Inspection system for textile machinery

Abstract

The invention provides an inspection system for a textile machine, which can reduce the data capacity stored in a storage part and can acquire the distribution of the abnormal degree of the textile machine. An inspection system for a textile machine is provided with: a classification unit that detects the degree of abnormality of the textile machine on the basis of newly acquired captured images, and classifies the newly acquired captured images into any one of a plurality of groups on the basis of the detected degree of abnormality of the textile machine; a storage unit that stores captured images for each group; a counting unit that counts the number of captured images classified into a target group, which is a group in which newly acquired captured images are classified, and stores the counted number of captured images in a storage unit; and a screening unit that determines whether or not to replace the captured image of the target group stored in the storage unit with a newly acquired captured image when the number of captured images of the target group stored in the storage unit reaches a predetermined upper limit number.

Description

TECHNICAL FIELD

[0001] The present application relates to an inspection system of a fiber machine. BACKGROUND

[0002] In Patent Literature 1, an opening defect detection device of a loom that detects an opening defect of a warp yarn is disclosed. The opening defect detection device of the loom is provided with a camera that captures an opening of the warp yarn, and a control device that detects an opening defect based on a captured image captured by the camera. The captured image is stored in a storage section of the control device.

[0003] The inspection system described in Patent Literature 2 is provided with a capturing section that captures a workpiece, a storage section that stores an image captured by the capturing section, a first determination section that determines whether or not the workpiece exhibited in the image is a defective product, and a second determination section that determines whether or not to cause the storage section to store the image. The distribution of measured values in the inspection of the workpiece that has been determined to be a good product in the past by the first determination section is divided into N regions. In a case where the number of images saved in the region to which the measured value measured in the inspection belongs among the N regions is less than a prescribed number of images, the second determination section causes the storage section to store the image.

[0004] Patent Literature 1: Japanese Patent Application Publication No. 2020-196972

[0005] Patent Literature 2: Japanese Patent Application Publication No. 2021-144000

[0006] In Patent Literature 1, in a case where the capturing by the camera is continuously performed in the operation of the loom, the captured images become a large number. Therefore, if all of the captured images are to be saved, there is a pressure on the storage capacity of the storage section. For example, as in Patent Literature 2, it is considered to reduce the data capacity stored in the storage section by setting an upper limit to the number of captured images to be saved. However, in this case, the number of captured images in each region is not clear, and therefore it is not possible to obtain the distribution of captured images in the entire region. Therefore, it is difficult to grasp the state of the inspection object. SUMMARY

[0007] An inspection system for a fiber machine that solves the above problems inspects a fiber machine based on a captured image by a camera, and the gist of the inspection system for the fiber machine is to have: a classification unit that detects an abnormality degree of the fiber machine based on a newly acquired captured image, and classifies the newly acquired captured image into any one of a plurality of groups based on the detected abnormality degree of the fiber machine; a storage unit that stores the captured image for each of the groups; a counting unit that counts the number of captured images classified into an object group to which the newly acquired captured image is classified, and stores the counted number of captured images in the storage unit; and a screening unit that determines whether the number of captured images of the object group stored in the storage unit reaches a prescribed upper limit number, stores the newly acquired captured image as the captured image of the object group in the storage unit in a case where it is determined that the number of captured images of the object group stored in the storage unit does not reach the prescribed upper limit number, and determines whether to replace the captured image of the object group stored in the storage unit with the newly acquired captured image in a case where it is determined that the number of captured images of the object group stored in the storage unit reaches the prescribed upper limit number.

[0008] According to the above structure, in a case where the number of captured images of the object group stored in the storage unit reaches the prescribed upper limit number, the screening unit determines whether to replace the captured image of the object group stored in the storage unit with the newly acquired captured image. Thus, the number of captured images of each group stored in the storage unit is limited to not exceed the upper limit number, and therefore it is possible to reduce the data capacity stored in the storage unit. In addition, the counting unit counts the number of captured images classified into the object group, and stores the counted number of captured images in the storage unit. Thus, even if all captured images are not saved, it is possible to acquire the distribution of the abnormality degree of the fiber machine. Therefore, it is possible to reduce the data capacity stored in the storage unit and acquire the distribution of the abnormality degree of the fiber machine.

[0009] In the above inspection system for the fiber machine, the classification unit can calculate the abnormality degree of the fiber machine as a score, and classify the captured image into any one of the plurality of groups based on the calculated score.

[0010] According to the above structure, it is possible to more finely detect the abnormality degree of the fiber machine, for example, compared to a case where the abnormality degree of the fiber machine is hierarchically detected as S·A·B·C / excellent·good·pass·fail, and the like.

[0011] In the above fiber machine inspection system, the classification section can be configured to calculate the score in such a manner that the higher the degree of abnormality of the fiber machine, the lower the score, and the screening section can replace the photographed image having the highest score among the photographed images of the object group stored in the storage section with the newly acquired photographed image in a case where the score of the newly acquired photographed image is lower than the score of the photographed image having the highest score among the photographed images of the object group stored in the storage section.

[0012] According to the above configuration, the photographed image having a low score, i.e., the photographed image of the fiber machine having a high degree of abnormality, is preferentially stored in the storage section. Therefore, it is easier to effectively use the photographed images when investigating the cause of the abnormality of the fiber machine than in a case where the photographed image having a high score, i.e., the photographed image of the fiber machine having a low degree of abnormality, is preferentially stored in the storage section.

[0013] In the above fiber machine inspection system, the classification section can be configured to further classify the photographed image into any of the plurality of groups based on the time of photographing of the photographed image.

[0014] According to the above configuration, it is possible to acquire the time progression of the distribution of the degree of abnormality of the fiber machine.

[0015] In the above fiber machine inspection system, the display section can be configured to display a table indicating the number of photographed images classified into each group.

[0016] According to the above configuration, it is easier for the operator to grasp the distribution of the degree of abnormality of the fiber machine.

[0017] In the above fiber machine inspection system, the display section can be configured to display the table in the form of a heat map according to the number of photographed images classified into each group.

[0018] According to the above configuration, it is easier for the operator to grasp the distribution of the degree of abnormality of the fiber machine.

[0019] According to the present application, it is possible to reduce the data capacity stored in the storage section and acquire the distribution of the degree of abnormality of the fiber machine. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 is a block diagram indicating the configuration of a fiber machine inspection system.

[0021] Figure 2 is a schematic view indicating one example of a photographed image of a camera.

[0022] Figure 3 is a block diagram indicating functional elements of a control device.

[0023] Figure 4 This is a flowchart showing a process of saving a captured image performed by the control device.

[0024] Figure 5 This is a diagram showing an example of data stored in the auxiliary storage device.

[0025] Figure 6 This is a schematic diagram showing an example of a table displayed on the display unit.

[0026] Figure 7 Schematic diagram showing an example of a captured image displayed on the display unit.

[0027] Description of Reference Signs

[0028] 10 ...Textile machinery inspection system; 11 ...Camera; 15 ...Auxiliary storage device serving as a storage unit; 17 ...Display unit; 41 ...Classification unit; 42 ...Counting unit; 43 ...Sorting unit; P ...Photographed image; H ...Table. DETAILED DESCRIPTION

[0029] The following, according to Figures 1-7 An embodiment of a specific inspection system for a textile machine will be described. The inspection system for a textile machine of this embodiment is applied to a loom as a textile machine. In the following description, the inspection system for a textile machine will be simply referred to as an "inspection system."

[0030] Loom

[0031] like Figure 1 As shown in FIG. 1 , the loom 100 includes a base 101. The base 101 includes a weft insertion nozzle and a main shaft 102 (not shown). The weft insertion nozzle is provided at the first end in the width direction of the base 101. The loom 100 of this embodiment is an air jet loom. The weft insertion nozzle ejects air from the first end toward the second end in the width direction of the base 101, thereby adjusting the opening Ta (refer to FIG. 1 ) of the warp yarn T. Figure 2 ) inserts the weft yarn. The main shaft 102 is driven by a motor (not shown). The timing at which the weft insertion nozzle inserts the weft yarn corresponds to the rotation angle of the main shaft 102. Specifically, the weft insertion nozzle inserts the weft yarn when the main shaft 102 rotates by a predetermined first angle from a predetermined reference angle.

[0032] The loom 100 includes an angle detection unit 103 and a signal output unit 104. The angle detection unit 103 detects the rotation angle of the main shaft 102. The angle detection unit 103 is, for example, a rotary encoder. The angle detection unit 103 is connected to the signal output unit 104. The angle detection unit 103 transmits the detected rotation angle of the main shaft 102 to the signal output unit 104. The signal output unit 104 outputs a signal to the control unit 13 of the inspection system 10 whenever the rotation angle of the main shaft 102 received from the angle detection unit 103 reaches a reference angle.

[0033] <Inspection system structure>

[0034] The inspection system 10 includes an imaging device 10a and a computer 10b. The imaging device 10a includes a camera 11, a lighting device 12, and a control unit 13. The computer 10b includes a control device 14, an auxiliary storage device 15 as a storage unit, an input unit 16, and a display unit 17. The inspection system 10 inspects the loom 100 based on images captured by the camera 11.

[0035] For example, when a part of the warp yarn T flies out into the opening Ta (see Figure 7 ), an abnormality has occurred in the loom 100. For example, the greater the amount of warp yarn T that has flown into the opening Ta, or the greater the number of warp yarns T that have flown into the opening Ta, the higher the degree of abnormality in the loom 100. The inspection system 10 of this embodiment inspects the loom 100 based on the warp yarns T shown in the captured image.

[0036] The camera 11 is a digital camera and includes an image sensor. Examples of the image sensor include a CCD image sensor (Charge Coupled Device image sensor) and a CMOS image sensor (Complementary Metal Oxide Semiconductor image sensor).

[0037] The camera 11 is positioned so that it can capture the opening Ta of the warp yarns T. Specifically, the camera 11 is located at the first end, in the width direction of the machine 101, on the side where the weft insertion nozzle is located. The camera 11 captures the opening Ta of the warp yarns T from upstream to downstream in the weft insertion direction. Images captured by the camera 11 are timestamped to indicate the time of capture.

[0038] Figure 2 is a schematic diagram showing an example of an image P captured by the camera 11. Figure 2 The photographed image P shown shows the opening Ta of the warp yarn T. Figure 2 In the captured image P shown, the warp yarns T do not fly out into the sheath Ta.

[0039] The lighting 12 in this embodiment is an LED light. The lighting 12 is installed at a position to illuminate the opening Ta of the warp yarns T. Specifically, the lighting 12 is located at the first end, which is located on the side of the weft insertion nozzle in the width direction of the machine 101. The lighting 12 illuminates the opening Ta of the warp yarns T from the upstream side to the downstream side in the weft insertion direction.

[0040] like Figure 1 As shown, the control unit 13 has a processor 13a and a main storage unit 13b. As the processor 13a, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and a DSP (Digital Signal Processor) can be listed. The main storage unit 13b includes a RAM (Random Access Memory) and a ROM (Read Only Memory). The main storage unit 13b stores program codes or instructions configured to enable the processor 13a to perform processing. The main storage unit 13b, that is, the computer-readable medium includes all available media that can be accessed by general-purpose or special-purpose computers. The control unit 13 can also be composed of hardware circuits such as ASIC (Application Specific Integrated Circuit) and FPGA (Field Programmable Gate Array). The control unit 13 as a processing circuit can include one or more processors that act according to a computer program, one or more hardware circuits such as ASIC or FPGA, or a combination thereof.

[0041] The control unit 13 is connected to the camera 11 and the lighting 12. The control unit 13 controls the timing of image capture by the camera 11 and the timing of light emission by the lighting 12. The control unit 13 is connected to the signal output unit 104 of the loom 100. The signal output by the signal output unit 104 is input to the control unit 13 as an external input signal. By receiving the external input signal, the control unit 13 recognizes the time when the rotation angle of the main shaft 102 reaches the reference angle. Each time the main shaft 102 rotates by a predetermined second angle from the reference angle, the control unit 13 simultaneously outputs a trigger signal to the camera 11 and the lighting 12.

[0042] The camera 11 takes an image when a trigger signal is input from the control unit 13. The lighting 12 emits light when a trigger signal is input from the control unit 13. Since the trigger signals are input simultaneously to the camera 11 and the lighting 12, the camera 11 takes an image of the warp opening Ta while the lighting 12 illuminates the warp opening Ta.

[0043] The control device 14 has a processor 14a and a main storage unit 14b. Examples of the processor 14a include a CPU, a GPU, and a DSP. The main storage unit 14b includes a RAM and a ROM. The main storage unit 14b stores program codes or instructions configured to enable the processor 14a to perform processing. The main storage unit 14b, i.e., the computer-readable medium, includes all available media that can be accessed by a general-purpose or special-purpose computer. The control device 14 can also be composed of hardware circuits such as ASICs and FPGAs. The control device 14 as a processing circuit can include one or more processors that act according to a computer program, one or more hardware circuits such as ASICs or FPGAs, or a combination thereof.

[0044] The control device 14 is connected to an auxiliary storage device 15, an input unit 16, and a display unit 17. The auxiliary storage device 15 is a nonvolatile storage device capable of rewriting data. The auxiliary storage device 15 is, for example, a hard disk drive or a solid-state drive. The input unit 16 is, for example, a keyboard or a mouse. The display unit 17 is a monitor. Furthermore, the control device 14 is connected to the camera 11 of the imaging device 10a. The control device 14 obtains an image captured by the camera 11. In this embodiment, the control device 14 obtains an image from the camera 11 each time the camera 11 captures an image. That is, the control device 14 obtains one image for each capture by the camera 11.

[0045] like Figure 3 As shown, the control device 14 includes a classifier 41, a counter 42, and a filter 43. The classifier 41, the counter 42, and the filter 43 are functional elements that function when the processor 14a executes a program stored in the main storage unit 14b.

[0046] Each time a new captured image is acquired from the camera 11, the classification unit 41 detects the degree of abnormality of the loom 100 based on the newly acquired captured image. The classification unit 41 of this embodiment assigns the detection result of the degree of abnormality of the loom 100 to the captured image. The classification unit 41 classifies the newly acquired captured image into one of a plurality of groups based on the detected degree of abnormality of the loom 100.

[0047] The auxiliary storage device 15 stores captured images for each group.

[0048] The counting unit 42 is configured to count the number of classified captured images for each group. For the group into which the newly acquired captured images are classified, i.e., the target group, the counting unit 42 counts the number of captured images classified into that target group. The counting unit 42 stores the counted number of captured images, i.e., the number of captured images classified into the target group, in the auxiliary storage device 15.

[0049] The filtering unit 43 is configured to determine whether the number of captured images in each group stored in the auxiliary storage device 15 has reached a predetermined upper limit set for each group. The filtering unit 43 determines whether the number of captured images in the target group stored in the auxiliary storage device 15 has reached the predetermined upper limit. In this embodiment, the predetermined upper limit is set to five for each group. Therefore, the filtering unit 43 in this embodiment determines whether the number of captured images in the target group stored in the auxiliary storage device 15 has reached five.

[0050] If the screening unit 43 determines that the number of captured images of the target group stored in the auxiliary storage device 15 has not reached a predetermined upper limit, the screening unit 43 stores the newly acquired captured image as the captured image of the target group in the auxiliary storage device 15. If the screening unit 43 determines that the number of captured images of the target group stored in the auxiliary storage device 15 has reached a predetermined upper limit, the screening unit 43 determines whether to replace the captured image of the target group stored in the auxiliary storage device 15 with the newly acquired captured image. If the predetermined upper limit is two or more, the screening unit 43 determines whether to replace one of the captured images of the target group stored in the auxiliary storage device 15 with the newly acquired captured image.

[0051] <Processing by the Control Device 14>

[0052] The following describes the processing performed by the control device 14. In this embodiment, the control device 14 performs the following processing every time a new captured image is acquired from the camera 11.

[0053] like Figure 4 As shown, in step S1, the classification unit 41 detects the degree of abnormality of the loom 100 based on the warp yarn T shown in the newly acquired captured image from the camera 11. The classification unit 41 of this embodiment calculates the degree of abnormality of the loom 100 as a score. The score is calculated to the fourth decimal place in the range of 0 to 1, for example. The classification unit 41 has an AI (artificial intelligence) that learns the captured image captured when the loom 100 is in a normal state as a correct image. The more similar the captured image captured by the camera 11 is to the correct image, the closer the score calculated by the classification unit 41 is to 1. Therefore, the classification unit 41 calculates the score in such a way that the higher the degree of abnormality of the loom 100, the lower the score. For example, when the captured image is Figure 2 In the case of the photographed image P shown in FIG. 1 , the classifying unit 41 calculates the score of the loom 100 as 0.9998 based on the similarity between the correct image and the photographed image P.

[0054] In step S2, the classification section 41 classifies the newly acquired captured image from the camera 11 into any one of the plurality of groups based on the degree of abnormality of the loom 100 detected in step S1. The classification section 41 of the present embodiment classifies the newly acquired captured image from the camera 11 into any one of the plurality of groups based on the score of the loom 100 calculated in step S1 and the photographing time of the captured image.

[0055] As shown in Figure 5 and Figure 6 In the present embodiment, a plurality of groups based on the score division are set by dividing the score into a plurality of score ranges with a scale of 0.01. In the case of the example shown in Figure 5 and Figure 6 The classification section 41 classifies the captured image into the group based on the score division based on the third digit after the decimal point of the score of the loom 100. For example, in the case where the score of the loom 100 is 0.999-0.995, the classification section 41 classifies the captured image into the group of 1.00-0.99. For example, in the case where the score of the loom 100 is 0.994-0.990, the classification section 41 classifies the captured image into the group of 0.99-0.98.

[0056] In addition, a plurality of groups based on the photographing time division are set by dividing the photographing time of the camera 11 into a plurality of photographing times with a scale of 1 minute. The plurality of groups into which the captured image is classified is constituted by a combination of the plurality of groups based on the score division and the plurality of groups based on the photographing time division. In the case where M groups based on the score division are set and N groups based on the photographing time division are set, the groups into which the captured image is classified are set to M x N. Further, M and N are each an integer of 2 or more.

[0057] The classification section 41 classifies the captured image into the group corresponding to both the score of the loom 100 and the photographing time of the captured image. For example, in the case where the captured image is a score of 0.9998 and a photographing time of 8:01, the classification section 41 classifies the captured image into the group G11 of a score range of 1.00-0.99 and a photographing time of 8:01.

[0058] As shown in Figure 4 In step S3, the counting section 42 counts the number of captured images classified into the target group. Specifically, the counting section 42 increases the number of captured images classified into the target group by 1 from the number at the time of the previous counting. In step S3, the counting section 42 stores the number of captured images counted, that is, the number of captured images classified into the target group, in the auxiliary storage device 15.

[0059] In step S4, the screening section 43 determines whether the number of captured images stored in the auxiliary storage device 15 reaches a prescribed upper limit number for the object group.

[0060] In a case where the screening section 43 determines that the number of captured images stored in the auxiliary storage device 15 does not reach the prescribed upper limit number for the object group (NO in step S4), the process proceeds to step S5. In step S5, the screening section 43 stores the newly acquired captured image as a captured image of the object group in the auxiliary storage device 15. Thus, in a case where the number of captured images of the object group stored in the auxiliary storage device 15 is 4 or less, the screening section 43 stores the newly acquired captured image as a captured image of the object group in the auxiliary storage device 15.

[0061] In a case where the screening section 43 determines that the number of captured images stored in the auxiliary storage device 15 reaches the prescribed upper limit number for the object group (YES in step S4), the process proceeds to step S6. In step S6, the screening section 43 determines whether to replace a captured image stored in the auxiliary storage device 15 as a captured image of the object group with the newly acquired captured image. Thus, in a case where the number of captured images of the object group stored in the auxiliary storage device 15 is 5, the screening section 43 determines whether to replace one of the captured images of the object group stored in the auxiliary storage device 15 with the newly acquired captured image.

[0062] The screening section 43 of the present embodiment proceeds to step S7 in a case where the score of the newly acquired captured image is less than the score of the captured image having the highest score among the captured images of the object group stored in the auxiliary storage device 15 (YES in step S6). In step S7, the screening section 43 replaces the captured image having the highest score among the captured images of the object group stored in the auxiliary storage device 15 with the newly acquired captured image. That is, the screening section 43 deletes the captured image having the highest score among the captured images of the object group stored in the auxiliary storage device 15 from the auxiliary storage device 15, and newly stores the newly acquired captured image as a captured image of the object group in the auxiliary storage device 15.

[0063] The screening section 43 of the present embodiment ends the saving process in a case where the score of the newly acquired captured image is equal to or higher than the score of the captured image having the highest score among the captured images of the object group stored in the auxiliary storage device 15 (NO in step S6). That is, the screening section 43 does not replace the captured image having the highest score among the captured images of the object group stored in the auxiliary storage device 15 with the newly acquired captured image. The screening section 43 deletes the newly acquired captured image without storing it in the auxiliary storage device 15.

[0064] As Figure 5As shown, the auxiliary storage device 15 stores each group of captured images and the number of captured images classified into each group.

[0065] Figure 5 The number of upper-level marks in each group in is the number of captured images stored in the auxiliary storage device 15. As described above, when the number of captured images of the target group stored in the auxiliary storage device 15 reaches the upper limit, the filtering unit 43 determines whether to replace the captured images of the target group stored in the auxiliary storage device 15 with newly acquired captured images. In other words, when the number of captured images of the target group stored in the auxiliary storage device 15 reaches the upper limit, the filtering unit 43 does not store the newly acquired captured images in the auxiliary storage device 15 in addition to the captured images of the target group stored in the auxiliary storage device 15. Therefore, in this embodiment, the maximum number of captured images per group stored in the auxiliary storage device 15 is five.

[0066] Figure 5 The number at the bottom of each group in represents the number of images classified into that group, regardless of the number of images stored in the auxiliary storage device 15. The counting unit 42 counts the number of classified images, so the number of images classified into each group may be five or more.

[0067] like Figure 6 As shown, the control device 14 creates a table H indicating the number of captured images classified into each group. The control device 14 of this embodiment creates the table H in a heat map format based on the number of captured images classified into each group.

[0068] For example, in Table H, a group with 120 or more and less than 150 classified images is displayed in light green. A group with 150 or more and less than 175 classified images is displayed in dark green. A group with 175 or more and less than 200 classified images is displayed in light red. A group with 200 or more and less than 250 classified images is displayed in red. A group with 250 or more classified images is displayed in dark red. In addition, Figure 6 In Table H shown, the density of dotted shadows increases for groups with a greater number of classified captured images, thereby expressing a heat map format.

[0069] The control device 14 displays the generated table H on the display unit 17. The display unit 17 displays the table H indicating the number of images classified into each group. The display unit 17 of this embodiment displays the table H in a heat map format according to the number of images classified into each group.

[0070] The operator selects a group of which the captured image is desired to be confirmed from the table H displayed on the display section 17 through the input section 16. The control device 14 causes the captured image of the group selected by the operator through the input section 16 from among the groups of captured images stored in the auxiliary storage device 15 to be displayed on the display section 17. The control device 14 of the present embodiment causes the score of the loom 100 to be displayed on the display section 17 together with the captured image.

[0071] Figure 7 is a schematic view showing one example of the captured image P displayed on the display section 17. In Figure 7 , five captured images P are displayed on the display section 17. In Figure 7 , the score of the loom 100 is displayed on the lower side of the captured image P.

[0072] [Effects of the Present Embodiment]

[0073] The effects of the present embodiment will be described.

[0074] The inspection system 10 that inspects the loom 100 based on the captured image of the camera 11 is provided with a classification section 41, an auxiliary storage device 15, a counting section 42, and a screening section 43.

[0075] The classification section 41 detects the degree of abnormality of the loom 100 based on the newly acquired captured image each time a new captured image is newly acquired from the camera 11. The classification section 41 classifies the newly acquired captured image into any one of a plurality of groups based on the detected degree of abnormality of the loom 100. The auxiliary storage device 15 stores the captured images by each group.

[0076] The counting section 42 counts the number of captured images classified into the object group for which the newly acquired captured image is classified. The counting section 42 stores the counted number of captured images, i.e., the number of captured images classified into the object group, in the auxiliary storage device 15. Thus, even if all the captured images are not saved, it is possible to acquire the distribution of the degree of abnormality of the loom 100.

[0077] The screening section 43 determines whether the number of captured images of the target group stored in the auxiliary storage device 15 reaches a prescribed upper limit number. The screening section 43 stores the newly acquired captured image as a captured image of the target group in the auxiliary storage device 15 in a case where it is determined that the number of captured images of the target group stored in the auxiliary storage device 15 does not reach the prescribed upper limit number. The screening section 43 determines whether to replace the captured image of the target group stored in the auxiliary storage device 15 with the newly acquired captured image in a case where it is determined that the number of captured images of the target group stored in the auxiliary storage device 15 reaches the prescribed upper limit number. Thus, the number of captured images stored in the auxiliary storage device 15 is limited to not exceed the upper limit number, and therefore it is possible to reduce the data capacity stored in the auxiliary storage device 15.

[0078] [Effects of the Present Embodiment]

[0079] The effects of the present embodiment will be described.

[0080] (1) The screening section 43 determines whether to replace the captured image of the target group stored in the auxiliary storage device 15 with the newly acquired captured image in a case where the number of captured images of the target group stored in the auxiliary storage device 15 reaches the prescribed upper limit number. Thus, the number of captured images of each group stored in the auxiliary storage device 15 is limited to not exceed the upper limit number, and therefore it is possible to reduce the data capacity stored in the auxiliary storage device 15. In addition, the counting section 42 counts the number of captured images classified into the target group, and stores the counted number of captured images in the auxiliary storage device 15. Thus, even if all captured images are not saved, it is possible to acquire the distribution of the abnormality degree of the loom 100. Therefore, it is possible to reduce the data capacity stored in the auxiliary storage device 15 and acquire the distribution of the abnormality degree of the loom 100.

[0081] (2) The classification section 41 calculates the abnormality degree of the loom 100 as a score. The classification section 41 classifies the captured image into any one of the plurality of groups on the basis of the calculated score. According to this structure, for example, it is possible to more finely detect the abnormality degree of the loom 100 compared to a case where the abnormality degree of the loom 100 is detected as S·A·B·C / Good·Good·Pass·Fail, and the like.

[0082] (3) The classification section 41 calculates the score in such a manner that the higher the abnormality degree of the loom 100, the lower the score. In a case where the score of the newly acquired captured image is lower than the score of the captured image having the highest score among the captured images of the target group stored in the auxiliary storage device 15, the screening section 43 replaces the captured image having the highest score among the captured images of the target group stored in the auxiliary storage device 15 with the newly acquired captured image.

[0083] According to this configuration, captured images with low scores, i.e., captured images showing a high degree of abnormality in the loom 100, are preferentially stored in the auxiliary storage device 15. Therefore, compared to a case where captured images with high scores, i.e., captured images showing a low degree of abnormality in the loom 100, are preferentially stored in the auxiliary storage device 15, it is easier to effectively use the captured images when investigating the cause of the abnormality in the loom 100.

[0084] (4) The classification unit 41 further classifies the captured images into any one of a plurality of groups based on the time at which the captured images were captured. This allows for obtaining a temporal distribution of the degree of abnormality of the loom 100. For example, the temporal distribution of the degree of abnormality of the loom 100 is useful for understanding the state of the loom 100 when the operating conditions of the loom 100 are changed or the installation environment of the loom 100 is changed during operation.

[0085] (5) The inspection system 10 includes the display unit 17. The display unit 17 displays a table H showing the number of captured images classified into each group. This makes it easier for the operator to grasp the distribution of the degree of abnormality of the loom 100.

[0086] (6) The display unit 17 displays the table H in a heat map format according to the number of captured images classified into each group. This makes it easier for the operator to grasp the distribution of the degree of abnormality of the loom 100.

[0087] (7) When the number of captured images of the target group stored in the auxiliary storage device 15 reaches a predetermined upper limit, the screening unit 43 determines whether to replace the captured images of the target group stored in the auxiliary storage device 15 with newly acquired captured images without terminating the storage of the captured images of the target group. This allows captured images that are more suitable for storage to be stored in the auxiliary storage device 15.

[0088] [Change Example]

[0089] Furthermore, the above-described embodiment can be implemented by being modified as follows: The above-described embodiment and the following modified examples can be implemented in combination with each other within a range that does not technically conflict.

[0090] In the above embodiment, the classification unit 41 detects the degree of abnormality of the loom 100 each time a new image is acquired from the camera 11. However, this is not limiting. Alternatively, the classification unit 41 may detect the degree of abnormality of the loom 100 when the number of images acquired from the camera 11 reaches a predetermined number.

[0091] The control device 14 can acquire the photographed images from the camera 11 every time the camera 11 performs photographing, but is not limited thereto. The control device 14 can acquire the photographed images corresponding to a predetermined number of times from the camera 11 at a timing at which the camera 11 has performed photographing the predetermined number of times.

[0092] The classification section 41 can also detect the degree of abnormality of the loom 100 in stages, such as S, A, B, C, excellent, good, qualified, and unqualified.

[0093] In the above embodiment, the classification section 41 classifies the photographed images into any one of the plurality of groups based on the degree of abnormality of the loom 100 and the timing of photographing the photographed images, but is not limited thereto.

[0094] The classification section 41 can classify the photographed images into any one of the plurality of groups based on only the degree of abnormality of the loom 100.

[0095] The classification section 41 can classify the photographed images into any one of the plurality of groups based on the degree of abnormality of the loom 100 and items other than the timing of photographing. As the items other than the timing of photographing, for example, the operation conditions of the loom 100, the setting environment of the loom 100, and the like can be listed.

[0096] The scale of the score when the classification section 41 classifies the photographed images into any one of the plurality of groups is not limited to 0.01 and can be appropriately changed.

[0097] The scale of the score when the classification section 41 classifies the photographed images into any one of the plurality of groups can not be a constant scale. For example, the scale of the score in a specific score range among the scores calculated in the range of 0 to 1 can be denser than the scale of the score in other score ranges.

[0098] As the plurality of groups based on the score, for example, three groups as follows can be provided. The first group is a group in which the score of the loom 100 is equal to or less than a first score. The second group is a group in which the score of the loom 100 is equal to or more than a second score. Further, the second score is larger than the first score. The third group is a group in which the score of the loom 100 is larger than the first score and smaller than the second score.

[0099] The scale of the timing of photographing when the classification section 41 classifies the photographed images into any one of the plurality of groups is not limited to one minute and can be appropriately changed.

[0100] The prescribed upper limit number of sheets is not limited to five sheets and can be appropriately changed.

[0101] The prescribed upper limit number of sheets can be different for each group.

[0102] The screening section 43 of the above embodiment replaces the photographed image having the highest score among the photographed images of the subject group stored in the auxiliary storage device 15 with the newly acquired photographed image in the case where the score of the newly acquired photographed image is lower than the score of the photographed image having the highest score among the photographed images of the subject group stored in the auxiliary storage device 15, but is not limited thereto.

[0103] For example, the screening section 43 can also replace the photographed image having the lowest score among the photographed images of the subject group stored in the auxiliary storage device 15 with the newly acquired photographed image in the case where the score of the newly acquired photographed image is higher than the score of the photographed image having the lowest score among the photographed images of the subject group stored in the auxiliary storage device 15. In this case, the photographed image having a high score, i.e., the photographed image of the loom 100 having a low degree of abnormality, is preferentially stored in the auxiliary storage device 15.

[0104] The number of cameras 11 can also be plural.

[0105] The storage section is not limited to the auxiliary storage device 15. The storage section can be, for example, the main storage section 14b of the control device 14, or a storage device provided to the machine base 101, or a cloud.

[0106] The classification section 41, the counting section 42, and the screening section 43 are not limited to the control device 14 of the computer 10b. The classification section 41, the counting section 42, and the screening section 43 can also be, for example, a control device that controls the loom 100.

[0107] The display section 17 can also not display the table H in the form of a heat map.

[0108] In the above embodiment, the classification section 41 detects the degree of abnormality of the loom 100 based on the warp yarn T exhibited in the photographed image, but can also detect the degree of abnormality of the loom 100 based on the weft yarn, the constituent member of the loom 100 exhibited in the photographed image.

[0109] The inspection system 10 of the fiber machine can also be applied to fiber machines other than the loom 100 such as a spinning machine.

[0110] [POSTSCRIPT]

[0111] Hereinafter, the technical ideas that can be grasped from the above embodiments and the modified examples are described.

[0112] <POSTSCRIPT 1>

[0113] An inspection system of a fiber machine that inspects a fiber machine based on a captured image captured by a camera, wherein: a classification unit detects an abnormality degree of the fiber machine based on a newly acquired captured image, and classifies the newly acquired captured image into any one of a plurality of groups based on the detected abnormality degree of the fiber machine; a storage unit stores the captured image for each of the groups; a counting unit counts the number of captured images classified into a target group to which the newly acquired captured image is classified, and stores the counted number of captured images in the storage unit; and a screening unit determines whether the number of captured images of the target group stored in the storage unit reaches a predetermined upper limit number, stores the newly acquired captured image as the captured image of the target group in the storage unit in a case where it is determined that the number of captured images of the target group stored in the storage unit does not reach the predetermined upper limit number, and determines whether to replace the captured image of the target group stored in the storage unit with the newly acquired captured image in a case where it is determined that the number of captured images of the target group stored in the storage unit reaches the predetermined upper limit number.

[0114] <Note 2>

[0115] The inspection system of a fiber machine according to Note 1, wherein

[0116] The classification unit calculates a score of the abnormality degree of the fiber machine, and classifies the captured image into any one of the plurality of groups based on the calculated score.

[0117] <Note 3>

[0118] The inspection system of a fiber machine according to Note 2, wherein

[0119] The classification unit calculates the score in such a manner that the higher the abnormality degree of the fiber machine, the lower the score, and the screening unit replaces, in a case where the score of the newly acquired captured image is lower than the score of the captured image having the highest score among the captured images of the target group stored in the storage unit, the captured image having the highest score among the captured images of the target group stored in the storage unit with the newly acquired captured image.

[0120] <Note 4>

[0121] The inspection system of a fiber machine according to any one of Notes 1 to 3, wherein

[0122] The classification unit classifies the captured image into any one of the plurality of groups based also on a captured time of the captured image.

[0123] <Supplementary note 5>

[0124] The fiber machine inspection system according to any one of Supplementary notes 1 to 4, wherein

[0125] The display section displays a table indicating the number of the photographed images classified into each group.

[0126] <Supplementary note 6>

[0127] The fiber machine inspection system according to Supplementary note 5, wherein

[0128] The display section displays the table in a heat map form according to the number of the photographed images classified into each group.

Claims

1. A fiber machine inspection system that inspects a fiber machine based on a captured image of a camera, wherein, Possessing: a classification section that detects an abnormality degree of the fiber machine based on the newly acquired photographed image, and classifies the newly acquired photographed image into any one of a plurality of groups based on the detected abnormality degree of the fiber machine; a storage section that stores the photographed image for each of the groups; a counting section that counts the number of the photographed images classified into the object group for which the newly acquired photographed image is classified, and stores the counted number of the photographed images in the storage section; and a screening section that determines whether the number of the photographed images of the object group stored in the storage section reaches a prescribed upper limit number, stores the newly acquired photographed image as the photographed image of the object group in the storage section in a case where it is determined that the number of the photographed images of the object group stored in the storage section does not reach the prescribed upper limit number, and determines whether to replace the photographed images of the object group stored in the storage section with the newly acquired photographed image in a case where it is determined that the number of the photographed images of the object group stored in the storage section reaches the prescribed upper limit number.

2. The fiber machine inspection system according to claim 1, wherein the classification section calculates a score as the abnormality degree of the fiber machine, and classifies the photographed image into any one of the plurality of groups based on the calculated score.

3. The fiber machine inspection system according to claim 2, wherein the classification section calculates the score in such a manner that the higher the abnormality degree of the fiber machine, the lower the score, the screening section replaces the photographed image having the highest score among the photographed images of the object group stored in the storage section with the newly acquired photographed image in a case where the score of the newly acquired photographed image is lower than the score of the photographed image having the highest score among the photographed images of the object group stored in the storage section.

4. The fiber machine inspection system according to claim 1, wherein the classification section classifies the photographed image into any one of the plurality of groups based on a photographed time of the photographed image as well.

5. The fiber machine inspection system according to claim 1, wherein a display section is provided, the display section displays a table indicating the number of the photographed images classified into each group.

6. The fiber machine inspection system according to claim 5, wherein the display section displays the table in a heat map form according to the number of the photographed images classified into each group. ​

Images