Epoxy Resin Composition Search for Balanced Strength and Toughness
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques fail to efficiently search for a thermosetting epoxy resin composition with a well-balanced set of characteristics for composite materials like CFRP, as they do not specifically address the optimization of blending raw materials.
Innovation Solution
A method involving an information processor that trains predictive models using feature values derived from actual data, including molecular fingerprints and descriptors, to inversely analyze and find a thermosetting epoxy resin composition with desired properties such as tensile strength, fracture toughness, and glass transition temperature.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Strength
If thermosetting epoxy resin composition is optimized for strength, then tensile strength is improved, but fracture toughness deteriorates
Solution Approach 1:
The patent applies parameter changes by systematically varying the composition ratios of multiple epoxy resins and curing agents to achieve optimal balance between tensile strength and fracture toughness. The machine learning model analyzes how changes in compositional parameters affect both properties simultaneously, enabling identification of composition ranges that satisfy both requirements.
Solution Approach 2:
The patent utilizes composite materials by combining multiple types of epoxy resins and curing agents in specific ratios. This composite approach allows the final resin composition to exhibit both high tensile strength and good fracture toughness, as different components contribute different properties that complement each other.
2Temperature
If thermosetting epoxy resin composition is optimized for heat resistance, then glass transition temperature is improved, but processing ease deteriorates
Solution Approach 1:
The patent applies parameter changes by adjusting the glass transition temperature of the base epoxy resin within a specific range (60-150°C) while compensating with curing agent selection and composition ratios. This allows achieving high heat resistance in the final cured product while maintaining adequate processing ease during manufacturing.
Solution Approach 2:
The patent applies preliminary action by pre-calculating and storing optimal composition ratios in a database that balance heat resistance and processing ease. The machine learning model learns from existing data the relationships between composition parameters and properties, enabling rapid prediction of compositions that will achieve desired glass transition temperatures while maintaining manufacturability.
3Measurement precision
If machine learning model is trained with extensive actual data, then prediction accuracy is improved, but data processing time deteriorates
Solution Approach 1:
The patent applies preliminary action by pre-processing and organizing actual data into structured formats with standardized feature extraction before training. The system pre-calculates molecular fingerprints, structural descriptors, and other features from raw chemical structure data, storing them in an optimized database format that accelerates subsequent model training and prediction processes.
Solution Approach 2:
The patent applies segmentation by dividing the machine learning process into multiple stages: data pre-processing, feature extraction, model training, and prediction. Each stage handles specific tasks independently, allowing parallel processing and optimization of each component, thereby reducing overall processing time while maintaining accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
To improve a technique of searching for a thermosetting epoxy resin composition. A method of searching for a thermosetting epoxy resin composition executed by an information processor, the method including the steps of: training a plurality of predictive models each corresponding to a target variable using actual data related to a thermosetting epoxy resin composition; and searching for a thermosetting epoxy resin composition with a desired balance of physical properties by inverse analysis using the plurality of predictive models, the actual data include a blend raw material and a blend ratio of the thermosetting epoxy resin composition, a polymer composition related to the blend raw material, and a structural formula related to the blend raw material, and the target variable includes tensile strength, fracture toughness, and a glass transition temperature.