Application-specific repeat defect detection in web manufacturing processes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional web inspection systems struggle to accurately identify the source of repeating anomalies in moving webs, particularly when rolls with similar diameters are used, and fail to account for spatial distortion or undocumented roll changes, leading to difficulties in defect detection and maintenance.
Innovation Solution
An automated inspection system that uses optical acquisition devices and sophisticated image processing algorithms to differentiate between repeating and random anomalies, correlating anomaly positions with roll synchronization signals to identify the source of defects, and applies application-specific defect detection recipes based on product selection parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional inspection systems use traditional repeat detection methods, then they can identify repeating defects, but they cannot accurately identify the specific offending roll when multiple rolls have similar diameters
Solution Approach 1:
The patent introduces an intermediary computational process that correlates defect positions with roll synchronization signals. This intermediary analysis layer connects the inspection system to roll rotation data, enabling precise identification of offending rolls without requiring complex hardware modifications. The synchronization signals act as mediators between the defect detection system and the roll identification process.
Solution Approach 2:
The system changes the parameter of measurement from simple repeat distance to a correlated parameter that combines defect position with roll synchronization timing. By analyzing the temporal and spatial relationship between defect occurrences and roll rotation signals, the system can distinguish which specific roll caused the defect even when multiple rolls have similar circumferences.
2Adaptability or versatility
If conventional systems require a priori knowledge of roll diameters, then they can process inspection data, but they fail to account for undocumented roll changes and spatial distortion
Solution Approach 1:
The inspection system performs self-calibration by using the web itself as a reference. Through fiducial marks and web tracking, the system automatically determines spatial relationships and roll positions without requiring external documentation or manual input of roll specifications. This self-service approach allows the system to adapt to undocumented roll changes while maintaining reliable defect detection.
Solution Approach 2:
The system implements feedback loops where defect detection results are continuously correlated with roll synchronization signals. This feedback mechanism allows the system to learn and adapt to actual roll positions and diameters in real-time, compensating for undocumented changes and spatial distortion through iterative refinement of the correlation model.
3Productivity
If web process lines have hundreds of rolls with similar diameters, then they can perform various manufacturing functions, but identifying the specific offending roll becomes extremely difficult
Solution Approach 1:
The patent segments the analysis by dividing the web traversal into discrete sections corresponding to each roll's influence zone. By using fiducial marks and synchronization signals to create segment boundaries, the system can analyze defects in the context of specific roll passages, making it feasible to identify offending rolls even among hundreds of rolls with similar diameters.
Solution Approach 2:
The system adds a temporal dimension to the spatial analysis of defects. By correlating defect positions with the timing of roll synchronization signals, the system creates a time-position matrix that enables identification of specific rolls. This dimensional transformation from purely spatial to spatio-temporal analysis dramatically improves detectability in complex multi-roll systems.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Techniques are described for inspecting a web and controlling subsequent conversion of the web into one or more products. A system, for example, comprises an imaging device, an analysis computer and a conversion control system. The imaging device images the web to provide digital information. The analysis computer processes the digital information to identify regions on the web containing anomalies. The conversion control system subsequently analyzes the digital information to determine which anomalies represent actual defects for a plurality of different products. The web inspection system may preferentially apply different application-specific defect detection recipes depending on whether a given anomaly is a repeating or random anomaly.