Web Inspection Spatial Registration for Multi-Process Defect Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current inspection systems for moving webs face challenges in processing high data rates and accurately detecting defects across multiple manufacturing operations, especially when web materials undergo various processes at different sites, making it difficult to maintain defect detection and product quality control.
Innovation Solution
The system performs spatial registration and combination of anomaly data collected throughout the production of a web, allowing for the alignment of anomaly information from different manufacturing processes to generate aggregate anomaly information, which can then be analyzed to determine actual defects and create a conversion control plan for optimal web utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple manufacturing operations are performed on web material at different physical sites, then process versatility and product complexity are improved, but spatial registration accuracy and defect detection reliability deteriorate due to cumulative positioning errors and coordinate system mismatches
Solution Approach 1:
The patent introduces a centralized registration system that acts as an intermediary between multiple distributed inspection systems. This system receives local anomaly data from various manufacturing operations at different sites and performs spatial registration by transforming coordinates to a common reference frame, thereby resolving the coordinate system mismatch problem while maintaining process versatility
Solution Approach 2:
The inspection system is segmented into multiple independent units, each performing local anomaly detection at its specific manufacturing operation. These segmented systems operate autonomously at different physical sites but their outputs are integrated through the centralized registration system, allowing versatility while managing spatial registration complexity
2Measurement precision
If high pixel resolution and web speed are used to maintain inspection quality, then defect detection precision is improved, but data processing rate requirements increase to tens or hundreds of megabytes per second
Solution Approach 1:
The system extracts only the critical information from high-resolution image data - specifically anomaly locations and characteristics - rather than processing the entire high-resolution image stream. This extraction approach maintains defect detection precision while significantly reducing the data processing rate requirement from tens or hundreds of megabytes per second to a manageable level
Solution Approach 2:
The system uses high pixel resolution for anomaly detection (excessive action) but then applies selective processing only to regions containing anomalies rather than processing the entire image at full resolution throughout the pipeline. This maintains detection precision while reducing overall data processing requirements
3Reliability
If anomaly data is collected at each manufacturing stage, then comprehensive defect detection is improved, but subsequent processes may mask or make detection of earlier anomalies difficult or impossible
Solution Approach 1:
The system performs preliminary anomaly detection and registration at each manufacturing stage, storing anomaly location data in a centralized database before subsequent processes are completed. This preliminary action ensures that even if later processes mask anomalies, the original anomaly positions are preserved and can be detected through the registered data, maintaining detection reliability
Solution Approach 2:
The system creates a digital copy of anomaly information from each inspection stage and stores it in the centralized registration system. This copy preserves the original anomaly data even when physical anomalies are masked by subsequent manufacturing processes, allowing retrospective detection and analysis without requiring re-inspection of the final product
Data Source
AI summary
A conversion control system is described that includes a database to store data defining a set of rules and an interface to receive local anomaly information from a plurality of different analysis machines associated with a plurality of manufacturing process lines that perform a plurality of operations on a web of material, and each of the manufacturing process lines includes position data for a set of regions on the web containing anomalies. The system also includes a computer that registers the position data of the local anomaly information for the plurality of manufacturing process lines to produce aggregate anomaly information. The system further includes a conversion control engine that applies the rules to the aggregate anomaly information to determine which anomalies represent actual defects in the web for a plurality of different products.