Container Bottom Inspection Using AI Image Analysis

Solution Overview

Problem

Current container inspection methods, particularly for container bottoms, rely on air blow-off to differentiate between internal and external contamination, which is inefficient and costly, with high energy consumption and false rejection rates, and struggle to accurately distinguish between internal and external disturbances.

Innovation Solution

An apparatus using an image recording and evaluation device to capture and analyze spatially resolved images of container bottoms, distinguishing between internal and external foreign objects by recognizing visual differences and using deep learning algorithms to classify defects, thereby eliminating the need for air blow-off and reducing false rejections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If air blow-off is used to remove external contamination, then external disturbances are cleared from container bottoms, but energy consumption increases and false rejections occur

Engineering Contradiction:

Improvecontamination detection accuracyVSAvoidenergy consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent replaces the mechanical air blow-off system with an optical inspection system using image recording devices and AI-based evaluation algorithms. The system captures images of container bottoms and uses machine learning models to distinguish between internal contamination and external disturbances, eliminating the need for energy-consuming air jets while maintaining detection accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent extracts and removes the air blow-off component from the inspection system entirely. By using purely optical and computational methods, the system eliminates the harmful air jet mechanism that caused both energy consumption and false rejections, while still achieving reliable contamination detection through advanced image analysis.

Inventive Principle:

Principle #2Taking out (Extraction)

2Measurement precision

If air blow-off is used to clear external contamination, then external disturbances are removed, but false rejection rate increases

Engineering Contradiction:

Improvecontamination detection accuracyVSAvoidfalse rejection rate

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent replaces the mechanical air blow-off system with an optical inspection system using image recording devices and AI-based evaluation algorithms. The system captures images of container bottoms and uses machine learning models to distinguish between internal contamination and external disturbances, eliminating the need for energy-consuming air jets while maintaining detection accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the detection parameters from physical air jet interaction to optical image analysis. By using multiple image recording devices capturing different perspectives and applying AI algorithms, the system transforms the detection approach to achieve higher reliability with lower false rejection rates.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If bottom-free transport is used to enable inspection, then container bottoms are accessible for detection, but external contamination adheres to bottoms

Engineering Contradiction:

Improvebottom inspection capabilityVSAvoidexternal contamination adherence

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the mechanical air blow-off system with an optical inspection system using image recording devices and AI-based evaluation algorithms. The system captures images of container bottoms and uses machine learning models to distinguish between internal contamination and external disturbances, eliminating the need for energy-consuming air jets while maintaining detection accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary AI-based image evaluation system between the container bottom and the detection decision. This intermediary analyzes optical images to differentiate between external contamination and internal foreign objects, allowing the system to tolerate external adherence without compromising detection accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20230288344A1Apparatus and method for inspecting containers

Publication Date: 2023.09.14 KRONES AG

AI summary

Apparatus for inspecting containers, having a transport device which transports the containers along a predetermined transport path, and having an inspection device for inspecting the containers, wherein this inspection device has an image recording device which is configured for recording a spatially resolved image of a bottom of the container. The apparatus includes an image evaluation device which is configured for evaluating the image recorded up by the image recording device, wherein this image evaluation device enables a distinction between images of those containers which have foreign bodies in their interior and those containers which have foreign bodies on an outer surface of the bottom.