Automated Optical Defect Detection for Fiber Composite Surfaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting defects in fiber composite materials during the production of large-scale structural components, such as wing shells or rotor blades, are inefficient and prone to human error, leading to significant downtime and reduced quality due to the reliance on manual inspection and complex, unverifiable algorithms.
Innovation Solution
An automated method using an optical detection system that employs two different machine classification methods, such as an artificial neural network and a support vector machine, to detect and classify defects in the fiber material surface based on digital image data, ensuring robust and process-reliable detection by comparing the results of these methods for validation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual inspection methods are used to detect defects in fiber composite materials, then operators can identify surface defects, but the inspection process is time-consuming and causes significant system downtime
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated optical detection system that uses light projection and camera imaging to capture surface topography. This substitution eliminates the time-consuming manual inspection process while maintaining defect detection capability, directly resolving the contradiction between detection reliability and time loss.
Solution Approach 2:
The system creates a digital copy (height profile) of the fiber material surface through optical scanning. This digital replica allows for automated analysis without requiring physical manual inspection, enabling rapid defect identification while preserving detection accuracy and eliminating system downtime associated with manual methods.
2Productivity
If complex machine learning algorithms are used for automated defect classification, then detection speed improves, but the algorithms become difficult to understand and verify
Solution Approach 1:
The patent segments the defect classification task into two distinct machine learning procedures with different approaches. This segmentation allows each procedure to have optimized complexity for its specific function, improving overall detection speed while maintaining verifiability through the division of classification responsibilities.
Solution Approach 2:
The system implements feedback by comparing the classification results of two different machine learning procedures. This cross-validation mechanism provides verification of the classification accuracy while maintaining relatively simple individual algorithms, resolving the contradiction between detection speed and algorithm verifiability.
3Device complexity
If a single machine classification method is used for defect detection, then the system is simpler to implement, but the detection results lack verification and reliability
Solution Approach 1:
The patent implements a feedback mechanism where two different machine classification procedures independently classify defects, and their results are compared for consistency. This cross-validation provides verification of detection reliability while keeping individual classification methods relatively simple, resolving the contradiction between system complexity and result reliability.
Solution Approach 2:
The system changes the parameter of classification approach by employing two different machine learning methods with distinct algorithms and parameters. This diversification of classification parameters enables mutual verification of results, improving reliability without requiring excessive complexity in any single classification procedure.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables rapid, accurate, and reliable detection of defects, reducing system downtime and improving the quality of fiber composite components by minimizing process errors and ensuring consistent classification results.
Implementation Method 1
capturing a fiber material surface of a deposited fiber material by means of at least one optical sensor and generating digital image data containing the captured fiber material surface
Data Source
Figure 1
Figure 2
AI summary
The invention relates to a method for detecting defects on the surface of a fiber material comprising a fiber composite material, the fiber material being a component of a fiber composite material comprising the fiber material and a matrix material embedding the fiber material, by means of an optical detection system. The invention also relates to a method for depositing fiber material of a fiber composite material comprising the fiber material and a matrix material embedding the fiber material onto a tool surface, wherein an optical detection system detects the surface of the deposited fiber material and detects defects in the deposited fiber material depending on the detected surface, and classifies the type of defect. The invention also relates to an apparatus for this purpose.