Unconsolidated Composite Property Prediction for In-Process Quality Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for quality testing of unconsolidated composite materials, such as prepreg rolls, are inefficient and time-consuming, as they require testing multiple portions to identify out-of-tolerance areas, leading to unnecessary discarding of entire rolls and reduced manufacturing capacity due to delayed process adjustments.
Innovation Solution
A composite material management system that uses real-time sensor data and machine learning models to predict the properties and quality levels of unconsolidated composite materials during manufacturing, allowing for in-process identification and correction of out-of-tolerance portions, thereby reducing waste and increasing production efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional quality testing methods are used for unconsolidated composite materials, then quality can be verified, but the testing process is time-consuming and requires discarding entire rolls when out-of-tolerance areas are found
Solution Approach 1:
The patent divides the composite material roll into multiple segments or portions, each with its own quality characteristics. Instead of treating the entire roll as a single unit, the system identifies and isolates out-of-tolerance portions individually, allowing in-tolerance portions to be utilized separately. This segmentation approach eliminates the need to discard entire rolls when local defects are detected.
Solution Approach 2:
The patent performs quality assessment and identification of out-of-tolerance portions during the manufacturing process itself, before the material is fully processed or shipped. By conducting preliminary detection and classification of quality portions, the system enables proactive quality management and prevents downstream rework or waste.
2Measurement precision
If multiple portions are tested to identify out-of-tolerance areas, then quality issues can be detected, but manufacturing capacity is reduced due to delayed process adjustments
Solution Approach 1:
The patent implements a feedback mechanism where quality data from sensor systems and machine learning models is continuously fed back to the manufacturing process control system. This real-time feedback enables immediate process adjustments when out-of-tolerance conditions are detected, eliminating delays associated with traditional batch testing and manual analysis.
Solution Approach 2:
The patent replaces traditional mechanical testing methods with sensor-based detection systems and machine learning algorithms. This substitution enables non-contact, real-time quality assessment during manufacturing, significantly reducing the time required for quality verification and process adjustment compared to conventional mechanical testing approaches.
3Reliability
If traditional quality testing is performed after manufacturing completion, then quality can be assessed, but waste increases due to discarding entire rolls with localized defects
Solution Approach 1:
The patent segments the composite material roll into distinguishable portions based on quality characteristics. By identifying the precise location and extent of out-of-tolerance areas, the system enables selective utilization of in-tolerance portions while isolating and discarding only the defective segments. This dramatically reduces material waste compared to traditional whole-roll rejection.
Solution Approach 2:
The patent implements a selective discarding and recovering strategy where only out-of-tolerance portions are discarded, while in-tolerance portions are recovered and utilized for their intended purpose. This approach maximizes material utilization and minimizes waste by preserving usable material that would otherwise be discarded with the entire roll.
Data Source
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.