compositions for complex and miniaturized parts due to the vast range of possible combinations and neglecting optimization of subsequent processes like degreasing, leading to incomplete binder removal.
Innovation Solution
A system utilizing a genetic algorithm to generate and analyze compositional information for optimal binder compositions, focusing on viscosity and residual binder ratios, which includes a searching logic unit and a synthesis/analysis module to efficiently extract and evaluate candidate compositions, thereby reducing the need for extensive experimental testing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If trial and error method is used to develop binder compositions, then various compositions can be tested, but the development time becomes excessively long and the process becomes impractical
Solution Approach 1:
The patent applies preliminary action by pre-establishing a genetic algorithm framework that generates candidate compositions and predicts their properties before actual experimentation. The system pre-calculates optimal compositional ranges and prioritizes candidate compositions for testing, thereby reducing the overall development time while maintaining compositional optimization reliability
Solution Approach 2:
The patent replaces the mechanical trial-and-error experimentation system with a computational genetic algorithm system. The genetic algorithm computationally searches the compositional space and predicts binder properties, substituting random physical experimentation with systematic computational modeling, thus dramatically reducing development time while maintaining or improving compositional optimization
2Adaptability or versatility
If the range of compositions to be searched is expanded to cover all possible binder combinations, then more optimal compositions can be found, but the number of experiments required becomes unmanageably large
Solution Approach 1:
The patent applies segmentation by dividing the vast compositional search space into manageable segments using the genetic algorithm. The system segments the binder composition variables (main materials, auxiliary materials, their ratios) into discrete genetic parameters that can be systematically varied and evaluated, allowing comprehensive compositional range coverage while maintaining experimental efficiency through intelligent sampling
Solution Approach 2:
The patent utilizes parameter changes by systematically varying compositional parameters (types and ratios of main materials, auxiliary materials, and their interactions) within the genetic algorithm framework. The algorithm efficiently explores parameter space by making targeted changes to compositional parameters rather than exhaustive testing, thus covering a wide compositional range while maintaining high experimental productivity
3Ease of manufacture
If focus is placed on researching binder compositions themselves, then compositional development can proceed, but subsequent processes like degreasing are neglected resulting in incomplete binder removal
Solution Approach 1:
The patent applies universality by designing a genetic algorithm system that simultaneously optimizes multiple functions: binder composition development, processing characteristics, and degreasing performance. The evaluation function in the genetic algorithm incorporates multiple objective criteria including compositional suitability, processability, and binder removal characteristics, allowing one system to handle multiple development goals concurrently
Solution Approach 2:
The patent implements feedback by incorporating degreasing performance and residual binder analysis results back into the genetic algorithm's evaluation function. The measured data from actual synthesis and analysis of candidate compositions, including binder removal completeness, feeds back to guide the genetic algorithm's selection and optimization processes, ensuring that subsequent processes like degreasing are not neglected
Data Source
AI summary
A system for developing a composition for powder molding which, after a viscosity of the composition for powder molding and a degreasing process, extracts optimal compositional information of the composition in terms of the ratios of the residual binder materials is disclosed. Such a system includes a searching logic unit configured, after generating a plurality of candidate compositional information, to extract the optimal compositional information therefrom and a synthesis/analysis module configured to synthesize and analyze compositions corresponding to the plurality of candidate compositional information and provide to the searching logic unit measurement information on the viscosities of the compositions corresponding to each of the plurality of candidate compositional information and ratios of residual binder materials after a degreasing process. Also, the searching logic unit extracts the optimal compositional information based on the candidate compositional information and the measurement information thereof.