Web Anomaly Data Spatial Registration and Aggregation

Resolve Bottlenecks,
Find Innovative Solutions
Generate 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, where anomalies introduced at different stages become difficult to detect due to complex web processing and multiple production lines.

Innovation Solution

A method for 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 is then used to create a conversion control plan for optimizing web utilization and defect detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple unit operations are performed on a single roll of material during production, then product complexity and manufacturing capability are improved, but anomaly detection difficulty and data processing complexity increase

Engineering Contradiction:
Improvemanufacturing capabilityVSAvoidanomaly detection difficulty
Core Design Contradiction:
Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent segments the complex manufacturing process into multiple unit operations, with each operation having its own inspection system that collects anomaly data locally. This segmentation allows each inspection system to focus on detecting anomalies specific to its process stage, making detection more effective while the centralized system integrates all segments' data to provide comprehensive anomaly tracking across the entire production chain.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements a nested data structure where local anomaly data from individual unit operations is nested within a hierarchical framework that progressively integrates data from multiple operations. The anomaly information from each process is nested within the broader context of the entire production sequence, allowing detailed local anomaly detection to be combined with global production tracking.

Inventive Principle:
Principle #7Nested doll (Nesting)

2Measurement precision

If web speed and pixel resolution are increased to meet manufacturing requirements, then inspection accuracy is improved, but data processing rate requirements increase to tens or hundreds of megabytes per second

Engineering Contradiction:
Improveinspection accuracyVSAvoiddata processing rate
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent extracts only the essential anomaly information from the high-resolution image data collected at each unit operation, rather than processing and storing complete high-speed image streams. By extracting key anomaly features and characteristics from the detailed inspection data, the system maintains high inspection accuracy while significantly reducing the data processing rate requirements for centralized analysis.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies partial processing at the local level (extracting only anomaly-related data) rather than processing all collected data in full detail. This partial action approach processes only the necessary portion of the high-resolution data that contains anomaly information, reducing overall data processing requirements while maintaining inspection accuracy.

Inventive Principle:
Principle #16Partial or excessive action

3Measurement precision

If local anomaly data from different processes is collected and spatially registered, then aggregate anomaly information accuracy is improved, but data integration and processing complexity increase

Engineering Contradiction:
Improveanomaly information accuracyVSAvoiddata integration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements a universal coordinate system and data structure that can accommodate anomaly data from multiple different unit operations and production lines. This universal framework allows anomaly information from diverse sources to be integrated using a common reference system, reducing the complexity of data integration while maintaining accurate spatial registration across different processes.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP2176648B1Method for inspection of anomalies in web materials
Publication Date: 2019.12.18 3M INNOVATIVE PROPERTIES CO
  • EP2176648B1 patent drawingFigure 1
  • EP2176648B1 patent drawingFigure 2
  • EP2176648B1 patent drawingFigure 3

AI summary

A conversion control system is described for spatially synchronizing data gathered from a plurality of operations performed on a web. The conversion control system applies a set of fiducial marks to a web, performs a plurality of operations on the web, generates a first and a second set of digital information for first and second operations, respectively, in accordance with respective first and second coordinate systems using the set of fiducial marks such that the each of the sets of digital information includes position data for respective first and second sets of regions on the web. The conversion control system may then register the position data of the first set of regions and the position data for the second set of regions to produce aggregate data and outputting a conversion control plan.