Composite Prepreg Quality Prediction for Selective Roll 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 and costly discarding of entire rolls due to inability to determine which portions have undesired quality levels during manufacturing.
Innovation Solution
A composite material management system that uses sensor data and machine learning models to predict properties of unconsolidated composite materials in real-time, allowing for identification of in-tolerance and out-of-tolerance portions during manufacturing, enabling corrective actions to be taken and reducing waste.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If quality testing of unconsolidated composite materials is performed using traditional methods, then quality assessment can be achieved, but the testing process is time-consuming and requires discarding entire rolls due to inability to identify specific out-of-tolerance portions
Solution Approach 1:
The patent divides the continuous unconsolidated composite material roll into discrete portions and assigns quality characteristics to each portion individually. Sensors monitor properties at different locations along the material, enabling identification of specific out-of-tolerance portions without requiring testing of the entire roll. This segmentation allows selective use of in-tolerance portions while discarding only defective segments.
Solution Approach 2:
The patent replaces traditional mechanical sampling and physical testing methods with non-contact optical sensors and image processing systems. The sensor system captures images and measures properties of the unconsolidated composite material in real-time during manufacturing, eliminating the need for time-consuming physical sample extraction and laboratory testing.
2Reliability
If traditional quality testing methods are used for unconsolidated composite materials, then quality control can be maintained, but entire rolls must be discarded when out-of-tolerance portions are detected
Solution Approach 1:
The system segments the continuous material roll into quality-classified portions, identifying which segments meet specifications and which do not. This enables selective discarding of only the out-of-tolerance portions while preserving and using the in-tolerance portions, dramatically reducing material waste compared to traditional whole-roll discarding practices.
Solution Approach 2:
The patent applies the principle of local quality by assigning different quality characteristics to different portions of the same material roll. Each portion is evaluated independently based on its specific properties measured by sensors, allowing in-tolerance portions to be used for their intended application while out-of-tolerance portions are discarded or diverted to alternative uses.
3Measurement precision
If multiple portions are tested to identify out-of-tolerance sections, then quality identification can be achieved, but the process becomes time-consuming and costly
Solution Approach 1:
The sensor system operates continuously during the manufacturing process, monitoring unconsolidated composite material properties in real-time as the material moves through the production line. This continuous monitoring eliminates the need for intermittent sampling and batch testing, maintaining uninterrupted production flow while identifying out-of-tolerance portions immediately upon defect occurrence.
Solution Approach 2:
The system performs quality assessment preliminarily during the manufacturing process itself, before the material is fully processed and consolidated. By detecting out-of-tolerance conditions early in production, the system prevents defective material from proceeding through subsequent manufacturing steps, avoiding waste of additional processing time and resources.
Data Source
AI summary
A system, apparatus, computer program product, and a method for manufacturing an unconsolidated composite material. Sensor data is received from a sensor system for a composite material manufacturing system. The sensor data is received during manufacturing an 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 using the sensor data. The set of predicted properties is for the number of portions of the unconsolidated composite material as a completed product. A corrective action is performed based on a quality level for the number of portions of the unconsolidated composite material.