Paper bag defect detection device based on machine vision

Abstract

The utility model relates to the technical field of paper bag detection, and discloses a paper bag defect detection device based on machine vision, which comprises a support frame and a detection conveyor belt arranged at the upper part of the support frame, a detection cabinet is arranged at the position, located above the detection conveying belt, of the middle of the supporting frame, an area-array camera is arranged in the detection cabinet, a high-brightness light source used for supplementing light is arranged on the side, close to the area-array camera, of the detection cabinet, and a removing module is arranged above the tail end of the detection conveying belt; a stacking conveying assembly is arranged at the tail end of the detection conveying belt, and the rejecting module is used for rejecting defective products and enabling the defective products to fall into a waste cabinet. The portable paper bag online detection device is based on the machine vision technology, solves the problem of online detection in the production process of portable paper bags, automatically removes defective products, is high in detection efficiency and automation degree, and has wide application prospects.

Description

TECHNICAL FIELD

[0001] The utility model relates to paper bag detection technical field, concretely is a paper bag defect detection device based on machine vision. BACKGROUND

[0002] As an environmental protection packing, the hand paper bag has the characteristics of degradable and recyclable. Compared with the plastic bag, the hand paper bag has less influence on the environment. At the same time, with the improvement of people's environmental protection consciousness, more and more consumers begin to choose to use the hand paper bag to replace the plastic bag and other disposable packing. The hand paper bag is prone to produce defects such as unsealed bottom, folded edge, damage, dirt, wrinkle, hand pulling loss and hand pulling damage in the production process. At present, the production factory adopts the manual detection mode, on the one hand, the efficiency is low, on the other hand, the manual evaluation standard is more subjective, and the consistency of the product cannot be controlled. UTILITY MODEL CONTENT

[0003] (I) technical problem solved

[0004] In view of the defects of the prior art, the utility model provides a paper bag defect detection device based on machine vision, which solves the problems of high product quality detection cost, low efficiency and poor product consistency control after the existing paper bag production.

[0005] (II) technical scheme

[0006] In order to realize the above object, the utility model realizes the following technical scheme:

[0007] A paper bag defect detection device based on machine vision, including support frame and detection conveying belt arranged on the upper part of support frame, one end of detection conveying belt is arranged with feeding conveying belt, the middle part of support frame is arranged with detection cabinet above detection conveying belt, face array camera is arranged in detection cabinet, high-brightness light source for light supplement is arranged on one side of detection cabinet close to face array camera, high-brightness light source for light supplement is arranged on one side of detection cabinet close to face array camera, the upper part of the end of detection conveying belt is arranged with rejection module, the end of detection conveying belt is arranged with code material conveying assembly, rejection module is used to reject defective products and fall into waste cabinet, waste cabinet is arranged directly below the gap between code material conveying assembly and detection conveying belt, electrical control cabinet is arranged on one side of waste cabinet in support frame, image calculation module for processing the photograph of face array camera is arranged in electrical control cabinet.

[0008] Preferably, the detection conveying belt is detachably installed with a trigger photoelectric sensor through a fixed mounting frame at one end close to the feeding conveying belt, and the upper end face of the detection cabinet is arranged with an audible and visual alarm module.

[0009] Preferably, a blockage triggering module is detachably mounted on the adjustable mounting bracket above the end of the detection conveying belt, and the blockage triggering module is located directly above the gap between the detection conveying belt and the material stacking conveying belt assembly.

[0010] Preferably, the rejection module is arranged on the adjustable mounting bracket, and the rejection module is a blowing valve or a mechanical turnover mechanism which is communicated with a gas supply assembly.

[0011] Preferably, a display and control module is arranged in the detection cabinet, the display and control module comprises a touch display, a mouse and a keyboard, the display and control module is sequentially electrically connected with an emergency stop switch, a system switch and a manual / automatic conversion switch, and one side of the detection cabinet is provided with a keyboard and mouse rack matched with the mouse and the keyboard.

[0012] Preferably, the image calculation module is used for receiving a raw image of the area array camera, performing operation on the raw image, and judging whether the detected sample has a defect, and the image calculation module is one or several of a GPU, an NPU and a CPU.

[0013] Preferably, the area array camera is arranged in the detection cabinet to detect the side of the sample to be detected, and a turnover mechanism is further arranged in the detection cabinet to turn over the sample to be detected.

[0014] (III) Beneficial effects

[0015] The utility model has the following beneficial effects:

[0016] The paper bag defect detection device based on machine vision, through the arrangement of the area array camera and the high-brightness light source, the sample to be detected on the loading transmission belt assembly is conveyed to the camera directly below by the detection transmission belt assembly, and the area array camera takes a photo. After the photo is taken, the sample picture is sent to the image calculation module in the electrical control cabinet through the network line for processing, and a defect alarm result is given. If the image processing module gives the current detection sample as a good product, the rejection module does not work, the sample normally passes through the material stacking conveying belt assembly and is conveyed to the good product pile; if the image processing module gives the current detection sample as a defective product, the sample moves to the rejection module and performs the rejection action, and the sample to be detected falls into the waste cabinet through the gap between the detection transmission belt assembly and the material stacking conveying belt assembly. The whole device is based on machine vision technology, solves the online detection problem in the production process of the paper bag, automatically rejects the defective product, has high detection efficiency and high automation degree, and has wide application prospect. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 It is a whole structure schematic view of the utility model;

[0018] Figure 2 It is a rejection module and blockage triggering module layout structure schematic view of the utility model;

[0019] Figure 3 It is the internal structure schematic view of the detection cabinet of the utility model;

[0020] Figure 4 It is the electric connection schematic view of the utility model;

[0021] Figure 5 It is the key control timing diagram of the utility model.

[0022] In the drawing: 1, feeding conveyor belt; 2, trigger photoelectric sensor; 3, area array camera; 4, highlight light source; 5, detection conveyor belt; 6, sound-light alarm module; 7, electrical control cabinet; 8, rejection module; 9, material blocking trigger module; 10, material coding conveyor belt; 11, waste cabinet; 12, sample to be measured; 13, display control module; 14, emergency stop switch; 15, system switch; 16, manual / automatic conversion switch; 17, keyboard and mouse rack; 18, fixed mounting rack; 19, detection cabinet; 20, adjustable mounting rack; 21, support rack. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the utility model will be clearly and completely described below with reference to the drawings in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, not all the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the utility model.

[0024] Please refer to Figure 1 The utility model provides a kind of technical solutions: a paper bag defect detection device based on machine vision, including paper tape detection, including support rack 21 and the detection conveyor belt 5 of being arranged on the upper portion of support rack 21, the one end of detection conveyor belt 5 is arranged with feeding conveyor belt 1, the middle portion of support rack 21 is located above detection conveyor belt 5 and is provided with detection cabinet 19, area array camera 3 is arranged in detection cabinet 19, high-brightness light source 4 for light compensation is arranged on the side of detection cabinet 19 close to area array camera 3, rejection module 8 is arranged above the end of detection conveyor belt 5, material coding conveyor assembly is arranged at the end of detection conveyor belt 5, rejection module 8 is used to reject defective product and fall into waste cabinet 11, waste cabinet 11 is arranged directly below the gap between material coding conveyor assembly and detection conveyor belt 5, electrical control cabinet 7 is arranged in the side of support rack 21 close to waste cabinet 11, image calculation module for processing the photograph of area array camera 3 is arranged in electrical control cabinet 7.

[0025] The utility model discloses, through the arrangement's area array camera 3 and high light source 4, the sample 12 of measuring to be detected on the loading transmission belt subassembly is conveyed to the camera just below by detection transmission belt subassembly, and area array camera 3 takes photograph. After photographing, sample picture is sent to the image calculation module processing in electrical control cabinet 7 through network line, and the defective alarm result is given. If the image processing module gives the current detection sample as good product, and the elimination module 8 does not work, and the sample normally passes the material conveying belt 10 subassembly, and is conveyed to the good product stack, if the image processing module gives the current detection sample as bad product, and the sample moves to the elimination module 8 place and carries out the elimination action, and the sample drops into the waste cabinet 11 through the gap between detection transmission belt subassembly and material conveying belt 10 subassembly. The whole device is based on machine vision technology, and the online detection problem in the production process of hand-held paper bag is solved, and the bad product is automatically eliminated, and the detection efficiency is high, and the automation degree is high, and has wide application prospect.

[0026] Referring to Figure 1 With 3 As shown in the figure, in the embodiment, the detection conveying belt 5 is detachably installed with the trigger photoelectric sensor 2 through the fixed mounting frame 18 close to one end of the loading conveying belt 1, and the upper end face of the detection cabinet 19 is arranged with the sound-light alarm module 6. The sample 12 to be detected is conveyed to the trigger sensor by the loading conveying belt 1, and the area array camera 3 and the high light source 4 are triggered to work, and after a certain time delay, the sample 12 to be detected is conveyed to the camera just below by the detection transmission belt subassembly, and the camera takes photograph. After photographing, the sample picture is sent to the image calculation module processing in the electrical control cabinet 7 through network line, and the defective alarm result is given.

[0027] Referring to Figure 2 With 4 As shown in the figure, in the embodiment, the upper side of the end of the detection conveying belt 5 is detachably installed with the blocking trigger module 9 through the adjustable mounting frame 20, and the blocking trigger module 9 is located just above the gap between the detection conveying belt and the material conveying belt 10 subassembly. The blocking trigger module 9 is used for providing a blocking trigger alarm signal, and when the blocking trigger module 9 exceeds a certain time threshold set by software, the sound-light alarm module 6 is controlled to give an alarm signal and carry out system shutdown operation, and after the blocked paper bag is taken away, the system returns to normal work. Usually, the blocking trigger module 9 selects the blocking trigger sensor.

[0028] In the embodiment, the elimination module 8 is arranged on the adjustable mounting frame 20, and the elimination module 8 is a blow valve or a mechanical turnover mechanism connected with a gas supply assembly. Referring to Figure 2 As shown in the figure, if the image processing module gives the current detection sample as bad product, the sound-light alarm module 6 alarms, and when the sample moves to the blow valve 8, the blow valve blows, and the sample drops into the waste cabinet 11 through the gap between the detection conveying belt 5 and the material conveying belt 10. When the material is blocked at the blocking trigger module 9 and cannot pass through, the sound-light alarm module 6 alarms. Usually, the sound-light alarm module 6 selects the sound-light alarm lamp and similar components.

[0029] Referring to Figure 2 With 4 As shown in the figure, in this embodiment, the detection cabinet 19 is arranged with a display and control module 13, which includes a touch display, a mouse and a keyboard. The display and control module 13 is electrically connected with an emergency stop switch 14, a system switch 15 and a manual / automatic switch 16 in sequence. The detection cabinet 19 is arranged with a keyboard and mouse stand 17 matched with the mouse and the keyboard. The display is used to display a software interaction interface. The emergency stop switch 14 is used to stop the machine in emergency. The system switch 15 is used to start or stop the whole device. The manual / automatic switch 16 is used to control the conveying belt. In the automatic mode, the start and stop of the conveying belt are controlled by the software. In the manual mode, the start and stop of the conveying belt are controlled by the device operator.

[0030] In this embodiment, the image calculation module is used to receive the original image of the area array camera 3, and to calculate the original image to determine whether the sample to be detected has defects. The image calculation module is one or several of GPU, NPU and CPU.

[0031] In this embodiment, the detection cabinet 19 is arranged with an area array camera 3 for detecting the side of the sample to be detected 12. The detection cabinet 19 is also arranged with a turnover mechanism for turning over the sample to be detected 12. Through the added side area array camera 3 and the turnover mechanism, the common surface of the paper bag can be automatically detected and the defective products can be removed.

[0032] The working principle of the device in actual application: the sample to be detected 12 is conveyed to the trigger sensor by the feeding conveying belt 1, and the camera and the high-brightness light source 4 are triggered to work. After a certain time delay, the sample to be detected 12 is conveyed to the position directly below the camera by the detection conveying belt, and the camera takes a picture. After the picture is taken, the sample picture is sent to the image calculation module in the electrical control cabinet 7 through the network line for processing, and the defect alarm result is given. The sound and light alarm lamp and the removing device are controlled to work. If the image calculation module gives the current detection sample as a good product, the sound and light alarm lamp and the blow valve do not work, the sample normally passes through the feeding conveying belt 10 and is conveyed to the good product stack; if the image calculation module gives the current detection sample as a defective product, the sound and light alarm lamp alarms, and the blow valve blows air when the sample moves to the blow valve. The sample falls into the waste cabinet 11 through the gap between the detection conveying belt and the feeding sensor. When the material is blocked at the blocking photoelectric sensor and cannot pass through, the sound and light alarm lamp alarms.

[0033] Figure 5 It is a key control timing diagram of this embodiment. T1 is the trigger enable time, T2 is the trigger interval of different samples, T3 is the light source trigger delay, T4 is the light source on time, T5 is the camera exposure time, T6 is the removal delay, and T7 is the removal enable time.

[0034] When the device is working, the speed of the feeding conveyor belt assembly, the detection conveyor belt and the code conveyor belt are all v. The length of the paper bag is L1, the distance between the trigger photoelectric sensor and the center of the camera field of view is L2, and the distance between the center of the camera field of view and the rejection device is L3.

[0035] The trigger enable duration T1 is given by the following formula (1):

[0036] T1=L2 / v (1)

[0037] The trigger interval of different samples is determined by the detection speed N (unit: pieces / s), as shown in the following formula (2):

[0038] T2=1 / N (2)

[0039] The light source trigger delay T3 is given by the following formula (3):

[0040] T3=L2 / v (3)

[0041] The light source opening duration T4 should be greater than the camera exposure time T5.

[0042] The product of the camera exposure time T5 and the conveyor belt speed v should be less than or equal to the camera object field resolution δL, that is, formula (4):

[0043] v·T5≤δL (4)

[0044] The rejection delay T6 is given by the following formula (5):

[0045] T6=L3 / v (5)

[0046] The rejection enable duration T7 should satisfy the following formula (6):

[0047] 0.1L1≤T7≤0.5L1 (6)

[0048] It should be noted that, in this document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without limitation, an element preceded by "comprises a..." does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus.

[0049] Although the embodiments of the present application have been shown and described, it is to be understood that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A machine vision based paper bag defect detection apparatus, characterized by, Including support frame and detection conveying belt arranged on the upper part of the support frame, one end of the detection conveying belt is arranged with a feeding conveying belt, the middle part of the support frame is arranged with a detection cabinet above the detection conveying belt, a face array camera is arranged in the detection cabinet, a highlight light source for light compensation is arranged on one side of the detection cabinet close to the face array camera, a rejection module is arranged above the end of the detection conveying belt, a code feeding conveying assembly is arranged at the end of the detection conveying belt, the rejection module is used to reject defective products into a waste cabinet, the waste cabinet is arranged directly below the gap between the code feeding conveying assembly and the detection conveying belt, an electrical control cabinet is arranged in the support frame on one side of the waste cabinet, and an image calculation module for processing photos taken by the face array camera is arranged in the electrical control cabinet.

2. The machine vision based paper bag defect detection apparatus as claimed in claim 1, wherein: The detection conveying belt is detachably mounted with a trigger photoelectric sensor at one end close to the feeding conveying belt through a fixed mounting frame, and an audible and visual alarm module is arranged on the upper end face of the detection cabinet.

3. The machine vision based paper bag defect detection apparatus as claimed in claim 1, wherein: A blockage triggering module is detachably mounted above the end of the detection conveying belt through an adjustable mounting frame, and the blockage triggering module is located directly above the gap between the detection conveying belt and the code feeding conveying belt assembly.

4. The machine vision based paper bag defect detection apparatus as claimed in claim 3, wherein: The rejection module is arranged on the adjustable mounting frame, and the rejection module is a blowing valve connected with a gas supply assembly or a mechanical turnover mechanism.

5. The machine vision based paper bag defect detection apparatus as claimed in any one of claims 1 to 4, wherein: A display control module is arranged in the detection cabinet, the display control module includes a touch display, a mouse and a keyboard, the display control module is electrically connected with an emergency stop switch, a system switch and a manual / automatic switch in sequence, and a keyboard and mouse rack matched with the mouse and the keyboard is arranged on one side of the detection cabinet.

6. The machine vision based paper bag defect detection apparatus as claimed in any one of claims 1 to 4, wherein: The image calculation module is used for receiving original images of the face array camera, operating the original images, and judging whether the detected sample has defects, and the image calculation module is one or several of GPU, NPU and CPU.

7. The machine vision based paper bag defect detection apparatus as claimed in any one of claims 1 to 4, wherein: The face array camera for detecting the side of the sample to be detected is arranged in the detection cabinet, and a turnover mechanism for turning over the sample to be detected is also arranged in the detection cabinet.

Images