Article inspection device, article inspection system, and article inspection system program

Abstract

To provide an article inspection device, an article inspection system and a program for the article inspection system with which, when installed in a manufacturing line where multiproduct production is carried out, it is possible to determine in advance whether or not a category can be identified.SOLUTION: The article inspection device comprises: an inspection unit for detecting a physical property value of content Wc of an inspection object W; acceptability determination means for determining the acceptability of the content Wc on the basis of the physical property value detected by the detection unit; a storage unit for storing a characteristic property value based on the physical property value that characterizes the category of the content Wc for each category; a comparison unit for comparing one of a plurality of characteristic property values stored in the storage unit with the other of the characteristic property values; an identification determination unit for determining whether or not it is possible to discriminate the category of the one characteristic property value from the category of the other characteristic property values as a result of the comparison by the comparison unit; and a display operation unit for outputting the result of determination by the identification determination unit.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to an article inspection device, an article inspection system, and a program for the article inspection system. [Background technology]

[0002] Article inspection devices are installed on production lines that manufacture articles such as food and medicine, and inspect the quality of articles, such as their weight, shape, and the presence of foreign matter. Examples of article inspection devices include X-ray inspection devices that use X-rays to check for the presence of foreign matter in articles, weight inspection devices that check the weight of articles, and metal detection devices that check for the presence of metal in articles by using changes in magnetic fields.

[0003] Patent Document 1 discloses an example of an article inspection device that irradiates an object to be inspected, which consists of tablets contained in multiple pockets formed in a sheet-like container, with X-rays, and uses the X-ray image corresponding to the X-rays that have passed through the object to determine whether the shape of the object is good or bad, and whether or not there is any foreign matter mixed in the object. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 5860347 Summary of the Invention [Problem to be solved by the invention]

[0005] In a manufacturing line equipped with the above-described product inspection device, multiple product types are sometimes produced on the same manufacturing line. In such a multi-product manufacturing process, the manufacturing line is cleaned after the production of the previous product, and then the production of the next product begins after the cleaning.

[0006] However, in multi-item production, for example, if the production line is long or cleaning is insufficient, there is a risk that the previous product type will accidentally be mixed in with the next product type during production. In this case, if the mixed previous product type is difficult to distinguish from the next product type due to its characteristics, there is a risk that the mixed previous product type cannot be removed during the production process of the next product type.

[0007] Furthermore, when the next variety is produced, there is a risk that not only the immediately preceding variety but also the variety before that may be mixed in.

[0008] To prevent the mixing of products with other types that are difficult to distinguish, it is desirable to take measures such as reviewing cleaning plans, separating the production line from other types that are difficult to distinguish, etc. However, to take such measures, it is necessary to know in advance whether it is possible to distinguish between different types on the same production line that produces multiple products.

[0009] In the conventional product inspection device described in Patent Document 1 above, when the device is installed on a manufacturing line that produces a wide variety of products, no consideration is given to determining in advance whether the product type can be identified.

[0010] In other words, for example, although the multiple pockets formed in the sheet-like container should originally contain tablets of the same type, there was no idea of ​​knowing in advance whether or not each type of product could be identified in the event of a mixture of earlier and later types of products in multi-product production, i.e., the accidental mixing of different types.

[0011] The present invention has been made in consideration of the above-mentioned circumstances, and aims to provide an item inspection device, an item inspection system, and an item inspection system program that, when installed on a production line that produces a wide variety of products, can determine in advance whether the product type can be identified. [Means for solving the problem]

[0012] The article inspection device according to the present invention includes an inspection unit (2) that detects physical property values ​​of an article (Wc), a quality determination unit (35) that determines whether the article is good or bad based on the physical property values ​​detected by the inspection unit, a memory unit (4) that stores, for each type of article, characteristic values ​​based on the physical property values ​​that characterize the type of the article, and a comparison unit (38) that compares one characteristic value with another characteristic value among the multiple characteristic values ​​stored in the memory unit. When the storage unit newly stores the characteristic values ​​calculated using a sample of the product of a new variety, The apparatus includes an identification / determination unit (39) that determines whether the variety of the one characteristic value and the variety of the other characteristic value are distinguishable based on the comparison result by the comparison unit, and an output unit (5) that outputs the determination result by the identification / determination unit.

[0013] With this configuration, the product inspection device of the present invention can compare one characteristic value with another characteristic value among multiple characteristic values ​​stored in the memory unit, thereby determining whether the variety of one characteristic value can be distinguished from the variety of another characteristic value, and can output the determination result. As a result, if a determination result is obtained that a product type with one characteristic value cannot be distinguished from a product type with another characteristic value, it is possible to prevent mixing of the other product types by, for example, reviewing the cleaning plan and expanding the cleaning range to be performed between the production of the product type with one characteristic value and the production of the product type with another characteristic value beyond the normal cleaning range, increasing the number of cleaning locations, etc. Furthermore, by allocating the production of the product type with one characteristic value and the production of the product type with another characteristic value to separate production lines, it is possible to prevent mixing of the other product types.

[0014] In addition, in the item inspection device according to the present invention, the comparison unit is configured to compare, among the multiple characteristic values ​​stored in the memory unit, characteristic values ​​that have already been stored with newly stored characteristic values.

[0015] With this configuration, the product inspection device according to the present invention can know in advance whether a product type to be newly produced on the same production line can be distinguished from products that have already been registered.

[0016] In addition, in the item inspection device according to the present invention, the comparison unit is configured to compare each of the plurality of characteristic values ​​already stored in the memory unit with the newly stored characteristic value.

[0017] With this configuration, when there are multiple varieties already registered, the product inspection device of the present invention can know in advance whether a new variety to be produced on the same production line as these varieties can be distinguished from all of the multiple varieties already registered.

[0018] The product inspection device according to the present invention also includes a ratio calculation unit (138) that calculates the ratio at which the variety of the one characteristic value can be distinguished from the variety of the other characteristic value as a result of the comparison by the comparison unit, and the output unit is configured to output the ratio calculated by the ratio calculation unit as the judgment result by the identification judgment unit or in addition to the judgment result.

[0019] With this configuration, the product inspection device according to the present invention can digitize the degree of discrimination between varieties with one characteristic value and varieties with other characteristic values ​​by outputting the rate at which varieties with one characteristic value can be distinguished from varieties with other characteristic values ​​as the judgment result or in addition to the judgment result. This makes it possible to specify in more detail measures to prevent the mixing of other varieties from the digitized judgment result, and to take efficient countermeasures.

[0020] The article inspection device according to the present invention is also configured to be able to delete some or all of the plurality of characteristic values ​​already stored in the storage unit.

[0021] With this configuration, the product inspection device according to the present invention can organize the characteristic values ​​stored in the storage unit, for example, by deregistering a product type that is no longer being produced on the production line.

[0022] In addition, in the item inspection device according to the present invention, the comparison unit is configured to compare the characteristic values ​​that are not to be deleted with the newly stored characteristic values ​​when attempting to delete some of the multiple characteristic values ​​that have already been stored.

[0023] With this configuration, when multiple varieties are registered, the product inspection device of the present invention can determine which variety needs to be deregistered so that the newly registered variety can be distinguished from the other varieties.

[0024] Furthermore, the product inspection system according to the present invention is a product inspection system that judges whether the product (Wc) is good or bad based on the physical property values ​​detected by an inspection unit (2) that detects the physical property values ​​of the product, and stores characteristic values ​​based on the physical property values ​​that characterize the product type in a memory unit (4) for each product type; The characteristic values ​​calculated using a sample of the new variety of the product the storage unit When a new value is stored, the storage unit The apparatus is configured to compare one characteristic value with another characteristic value among a plurality of characteristic values ​​stored in the apparatus, determine whether or not the variety of the one characteristic value can be distinguished from the variety of the other characteristic value based on the comparison result, and output the determination result by an output unit (5).

[0025] Furthermore, a program for an article inspection system according to the present invention is a program for an article inspection system for determining whether an article (Wc) is good or bad based on physical property values ​​detected by an inspection unit (2) that detects physical property values ​​of the article (Wc), and includes the steps of causing a computer to store, for each type, characteristic values ​​based on the physical property values ​​that characterize the type of the article in a storage unit (4); The characteristic values ​​calculated using a sample of the new variety of the product the storage unit When a new value is stored, the storage unit The system is configured to execute the steps of: comparing one characteristic value with another characteristic value among a plurality of characteristic values ​​stored in the storage unit; determining whether or not the variety of the one characteristic value can be distinguished from the variety of the other characteristic value based on the comparison; and outputting the determination result by an output unit (5). [Effects of the Invention]

[0026] According to the present invention, it is possible to provide an item inspection device, an item inspection system, and an item inspection system program that, when installed on a production line that produces a wide variety of products, can determine in advance whether the product type can be identified. [Brief explanation of the drawings]

[0027] [Figure 1] FIG. 1 is a schematic diagram of an article inspection device according to a first embodiment of the present invention. [Figure 2] FIG. 2 is a diagram showing an example of correlations between characteristic values ​​for each product type. [Figure 3] FIG. 3 is a diagram showing an example of the result of the identification and determination process in the article inspection device according to the first embodiment of the present invention. [Figure 4] FIG. 4 is a flowchart illustrating the flow of the identification and determination process in the article inspection device according to the first embodiment of the present invention. [Figure 5] FIG. 5 is a diagram showing the configuration of the identification control unit of an article inspection apparatus according to the second embodiment of the present invention. [Figure 6] 6A and 6B are diagrams showing the discrimination rate as a result of the discrimination judgment process between two varieties in an item inspection device according to the second embodiment of the present invention, where (a) is a diagram showing an example where the discrimination rate is high, and (b) is a diagram showing an example where the discrimination rate is low. [Figure 7] 7A and 7B are diagrams showing the identifiable rate as a result of the identification and determination process for a newly registered variety compared to two already registered varieties in an item inspection device according to the second embodiment of the present invention, where (a) shows an example in which the identifiable rate is high, and (b) shows an example in which the identifiable rate is low. [Figure 8] FIG. 8 is a diagram showing the configuration of an operation and display unit of an article inspection device according to the third embodiment of the present invention. [Figure 9] Figure 9 is a conceptual diagram of an example in which identification and judgment processing is performed by a device outside the item inspection device, where (a) is a diagram showing an example in which there is a one-to-one relationship between the item inspection device and the device that performs the identification and judgment processing, and (b) is a diagram showing an example in which multiple item inspection devices are centrally managed by one device that performs the identification and judgment processing. DETAILED DESCRIPTION OF THE INVENTION

[0028] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0029] (First embodiment) An article inspection apparatus according to a first embodiment of the present invention will be described with reference to Figures 1 to 4. In this embodiment, an X-ray inspection apparatus will be used as an example of the article inspection apparatus.

[0030] In this embodiment, an example will be described in which an article inspection device is provided in a production line that produces a wide variety of solid dosage forms and that produces tablet sheets in which tablets are contained in sheets as final products. Furthermore, in this embodiment, an example will be described in which an article inspection device is provided in the production line in a process after a plurality of tablets have been contained in a packaging sheet.

[0031] In a production line for producing solid dosage forms, raw powder is processed and treated sequentially through multiple pieces of formulation equipment to produce tablets as the final product.In addition, in a production line for producing solid dosage forms, methods such as the kangaroo system using an unmanned guided vehicle or the pneumatic bar chain system are often used to transport the solid dosage forms during processing.

[0032] As described above, a production line for producing a solid dosage form passes through a plurality of formulation facilities and uses a special transfer method, so the production line becomes long and complicated.

[0033] As shown in FIG. 1, the article inspection device 1 includes an inspection unit 2, a control unit 3, a storage unit 4, a display operation unit 5, and a sorting unit 6.

[0034] [Inspection Department] The inspection unit 2 includes a transport means 20 for transporting an object W to be inspected as an item to be inspected, an X-ray source 21 for generating X-rays, and an X-ray sensor 22 for detecting the X-rays as a physical property value. The transport means 20, the X-ray source 21, and the X-ray sensor 22 are housed in a housing (not shown).

[0035] This embodiment is an example in which a tablet sheet is used as the inspection object W, in which a plurality of tablets are arranged in multiple rows as the contents Wc, and the tablets are contained in a sheet as a container Ws. Specifically, pockets P are formed in the sheet as the container Ws, and each of the pockets P contains one tablet as the contents Wc, and the opening side of the pocket P is sealed. The contents Wc in this embodiment corresponds to the article in the present invention.

[0036] Another example of the object to be inspected W in this embodiment is a continuous wrapping sheet in which a plurality of candies are arranged in a row as the contents Wc and the candies are packaged in a sheet serving as a container Ws. Specifically, the continuous wrapping sheet serving as the container Ws has packaging sections in which each candy is packaged individually. The container Ws is not limited to being a continuous wrapping of multiple candies, but may also be cut at predetermined intervals.

[0037] For example, a belt conveyor can be used as the conveying means 20. For example, a conveyor other than a belt conveyor, such as a top chain conveyor, can also be used as the conveying means 20.

[0038] The X-ray source 21 and the X-ray sensor 22 are arranged facing each other and spaced apart from each other in the vertical direction with the transport means 20 interposed therebetween.

[0039] The X-ray source 21 generates X-rays by irradiating an electron beam from a cathode of an X-ray tube (not shown) installed inside the X-ray source 21 onto an anode target, and shapes the generated X-rays into a substantially triangular screen shape using a slit (not shown). The X-ray source 21 also irradiates the X-rays shaped into the screen-shaped X-ray irradiation field toward the X-ray sensor 22 across the transport direction (left-right direction in FIG. 1).

[0040] The X-ray sensor 22 is an X-ray line sensor in which multiple detection elements (not shown) are arranged in a line. The detection elements of the X-ray sensor 22 are composed of a photodiode (not shown) and a scintillator (not shown) provided on the photodiode, and the scintillator converts X-rays into light, which is then detected by the photodiode. The multiple detection elements of the X-ray sensor 22 are arranged linearly on a plane parallel to the conveying surface of the conveying means 20, in a direction perpendicular to the conveying direction of the conveying means 20.

[0041] The X-ray sensor 22 configured in this manner outputs an X-ray image corresponding to the amount (detection level) of X-rays transmitted through the object W to be inspected as the object W passes through the X-ray sensor 22. The X-ray sensor 22 is equipped with an A / D conversion unit (not shown), which converts the brightness value data from the photodiode into digital data. The data output from the A / D conversion unit may be an X-ray image (brightness image) represented by brightness values, or an X-ray image (grayscale image) represented by shades of gray based on density values ​​obtained by converting brightness values ​​to a desired density. In this embodiment, the X-ray image output from the A / D conversion unit of the X-ray sensor 22 is a shades of gray image in which the detection level is represented by shades of gray.

[0042] [Control Unit] The control unit 3 includes an image processing control unit 30, an inspection control unit 31, and an identification control unit 32.

[0043] The image processing control unit 30 has an X-ray image storage means 33 and an image processing means 34. The X-ray image storage means 33 stores the X-ray image input from the X-ray sensor 22.

[0044] The image processing means 34 performs image processing such as synthesis and applying various image processing algorithms to the X-ray images read out from the X-ray image storage means 33. An image processing algorithm is a combination of multiple image processing filters. In this embodiment, the image processing means 34 performs image processing on the X-ray images read out from the X-ray image storage means 33 such that the container Ws of the inspection object W is removed and only the contents Wc are extracted.

[0045] The inspection control unit 31 has a pass / fail determination means 35 as a pass / fail determination unit, and a sorting control means 36. The pass / fail determination means 35 determines whether the shape of the object W to be inspected is pass / fail based on the area value, volume value, complexity, etc. of the object W to be inspected for the X-ray image processed by the image processing means 34, and also distinguishes between the object W to be inspected and foreign matter to determine whether foreign matter is present.

[0046] The area value is the area value on an X-ray image of the object W or the contents Wc that are the object to be inspected in the object W, and the number of pixels that form an image area within a predetermined density range is calculated as the contents Wc. The volume value is the volume value on an X-ray image of the object W or the contents Wc that are the object to be inspected in the object W, and is calculated from the area value of the area corresponding to the contents Wc and the density or the integrated value of the density of each pixel. The complexity value is a value that represents the complexity of the shape on an X-ray image of the object W or the contents Wc that are the object to be inspected in the object W, and is calculated, for example, by dividing the area value by the square of the perimeter.

[0047] The area or volume value of the object W or the contents Wc increases or decreases due to changes in the area or volume of the object W or the contents Wc caused by manufacturing defects or chipping of the object W or the contents Wc. The complexity of the object W or the contents Wc increases or decreases due to unevenness caused by chipping of parts of the object W or the contents Wc.

[0048] Foreign matter mixed into the object W to be inspected is determined by the size of the part in the X-ray image where the amount of X-ray transmission has a different distribution of shades from the rest, for example, the number of pixels in the image area where the density is different from the rest, or the number of pixels in the edge part where the shade changes suddenly.

[0049] The pass / fail judgment means 35 judges the pass / fail of the shape of the inspected object W or the contents Wc based on the area value, volume value, or complexity, and makes the pass / fail judgment by comparing it with upper and lower limit values ​​as pass / fail judgment threshold values.

[0050] The pass / fail determining means 35 determines whether or not there is any foreign matter mixed in the object W or the contents Wc by comparing the object W or the contents Wc with a foreign matter detection limit serving as a pass / fail determination threshold.

[0051] The sorting control means 36 receives the judgment result of the quality judgment means 35 and controls the driving of the sorting means 61 of the sorting unit 6 in accordance with the judgment result.

[0052] Here, the sorting section 6 is configured to include a conveying means 60 that conveys the inspection object W that has passed through the inspection section 2, and a sorting means 61 that selects the inspection object W according to the judgment result of the pass / fail judgment means 35 by switching the conveying path of the inspection object W in the conveying means 60.

[0053] The sorting means 61 is made up of an actuator such as a motor, and is driven based on instructions from the sorting control means 36 .

[0054] If the judgment result of the pass / fail judgment means 35 is NG, i.e., poor shape or foreign matter is present, the sorting control means 36 controls the sorting means 61 to switch the transport path for the inspected object W in the transport means 60 to the discharge path for NG products (shown by the dashed line in Figure 1) so that the NG inspected object W is discharged as an NG product in the sorting section 6.

[0055] The discrimination control section 32 includes a characteristic value calculation means 37, a comparison means 38 as a comparison section, and a discrimination determination means 39 as a discrimination determination section.

[0056] The characteristic value calculation means 37 is configured to calculate a characteristic value based on a physical property value that characterizes the type of contents Wc in the inspection object W. For example, the characteristic value calculation means 37 can calculate the characteristic value of each type based on an X-ray image obtained by the image processing means 34 by passing a predetermined number of inspection objects W for each type of contents Wc through the inspection unit 2.

[0057] In this embodiment, the characteristic values ​​include area values, volume values, complexity values ​​used to determine the quality of the contents Wc, and upper and lower limit values ​​as quality determination thresholds used for each quality determination, and differ depending on the type of contents Wc.

[0058] These upper and lower limit values ​​are set, for example, as values ​​obtained by carrying out a test inspection in which a predetermined number of good samples are passed through the inspection unit 2, and the minimum and maximum values ​​of the area value, volume value, and complexity of the contents Wc obtained are set with a predetermined margin added.

[0059] If there are production or quality control standards for the contents Wc, upper and lower limit values ​​may be set as pass / fail judgment thresholds based on those standards.

[0060] Then, when a test inspection is performed in which a predetermined number of defective product samples are fed into the inspection unit 2 and the product is judged as NG, it is confirmed that the upper and lower limit values ​​set as the pass / fail judgment thresholds are valid values, and actual production can be started.

[0061] In this way, the characteristic values ​​are calculated based on the area value, volume value, and complexity of the contents Wc obtained by processing the X-ray images obtained by running a predetermined number of samples of the test object W containing the contents Wc of the variety to be newly produced through the inspection unit 2 before the start of actual production of a large amount of the test object W.

[0062] In the article inspection device 1 of this embodiment, which is installed in a production line that produces a wide variety of products, the above-mentioned characteristic values ​​are stored for each type of content Wc in the memory unit 4. As a result, the types stored in the memory unit 4 are registered in the article inspection device 1 as types produced on the production line on which the article inspection device 1 is installed.

[0063] The comparison means 38 is configured to compare a characteristic value of one product type (hereinafter referred to as "one characteristic value") that is the same type used for determining pass / fail among the plurality of characteristic values ​​stored in the storage unit 4 with a characteristic value of the same type of another product type (hereinafter referred to as "another characteristic value"). Specifically, the comparison means 38 compares one characteristic value that has already been stored among the plurality of characteristic values ​​stored in the storage unit 4 with another newly stored characteristic value.

[0064] Furthermore, when there are two or more characteristic values ​​already stored in the memory unit 4, the comparison means 38 compares each of the multiple characteristic values ​​already stored in the memory unit 4 with the newly stored characteristic value.

[0065] The identification and determination means 39 determines whether or not a variety having one characteristic value can be distinguished from a variety having another characteristic value as a result of the comparison by the comparison means 38. Specifically, the identification and determination means 39 determines whether or not an already registered variety can be distinguished from a newly registered variety as a result of the comparison between a variety characterized by an already stored characteristic value and a variety characterized by a newly stored characteristic value.

[0066] Here, the determination by the identification and determination means 39 will be explained using a specific example shown in Figures 2 and 3. Figures 2 and 3 show an example in which product types A and B have already been registered in the product inspection device 1, and a new product type C is to be registered.

[0067] As shown in Figure 2, the ranges defined by the upper and lower limit characteristic values ​​of already registered product types A and B do not overlap, i.e., the ranges that are determined to be OK products in the pass / fail judgment by the pass / fail judgment means 35. As a result, the already registered product types A and B are determined to be distinguishable from each other.

[0068] In contrast, the newly registered type C has a range that is determined to be a good product in the pass / fail judgment that slightly overlaps with type A. For example, even if the ranges that are determined to be good products overlap, as in the case of types A and C shown in FIG. 2, the types may be considered to be distinguishable from each other if the overlap rate is equal to or less than a predetermined value. In this case, types A and C are determined to be distinguishable from each other. Note that if the ranges that are determined to be good products overlap even partially, regardless of the overlap rate, the types may be determined to be indistinguishable from each other.

[0069] Furthermore, the range of newly registered product type C that is judged to be OK in the quality assessment partially overlaps with product type B, and this overlapping range is larger than the overlapping range between product types A and C. In this case, product types B and C are judged to be indistinguishable from each other.

[0070] In the example shown in Figure 2, the relationship between product types A, B, and C is as shown in the table in Figure 3, and because there is a high possibility that product type C cannot be distinguished from product type B, various measures are taken to prevent product types B and C from being mixed together. These measures include, for example, creating a cleaning plan to expand the scope of cleaning of the production line carried out between the production of product types B and C beyond the normal cleaning scope or to increase the number of cleaning locations, or creating a production plan to allocate product types B and C to different production lines. In Figure 3, "◯" indicates that the product types are distinguishable from each other, and "×" indicates that the product types are indistinguishable from each other.

[0071] In addition, in the judgment by the identification judgment means 39, it may be determined that the varieties are distinguishable from each other if it is determined that they are distinguishable in at least one of the characteristic values ​​calculated based on the area value, volume value, and complexity of the contents We, or it may be determined that the varieties are distinguishable from each other if it is determined that they are distinguishable in all of the characteristic values ​​calculated based on the area value, volume value, and complexity of the contents We.

[0072] 1, the display operation unit 5 is configured with, for example, a touch panel display, and receives operations from the user and displays and outputs to the user. The display operation unit 5 is used by the user to input settings such as various parameters and to select an inspection mode, etc.

[0073] The display operation unit 5 displays inspection results such as the pass / fail judgment result of the inspected object W, the total number of inspections, the number of good products, and the total number of NG products, as well as the judgment result by the identification judgment means 39, such as "identifiable" or "unidentifiable." The display form of the judgment result by the identification judgment means 39 is not limited to characters, but may be symbols or other display formats such as a table format combining characters and symbols as shown in Fig. 3. The display operation unit 5 of this embodiment constitutes the output unit of the present invention.

[0074] [Identification and Judgment Processing] Next, the identification and determination process executed by the control unit 3 of the article inspection device 1 will be described with reference to FIG.

[0075] As shown in Figure 4, in step S1, when a test inspection is performed on a variety to be newly produced in the item inspection device 1 (referred to as a "newly registered variety" in Figure 4), the control unit 3 determines whether the number of inspected objects W that have passed through the inspection unit 2 in the test inspection has reached a predetermined number of samples (step S2).

[0076] If the control unit 3 determines in step S2 that the number of inspection objects W that have passed through the inspection unit 2 has not reached the predetermined number of samples, the control unit 3 returns the process to step S1.

[0077] If the control unit 3 determines in step S2 that the number of test objects W that have passed through the inspection unit 2 has reached a predetermined number of samples, it calculates the characteristic values ​​of the newly registered variety based on the area value, volume value, and complexity of the test objects W obtained in the test inspection (step S3).

[0078] Next, the control unit 3 compares the characteristic values ​​of the product types already stored in the storage unit 4 (referred to as "registered product types" in FIG. 4) with the characteristic values ​​of the newly registered product type (step S4).

[0079] Based on the comparison result in step S4, the control unit 3 determines whether the registered variety and the newly registered variety are distinguishable (step S5). If the control unit 3 determines in step S5 that the registered variety and the newly registered variety are distinguishable, the control unit 3 controls the display operation unit 5 to display "distinguishable" indicating that the newly registered variety is distinguishable from the registered variety (step S6).

[0080] If the control unit 3 determines in step S5 that the registered variety and the newly registered variety are indistinguishable, it controls the display operation unit 5 to display "indistinguishable" to indicate that the newly registered variety is indistinguishable from the registered variety (step S7).

[0081] [Action and effect] As described above, the article inspection device according to this embodiment is configured to compare one characteristic value with another characteristic value among the plurality of characteristic values ​​stored in the memory unit 4. Specifically, it is configured to compare a characteristic value that has already been stored among the plurality of characteristic values ​​stored in the memory unit 4 with a newly stored characteristic value.

[0082] With this configuration, the product inspection device of this embodiment can determine whether the variety of characteristic values ​​that have already been stored and the variety of characteristic values ​​that have been newly stored are distinguishable, and can output the determination result via the display operation unit 5.

[0083] Furthermore, the product inspection device according to this embodiment can determine in advance whether a product type to be newly produced on the same production line can be distinguished from already registered product types.

[0084] As a result, if a determination result is obtained that the product type with the already stored characteristic values ​​and the product type with the newly stored characteristic values ​​cannot be distinguished, i.e., they are indistinguishable, it is possible to prevent mixing of other product types by, for example, reviewing the cleaning plan and expanding the cleaning range to be performed between the production of the product type with the already stored characteristic values ​​and the production of the product type with the newly stored characteristic values ​​beyond the normal cleaning range, increasing the number of cleaning locations, etc. Furthermore, it is possible to prevent mixing of other product types by allocating the production of the product type with the already stored characteristic values ​​and the production of the product type with the newly stored characteristic values ​​to separate production lines.

[0085] In addition, the item inspection device of this embodiment is configured to compare each of the multiple characteristic values ​​already stored in the memory unit 4 with the newly stored characteristic value.

[0086] With this configuration, when there are multiple varieties already registered, the product inspection device of this embodiment can determine in advance whether a new variety to be produced on the same production line as these varieties can be distinguished from all of the multiple varieties already registered.

[0087] (Modification of the first embodiment) The identification and judgment means 39 may set the upper and lower limit values ​​based on statistical values ​​(for example, maximum value, minimum value, average value, standard deviation, etc.) calculated using characteristic values ​​actually used for pass / fail judgment as characteristic values ​​of registered varieties that have already been stored, and it is also preferable to be able to select whether to use statistical values ​​covering only OK products within a specified range or statistical values ​​covering all products within the specified range including NG products.

[0088] As an example, the identification and judgment means 39 can set the maximum and minimum values ​​of the most recent 5,000 pieces of area values ​​that were actually used to judge whether a product is good or bad as characteristic values ​​of a registered product type that have already been stored as the upper and lower limit values ​​of the characteristic values, respectively.

[0089] As another example, the identification and judgment means 39 can set the upper and lower limit values ​​of the characteristic values ​​of the registered variety that have already been stored as the values ​​obtained by adding and subtracting a variation width of two to three times the standard deviation from the average value of the volume values ​​of all the items actually used for pass / fail judgment in the past day.

[0090] According to this modified example, for a registered variety that has already been stored, statistical values ​​based on characteristic values ​​obtained when the contents Wc of that variety were produced in the past can be used to estimate the possible range of characteristic values ​​of the contents Wc of the previous variety that may be mixed in, thereby allowing for the calculation of a more reliable identification possibility.

[0091] (Second embodiment) Next, a second embodiment of the present invention will be described with reference to FIGS.

[0092] The article inspection device according to this embodiment differs from the article inspection device 1 according to the first embodiment in the configuration of the identification control unit, but other configurations are the same as those of the first embodiment. Therefore, in the following, the same components as those of the first embodiment are denoted by the same reference numerals as those of the first embodiment, and descriptions thereof will be omitted.

[0093] As shown in Figure 5, the identification control unit 132 of the item inspection device of this embodiment is configured to include a characteristic value calculation means 37, a comparison means 38 as a comparison unit, a ratio calculation means 138 as a ratio calculation unit, and an identification judgment means 39 as an identification judgment unit.

[0094] The ratio calculation means 138 is configured to calculate the ratio at which varieties with one characteristic value can be distinguished from varieties with other characteristic values ​​as a result of the comparison by the comparison means 38. For example, the ratio calculation means 138 determines a range (hereinafter referred to as a "non-overlapping range") in which a newly registered characteristic value range defined by upper and lower limit values ​​of the characteristic values ​​of a newly registered variety does not overlap with a registered characteristic value range defined by upper and lower limit values ​​of the characteristic values ​​of varieties that have already been registered. Next, the ratio calculation means 138 calculates the ratio of the non-overlapping range to the registered characteristic value range defined by the upper and lower limit values ​​of the characteristic values ​​of varieties that have already been registered. The ratio calculation means 138 calculates the ratio of the non-overlapping range as the ratio at which varieties with one characteristic value can be distinguished from varieties with other characteristic values.

[0095] For example, if the registered characteristic value range of registered variety A is specified with an upper limit of "150" and a lower limit of "100," and the newly registered characteristic value range of newly registered variety B is specified with an upper limit of "200" and a lower limit of "120," the proportion of the width of the non-overlapping range (the difference between the lower limit of variety B, "120," and the lower limit of variety A, "100"), "20," to the width of the registered characteristic value range (the difference between the upper limit of variety A, "150," and the lower limit of variety A, "100"), "50," is "40%."

[0096] In this embodiment, the identifiable ratio calculated in the non-overlapping range is an estimated value when the characteristic values ​​of the contents We are evenly distributed within the range defined by the upper and lower limits, i.e., when the probability density is assumed to be uniform within this range. Generally, the characteristic values ​​of the produced contents We show a normal distribution, so this estimated value contains an error, but the ratio can be easily calculated with sufficient accuracy for practical purposes.

[0097] In addition, in this embodiment, the above ratio calculated by the ratio calculation means 138 may be displayed on the display operation unit 5 as the judgment result by the identification judgment means 39, or may be displayed on the display operation unit 5 in addition to the judgment result by the identification judgment means 39.

[0098] When the ratio calculated by the ratio calculation means 138 is displayed on the display operation unit 5 in addition to the judgment result by the identification judgment means 39, the identification judgment means 39 can judge that the object is identifiable if the ratio is equal to or greater than a predetermined ratio, and can judge that the object is not identifiable if the ratio is less than the predetermined ratio.

[0099] For example, when the above-mentioned predetermined ratio is set to 90%, as shown in FIG. 6(a), if the ratio at which type A and type B can be distinguished is 95%, a message is displayed on the display operation unit 5 indicating that the ratio at which they can be distinguished is 95% and that they are distinguishable.

[0100] In contrast, as shown in FIG. 6(b), if the rate at which type A and type B can be distinguished is 40%, the display operation unit 5 will display a message indicating that the rate at which they can be distinguished is 40% and that they cannot be distinguished.

[0101] Also in this embodiment, if there are two or more characteristic values ​​already stored in storage unit 4, each of the multiple characteristic values ​​already stored in storage unit 4 is compared with the newly stored characteristic value, and the identifiable ratio of the newly registered variety for each registered variety is calculated, as shown in Figures 7(a) and 7(b), for example. In Figures 7(a) and 7(b), variety A and variety B are mutually distinguishable and are already registered varieties, and variety C is a newly registered variety.

[0102] [Action and effect] As described above, the product inspection device according to this embodiment can quantify the degree of distinction between registered varieties and newly registered varieties by outputting the rate at which registered varieties can be distinguished from newly registered varieties as a judgment result, or in addition to the judgment result, via the display operation unit 5. This makes it possible to specify in more detail, from the quantified judgment result, measures to prevent mixing in of other varieties, and to take efficient countermeasures.

[0103] Therefore, even if it is determined that the object is not identifiable, measures can be taken, such as changing the cleaning content depending on the identifiable rate. For example, if the identifiable rate is high, measures can be taken, such as reducing the cleaning range or cleaning fewer areas, compared to when the identifiable rate is low. Such changes in measures are merely examples, and are not limited to these.

[0104] (Modification of the second embodiment) The ratio calculation means 138 may calculate the ratio at which one variety can be distinguished from another variety based on distribution data of characteristic values ​​obtained from characteristic values ​​that have already been stored and that have actually been used for determining whether a product is good or bad.

[0105] As an example, the ratio calculation means 138 can estimate the probability that the area value of the contents Wc of the previous variety that may be mixed in will not fall within the range defined by the upper and lower limits of the area value of the newly registered variety, based on the frequency distribution of the area values ​​of the most recent 10,000 items or the past day's worth that were actually used to determine whether the product is good or bad as a characteristic value of an already registered variety, and can more specifically quantify the identifiable ratio.

[0106] According to this modified example, the identifiable proportion can be calculated based on the distribution of characteristic values ​​for the production lot of contents Wc that are more likely to be mixed in, and therefore the identifiable proportion for each variety can be updated not only when a new variety is registered, but also each time a variety to be produced is determined according to a production plan.

[0107] (Third embodiment) Next, a third embodiment of the present invention will be described with reference to FIG.

[0108] The article inspection device according to this embodiment differs from the article inspection device 1 according to the first embodiment in the configuration of the display operation unit, but other configurations are the same as those of the first embodiment. Therefore, in the following, the same components as those of the first embodiment will be assigned the same reference numerals as those of the first embodiment and will not be described again. This embodiment can also be applied to the second embodiment.

[0109] 8, the display operation unit 105 of the article inspection device according to this embodiment has a deletion means 50. The deletion means 50 is configured to be able to delete some or all of the multiple characteristic values ​​already stored in the storage unit 4 in response to a user operation.

[0110] In this embodiment, when the deletion means 50 is to delete some of the plurality of characteristic values, the comparison means 38 compares the characteristic values ​​that are not to be deleted with the newly stored characteristic values.

[0111] The discrimination determination means 39 determines whether or not the variety of the characteristic value that is not the object of deletion and the variety to be newly registered can be distinguished from each other as a result of the comparison by the comparison means 38. The result of the determination is displayed on the display operation unit 5.

[0112] [Action and effect] As described above, the product inspection device of this embodiment can delete some or all of the multiple characteristic values ​​already stored in the memory unit 4, making it possible to organize the characteristic values ​​stored in the memory unit 4, for example, by deregistering a variety that is no longer being produced on the production line.

[0113] In addition, in the product inspection device of this embodiment, when the deletion means 50 is to delete some of the multiple characteristic values, the comparison means 38 is configured to compare the characteristic values ​​that are not to be deleted with the newly stored characteristic values.

[0114] With this configuration, the product inspection device of this embodiment can determine, when multiple varieties are registered, which variety needs to be deregistered so that the newly registered variety can be distinguished from the other varieties.

[0115] In each of the above-described embodiments, an example has been described in which the article inspection device of the present invention is applied to an article inspection device 1 installed in a process after multiple tablets are placed in a packaging sheet in a production line that produces a variety of solid dosage forms, but the present invention is not limited to this and may also be applied to an article inspection device installed in another process in the same production line.

[0116] In addition, in the above-described embodiments, examples have been described in which the upper and lower limit values ​​of the pass / fail judgment thresholds used for pass / fail judgment are used as the characteristic values, but this is not limiting, and a physical property value for identifying and specifying the type or an identification index value obtained by arithmetic processing of the physical property value may be used as the characteristic value, separate from the pass / fail judgment threshold. For example, when a predetermined number of samples of the objects to be inspected W are passed through the inspection unit 2, the characteristic values ​​are calculated by adding a predetermined margin to the minimum and maximum values ​​of the area value, volume value, and complexity of the contents Wc obtained, and a value obtained in advance by a method different from the characteristic value is used as the pass / fail judgment threshold.

[0117] Furthermore, even if the area value, volume value, complexity, etc. of the contents Wc obtained as a result of flowing a predetermined number of samples of the test object W into the inspection section 2 are not used for determining whether the test object is good or bad, these characteristic values ​​may be set as identification index values.

[0118] Here, the "characteristic value" that characterizes the type of contents Wc is not limited to area value, volume value, or complexity, as long as it is an index value that can characterize the type of contents Wc, and there is no prohibition on applying a characteristic value that is solely intended to characterize the type of contents Wc.

[0119] Furthermore, in the above-described embodiments, an example has been described in which the identification control unit 32 is provided in the article inspection apparatus 1, but this is not limiting. For example, as shown in FIG. 9(a), all or part of the functions of the identification control unit 32 may be provided in an external computer 200 connected to the article inspection apparatus 101. Furthermore, the determination results by the identification control unit 32 may be configured to be displayed on the screen of the computer 200, or the memory unit 4 may be provided in the computer 200. In this case, the control unit 103 of the article inspection apparatus 101 does not include the functions of the identification control unit 32.

[0120] According to the example shown in Figure 9(a), the computer 200 receives various parameters including characteristic values ​​required by the identification control unit 32 from the existing item inspection device 101 and performs identification judgment processing, so that the item inspection system of the present invention can be applied to a production line configured with an existing item inspection device 101.

[0121] 9(b), multiple article inspection devices 101 may be connected to each other so as to be able to send and receive data, and all or part of the functions of the identification control unit 32 may be provided in a computer 300 that centrally manages the multiple article inspection devices 101. The multiple article inspection devices 101 may be provided, for example, in different production lines.

[0122] According to the example shown in FIG. 9(b), the determination result by the discrimination control unit 32 can be received, and the allocation of the production line can be easily performed.

[0123] Furthermore, in each of the above-described embodiments, an example has been described in which the object inspection device is an X-ray inspection device, but it may also be an appearance inspection device using a camera, etc., and it may also be applied to other object inspection devices such as weight measuring devices (weight sorting devices) and metal detection devices that can obtain characteristic values ​​of objects, and it may also be applied to combinations of these devices.

[0124] Furthermore, in each of the above-described embodiments, "tablets" have been used as an example of the type of product to be determined as to whether they are distinguishable from one another, but this is not limited to this, and the invention can also be applied to, for example, capsules or other forms of products, i.e., foods that are processed from raw materials and filled into containers or packaged in packaging material.

[0125] While an embodiment of the present invention has been disclosed, it will be apparent to one skilled in the art that modifications may be made thereto without departing from the scope of the present invention, and it is intended that all such modifications and equivalents be included in the following claims. [Explanation of symbols]

[0126] 1, 101 Item inspection equipment 2. Inspection Department 3, 103 Control section 4 Storage section 5, 105 Display operation unit (output unit) 6. Sorting Department 20 Transportation 21 X-ray source 22 X-ray sensor 30 Image processing control unit 31 Inspection control section 32, 132 Identification control section 33 X-ray image storage means 34 Image processing means 35. Good / bad judgment means (good / bad judgment unit) 36 Selection control measures 37 Characteristic value calculation means 38 Comparison means (comparison part) 39 Identification and determination means (identification and determination unit) 50 Removal Method 60 Transportation 61 Selection methods 138 Ratio calculation means (ratio calculation unit) 200, 300 computers W Inspection object Wc Contents (articles) Ws Containment Facility P pocket

Claims

1. an inspection unit (2) for detecting the physical properties of an article (Wc); a quality determination unit (35) that determines whether the article is good or bad based on the physical property values ​​detected by the inspection unit; a storage unit (4) for storing, for each product type, characteristic values ​​based on physical property values ​​that characterize the product type; a comparison unit (38) that compares one characteristic value with another characteristic value among the plurality of characteristic values ​​stored in the storage unit; an identification / determination unit (39) that, when the storage unit newly stores the characteristic values ​​calculated using a sample of the article of a new type, determines whether the type of the one characteristic value and the type of the other characteristic value are distinguishable as a result of comparison by the comparison unit; and an output unit (5) that outputs the determination result from the identification determination unit.

2. 2. The object inspection device according to claim 1, wherein the comparison unit compares a characteristic value that has already been stored with a newly stored characteristic value among the plurality of characteristic values ​​stored in the memory unit.

3. 3. The object inspection device according to claim 1, wherein the comparison unit compares each of the plurality of characteristic values ​​already stored in the memory unit with the newly stored characteristic value.

4. a ratio calculation unit (138) that calculates a ratio at which the variety of the one characteristic value and the variety of the other characteristic value are distinguishable as a result of the comparison by the comparison unit, 4. The object inspection device according to claim 1, wherein the output unit outputs the ratio calculated by the ratio calculation unit as the judgment result by the identification judgment unit or in addition to the judgment result.

5. 5. The object inspection device according to claim 2, wherein a part or all of the plurality of characteristic values ​​already stored in the storage unit can be deleted.

6. An object inspection device as described in any one of claims 3 to 5, characterized in that when attempting to delete some of the multiple characteristic values ​​already stored, the comparison unit compares the characteristic values ​​not to be deleted with the newly stored characteristic values.

7. An object inspection system that judges whether an object (Wc) is good or bad based on physical property values ​​detected by an inspection unit (2) that detects physical property values ​​of the object (Wc), storing characteristic values ​​based on physical property values ​​characterizing the product type in a storage unit (4) for each product type; When the storage unit newly stores the characteristic values ​​calculated using a sample of the product of a new variety, one characteristic value is compared with another characteristic value among the plurality of characteristic values ​​stored in the storage unit; As a result of the comparison, it is determined whether the product type having the one characteristic value and the product type having the other characteristic value can be distinguished, and the result of the determination is output by an output unit (5).

8. A program for an article inspection system that judges whether an article (Wc) is good or bad based on physical property values ​​detected by an inspection unit (2) that detects physical property values ​​of the article (Wc), On the computer, a step of storing characteristic values ​​based on physical property values ​​characterizing the type of the article in a storage unit (4) for each type; a step of comparing one characteristic value with another characteristic value among the plurality of characteristic values ​​stored in the storage unit when the characteristic values ​​calculated using a sample of the article of a new variety are newly stored in the storage unit; a step of determining whether or not the variety of the one characteristic value and the variety of the other characteristic value can be distinguished as a result of the comparison; and outputting the determination result by an output unit (5).

Images