Tyre Surface Defect Detection Using Homologous Pattern Averaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for quality control in tyre production face challenges in detecting defects on the inner surface of tyres due to the presence of patterns, which can mask anomalies and require excessive computational resources, making it difficult to achieve efficient and accurate defect detection in a production line setting.
Innovation Solution
A method that acquires digital images of the tyre surface, identifies homologous regions with repeated patterns, calculates an average model of the pattern free of defects by combining pixel values from these regions, and uses this model for comparison to detect any deviations, thereby reducing computational requirements and enhancing sensitivity in defect detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If digital images are acquired and processed to detect defects on the tyre surface, then defect detection capability is improved, but computational resources required increase excessively
Solution Approach 1:
The patent segments the tyre surface into multiple zones based on the periodic pattern structure. By dividing the surface into repeating units and analyzing them separately, the computational burden is reduced while maintaining defect detection capability. The system processes only representative segments rather than the entire high-resolution image.
Solution Approach 2:
The patent extracts the essential pattern characteristics and defect features from the full digital image, separating the periodic pattern structure from potential defects. This extraction process removes redundant information while preserving the critical data needed for defect detection, thereby reducing computational requirements.
2Measurement precision
If the entire surface is analyzed in detail to detect defects, then measurement precision is improved, but analysis time increases
Solution Approach 1:
The patent performs preliminary analysis by first identifying the periodic pattern structure and selecting representative zones before conducting detailed defect detection. This preliminary segmentation and zone selection prepares the data in advance, enabling faster subsequent analysis while maintaining comprehensive coverage.
Solution Approach 2:
The patent applies partial action by analyzing only the most representative zones of the tyre surface in detail, rather than every single point. By selecting key areas that capture the essential pattern characteristics and potential defect locations, the system achieves sufficient detection accuracy with reduced analysis time.
3Ease of manufacture
If the pattern on the tyre surface is present to facilitate manufacturing, then ease of manufacture is improved, but defect detection becomes more difficult
Solution Approach 1:
The patent applies local quality by adapting the analysis method to different regions of the tyre surface. By identifying zones with distinct pattern characteristics and applying appropriate detection algorithms to each zone, the system overcomes the masking effect of the pattern while preserving the manufacturing benefits of the periodic structure.
Solution Approach 2:
The patent utilizes optical property changes (analogous to color changes) by analyzing variations in light reflection, absorption, or scattering from different surface regions. This allows the detection system to distinguish between the periodic pattern structure and actual defects based on their different optical signatures.
Data Source
AI summary
Method and related apparatus for analysing a surface of a tyre, includes: acquiring one or more digital images of a surface portion having a pattern that includes a scheme that is repeated substantially equal thereto in a plurality of positions; identifying a plurality of first regions of said one or more digital images, each corresponding to a respective scheme sub-portion; identifying a respective plurality of regions homologous to each first region, wherein the respective scheme sub-portion is substantially identical to the respective scheme sub-portion of each first region; calculating a model of the respective scheme sub-portion, where each pixel is associated with a mean value of the values associated with the pixels of each first region and of the respective homologous regions having the same relative coordinates of said each pixel; and obtaining a pattern model using the calculated scheme sub-portion models.