Unconsolidated Composite Property Prediction for Selective Quality Use
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for testing unconsolidated composite materials, such as prepreg rolls, are inefficient as they require testing multiple portions to identify out-of-tolerance sections, leading to time-consuming quality control processes and potential waste due to discarding entire rolls when only a portion is defective.
Innovation Solution
A composite material management system that uses sensor data from the manufacturing process to predict properties and quality levels of unconsolidated composite materials in real-time, allowing for the identification of in-tolerance and out-of-tolerance portions, enabling selective marking and use of only high-quality sections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If quality testing is performed on unconsolidated composite materials using traditional methods, then quality control is achieved, but the process becomes time-consuming and requires testing multiple portions
Solution Approach 1:
The system performs preliminary quality assessment during the manufacturing process itself, predicting properties of unconsolidated composite materials before consolidation occurs. This allows quality issues to be identified early, avoiding time-consuming post-manufacturing testing while maintaining reliable quality control through real-time monitoring of properties such as resin content, fiber distribution, and thickness during the layup and infusion processes
2Reliability
If traditional quality testing methods are used on prepreg rolls, then defective portions can be identified, but entire rolls must be discarded when only portions are defective
Solution Approach 1:
The system divides the prepreg roll into discrete portions or sections and assesses quality independently for each segment. By using sensors and machine learning models to predict properties at different locations along the roll, the system can identify exactly which portions meet quality specifications and which do not, allowing only defective sections to be discarded while salvaging good portions for use in composite manufacturing
Solution Approach 2:
The system applies local quality assessment by evaluating specific properties (resin content, fiber distribution, thickness) at specific locations within the prepreg roll rather than treating the entire roll as a single unit. This localized evaluation enables precise identification of defective areas and preserves material from regions that meet quality standards, reducing overall material waste while maintaining rigorous quality assurance
3Reliability
If extensive quality control testing is performed on unconsolidated composite materials, then quality levels can be identified, but manufacturing efficiency decreases
Solution Approach 1:
The system replaces traditional mechanical and manual quality testing methods with non-contact sensor-based measurement and machine learning prediction. Sensors monitor properties during manufacturing, and algorithms predict final material characteristics without requiring physical sampling, cutting, or destructive testing. This substitution maintains accurate quality identification while dramatically improving manufacturing efficiency by eliminating time-consuming manual inspection processes
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method, apparatus, system, and computer program product for manufacturing an unconsolidated composite material. Sensor data is received from a sensor system for a composite material manufacturing system, wherein the sensor data is received during manufacturing of the unconsolidated composite material by the composite material manufacturing system. A set of predicted properties is determined for a number of portions of the unconsolidated composite material as completed from manufacturing by the composite material manufacturing system using the sensor data. A quality level for the number of portions of the unconsolidated composite material is identified based on the set of predicted properties for the number of portions of the unconsolidated composite material.