Horizontal Mold Seal Defect Detection in Glass Containers

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for detecting defects in the horizontal mold seal of glass containers are inadequate in terms of speed and reliability, particularly for small defects, and often fail to distinguish between different types of defects, leading to potential aesthetic or safety issues.

Innovation Solution

A method involving a camera and light source setup that rotates the container to capture multiple images per revolution, analyzing the ring edge profiles against a reference to detect deviations and discriminate between external spike, external burr, and offset ring defects, with high-speed inspection capable of identifying containers with defects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a light source and camera setup is used to detect defects in the horizontal mold joint, then defect detection capability is improved, but the inspection speed is limited and cannot meet manufacturing rates

Engineering Contradiction:
Improvedefect detection capabilityVSAvoidinspection speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The inspection method segments the ring inspection into multiple discrete positions around the ring circumference. By rotating the container and capturing images at multiple angular positions (e.g., every 10-30 degrees), the system divides the inspection task into manageable segments that can be processed efficiently, enabling high-speed inspection without compromising defect detection capability

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-defining inspection zones and reference profiles before actual inspection begins. The method establishes expected profile characteristics and defect criteria in advance, allowing rapid comparison and decision-making during high-speed production without real-time complexity

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If the container is rotated to capture multiple images per revolution, then detection reliability for small defects is improved, but the inspection time increases

Engineering Contradiction:
Improvedetection reliability for small defectsVSAvoidinspection time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial action by capturing images at strategically selected angular positions rather than continuously throughout the entire rotation. By inspecting specific critical zones (such as the horizontal mold joint region) at optimized angular intervals, the method achieves sufficient detection reliability for small defects while minimizing total inspection time to meet production rates

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The inspection method applies local quality by concentrating imaging and analysis resources on specific critical inspection zones rather than uniformly inspecting the entire container surface. The system identifies and focuses on regions where horizontal mold joint defects are most likely to occur, capturing high-resolution images only at these critical locations during rotation

Inventive Principle:
Principle #3Local quality

3Measurement precision

If the inspection method analyzes reflected light variations to detect defects, then small defects can be detected, but different types of defects cannot be distinguished

Engineering Contradiction:
Improvedetection of small defectsVSAvoiddefect type discrimination capability
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system transitions from analyzing only light intensity variations to examining multi-dimensional profile characteristics. By extracting geometric profile information (such as radial distance, slope, curvature) from the captured images and comparing these profiles against reference data, the method not only detects small defects but also distinguishes between different defect types (such as protrusions, recesses, or irregularities) based on their unique profile signatures

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

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

The method provides high-speed, reliable detection of various horizontal mold seal defects, ensuring only compliant containers are not rejected, with the ability to distinguish between different defect types, enhancing production line efficiency and safety.

Implementation Method 1

projecting a light line vertically onto the ring. A linear camera collects the light reflected by the ring

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP4267946B1Method for detecting defects of the horizontal mold seal for glass containers
Publication Date: 2025.09.10 TIAMA SOCIETE ANONYME
  • EP4267946B1 patent drawingFigure 1~2
  • EP4267946B1 patent drawingFigure 3A~3B
  • EP4267946B1 patent drawingFigure 4A~4B

AI summary

The invention relates to a method for detecting defects of the horizontal mold seal (JH) on the bottle finish (B) of containers (R), the method comprising the following steps: - arranging the container (R) between a light source and a camera; - rotating the container (R) on itself through one revolution; - acquiring an image by the camera, at each rotational increment of the container, such that the number of images per revolution is greater than 36; - analyzing the images taken for each container in such a way that: * the profile of the edge of the bottle finish is detected in each image; *the profiles of the bottle finish edge are compared with a reference profile of the bottle finish edge, so as to detect differences between these profiles; *and a defect in the horizontal mold seal (JH) is detected for a container when at least one image of the container exhibits a difference.