PTP Tablet Inspection Using Near-IR Spectral Grouping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for inspecting PTP sheets by averaging spectral data across a tablet fail to account for variations in spectral data due to microscopic non-uniformity and surface unevenness, leading to reduced accuracy in differentiating similar types of tablets.

Innovation Solution

An inspection device that groups spectral data based on similarity, extracts a group with the largest number of similar data, calculates average spectral data for each tablet, and performs analysis using principal component analysis to improve accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If spectral data is simply averaged at multiple coordinate points on a tablet, then the inspection process is straightforward, but the inspection accuracy deteriorates due to microscopic non-uniformity and surface unevenness

Engineering Contradiction:
Improvesimplicity of averaging processVSAvoidinspection accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent applies local quality by differentiating the treatment of spectral data based on their spatial location and characteristics. Instead of uniform averaging, the system identifies and excludes outlier points (such as those affected by cleavage lines or surface unevenness) while retaining reliable spectral data from representative areas, thereby achieving both operational simplicity and high measurement precision.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent extracts and removes problematic spectral data points that are contaminated by local defects such as cleavage lines or surface irregularities. By selectively extracting only the reliable spectral information from multiple coordinate points, the system maintains ease of operation while significantly improving inspection accuracy through the exclusion of erroneous data.

Inventive Principle:
Principle #2Taking out (Extraction)

2Quantity of substance

If spectral data from areas with lumps or defects are included in the average, then more data points are used, but the uniformity of the average spectral data deteriorates

Engineering Contradiction:
Improvenumber of spectral data pointsVSAvoiduniformity of average spectral data
Core Design Contradiction:
Quantity of substanceVSStability of the object's composition

Solution Approach 1:

The patent extracts and removes spectral data points that are contaminated by local defects such as lumps or surface irregularities. By selectively extracting only the reliable spectral information from multiple coordinate points, the system maintains ease of operation while significantly improving inspection accuracy through the exclusion of erroneous data.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies local quality by differentiating the treatment of spectral data based on their spatial location and characteristics. Instead of uniform averaging, the system identifies and excludes outlier points (such as those affected by cleavage lines or surface unevenness) while retaining reliable spectral data from representative areas, thereby achieving both operational simplicity and high measurement precision.

Inventive Principle:
Principle #3Local quality

3Device complexity

If all spectral data points are used for averaging, then the calculation is simple, but the ability to differentiate similar types of tablets deteriorates

Engineering Contradiction:
Improvesimplicity of data processingVSAvoiddifferentiation capability
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent extracts and removes problematic spectral data points that are contaminated by local defects such as cleavage lines or surface irregularities. By selectively extracting only the reliable spectral information from multiple coordinate points, the system maintains ease of operation while significantly improving inspection accuracy through the exclusion of erroneous data.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies local quality by differentiating the treatment of spectral data based on their spatial location and characteristics. Instead of uniform averaging, the system identifies and excludes outlier points (such as those affected by cleavage lines or surface unevenness) while retaining reliable spectral data from representative areas, thereby achieving both operational simplicity and high measurement precision.

Inventive Principle:
Principle #3Local quality

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

This method enhances inspection accuracy by obtaining appropriate average spectral data, effectively distinguishing between different types of tablets, even when data varies across the tablet surface.

Implementation Method 1

an irradiation unit configured to irradiate a tablet with near-infrared light; a spectral unit configured to disperse reflected light that is reflected from the tablet irradiated with the near-infrared light

Methodology Applied
Scientific EffectNear-infrared light reflection: Reflection

Implementation Method 2

a spectral unit configured to disperse reflected light that is reflected from the tablet irradiated with the near-infrared light

Methodology Applied
Scientific EffectSpectral dispersion: Dispersion (of waves)

Data Source

PatentEP3614127B1Inspection device, PTP packaging machine, and PTP sheet manufacturing method
Publication Date: 2025.12.10 CKD CORP
  • EP3614127B1 patent drawingFigure 1(a)~2
  • EP3614127B1 patent drawingFigure 3
  • EP3614127B1 patent drawingFigure 4

AI summary

There are provided an inspection device configured to improve the inspection accuracy relating to a different type inclusion inspection that takes advantage of spectral analysis, as well as a PTP packaging machine and a PTP sheet manufacturing method. An inspection device 22 comprises an illumination device 52 configured to irradiate tablets 5 filled in pocket portions 2 of a conveyed container film 3 with near-infrared light; an imaging device 53 configured to disperse reflected light of the near-infrared light that is reflected from the tablets 5 and to take a spectroscopic image of the reflected light; and a control processing device configured to obtain spectral data, based on the spectroscopic image taken by the imaging device 53 and to perform a predetermined analysis process based on the spectral data. The inspection device 22 is configured to inspect for inclusion of a different type of object.