Inspection equipment and production management system

Abstract

The present invention provides an inspection device that can more accurately and quickly perform tests for the continuous presence of minute amounts of foreign matter in tablets without destroying the tablets. [Solution] The inspection device 51 includes an illumination device 52 that irradiates the tablet 5 with electromagnetic waves, a two-dimensional spectrometer 62 that can spectrally analyze reflected light from the tablet 5, and an image sensor 63 that captures the spectral image to acquire spectral image data. Based on the spectral image data obtained by the image sensor 63, spectral data of the tablet 5 is acquired, and the quality of the tablet 5 is determined based on this spectral data. Furthermore, based on the summed good product spectral data obtained by adding up multiple spectral data related to the tablet 5 that has been determined to be good, the presence or absence of continuous foreign matter contamination in the tablet 5 is determined.

Description

Technical Field

[0001] The present invention relates to an inspection device for inspecting the presence or absence of continuous foreign matter contamination in tablets, and a production management system having the inspection device.

Background Art

[0002] Drugs such as tablets, foods, cosmetics, etc. are ingested by humans or animals or applied to humans, etc. Therefore, it is necessary to achieve a particularly high level of safety for these. As a method for achieving high safety, it is generally known to inspect the presence or absence of foreign matter contamination in the test object (drugs such as tablets, foods or cosmetics, etc.).

[0003] As an apparatus for inspecting the presence or absence of foreign matter (e.g., different varieties) contamination in drugs (especially tablets), an inspection apparatus using spectroscopic analysis has been proposed (see, for example, Patent Document 1, etc.). This inspection apparatus includes irradiation means for irradiating a test object with predetermined light, imaging means for imaging the reflected light from the test object, spectral data acquisition means for obtaining spectral data based on the spectroscopic image data obtained by the imaging means, and determination means for determining the presence or absence of foreign matter (different varieties) using the obtained spectral data.

[0004] In addition, as a method for analyzing foreign matter (e.g., mold toxin) that can be mixed into a test object, an analytical sample is generated from an initial sample, an analytical spectrum is obtained from the analytical sample using vibrational spectroscopic analysis, and a reference spectrum is obtained from a standard sample. Further, a method for extracting the spectrum of foreign matter using the data of the analytical spectrum and the reference spectrum is known (see, for example, Patent Document 2, etc.). In this Patent Document 2, as conventional methods for analyzing mold toxins, methods such as liquid chromatography and gas chromatography are mentioned.

Prior Art Documents

Patent Documents

[0005] [Patent Document 1] Japanese Patent Publication No. 2019-207193 [Patent Document 2] Japanese Patent Publication No. 2018-4252 [Overview of the Initiative] [Problems that the invention aims to solve]

[0006] Incidentally, it is possible that trace amounts of foreign substances (such as mycotoxins) that do not have any effect on humans or animals may be continuously mixed into the samples being tested. In order to achieve better safety, it is desirable to be able to quickly determine whether or not such a situation is occurring.

[0007] However, the inspection device described in Patent Document 1 inspects the transported objects (tablets) sequentially, so while it can perform rapid inspections, it is extremely difficult to accurately detect even minute amounts of foreign matter.

[0008] On the other hand, while methods such as those described in Patent Document 2 and liquid chromatography may be able to detect minute amounts of foreign matter contained in the object being inspected, they require the preparation of analytical samples, making it impossible to inspect the object non-destructively and quickly.

[0009] The present invention has been made in view of the above circumstances, and its purpose is to provide an inspection device, etc., that can perform an inspection for the presence or absence of trace amounts of foreign matter continuously present in a test object (tablet) more accurately and quickly without damaging the test object. [Means for solving the problem]

[0010] Below, we will describe, in separate sections, each means suitable for achieving the above objectives. Furthermore, we will add notes on the effects and benefits specific to each means as needed.

[0011] Method 1. An inspection device for continuously checking for the presence or absence of foreign matter in tablets, A conveying means for transporting multiple tablets arranged in one or more rows, An irradiation means for irradiating the transported tablets with near-infrared light, visible light, ultraviolet light, or X-rays, A spectroscopic means capable of spectrally analyzing reflected light reflected from the tablet, transmitted light transmitted through the tablet, or fluorescence emitted from the tablet due to electromagnetic waves irradiated from the irradiation means, An imaging means for capturing the spectral spectrum obtained by the spectral means and acquiring spectral image data, A spectral data acquisition means for acquiring spectral data of a tablet based on spectral image data obtained by the imaging means, A quality determination means for determining the quality of the tablets based on the spectral data, An added good product spectral data acquisition means obtains added good product spectral data by adding together a plurality of spectral data related to tablets that have been determined to be good products by the good / bad product determination means, which correspond to a predetermined period. An inspection apparatus characterized by comprising a means for determining whether or not there is continuous contamination of tablets with foreign matter, based on the added good product spectrum data obtained by the means for acquiring added good product spectrum data.

[0012] According to the above-described method 1, even if the amount of foreign matter mixed in one inspected object (tablet) is very small, if the foreign matter is continuously mixed in multiple inspected objects (tablets), the spectral data of the foreign matter can be amplified in the aggregated good product spectral data. Therefore, based on the aggregated good product spectral data, it is possible to more accurately inspect whether or not there is continuous contamination of the inspected objects (tablets) with even a very small amount of foreign matter.

[0013] Furthermore, because the test utilizes spectral data, it can be performed more quickly without destroying the object being tested (tablet).

[0014] Furthermore, according to the above means 1, summed good product spectral data can be obtained using only the spectral data of the inspected items (tablets) that have been determined to be good products by the quality determination means. Therefore, the accuracy of the determination regarding the presence or absence of continuous foreign matter contamination can be further improved. To explain in more detail, when a relatively large amount of foreign matter is mixed into a small number of inspected items (tablets) to the extent that the quality determination means determines them to be defective, if the determination is made using summed spectral data obtained using the spectral data of these inspected items (tablets), there is a risk of misjudging that continuous foreign matter contamination has occurred in the inspected items (tablets) other than these inspected items (tablets), even if no continuous foreign matter contamination has occurred in the inspected items (tablets) other than these inspected items (tablets). In contrast, according to the above means 1, summed good product spectral data can be obtained using only the spectral data of the inspected items (tablets) that have been determined to be good products by the quality determination means, that is, without using spectral data of the inspected items (tablets) that are defective products. Therefore, the occurrence of misjudgments caused by defective inspected items (tablets) can be prevented more reliably, and the accuracy of the determination regarding the presence or absence of continuous foreign matter contamination can be further improved.

[0015] Means 2. The inspection apparatus according to Means 1, characterized in that the means for acquiring aggregated good product spectral data is configured to obtain aggregated good product spectral data by adding spectral data relating to one lot of tablets corresponding to the production period of the one lot of tablets, or spectral data relating to tablets used in the production of one lot of products corresponding to the production period of the one lot of products.

[0016] Furthermore, a "lot" can be defined as a group of tablets or products manufactured in a homogeneous manner through a series of processes within a single manufacturing period. Therefore, the "production period for one lot of tablets" is the period during which tablets are produced using raw materials of the same quality under the same conditions, resulting in the production of homogeneous tablets. Similarly, the "production period for one lot of products" is the period during which products (such as PTP sheets) are produced using raw materials of the same quality under the same conditions, resulting in the production of homogeneous products.

[0017] According to the above method 2, aggregate good product spectral data can be obtained by adding spectral data relating to one lot of inspected materials (tablets) corresponding to the production period of the one lot of inspected materials (tablets), or spectral data relating to inspected materials (tablets) used in the production of one lot of products corresponding to the production period of the one lot of products. For example, if the product is a PTP sheet, aggregate good product spectral data can be obtained by adding spectral data relating to tablets used in the production of one lot of PTP sheets. If continuous contamination of foreign matter occurs, it is considered that the same foreign matter is present in many of the inspected materials (tablets) in one lot, so spectral data relating to the foreign matter can be amplified more effectively in the aggregate good product spectral data. This makes it possible to further improve the accuracy of judgment regarding the presence or absence of continuous contamination of foreign matter.

[0018] Furthermore, based on the results of the determination regarding the presence or absence of continuous foreign matter contamination, it is possible to determine whether processing (e.g., disposal) is necessary for each homogeneous lot of inspected material (tablets) or product, and if processing is necessary, it can be easily carried out.

[0019] Means 3. The inspection apparatus according to Means 2, characterized in that the means for acquiring aggregated good product spectral data is configured to obtain aggregated good product spectral data by adding spectral data relating to 10,000 or more tablets.

[0020] According to the above method 3, spectral data related to foreign matter can be amplified more effectively in the aggregated good product spectral data. Therefore, even when the amount of foreign matter in each of the multiple inspected objects (tablets) is extremely small, the presence or absence of continuous foreign matter can be determined more accurately.

[0021] Means 4. The inspection apparatus according to Means 1, characterized in that the means for determining whether or not there is continuous foreign matter contamination in a tablet is configured to determine whether or not there is continuous foreign matter contamination in the tablet using aggregate good product spectrum data for tablets in which continuous foreign matter contamination has not occurred.

[0022] According to the above-mentioned means 4, it is determined whether there is continuous foreign matter contamination by using the added good product spectrum data related to the inspected object (tablet) in which continuous foreign matter contamination has not occurred. For example, by comparing the added good product spectrum data related to the inspected object (tablet) to be inspected with the added good product spectrum data related to the inspected object (tablet) in which continuous foreign matter contamination has not occurred, it is determined whether there is continuous foreign matter contamination in the inspected object (tablet) to be inspected. Therefore, when determining whether there is continuous foreign matter contamination, different from the case of selectively checking a specific wavelength corresponding to the assumed foreign matter, it is possible to more easily detect continuous contamination of unexpected foreign matter.

[0023] Means 5. The inspection device described in means 2, and a shipment permission means for permitting the shipment of the tablets for one lot or the tablets used for the production of one lot of products when it is determined based on the added good product spectrum data related to the tablets that there is no continuous foreign matter contamination in the tablets by the foreign matter continuous contamination determination means. A production management system characterized by comprising.

[0024] According to the above-mentioned means 5, when shipping the inspected object (tablet) or product for one lot, only the inspected object (tablet) without continuous foreign matter contamination or the product having such an inspected object (tablet) can be shipped. Therefore, it is possible to suppress the shipment of inspected objects (tablets) that may contain foreign matter even in trace amounts, and improve the safety of the inspected objects (tablets) circulating in the market.

[0025] In addition, the technical matters related to the above-mentioned means may be appropriately combined. Therefore, for example, the technical matters related to the above-mentioned means 2, 3 or 5 may be combined with the technical matters related to the above-mentioned means 4.

Brief Description of the Drawings

[0026] [Figure 1] It is a perspective view showing a PTP sheet. [Figure 2] It is a partially enlarged cross-sectional view of a PTP sheet. [Figure 3] This is a perspective view showing PTP film. [Figure 4] This is a schematic diagram showing the general configuration of a PTP packaging machine. [Figure 5] This is a block diagram showing the electrical configuration of a production management system. [Figure 6] This is a schematic perspective view showing the layout and configuration of the inspection equipment. [Figure 7] This is a schematic diagram showing the general configuration of a spectral camera. [Figure 8] This is a flowchart of the measurement routine. [Figure 9] This is an explanatory diagram illustrating the relationship between the imaging range in the transport direction and tablets, etc. [Figure 10] This is a schematic diagram showing a spectral image. [Figure 11] This is a flowchart of the inspection routine. [Figure 12] This graph shows an example of average spectral data for tablets. [Figure 13] This graph shows an example of average spectral data for tablets. [Figure 14] This is a flowchart showing the analysis process. [Figure 15] This is a flowchart showing the process for continuous foreign object contamination detection. [Figure 16] This graph shows an example of aggregated good product spectral data. [Figure 17] In another embodiment, this is a schematic diagram showing a spectral camera and the like configured so that transmitted light that has passed through a tablet is incident on it. [Figure 18] This is a schematic diagram illustrating the case where the object being inspected is food. [Figure 19] This is a schematic diagram illustrating the case where the object being tested is a cosmetic product. [Modes for carrying out the invention]

[0027] The following describes one embodiment with reference to the drawings. First, the configuration of the PTP sheet containing the tablets, which are the "objects to be inspected," will be described in detail.

[0028] As shown in Figures 1 and 2, the PTP sheet 1 has a container film 3 with a plurality of pocket portions 2 and a cover film 4 attached to the container film 3 so as to close the pocket portions 2. In this embodiment, the PTP sheet 1 corresponds to the "product".

[0029] The container film 3 is formed from a transparent thermoplastic resin material such as PP (polypropylene) or PVC (polyvinyl chloride) and is light-transmitting. On the other hand, the cover film 4 is made of an opaque material (such as aluminum foil) with a sealant made of polypropylene resin or the like applied to its surface. The materials of the container film 3 and the cover film 4 may be changed as appropriate.

[0030] The PTP sheet 1 is formed in a roughly rectangular shape when viewed from above. The PTP sheet 1 has two rows of pockets, each consisting of five pockets 2 arranged along its longitudinal direction, and two rows of pockets 2 arranged along its short direction. In other words, a total of 10 pockets 2 are formed. Each pocket 2 contains one tablet 5.

[0031] The PTP sheet 1 is manufactured by punching out a sheet of strip-shaped PTP film 6 (see Figure 3), which is formed from a strip-shaped container film 3 and a strip-shaped cover film 4.

[0032] Next, the general configuration of the PTP packaging machine 10 that manufactures the above-mentioned PTP sheet 1 will be explained with reference to Figure 4. The PTP packaging machine 10 manufactures PTP sheets 1 in lot units. The "production period for one lot of PTP sheets 1" is the period during which PTP sheets 1 are produced using raw materials of the same quality and under the same conditions, and is the period during which homogeneous PTP sheets 1 are produced.

[0033] As shown in Figure 4, at the upstream end of the PTP packaging machine 10, a strip of container film 3 is wound into a roll. The end of the roll of container film 3 is guided by a guide roll 13. Downstream of the guide roll 13, the container film 3 is mounted on an intermittent feed roll 14. The intermittent feed roll 14 is connected to a motor that rotates intermittently, and intermittently conveys the container film 3.

[0034] Between the guide roll 13 and the intermittent feed roll 14, a heating device 15 and a pocket forming device 16 are arranged in order along the transport path of the container film 3. When the container film 3 is heated by the heating device 15 and becomes relatively flexible, the pocket forming device 16 forms multiple pockets 2 at predetermined positions on the container film 3. The formation of the pockets 2 takes place during the intervals between the transport operations of the container film 3 by the intermittent feed roll 14.

[0035] The container film 3, fed out from the intermittent feed roll 14, is mounted on the tension roll 18, guide roll 19, and film receiving roll 20 in that order.

[0036] The film receiving roll 20 is connected to a motor that rotates at a constant speed, and therefore conveys the container film 3 continuously and at a constant speed. As the film receiving roll 20 conveys the container film 3, the multiple tablets 5 are conveyed in multiple rows (five rows in this embodiment). Therefore, in this embodiment, the film receiving roll 20 constitutes the "conveying means".

[0037] The tension roll 18 is positioned to pull the container film 3 towards the side that is under tension by elastic force, preventing slack in the container film 3 due to differences in the transport operation between the intermittent feed roll 14 and the film receiving roll 20, and keeping the container film 3 in a constantly taut state.

[0038] Between the guide roll 19 and the film receiving roll 20, a tablet filling device 21 is positioned along the transport path of the container film 3. The tablet filling device 21 opens its shutters at predetermined intervals in synchronization with the transport operation of the container film 3 by the film receiving roll 20, causing the tablets 5 to fall out. Each pocket 2 is filled with tablets 5 as the shutters open.

[0039] An inspection device 51 is positioned between the tablet filling device 21 and the film receiving roll 20, along the transport path of the container film 3. The production management system 50, which includes the inspection device 51, will be described later.

[0040] Meanwhile, the raw material of the strip-shaped cover film 4 is wound into a roll at the upstream end. The end of the roll-shaped cover film 4 is guided by a guide roll 24 and then towards the heating roll 25. The heating roll 25 can be pressed against the film receiving roll 20, and the container film 3 and cover film 4 are fed between the two rolls 20 and 25. As the container film 3 and cover film 4 pass between the two rolls 20 and 25 under heated and pressed conditions, the cover film 4 is attached to the container film 3, and the pocket portions 2 are sealed with the cover film 4. This produces a strip-shaped PTP film 6 in which tablets 5 are contained in each pocket portion 2.

[0041] The PTP film 6, fed from the film receiving roll 20, is mounted on the tension roll 27 and then the intermittent feed roll 28 in that order. The intermittent feed roll 28 is connected to a motor that rotates intermittently, thus intermittently transporting the PTP film 6. The tension roll 27 is positioned to pull the PTP film 6 towards the side where it is tensioned by elastic force, preventing slack in the PTP film 6 due to the difference in transport operation between the film receiving roll 20 and the intermittent feed roll 28, and keeping the PTP film 6 in a constantly taut state.

[0042] The PTP film 6 fed from the intermittent feed roll 28 is mounted on the tension roll 31 and then the intermittent feed roll 32 in that order. The intermittent feed roll 32 is connected to a motor that rotates intermittently, so it conveys the PTP film 6 intermittently. The tension roll 31 is positioned to pull the PTP film 6 towards the side where it is tensioned by elastic force, preventing slack in the PTP film 6 between the intermittent feed rolls 28 and 32.

[0043] Between the intermittent feed roll 28 and the tension roll 31, a slitting device 33 and an engraving device 34 are arranged in order along the transport path of the PTP film 6. The slitting device 33 has the function of forming separation slits at predetermined positions on the PTP film 6. The engraving device 34 has the function of engraving at predetermined positions (e.g., the tag portion) on the PTP film 6. Note that the separation slits and engraving are not shown in Figure 1, etc.

[0044] The PTP film 6 fed from the intermittent feed roll 32 is then mounted downstream on the tension roll 35 and the continuous feed roll 36 in that order. Between the intermittent feed roll 32 and the tension roll 35, a sheet punching device 37 is positioned along the transport path of the PTP film 6. The sheet punching device 37 functions as a sheet punching means (cutting means) that punches the outer edge of the PTP film 6 into units of PTP sheets.

[0045] The PTP sheets 1 obtained by the sheet punching device 37 are transported by the conveyor 39 and temporarily stored in the finished product hopper 40. However, if a PTP sheet 1 is determined to be defective by the inspection device 51, that defective PTP sheet 1 is not sent to the finished product hopper 40, but is discharged separately by a defective sheet discharge mechanism (not shown).

[0046] Furthermore, the PTP sheets 1 stored in the finished product hopper 40 are collected by a predetermined collection means. Then, the collected PTP sheets 1 are subjected to processing such as banding, pillow packaging, or boxing to obtain sheet packages. Of the obtained sheet packages, only those PTP sheets 1 authorized for shipment by the shipment authorization device 81, described later, are ultimately shipped.

[0047] In addition, a cutting device 41 is located downstream of the continuous feed roll 36. The scrap 42 remaining after punching by the sheet punching device 37 is guided to the tension roll 35 and the continuous feed roll 36, and then to the cutting device 41. The cutting device 41 cuts the scrap 42 to predetermined dimensions. The cut scrap 42 is stored in the scrap hopper 43 and then disposed of separately.

[0048] Next, the production management system 50 will be described. The production management system 50 includes an inspection device 51 and a shipping authorization device 81. In this embodiment, the shipping authorization device 81 constitutes the "shipping authorization unit".

[0049] The inspection device 51 uses spectroscopic analysis to inspect for the presence of foreign matter in the tablets 5. As shown in Figure 5, the inspection device 51 comprises an illumination device 52, a spectral camera 53, and a control device 54 that performs various controls within the inspection device 51, such as driving the illumination device 52 and the spectral camera 53, as well as image processing and calculation processing. In this embodiment, the illumination device 52 constitutes the "irradiation means".

[0050] The illumination device 52 and the spectral camera 53 are positioned on the side of the pocket portion 2 opening of the container film 3 (see Figures 6 and 7). In other words, in this embodiment, inspection is performed from the side of the pocket portion 2 opening of the container film 3 before the cover film 4 is attached. Note that the container film 3 is not shown in Figure 7, etc.

[0051] The illumination device 52 is a known device configured to emit near-infrared light, visible light, ultraviolet light, or X-rays as electromagnetic waves. The illumination device 52 irradiates light from an oblique angle above a predetermined area on the continuously transported container film 3. In this embodiment, the illumination device 52 is configured as a halogen lamp as a light source capable of emitting near-infrared light with a continuous spectrum (for example, in the near-infrared region with wavelengths of 700 to 2500 nm). Other light sources that can be used include deuterium discharge tubes, tungsten lamps, and xenon lamps.

[0052] The spectral camera 53 is for acquiring spectral image data relating to the tablet 5. The spectral camera 53 includes a two-dimensional spectrometer 62 and an image sensor 63. In this embodiment, the two-dimensional spectrometer 62 constitutes the "spectrometric means," and the image sensor 63 constitutes the "imaging means."

[0053] The two-dimensional spectrometer 62 is a device that spectrally analyzes the reflected light from the tablet 5, which is affected by electromagnetic waves irradiated from the illumination device 52. The two-dimensional spectrometer 62 comprises a slit 62a, an incident lens 62b, and a spectroscopic unit 62c.

[0054] The slit 62a is formed as an elongated, roughly rectangular (linear) opening, with its width direction (short side) aligned with the transport direction (Y direction) of the container film 3, and its longitudinal side aligned with the width direction (X direction) of the container film 3 perpendicular to the transport direction. Light passing through the slit 62a is made into parallel light by the incident lens 62b, then spectrally separated into a spectral spectrum by the spectrometer 62c, and formed as a two-dimensional spectral image (spectral spectral image) on the image sensor 63. In addition, a reflective diffraction grating or prism may be used as a spectral means instead of the two-dimensional spectrometer 62.

[0055] The image sensor 63 is used to capture the spectral spectrum dispersed by the two-dimensional spectrometer 62 and obtain spectral image data. The image sensor 63 has a light-receiving surface 63a in which a plurality of light-receiving elements (light-receiving parts) 64 are arranged in a matrix in two dimensions. In this embodiment, a known CCD area sensor having sufficient sensitivity to the near-infrared region, for example, in the wavelength range of 1300 to 2000 nm, is used as the image sensor 63. Of course, the image sensor 63 is not limited to this and may be other sensors. For example, a CMOS sensor or an MCT (HgCdTe) sensor may be used as the image sensor 63.

[0056] The field of view (imaging area) of the spectral camera 53 is a linear region extending along the width direction (X direction) of the container film 3, and includes at least the entire width of the container film 3. On the other hand, the field of view of the spectral camera 53 in the transport direction (Y direction) of the container film 3 corresponds to the aperture width of the slit 62a. In other words, it is the region in which light passing through the slit 62a (slit light) forms an image on the light-receiving surface 63a of the image sensor 63.

[0057] As a result, each photodetector 64 of the image sensor 63 receives light from each wavelength band (for example, every 10-20 nm bandwidth) of the spectral spectrum of the reflected light reflected at each position in the width direction (X direction) of the container film 3. Then, a signal corresponding to the intensity of the light received by each photodetector 64 is converted into a digital signal and output from the spectral camera 53 to the control device 54. In other words, the image signal (spectral image data) for one screen captured across the entire light-receiving surface 63a of the image sensor 63 is output to the control device 54.

[0058] The control device 54 includes a CPU and input / output interface 71 (hereinafter referred to as "CPU etc. 71") which controls the entire inspection device 51, an input device 72 consisting of a keyboard, mouse, touch panel, etc., a display device 73 having a display screen such as a CRT or liquid crystal, an image data storage device 74 for storing various image data, a calculation result storage device 75 for storing various calculation results, etc., and a setting data storage device 76 for pre-storing various information. Each of these devices 72 to 76 is electrically connected to the CPU etc. 71.

[0059] The CPU and other components 71 are connected to the components of the PTP packaging machine 10 so as to be able to send and receive various signals. This allows for control of, for example, the defective sheet discharge mechanism of the PTP packaging machine 10.

[0060] The image data storage device 74 is for storing spectral image data acquired by the spectral camera 53, as well as binarized image data, which will be described later.

[0061] The calculation result storage device 75 stores various spectral data, test result data, and statistical data obtained by probabilistically processing the test result data, based on spectral image data. The various spectral data and test result data can be displayed on the display device 73 as appropriate.

[0062] The setting data storage device 76 stores, for example, the shape and dimensions of the PTP sheet 1, the pocket portion 2, and the tablet 5, a spectral tolerance table for determining the quality of the tablet 5, and reference spectral data for determining whether or not there is continuous contamination of the tablet 5.

[0063] Next, the procedure for determining the quality of individual tablets 5 for foreign matter contamination, as performed by the inspection device 51, will be explained.

[0064] First, the measurement routine for acquiring spectral data will be explained with reference to the flowchart in Figure 8. This routine is executed repeatedly each time a predetermined amount of container film 3 is transported.

[0065] In step S01, the control device 54 first irradiates the continuously transported container film 3 (tablet 5) with near-infrared light from the illumination device 52 while performing imaging processing (exposure processing) with the spectral camera 53.

[0066] Here, the control device 54 drives and controls the spectral camera 53 based on signals from an encoder (not shown) provided in the PTP packaging machine 10, and acquires the spectral image data captured by the spectral camera 53 into the image data storage device 74.

[0067] As a result, of the near-infrared light irradiated from the illumination device 52 toward the container film 3, the reflected light reflected from the transport direction imaging range W (the area with a scattered dot pattern in Figure 9) during the execution period (exposure period) of the imaging process in step S01 is incident on the spectral camera 53. In other words, the transport direction imaging range W is imaged in a single imaging process.

[0068] Reflected light incident on the spectral camera 53 is spectrally separated into a spectral spectrum by the two-dimensional spectrometer 62, and this spectral spectrum is captured by the image sensor 63. Since the container film 3 (tablet 5) is continuously transported during the imaging process (exposure period), the average spectral spectrum of the transport direction imaging range W is captured here. The spectral image (spectral spectrum) data captured by the image sensor 63 is output to the control device 54 and stored in the image data storage device 74.

[0069] When spectral image data is acquired, the control device 54 starts the data generation process in step S02. In the data generation process, spectral data is generated based on the spectral image data acquired in step S01. Once the spectral data is generated, the control device 54 stores it in the image data storage device 74 and terminates this routine.

[0070] Then, each time a predetermined amount of container film 3 (tablet 5) is transported, the transport direction imaging range W moves intermittently relative to the container film 3, and as the above measurement routine is repeated, spectral data corresponding to each transport direction imaging range W is sequentially stored in the image data storage device 74 in chronological order along with the position information of the transport direction (Y direction) and width direction (X direction) of the container film 3. As a result, a two-dimensional spectral image Q is generated, with spectral data for each pixel.

[0071] The spectral image Q is image data consisting of multiple pixels Qa arranged in a two-dimensional array, as shown in Figure 10. Each pixel Qa contains spectral data [data showing spectral intensity (luminance) in a predetermined number of n wavelength bands (e.g., n=100 bands)].

[0072] Then, when a spectral image Q of a predetermined inspection area (see the dashed-dot line in Figure 10) corresponding to one PTP sheet 1 to be inspected is acquired, the control device 54 executes the inspection routine. This routine is repeated each time a spectral image Q of the above inspection area is acquired.

[0073] In the inspection routine, the control device 54 first performs a tablet pixel extraction process in step S11, as shown in Figure 11. In this process, from each pixel Qa of the spectral image Q, the pixel Qb corresponding to the tablet 5 to be analyzed (hereinafter referred to as "tablet pixel") is extracted.

[0074] In this embodiment, for example, it is determined whether the spectral intensity (luminance) of a predetermined wavelength in the spectral data of each pixel Qa is above a predetermined threshold, and the spectral image Q is subjected to binarization processing. Then, based on the obtained binarized image data, the tablet pixels Qb are extracted (see Figure 10). In Figure 10, the pixels extracted as tablet pixels Qb are indicated by diagonal lines. In this embodiment, pixels Qa containing data that captures only the area of ​​the tablet 5 without being affected by the background are extracted as tablet pixels Qb.

[0075] Next, the control device 54 performs the tablet area identification process of step S12. This process identifies the areas of the 10 tablets 5 contained in each pocket 2 within the inspection range.

[0076] In this embodiment, for example, the tablet pixels Qb obtained in step S11 are labeled, and all adjacent tablet pixels Qb are considered as connected components of tablet pixels Qb belonging to the same tablet 5. Then, the range of one connected component is identified as the tablet region relating to one tablet 5 housed in a predetermined pocket 2. In Figure 10, the connected components (tablet regions) of multiple tablet pixels Qb belonging to each tablet 5 are each enclosed by a thick frame.

[0077] Furthermore, the method for identifying the region of tablet 5 is not limited to this, and other methods may be employed. For example, pixels included in a predetermined range centered on a specific pixel may be determined to belong to the same tablet 5 as the specific pixel.

[0078] Next, the control device 54 executes the average spectrum calculation process of step S13. In this process, for each tablet region of each tablet 5 identified in step S12, the control device 5 calculates the average spectrum data for that tablet 5 using the spectral data of multiple tablet pixels Qb contained therein.

[0079] In this embodiment, the spectral data of all the tablet pixels Qb belonging to the tablet region of one tablet 5 is averaged and calculated as the average spectral data for the tablet 5 (see Figures 12 and 13). Alternatively, a configuration may be used in which a portion of the multiple tablet pixels Qb belonging to the tablet region of one tablet 5 is extracted, and the spectral data of these tablet pixels Qb is used to calculate the average spectral data for the tablet 5. In this embodiment, this average spectral data corresponds to the "spectral data of tablet 5".

[0080] The average spectral data basically shows that the intensity (brightness) of the spectrum Sx related to the components contained in tablet 5 (the intrinsic components of tablet 5) is high, while the intensity of the spectra related to other components is low. However, spectra related to other components may appear not only when those components are actually present, but also when they are not. This is due to the influence of noise, etc. Therefore, if a small amount of foreign matter (for example, mycotoxin) is actually mixed into tablet 5, the low-intensity spectrum Sz related to that foreign matter may be buried, so to speak, within the spectra of the other components. In this embodiment, the control device 54 that performs processing for acquiring average spectral data constitutes the "spectral data acquisition means".

[0081] Once the average spectral data for each of the 10 tablets 5 contained in each pocket 2 within the inspection range is calculated, the control device 54 stores these data together as measurement data for a single inspection range in the calculation result storage device 75.

[0082] In this embodiment, the spectral intensity V(i) for each wavelength band (band number i=1 to n) is stored in the average spectral data of one tablet 5. Here, "band number i (1≦i≦n, i is a natural number)" is a sequential number assigned to a predetermined number of n wavelength bands (for example, n=100 bands) included in the average spectral data.

[0083] In the following step S14, the control device 54 sets the counter value P of the pocket number counter set in the calculation result storage device 75 to the initial value of "1". A "pocket number" is a sequential number set to correspond to each of the 10 pocket sections 2 within one inspection range, and the position of the pocket section 2 can be identified by the counter value P of the pocket number counter (hereinafter simply referred to as "pocket number counter value P") (see Figure 10).

[0084] Next, in step S15, the control device 54 performs a tablet data extraction process. In this process, the control device 54 extracts the average spectral data of the tablet 5 stored in the pocket section 2 corresponding to the current pocket number counter value P (for example, P=1) from the measurement data related to one inspection range (average spectral data of 10 tablets 5) obtained in step S13.

[0085] Next, the control device 54 performs an analysis on the average spectral data of the tablets 5 extracted in step S15 (step S16).

[0086] In the analysis process, as shown in Figure 14, the control device 54 sets the counter value I of the band number counter set in the calculation result storage device 75 (hereinafter simply referred to as "band number counter value I") to an initial value of "1" in step S31. The "band number counter value I" corresponds to the "band number i" and is used to identify the wavelength band to be analyzed.

[0087] In the following step S32, the control device 54 performs a spectral determination process. In this process, among the spectral intensities V(i) of n wavelength bands (band numbers i=1 to n) included in the average spectral data of the tablet 5 extracted in step S15, the control device 54 determines whether the spectral intensity V(i) pertaining to the wavelength band of band number i, which is identified by the current band number counter value I, is determined by referring to the spectral tolerance range table set in the setting data storage device 76.

[0088] The spectral tolerance table defines the tolerance range D(i) of spectral intensity V(i) for each of the n wavelength bands (band numbers i=1 to n). One spectral tolerance table is set up corresponding to each of the 10 pocket sections 2 (pocket number counter value P) within one inspection range. In other words, in this embodiment, 10 spectral tolerance tables are set up for one inspection range. The spectral tolerance table contains the tolerance range D(i) for each wavelength band, calculated based on spectral measurement data for a predetermined number (e.g., 200) of good tablets 5 on PTP sheets 1 acquired in advance before the start of inspection. Alternatively, one spectral tolerance table may be set up for one inspection range.

[0089] Therefore, in this process, the spectral intensity V(i) related to the wavelength band of band number i, specified by the current band number counter value I, is determined by referring to the spectral tolerance table corresponding to the current pocket number counter value P, and whether or not it falls within the tolerance range D(i) corresponding to the wavelength band of band number i.

[0090] The control device 54 then stores the judgment result ("good" or "bad") in the calculation result storage device 75.

[0091] Subsequently, in step S33, the control device 54 adds "1" to the current band number counter value I, then proceeds to step S34, where it determines whether the newly set band number counter value I exceeds the maximum value n (the number of wavelength bands n included in the spectral measurement data).

[0092] If a negative result is obtained here, the process returns to step S32 and the above series of operations is executed again. On the other hand, if a positive result is obtained, it is considered that a pass / fail judgment has been made for the spectral intensity V(i) of all wavelength bands, and this process is terminated.

[0093] Returning to Figure 11, after the analysis process, the control device 54 performs a tablet quality determination process in step S17.

[0094] In this process, based on the analysis results from step S16 above, it is determined whether the tablet 5 contained in the pocket section 2 corresponding to the current pocket number counter value P (for example, P=1) is a good product or a defective product.

[0095] Specifically, if none of the spectral intensities V(i) in the n wavelength bands (band numbers i=1 to n) included in the average spectral data of tablet 5 are judged as "defective," then tablet 5 is judged as "good." On the other hand, if even one is judged as "defective," then tablet 5 is judged as "defective." Furthermore, if the amount of foreign matter mixed into tablet 5 is so small that it does not affect the human body, then tablet 5 is judged as "good." However, as determined by the continuous foreign matter contamination inspection process described later, it may be found that tablets 5 used in a lot of PTP sheets 1, including this tablet 5, have a continuous foreign matter contamination.

[0096] The control device 54 then stores the judgment result ("good product" or "defective product") for the tablet 5 in the calculation result storage device 75. Therefore, in this embodiment, the control device 54 that performs the quality judgment processing for the tablet 5 constitutes the "quality judgment means".

[0097] Subsequently, in step S18, the control device 54 adds "1" to the current pocket number counter value P, then proceeds to step S19 to determine whether the newly set pocket number counter value P exceeds the maximum value Pmax. The maximum value Pmax is the maximum number of pockets 2 in one inspection range (in this embodiment, "10").

[0098] If the result is negative, the process returns to step S15 and the above series of processes are executed again. On the other hand, if the result is positive, it is considered that the quality determination of all tablets 5 related to the pocket portion 2 has been completed, and the process proceeds to step S20.

[0099] In the following step S20, the control device 54 performs a sheet quality determination process. In this process, based on the determination result from the tablet quality determination process in step S17, it is determined whether the PTP sheet 1 corresponding to the inspection area is a "good product" or a "defective product".

[0100] Specifically, if even one tablet 5 is found to be a "defective product" within the inspection range, the PTP sheet 1 corresponding to that inspection range is determined to be a "defective product," and the process proceeds to step S21. In the defective product processing of step S21, the control device 54 stores the determination result as a "defective product" in the calculation result storage device 75, outputs this information to the defective sheet discharge mechanism of the PTP packaging machine 10, and terminates the inspection routine.

[0101] On the other hand, if no tablets 5 are found to be "defective" within the inspection range, in step S20, the PTP sheet 1 corresponding to that inspection range is determined to be "good," and the process proceeds to step S22.

[0102] In the good product processing step S22, the control device 54 stores the judgment result of "good product" in the calculation result storage device and stores the measurement data (average spectral data of 10 tablets 5) related to the PTP sheet 1 that was judged as "good product" in the calculation result storage device 75. The calculation result storage device 75 sequentially stores the average spectral data related to the PTP sheet 1 that was judged as "good product" each time an inspection is performed, in chronological order.

[0103] Furthermore, the control device 54 performs a continuous foreign matter contamination inspection process each time the production of one lot of PTP sheets 1 is completed. The continuous foreign matter contamination inspection process is a process to determine whether or not there is continuous foreign matter contamination in the tablets 5.

[0104] In the continuous foreign matter contamination inspection process, the control device 54 first performs a good product data extraction process in step S41, as shown in Figure 15. In this process, it extracts average spectral data for 10,000 or more good tablets 5 stored in the calculation result storage device 75. In other words, the control device 54 extracts 10,000 or more average spectral data for tablets 5 that have been determined to be "good products" from among the tablets 5 used in the production of one lot of PTP sheets 1, corresponding to a predetermined period (in this embodiment, the production period of one lot of PTP sheets 1).

[0105] For example, suppose a PTP packaging machine 10 capable of processing 100 tablets 5 per second is operated for 8 hours to produce one lot of PTP sheets 1. In this case, one lot of PTP sheets 1 uses 2.88 million tablets 5 [= 100 (seconds / second) × 60 (seconds) × 60 (minutes) × 8 (hours)]. Normally, the number of tablets 5 that are judged as "defective" individually is extremely small. Therefore, the number of average spectral data extracted is a maximum of 2.88 million, and is usually very close to 2.88 million.

[0106] In the subsequent step S42, the control device 54 obtains summed good product spectral data by adding the extracted average spectral data (see Figure 16). In the summed good product spectral data, if a small amount of foreign matter is continuously present, the intensity of the spectrum Sz related to the foreign matter will be significantly larger than the intensity of the spectrum related to components other than the components contained in the tablet 5, that is, the intensity of the spectrum that can be expressed by noise (noise intensity). Alternatively, the summed good product spectral data may be obtained by adding the average spectral data and dividing by the number of such data, i.e., the average value of the average spectral data. In this embodiment, the control device 54 that performs processing to obtain summed average spectral data constitutes the "summed good product spectral data acquisition means".

[0107] Next, in the comparison process of step S43, the control device 54 compares the spectral intensity of the added good product spectral data obtained in step S42 with the spectral intensity of the reference spectral data pre-stored in the setting data storage device 76 for each spectrum in the same wavelength band. The reference spectral data is the added good product spectral data for tablets 5 that have not experienced continuous contamination, which has been acquired in advance. Note that in the comparison process S43, only the spectral intensity of a specific wavelength band (for example, a specific wavelength band corresponding to mycotoxins) may be compared.

[0108] Then, if the intensity difference (luminance difference) K of the spectral intensities of both spectral data is smaller than the maximum allowable value Kmax pre-stored in the setting data storage device 76 (step S44: Yes), the control device 54 determines in step S45 that there is no continuous foreign matter contamination and terminates the continuous foreign matter contamination inspection process.

[0109] On the other hand, if the strength difference K is greater than or equal to the maximum allowable value Kmax (step S44: No), the control device 54 determines in step S46 that there is continuous contamination of foreign matter and notifies the outside of this fact using the display device 73 or the like.

[0110] If it is determined that there is continuous contamination of foreign matter, the operator or other personnel will determine whether processing (e.g., disposal) is necessary for one lot of PTP sheets 1, or take measures such as cleaning the equipment. In this embodiment, the control device 54, which performs processing to determine whether there is continuous contamination of the tablets 5 based on the sum of good product spectrum data, constitutes the "continuous foreign matter contamination determination means".

[0111] The shipping authorization device 81 determines whether a lot of PTP sheets 1 obtained by the PTP packaging machine 10 is eligible for shipment. Based on the aggregate good product spectrum data for the tablets 5 used in the production of a lot of PTP sheets 1, the shipping authorization device 81 determines that there is no continuous contamination of the tablets 5 (i.e., a positive determination is made in step S44), and therefore authorizes the shipment of that lot of PTP sheets 1 (more precisely, the multiple sheet packages related to this lot of PTP sheets 1). Only with authorization from the shipping authorization device 81 can the shipping personnel ship a lot of PTP sheets 1. On the other hand, if the shipping authorization device 81 determines that there is continuous contamination of the tablets 5, it denies the shipment of a lot of PTP sheets 1 produced using these tablets 5.

[0112] As detailed above, according to this embodiment, even if the amount of foreign matter mixed into one tablet 5 is very small, if the foreign matter is continuously mixed into multiple tablets 5, the spectral data of the foreign matter can be amplified in the aggregated good product spectral data. Therefore, based on the aggregated good product spectral data, it is possible to more accurately inspect whether or not there is continuous contamination of tablets 5 with even a very small amount of foreign matter.

[0113] Furthermore, because the test utilizes spectral data, it can be performed more quickly without destroying tablet 5.

[0114] Furthermore, by using only the average spectral data related to the tablets 5 that have been determined to be "good," summed good product spectral data can be obtained. Therefore, the accuracy of the determination regarding the presence or absence of continuous foreign matter contamination can be further improved. To explain in more detail, if a relatively large amount of foreign matter is mixed into a small number of tablets 5 to the extent that it is determined to be "defective," if the determination is made using summed spectral data obtained using the average spectral data related to these tablets 5, there is a risk of misjudging that continuous foreign matter contamination has occurred in the tablets 5 other than these tablets 5, even if no continuous foreign matter contamination has occurred in those tablets 5. In contrast, as in this embodiment, by obtaining summed good product spectral data using only the average spectral data related to the tablets 5 that have been determined to be "good," it is possible to more reliably prevent misjudgments caused by "defective" tablets 5. Therefore, the accuracy of the determination regarding the presence or absence of continuous foreign matter contamination can be further improved.

[0115] In addition, by adding the average spectral data for tablets 5 used in the production of one lot of PTP sheets 1, corresponding to the production period of that lot of PTP sheets 1, aggregated good product spectral data can be obtained. If continuous contamination of foreign matter occurs, it is considered that the same foreign matter is present in many of the tablets 5 in one lot, so the spectral data (spectral intensity) related to the foreign matter can be more effectively amplified in the aggregated good product spectral data. This makes it possible to further improve the accuracy of determining whether or not continuous contamination of foreign matter is present.

[0116] Furthermore, based on the results of the determination regarding the presence or absence of continuous foreign matter contamination, it is possible to determine whether processing (e.g., disposal) is necessary for each homogeneous lot of PTP sheets, and if processing is necessary, it can be easily carried out.

[0117] Furthermore, by using average spectral data for more than 10,000 tablets 5 to obtain aggregated good product spectral data, the spectral data (spectral intensity) related to foreign matter can be amplified more effectively in the aggregated good product spectral data. Therefore, even when the amount of foreign matter in each of the multiple tablets 5 is extremely small, the presence or absence of continuous foreign matter contamination can be determined more accurately.

[0118] In addition, the presence or absence of continuous foreign matter contamination is determined using the added good product spectral data (reference spectral data) for tablet 5, which does not show continuous foreign matter contamination. Therefore, when determining the presence or absence of continuous foreign matter contamination, unlike when selectively checking a specific wavelength corresponding to an assumed foreign matter, it is possible to more easily detect the continuous contamination of unexpected foreign matter.

[0119] Furthermore, when shipping one lot of PTP sheets 1, only PTP sheets 1 containing tablets 5 free from continuous foreign matter contamination can be shipped. Therefore, the shipment of tablets 5 that may contain even trace amounts of foreign matter can be suppressed, thereby improving the safety of tablets 5 distributed in the market.

[0120] Furthermore, the embodiment is not limited to the description above, and may be implemented as follows, for example. Of course, other applications and modifications not exemplified below are also possible.

[0121] (a) In the above embodiment, the reflected light from the tablet 5 is set to enter the spectral camera 53. In contrast, as shown in Figure 17, the transmitted light from the tablet 5 may be set to enter the spectral camera 53. Also, when the illumination device 52 irradiates with blue light, ultraviolet light, or X-rays, the fluorescence emitted by the tablet 5 may be set to enter the spectral camera 53.

[0122] (b) In the above embodiment, the case where the object to be inspected is tablet 5 is described, but the technical concept of the present invention can also be applied to the inspection of objects other than tablet 5. Therefore, the objects to be inspected may be, for example, pharmaceuticals such as tablets, powders, liquids, and ointments; cosmetics such as facial cleansers, lotions, toners, and lipsticks; and foods such as seasonings, confectionery, processed meats, drinking water, and pet food, which are taken into the body by humans or animals or applied to humans or animals.

[0123] Therefore, for example, when food is the object to be inspected, as shown in Figure 18, the food 91, which is contained in a predetermined container 92 and transported by a conveyor belt, is sequentially imaged with a spectral camera 53, and the presence or absence of continuous foreign matter contamination in the food 91 is inspected based on the spectral data of the food 91. Alternatively, for example, when cosmetics are the object to be inspected, as shown in Figure 19, the cosmetics 95, which are contained in a predetermined tube 96 and transported by a conveyor belt, are sequentially imaged with a spectral camera 53, and the presence or absence of continuous foreign matter contamination in the cosmetics 95 is inspected based on the spectral data of the cosmetics 95.

[0124] Furthermore, although the above embodiment uses PTP sheet 1 as an example of a "product," if the object to be inspected is a drug, cosmetic, or food, as described above, the product can be anything that contains these objects. Therefore, the product may be a package product containing food in a container, a tube product containing cosmetics or drugs in a tube, or a bottle product containing food or drugs (e.g., tablets or capsules) in a bottle.

[0125] Therefore, inspection devices such as those described in the following means a to e may be employed.

[0126] (b-1) Means a. An inspection device for inspecting whether a drug, cosmetic, or food product is continuously contaminated with foreign substances, A transport means for transporting multiple items to be inspected in one or more rows, An irradiation means for irradiating the object to be transported with near-infrared light, visible light, ultraviolet light, or X-rays, A spectroscopic means capable of spectrally analyzing reflected light, transmitted light, or fluorescence emitted from an object being inspected, as a result of electromagnetic waves irradiated from the aforementioned irradiation means. An imaging means for capturing the spectral spectrum obtained by the spectral means and acquiring spectral image data, A spectral data acquisition means for acquiring spectral data of an object under inspection based on spectral image data obtained by the imaging means, A quality determination means for determining whether an object to be inspected is good or bad based on the spectral data, An added good product spectral data acquisition means obtains added good product spectral data by adding together a plurality of spectral data related to an inspected product that has been determined to be good by the good / bad determination means, which correspond to a predetermined period. An inspection apparatus characterized by comprising a means for determining whether or not there is continuous contamination of an object to be inspected with foreign matter, based on the added good product spectrum data obtained by the added good product spectrum data acquisition means.

[0127] According to the above-described means a, the same effects and advantages as those of means 1 are achieved.

[0128] (b-2) Means b. The inspection apparatus according to means a, characterized in that the means for acquiring aggregate good product spectral data is configured to obtain aggregate good product spectral data by adding spectral data relating to one lot of inspected objects corresponding to the production period of the one lot of inspected objects, or spectral data relating to inspected objects used in the production of one lot of products corresponding to the production period of the one lot of products.

[0129] Furthermore, "production period for one lot of inspected items" refers to the period during which inspected items are produced using raw materials of the same quality under the same conditions, and is the period during which homogeneous inspected items are produced.

[0130] According to the above-described means b, the same effects and advantages as those of means 2 are achieved.

[0131] (b-3) Means c. The inspection apparatus according to means b, characterized in that the means for acquiring aggregated good product spectral data is configured to obtain aggregated good product spectral data by adding spectral data relating to 10,000 or more inspected objects.

[0132] According to the above means c, the same effects as those of the above means 3 are achieved.

[0133] (b-4) Means d. The inspection apparatus according to means a, characterized in that the means for determining whether or not there is continuous foreign matter contamination in the inspected object is configured to determine whether or not there is continuous foreign matter contamination in the inspected object using summation good product spectrum data relating to the inspected object in which no continuous foreign matter contamination has occurred.

[0134] According to the above means d, the same effects as those of the above means 4 are achieved.

[0135] (b-5) Means e. The inspection device described in means b, A production management system characterized by comprising: a shipment authorization means that, based on the cumulative good product spectrum data relating to the inspected items used in the production of one lot of inspected items or one lot of products, determines that there is no continuous contamination of the inspected items with foreign matter, and then permits the shipment of the inspected items or products from that lot.

[0136] According to the above-described means e, the same effects and advantages as those of means 5 are achieved. Furthermore, the technical aspects related to means a to e may be combined as appropriate.

[0137] (c) In the above embodiment, the inspection by the inspection device 51 is performed after the tablets 5 have been filled into the pocket portion 2 and before the cover film 4 has been attached to the container film 3.

[0138] Alternatively, the inspection may be performed by the inspection device 51 from the container film 3 side of the PTP film 6 through the pocket portion 2 after the cover film 4 has been attached to the container film 3 and before the PTP film 6 has been punched out.

[0139] (d) In the above embodiment, the inspection device 51 is applied to the PTP packaging machine 10 and inspects the tablets 5 after they have been filled into the pockets 2, but it may also be used to inspect the tablets 5 before they are filled into the pockets 2.

[0140] Therefore, the inspection device 51 may be applied to a tablet press for manufacturing tablets 5, or an inspection device for inspecting tablets 5 obtained by the tablet press. In this case, the average spectral data for one lot of tablets 5, corresponding to the production period of the one lot of tablets 5, may be added to obtain the aggregate good product spectral data. The "production period of one lot of tablets 5" is the period during which tablets are produced using raw materials of the same quality under the same conditions, and is the period during which homogeneous tablets 5 are produced.

[0141] (e) In the above embodiment, the reference spectral data used is the addition of good product spectral data for tablets 5 that have not experienced continuous contamination by foreign matter, which has been acquired in advance. However, the reference spectral data is not limited to this. Therefore, for example, reference spectral data obtained using the following AI model may be used.

[0142] The AI ​​model has been trained only on additive good product spectral data (data without contamination) related to tablet 5, which does not experience continuous contamination, and outputs reconstructed additive good product spectral data that is reconstructed according to the input additive good product spectral data. Since the AI ​​model was generated by training only on data without contamination, when additive good product spectral data (data with contamination) related to tablet 5, which experiences continuous contamination, is input, the reconstructed additive good product spectral data will output data that is almost identical to the input data in which the spectrum related to the continuously contaminated foreign matter has been normalized. In other words, when data with contamination is input, the AI ​​model generates hypothetical data without contamination as reconstructed additive good product spectral data, assuming that there is no continuous contamination. This hypothetical data without contamination may then be used as reference spectral data.

[0143] (f) In the above embodiment, the number of rows of tablets 5 being transported is set to 5 rows, but the number of rows of tablets 5 can be changed as appropriate depending on the configuration of the PTP sheet 1, etc. Therefore, for example, if the PTP sheet 1 has 3 rows of 12 pockets, the number of rows of tablets 5 being transported may be 3 rows. Of course, when the inspection device 51 is applied to a tablet press or the like, the number of rows of tablets 5 being transported may be 1 row.

[0144] (g) The arrangement and number of pockets 2 in the PTP sheet 1 are not limited to the above embodiment and may be changed as appropriate. [Explanation of symbols]

[0145] 1...PTP sheet 1 (product), 5...tablet, 20...film receiving roll (conveying means), 50...production management system, 51...inspection device, 52...lighting device (irradiation means), 54...control device (spectral data acquisition means, quality determination means, addition good product spectral data acquisition means, foreign matter continuous contamination determination means), 63...image sensor (imaging means), 81...shipping authorization device (shipping authorization unit).

Claims

1. An inspection device for continuously checking for the presence of foreign matter in tablets, A conveying means for transporting multiple tablets arranged in one or more rows, An irradiation means for irradiating the transported tablets with near-infrared light, visible light, ultraviolet light, or X-rays, A spectroscopic means capable of spectrally analyzing reflected light reflected from the tablet, transmitted light transmitted through the tablet, or fluorescence emitted from the tablet due to electromagnetic waves irradiated from the irradiation means, An imaging means for capturing the spectral spectrum obtained by the spectral means and acquiring spectral image data, A spectral data acquisition means for acquiring spectral data of a tablet based on spectral image data obtained by the imaging means, A quality determination means for determining the quality of the tablets based on the spectral data, An added good product spectral data acquisition means obtains added good product spectral data by adding together a plurality of spectral data related to tablets that have been determined to be good products by the good / bad product determination means, which correspond to a predetermined period. An inspection apparatus characterized by comprising a means for determining whether or not there is continuous contamination of tablets with foreign matter, based on the added good product spectrum data obtained by the means for acquiring added good product spectrum data.

2. The inspection apparatus according to claim 1, characterized in that the means for acquiring aggregated good product spectral data is configured to obtain aggregated good product spectral data by adding spectral data relating to one lot of tablets corresponding to the production period of the one lot of tablets, or spectral data relating to tablets used in the production of one lot of products corresponding to the production period of the one lot of products.

3. The inspection apparatus according to claim 2, characterized in that the means for acquiring aggregated good product spectral data is configured to obtain aggregated good product spectral data by adding spectral data relating to 10,000 or more tablets.

4. The inspection apparatus according to claim 1, characterized in that the foreign matter continuous contamination determination means is configured to determine whether or not there is continuous foreign matter contamination in the tablets using aggregate good product spectrum data for tablets in which no continuous foreign matter contamination has occurred.

5. The inspection apparatus according to claim 2, A production management system characterized by comprising: a shipment authorization means that, when the foreign matter continuous contamination determination means determines, based on the aggregate good product spectrum data relating to tablets used in the production of one lot of tablets or one lot of products, that there is no continuous contamination of the tablets, it permits the shipment of the one lot of tablets or products.

Images