Real-Time Prepreg Quality Prediction During Composite Manufacturing
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 samples to identify out-of-tolerance portions, leading to time-consuming quality control processes and potential waste, and cannot determine the cause of quality issues during manufacturing.
Innovation Solution
A system using a prediction manager that generates real-time predictions of composite material characteristics by combining sensor data with physics-based and machine learning models, allowing for the identification of in-tolerance and out-of-tolerance portions during manufacturing, enabling immediate corrective actions and reduced waste.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple samples are tested to identify out-of-tolerance portions, then measurement precision is improved, but loss of time increases and productivity decreases
Solution Approach 1:
The system performs preliminary quality assessment during the manufacturing process itself, predicting characteristics of unconsolidated composite materials before consolidation occurs. This allows early identification of out-of-tolerance portions without requiring multiple post-manufacturing tests, thereby reducing time loss while maintaining measurement precision.
Solution Approach 2:
The patent replaces physical sampling and manual testing with a computational prediction system that uses sensor data, physics-based models, and machine learning models to assess quality. This substitution eliminates the need for multiple physical samples and accelerates the quality control process significantly.
2Measurement precision
If multiple samples are tested to identify out-of-tolerance portions, then measurement precision is improved, but productivity decreases
Solution Approach 1:
The system performs preliminary quality assessment during the manufacturing process itself, predicting characteristics of unconsolidated composite materials before consolidation occurs. This allows early identification of out-of-tolerance portions without requiring multiple post-manufacturing tests, thereby reducing time loss and improving manufacturing efficiency while maintaining measurement precision.
Solution Approach 2:
The patent replaces physical sampling and manual testing with a computational prediction system that uses sensor data, physics-based models, and machine learning models to assess quality. This substitution eliminates the need for multiple physical samples and accelerates the quality control process significantly, thereby improving productivity.
3Reliability
If quality testing is performed on unconsolidated composite materials, then reliability is improved, but device complexity increases
Solution Approach 1:
The prediction system is segmented into distinct functional modules: sensor data acquisition, physics-based modeling, machine learning prediction, and result integration. This modular architecture manages complexity by organizing the system into manageable, independent components that can be developed and validated separately while ensuring reliable quality control.
Solution Approach 2:
The system introduces an intermediary computational layer between manufacturing and quality assessment. This intermediary uses sensor data and predictive models to bridge the gap between raw manufacturing processes and quality decisions, managing complexity by providing a structured interface that translates physical measurements into quality predictions.
4Productivity
If real-time prediction system is implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The prediction system is segmented into distinct functional modules: sensor data acquisition, physics-based modeling, machine learning prediction, and result integration. This modular architecture manages complexity by organizing the system into manageable, independent components that can be developed and validated separately while enabling real-time quality control and improving productivity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method, apparatus, system, and computer program product for predicting a number of characteristics of an unconsolidated composite material. Sensor data is received in real time from a composite material manufacturing system during manufacturing of an unconsolidated composite material. Initial predictions are generated for a number of characteristics of the unconsolidated composite material in a completed form in real time during manufacturing of the unconsolidated composite material in the composite material manufacturing system using a number of physics-based models and a number of machine learning models trained using data. A final prediction is determined in real time for the number of characteristics based on the initial predictions.