FRP Composite Molding with CNN-Based Property Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing molding systems for fabricating fiber reinforcement polymer (FRP) composite articles face challenges in accurately predicting mechanical properties during the lamination process, which is affected by high temperature and pressure, leading to inefficiencies and inaccuracies in the molding process.
Innovation Solution
A molding system that includes a detector to capture a graph of woven fibers, a resin dispenser to form FRP, a processing module with a convolutional neural network (CNN) model to predict mechanical properties based on the graph and parameters, and a molding machine to fabricate the FRP composite article according to the predicted properties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional calculation methods are used to determine mechanical properties during lamination, then accuracy can be maintained, but the process becomes time-consuming and inefficient
Solution Approach 1:
The system performs preliminary actions by capturing images of the fiber reinforcement and predicting mechanical properties before the actual molding process begins. The processing module analyzes the captured images and generates predicted mechanical properties (Young's modulus, shear modulus, Poisson's ratio, coefficient of thermal expansion) in advance, allowing the molding machine to be pre-configured with accurate parameters without time-consuming calculations during production.
Solution Approach 2:
The patent replaces traditional mechanical calculation methods with an intelligent system comprising a detector, processing module with CNN model, and molding machine. Instead of using conventional time-consuming calculation methods to determine mechanical properties, the system uses image capture and AI-based prediction to rapidly obtain accurate mechanical property data, significantly reducing processing time while maintaining or improving accuracy.
2Productivity
If the lamination process is performed without accurate prediction of mechanical properties, then the process speed increases, but the quality and reliability of the FRP composite article decreases
Solution Approach 1:
The system implements feedback by using the predicted mechanical properties to control the molding machine parameters. The processing module generates predictions based on captured images, and this feedback information is used to adjust and optimize the lamination process parameters (temperature, pressure, time), ensuring high-quality FRP composite articles are produced efficiently. The controller uses the predicted properties to automatically adjust molding parameters for optimal results.
Solution Approach 2:
The system performs preliminary analysis and prediction before the molding process to ensure quality. By capturing images of the fiber reinforcement and predicting mechanical properties in advance, the system allows the molding machine to be pre-configured with accurate parameters, ensuring high-quality output without compromising production speed or efficiency.
3Manufacturing precision
If detailed analysis of fiber arrangement is performed, then manufacturing precision improves, but device complexity increases
Solution Approach 1:
The system uses copying by capturing an image (visual copy) of the fiber reinforcement arrangement instead of performing complex physical analysis. The detector captures a graphical representation of the fiber layout, and the processing module analyzes this copied visual information to predict mechanical properties accurately. This approach achieves high manufacturing precision while avoiding the need for complex analytical devices or procedures.
Data Source
AI summary
The present disclosure provides a molding system for fabricating a FRP composite article. The molding system includes a detector, a resin dispenser, a processing module, and a molding machine. The detector is configured to capture a graph of a woven fiber from a top view. The resin dispenser is configured to provide a resin to the woven fiber to form a FRP. The processing module is configured to receive the graph and a plurality of parameters of the FRP. The processing module includes a CNN model, and is configured to use the CNN model to obtain a plurality of predicted mechanical properties of the FRP according to the graph and the plurality of parameters of the FRP. The molding machine is configured to mold the FRP to fabricate the FRP composite article according to the plurality of predicted mechanical properties.