Machine Learning ABS Property Estimation System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Recycled acrylonitrile butadiene styrene (ABS) often contains impurities and broken polymer chains, making it difficult to produce products with properties similar to virgin ABS, requiring extensive experimentation to determine optimal mixing ratios with additional materials.
Innovation Solution
A system using machine learning models to analyze composition information from gel permeation chromatography (GPC) analysis, estimating the properties of mixed materials by determining the necessary content ratios of recycled ABS, general ABS, carbon nanotubes, carbon fiber, and recycled thermoplastic polyurethane, and providing reliability indices to guide further experimentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If recycled ABS is used to reduce environmental pollution, then environmental friendliness is improved, but the material properties deviate from virgin ABS requiring extensive experimentation
Solution Approach 1:
The system performs preliminary analysis of recycled ABS composition using GPC to determine molecular weight distribution and degradation level before mixing. This preliminary characterization enables prediction of optimal mixing ratios with virgin ABS and additives, eliminating the need for extensive trial-and-error experimentation while maintaining desired material properties.
Solution Approach 2:
The invention replaces the mechanical trial-and-error experimentation process with an automated computational system that uses machine learning models to predict optimal mixing ratios. The system substitutes physical experimentation with digital simulation and data analysis, significantly reducing time and resource consumption.
2Manufacturing precision
If extensive experimentation is conducted to match properties of recycled ABS with virgin ABS, then manufacturing precision is improved, but productivity deteriorates
Solution Approach 1:
The system changes the approach from adjusting physical mixing ratios through experimentation to adjusting computational parameters in machine learning models. By varying input parameters such as recycled ABS composition data, molecular weight distribution, and degradation indices, the system rapidly predicts optimal formulations without physical trial-and-error, maintaining precision while accelerating development.
Solution Approach 2:
Physical experimentation and manual property matching are replaced with automated machine learning algorithms that process composition data and predict optimal mixing ratios. This substitution maintains manufacturing precision through computational accuracy while dramatically improving productivity by eliminating iterative physical testing.
3Productivity
If machine learning models are used to estimate properties of mixed materials, then productivity is improved, but device complexity increases
Solution Approach 1:
The system introduces an intermediary computational layer between raw composition data and final mixing ratio determination. Machine learning models act as mediators that process GPC analysis results and translate them into predicted material properties and optimal formulations. This intermediary layer automates complex calculations while maintaining system manageability through modular architecture.
Solution Approach 2:
The machine learning system performs multiple functions within a unified platform: characterizing recycled ABS composition, predicting material properties, determining optimal mixing ratios, and generating formulation recommendations. This multi-functionality consolidates what would otherwise require separate analytical tools and expert knowledge, managing complexity through integration while enhancing productivity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system significantly reduces the time and effort required to match the properties of recycled ABS with virgin ABS by providing accurate content ratios and reliability indices, facilitating the production of materials with desired properties.
Implementation Method 1
performing, by the data collection unit, gel permeation chromatography (GPC) analysis on recycled ABS to acquire recycled ABS composition information
Data Source
AI summary
A system for estimating a property of a mixed material including acrylonitrile butadiene styrene (ABS) is provided. The system includes a server for analyzing data using a machine learning model, a user terminal for receiving an input of a user and transmitting the input to the server, and a data collection unit for collecting data.