KR20220149381A - Artificial intelligence-based tampon outer high-speed quality inspection system - Google Patents

Abstract

The present invention relates to an artificial intelligence-based injection molding product high-speed quality inspection system. The artificial intelligence-based injection molding product high-speed quality inspection system according to the present invention may comprise: a supply unit which supplies an injection molding product; an arrangement transfer unit which arranges and transfers the injection molding product which is supplied from the supply unit; an image acquisition unit which receives the injection molding product transferred from the arrangement transfer unit to transfer the same in one direction, while filming the transferred injection molding product to acquire an image; a control analysis unit which discerns a faulty product by analyzing based on an artificial intelligence module by using the image of the injection molding product acquired by the image acquisition unit, and performs the control of each unit; and a faulty product detection unit which is disposed in the transfer direction of the injection molding product transferred by the image acquisition unit to find out the discerned faulty product. Therefore, quality inspection may be precisely and quickly performed.

Description

Artificial intelligence-based tampon outer high-speed quality inspection system

The present invention relates to an injection molding quality inspection system, and more particularly, to an artificial intelligence-based high-speed injection molding quality inspection system capable of performing quality inspection accurately and at high speed by performing machine vision based on an artificial intelligence module.

An injection-molded product is a product made by putting a plastic resin in a heated cylinder and melting it, and then shooting the melted resin into a mold with a piston. An example of an injection-molded product is a tampon outer.

A tampon outer is used in a tampon, which is a disposable absorbent article inserted into a woman's vaginal cavity to absorb body fluids discharged during a woman's menstrual period. As shown, it is assembled into a tampon, which is a menstrual blood absorber, and is used to insert the tampon into the body.

Here, since the tampon outer is a product to be inserted into the body and must be hygienic, quality inspection during or after the manufacture of the tampon outer for this purpose is an essential and very important task, but the development of a quality inspection system for the tampon outer is insignificant.

To overcome this, conventionally, an inspection system grafted with a vision system is used to inspect the tampon outer, but the entire surface of the tampon outer, which is a cylindrical base in structure, cannot be inspected and detailed inspection is not performed. There are disadvantages in that the error rate is high and the inspection speed is also slow, which slows down the entire product production process, so a solution is required.

The present invention is proposed to solve the above-mentioned problems, and it is very accurate and yet It aims to provide an artificial intelligence-based high-speed quality inspection system for injection molding that can perform quality inspection at high speed.

In accordance with an embodiment of the present invention for solving the above problems, an artificial intelligence-based high-speed quality inspection system for injection-molded products includes: a supply unit for supplying injection-molded products; an alignment transfer unit for aligning and conveying the injection product supplied from the supply unit; an image acquisition unit configured to acquire an image by capturing the conveyed injection material while receiving the injection material transferred from the alignment transfer unit and transferring it to one side; Using the image of the injection molding obtained from the image acquisition unit, it is analyzed based on the artificial intelligence module and the vision module to classify defective products, and a control analysis unit that controls each unit and the conveying direction of the injection product transferred by the image acquisition unit It may include a defective product retrieval unit for searching for the classified defective products provided in the .

Here, the alignment transfer unit provides an accommodating space therein to receive the injection product supplied from the supply unit, and forms a guide plate that extends spirally from the lower end of the accommodation space to the upper end, and rotates by power to provide the guide plate for the received injection product. It may include a linear feeder that forms a straight line length from the end of the guide plate of the rotary feeder to the image acquisition unit and transfers the injection product transferred from the rotation feeder to the image acquisition unit.

In addition, the linear feeder receives the injection material from the rotary feeder and transfers it at a constant speed to the constant speed linear feeder and the constant speed linear feeder to receive the injection material transferred from the constant speed linear feeder and transfer it to the image acquisition unit at a faster speed than the constant speed linear feeder It may include a high-speed straight feeder.

In addition, the linear feeder may further include an escape roller for separating the injection product transferred from the constant-speed linear feeder to the high-speed linear feeder.

In addition, the image acquisition unit, a plurality of separation membranes are regularly installed at intervals sufficient to accommodate one injection product, receive the injection product from the alignment transfer unit, load it, and transfer it in one direction, and the upper side of the conveyer It may include a machine vision camera that acquires an image by capturing the installed and transported injection product, and transmits the acquired image to the control analysis unit.

In addition, the transfer conveyor is formed to have a width smaller than the length of the loaded injection-molded product so that at least one end of both ends of the injection-molded product protrudes to the outside, and a center between both sides or both sides in the conveying direction of the injection-molded product is for rotating the injection-molded product. A rotation generating means is provided so that the injection-molded product transported by the transfer conveyor rotates and moves, so that the machine vision camera can acquire an entire image of the injection-molded product.

In addition, the image acquisition unit may further include a multi-stage loading prevention means provided on the upper side of the transfer conveyor in front of the position of the machine vision camera to prevent the multi-stage loading of the transferred injection product.

In addition, the image acquisition unit may further include a lighting device installed on both sides of the conveying conveyor on which the machine vision camera is located and emitting light to further enhance the sharpness of the image acquired by the machine vision camera.

In addition, the artificial intelligence module, an image collecting step of collecting the image taken from the machine vision camera; a control step of controlling the machine vision camera and lighting device to meet the learning and verification requirements when the image does not meet the learning and verification requirements in the image acquisition step; an image pre-processing step of pre-processing the images collected after the control step to remove light reflection using a vision module; Including a learning step of learning the defective location while comparing the image preprocessed in the image pre-processing step with the normal product image, and a defective product determination step of labeling and labeling the defective location learned through the learning step, and classifying defective products. can

In addition, the defective product retrieval unit is provided on one side of the conveying direction of the injection-molded material conveyed by the image acquisition unit, and receives a control signal from the control analysis unit to push the defective product from the provided position to the other side, and the punching unit; It may include a recovery device provided at opposing positions to recover defective products pushed out by the punching means.

In addition, the artificial intelligence-based high-speed quality inspection system for injection moldings may further include a cloud server that receives information about defective products classified from the control analysis unit, performs defective product re-analysis, and transmits the performed defective product re-analysis information to the control analysis unit. have.

In addition, the artificial intelligence-based high-speed injection quality inspection system may further include a non-defective product counter unit provided in a transport direction of the injection-molded product transferred by the image acquisition unit to the rear of the defective product detection unit to count the good product injection product.

The artificial intelligence-based high-speed quality inspection system for injection molding according to an embodiment of the present invention performs inspection using a machine vision module based on an artificial intelligence module, and further inspects using an image captured while rotating a cylindrical-based injection molding product 360° By doing this, it is possible to perform quality inspection very accurately and at high speed.

In addition, in the process of transporting the injection molded product, an escape roller or a multi-stage loading prevention means is used to align the injection product in a line so that there is no agglomeration, thereby increasing the accuracy of the inspection and preventing malfunction of the device.

In addition, re-inspection by the cloud server can be performed and this can be reflected in the test result, thereby significantly reducing the false-positive rate.

In addition, the above-mentioned effects according to the embodiments of the present invention are not limited to the described content, and may further include all effects predictable from the specification and drawings.

1 is a perspective view of an artificial intelligence-based high-speed quality inspection system for injection moldings according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating an example of a supply unit that is a component of the artificial intelligence-based high-speed quality inspection system for injection molding of FIG. 1 .
FIG. 3 is a detailed view of an alignment transfer unit, which is a configuration of the artificial intelligence-based high-speed quality inspection system for injection molding of FIG. 1 .
FIG. 4 is a diagram illustrating the vicinity of an image acquisition unit and a defective product detection unit, which are components of the artificial intelligence-based high-speed injection quality inspection system of FIG. 1 .
5 is a detailed view of the interior viewed from the upper end in the drawing of FIG. 4 .
FIG. 6 is a view of the drawing of FIG. 5 as viewed from a planar direction.
7 is an enlarged view of the image acquisition unit of FIG. 4 .
FIG. 8 is a view of the drawing of FIG. 7 viewed from a planar direction.
9 is a view illustrating a process in which an injection product is transferred while rotating in a transfer conveyor according to an embodiment of the present invention.
10 is a view showing in detail an example of a multi-stage loading prevention means according to an embodiment of the present invention.
11 is a view showing a series of processes in which the multi-stage loading of the injection-molded product is prevented by the multi-stage loading preventing means of FIG. 10 .
12 is a view showing an example of a non-defective counter unit configured according to an embodiment of the present invention.
13 is a block diagram showing the connection between components of the artificial intelligence-based high-speed quality inspection system for injection molding according to the embodiment of the present invention of FIG. 1 .
14 is a view showing a detailed configuration of the control analysis unit shown in FIG. 13 and a connection state of the configurations.
15 is a detailed configuration diagram of the PC control panel shown in FIG. 14 .
16 is a flowchart schematically illustrating a process in which the artificial intelligence module shown in FIG. 15 operates.

Hereinafter, the description of the present invention with reference to the drawings is not limited to specific embodiments, and various modifications may be made and various embodiments may be provided. In addition, it should be understood that the content described below includes all transformations, equivalents, and substitutes included in the spirit and scope of the present invention.

In the following description, terms such as 1st, 2nd, etc. are terms used to describe various components, meanings are not limited thereto, and are used only for the purpose of distinguishing one component from other components.

Like reference numbers used throughout this specification refer to like elements.

As used herein, the singular expression includes the plural expression unless the context clearly dictates otherwise. In addition, terms such as "comprises", "comprises" or "have" described below are intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist. It should be construed as not precluding the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

In addition, terms such as “…unit”, “…group”, “…module”, etc. described in the specification mean a unit that processes at least one function or operation, which may be implemented by hardware or software or a combination of hardware and software. can

Hereinafter, an artificial intelligence-based high-speed quality inspection system for injection molding according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

The injection-molded product described in the present invention is not limited to any particular shape, but may be a circular or cylindrical injection-molded product that can be rotated by a rotation generating means 317 to be described later, for example, assembled to a tampon. It can be a tampon outer. However, the molded article is not necessarily limited to any specific shape as described above.

1 to 16, the artificial intelligence-based high-speed quality inspection system for injection molding according to an embodiment of the present invention includes a supply unit 100, an alignment transfer unit 200, an image acquisition unit 300, and a control analysis unit. 400 and may be configured to include a defective product detection unit 500 .

Specifically, the supply unit 100 is configured to supply the injection-molded material, and the form of the supply unit 100 is not limited to any specific type, but as an example, an injection hopper 110 into which the injection-molded material is injected as shown in the drawing, and an injection hopper ( It may be configured to include a supply conveyor 120 forming a length from 110 to the alignment transfer unit 200 .

At this time, one end of the supply conveyor 120 may be connected to the injection product outlet (not shown) of the input hopper 110, and the other end may be connected to the receiving space 212 of the rotary feeder 210 of the alignment transfer unit 200 to be described later. can

More preferably, the input hopper 110 has an open upper end to form an inlet 112, and an open lower end to form an outlet, so that the injection product injected into the inlet 112 falls and is discharged to the outlet at the bottom. Here, one end of the supply conveyor 120 is connected to the input hopper 110 so as to be located at the lower end of the outlet, and the injection product falling and discharged from the input hopper 110 may be transported along the longitudinal direction.

In addition, the rotary feeder 210 of the alignment transfer unit 200 is formed in an open top form and can accommodate the injection product by providing an accommodating space 212 therein, where the other end of the supply conveyor 120 is rotated The injection product transferred by being connected to the rotary feeder 210 to be positioned at the upper end of the feeder 210 may be introduced into the receiving space 212 .

At this time, due to the height difference between the outlet of the input hopper 110 and the upper end of the rotary feeder 210, the supply conveyor 120 may form a length in an inclined direction as shown in the figure, but this is not necessarily limited as an example, When the outlet of the input hopper 110 and the upper end of the rotary feeder 210 form the same height, the supply conveyor 120 may form a length in a straight direction.

On the other hand, the supply conveyor 120 may be formed in a private shape as shown in FIG. 1 , but preferably, when the length is formed in an inclined direction, in order to prevent the injection product from rolling in the reverse direction of the conveying direction, FIG. 2 . As shown in , the movement preventing film 125 protruding vertically or obliquely with respect to the supply conveyor 120 at regular intervals along the length may be formed.

In addition, the input hopper 110 may provide a safety door 114 interlocked with a worker detection sensor (not shown) on the input port 112 side as shown in FIG. 2 , and the safety door 114 detects the operator It is formed to be opened only when the operator is not detected near the input hopper 110 through the sensor, thereby preventing the operator from accidentally falling into the input hopper 110 .

At this time, the safety door 114 is preferably provided at a lower position than the inlet 112 of the input hopper 110, and when it is not opened, there is a space between the inlet 112 and the safety door 114 for the injection product to be temporarily mounted. It can be formed, and only the injection molded product that is opened and accommodated in the temporary storage space when the operator is not detected in the vicinity can be dropped and transferred to the supply conveyor 120 .

In addition, the receiving space 212 provided inside the rotary feeder 210 is provided with an injection quantity detection sensor (not shown) capable of detecting the quantity of injection products, and the injection quantity detection sensor is interlocked with the safety door 114 . can do. Through this, the safety door 114 may be opened only when the amount of the injection-molded product in the accommodation space 212 is maintained below an appropriate level, so that the injection-molded product does not overflow from the accommodation space 212 .

The alignment transfer unit 200 is configured to transfer the injection material supplied from the supply unit 100 while aligning, and for this purpose, the alignment transfer unit 200 may include a rotary feeder 210 and a linear feeder 220 .

Specifically, the rotary feeder 210 may provide an accommodating space 212 therein to receive the injection-molded product transferred from the supply unit 100 . In addition, the rotary feeder 210 may form a guide plate 214 helically extending from the lower end to the upper end of the receiving space 212 . In addition, the rotary feeder 210 may be connected to a power generating means (not shown) such as a motor to rotate by power.

Through this, the rotary feeder 210 may transfer the injection product accommodated in the accommodation space 212 in a line along the guide plate 214 while rotating by the power of the power generating means.

Here, only one guide plate 214 may be provided, but a plurality of guide plates 214 may be provided within a range that does not interfere with each other in order to align and transport more injection products. Thus, it is possible to prevent the extruded product from being separated to the outside by centrifugal force.

The linear feeder 220 is provided in a number corresponding to the number of guide plates 214 of the rotary feeder 210, and forms a straight length from the end of the guide plate 214 of the rotary feeder 210 to the image acquisition unit 300. Thus, it may be configured to transfer the injection-molded material transferred from the rotary feeder 210 to the image acquisition unit 300 .

At this time, the linear feeder 220 may include a constant-speed linear feeder 222 and a high-speed linear feeder 224 to transport the injection product at different speeds.

Specifically, the constant speed linear feeder 222 is a conveyor rotating by a power generating means 222a such as a motor, and is located between the rotary feeder 210 and the image acquisition unit 300 and adjacent to the rotary feeder 210. can be placed. In addition, the guide films 222b are erected on both sides to form a transfer line, and may be formed to transfer the injection product delivered from the rotary feeder 210 in a line along the transfer line.

Here, the constant speed linear feeder 222 is set to rotate at a constant speed at the same or similar speed to the feed speed of the injection product transmitted from the rotary feeder 210, and the constant speed linear feeder 222 from the rotary feeder 210. During the delivery process to

The high-speed linear feeder 224 is rotated by a power generating means 224a such as a motor, and guide films 224b are erected on both sides to form a conveying line for the injection product, and substantially constant-speed linear feeder 222. It may have the same shape as, but the installation position and rotation speed may be configured to be different from the constant speed linear feeder 222 .

Specifically, the high-speed linear feeder 224 may be disposed between the rotary feeder 210 and the image acquisition unit 300 and adjacent to the image acquisition unit 300 . That is, the high-speed linear feeder 224 may be located behind the constant-speed linear feeder 222 , and deliver the injection product delivered from the constant-speed linear feeder 222 to the image acquisition unit 300 .

In this case, the high-speed linear feeder 224 may have a rotational speed set so that the injection product can be instantaneously transferred to the image acquisition unit 300 faster than the constant-speed linear feeder 222 .

This is because the distance between the supply unit 100 and the image acquisition unit 300 is wide so that the distance through which the injection material is transported is long, or even if a large number of injection products are continuously transferred from the rotary feeder 210 to the constant speed linear feeder 222, the high-speed linear feeder By transferring from 224 to the image acquisition unit 300 instantly and quickly, it is possible to prevent congestion caused by friction, etc., and to enable faster work.

Meanwhile, the linear feeder 220 may further include an escape roller 230 for separating the injection product transferred from the constant-speed linear feeder 222 to the high-speed linear feeder 224 .

The escape roller 230 may be provided above the clearance space generated between the constant-speed linear feeder 222 and the high-speed linear feeder 224, preferably in the constant-speed linear feeder 222 and the high-speed linear feeder 224. A plurality may be provided so as to be positioned at least one by one. However, the present invention is not limited thereto, and only one may be provided between the constant-speed linear feeder 222 and the high-speed linear feeder 224 .

The escape roller 230 is formed to pressurize the continuously delivered injection material to a certain degree, and can separate the continuous injection product when it is transferred from the constant-speed linear feeder 222 to the high-speed linear feeder 224, and the injection product is transferred to the high-speed linear feeder ( 224) so that it does not float before being transferred quickly, so that it can be transferred with stability even at the high speed of the high-speed linear feeder 224.

At this time, the escape roller 230 may be connected to a rotatable link 230a with one end connected to a rotation shaft so as to control the degree of pressurization of the injection product, and the height of the escape roller 230 is variable from the straight feeder 220 by adjusting the angle of the link. Thus, the degree of pressure can be adjusted. Further, by connecting a power generating means such as a cylinder or a motor to the link 230a, the angle adjustment of the link 230a may be automated.

The image acquisition unit 300 may be configured to acquire an image by capturing the conveyed injection material while receiving the injection product transferred from the alignment transfer unit 200 and transferring it to one side.

To this end, the image acquisition unit 300 may include a transfer conveyor 310 and a machine vision camera 320 .

Specifically, the transport conveyor 310 may form a length in a direction perpendicular to the high-speed linear feeder 224, and a plurality of separation membranes 311 may be uniformly installed at intervals sufficient to accommodate one injection product. . Here, the longitudinal direction of the transfer conveyor 310 is only a preferred example, and is not limited thereto.

In addition, the transfer conveyor 310 is configured to pivot along the longitudinal direction, and can receive and load the injection product from the alignment transfer unit 200 and transfer it in one direction.

The machine vision camera 320 may be installed on the upper side of the transfer conveyor 310 for transporting the injection-molded product, and may acquire an image by capturing the conveyed injection-molded product. Also, the acquired image may be configured to be transmitted to the control analysis unit 400 .

Here, the control analysis unit 400 is configured to analyze the image of the injection product transmitted from the image acquisition unit 300 to classify defective products, and a detailed description of the control analysis unit 400 will be described later.

On the other hand, the image acquisition unit 300 is preferably configured to rotate and pass the injection product TO when the conveying conveyor 310 passes through the imaging range of the machine vision camera 320, and captures the injection product at 360 °. It may be configured to acquire an image of the front surface of the injection-molded product.

To this end, as shown in FIGS. 7 to 9 , the transport conveyor 310 is formed to have a width smaller than the length of the loaded injection product TO, so that at least one end of both ends of the injection product protrudes to the outside of the transport conveyor 310 . More preferably, the transport conveyor 310 is formed to have a width smaller than the length of the injection-molded product, and guide films 315 are erected on both sides of the transport conveyor 310 so that both ends of the injection-molded product TO protrude. .

In addition, rotation generating means 317 for rotating the injection-molded product may be provided at both sides or in the center between both sides in the transport direction of the injection-molded material. That is, the rotation generating means 317 may be provided on the left and right sides when the injection product is transferred forward, or the rotation generating means 317 may be provided at the center between the left and right sides.

Here, the rotation generating means 317 may be a friction body that causes rolling friction or surface friction such as a roller or a conveyor to rotate, and may be provided along the entire length of the transfer conveyor 310, but is preferably a machine vision camera It may be formed only by a length corresponding to the imaging range of 320 .

Through this, the injection product TO transported by the transfer conveyor 310 rotates by friction with the rotation generating means 317 when passing through the imaging range of the machine vision camera 320 so that the machine vision camera 320 is It is possible to acquire an entire image of the injection product TO.

In addition, the image acquisition unit 300 may further include a multi-stage loading prevention means 330 for preventing the injection product TO, which is loaded and transported on the transfer conveyor 310 from being stacked in multiple stages.

Specifically, the transfer conveyor 310 forms the separation membrane 311 as high as the diameter of the injection product TO so that the injection product TO, which is rapidly transferred from the high-speed linear feeder 224, is not loaded in two or more stages. , cannot be prevented from being loaded between the loaded injection products of the transfer conveyor 310, but it is possible to prevent the loading by configuring the multi-stage loading prevention means 330 .

Here, the multi-stage loading prevention means 330 may be provided on the upper side of the transfer conveyor 310 in front of the position of the machine vision camera 320 , but is not limited, but preferably when the injection product TO is loaded in two stages. It may be provided with a fixing plate 331 or a fixing rod 332 positioned at a height lower than the height of the .

In the case of the fixed plate 331, as shown in Fig. 4 or 5, it is formed in an 'a' shape for example and can be fixedly installed on one side of the transfer conveyor 310, and the fixed rod 332 is shown in Fig. As shown, a mounting groove 332a is formed on the guide film 315 formed in front of the machine vision camera 320, and it is formed to be mounted in the mounting groove 332a, so that it can be easily separated. .

However, as described above, the shape of the multi-stage loading prevention means 330 is not limited thereto, and it does not matter what shape it is formed in as long as it is a configuration that can prevent the loading of two or more stages of the injection-molded product. may be provided.

The multi-stage loading prevention means 330 including the fixing plate 331 or the fixing rod 332 is loaded in multiple stages at a fixed or mounted position as shown in FIG. 11 and transported along the transfer conveyor 310 . can be pushed backward, and the injection product pushed by the multi-stage loading prevention means 330 can be moved to an empty space between the separation membranes 311 of the transfer conveyor 310 and loaded.

In addition, the image acquisition unit 300 may further include lighting devices 340 installed on both sides of the transfer conveyor 310 on which the machine vision camera 320 is located. The lighting device 340 emits light within the range in which the machine vision camera 320 captures the injection product to further increase the clarity of the image acquired by the machine vision camera 320, and through this, the control analysis unit 400 analyzes When performing, it is possible to distinguish defective products with a clearer picture quality, so that the rate of classification of defective products can be further improved.

The control analysis unit 400 may be interlocked with the image acquisition unit 300 to receive an image of the injection product acquired from the image acquisition unit 300 . In addition, the control analysis unit 400 is provided with the artificial intelligence module and can analyze the received injection molding image based on the equipped artificial intelligence module to classify defective products.

In addition, the control analysis unit 400 includes each part of the artificial intelligence-based high-speed quality inspection system for injection molding of the present invention, that is, the supply unit 100 , the alignment transfer unit 200 , the image acquisition unit 300 , the defective product search unit 500 , etc. can be configured to control

Through this, the control analysis unit 400 may classify defective products based on the artificial intelligence module and then control the defective product search unit 500 to be described later so that the defective product search unit 500 searches for defective products.

Specifically, the control analysis unit 400 includes a PLC control panel 410 interlocked with an HMI (Human Machine Interface, 415), and a PC control panel 420 including an artificial intelligence module 421 and a vision module 422. It may be configured, and the PLC control panel 410 and the PC control panel 420 are configured to be connected to each other through a wired or wireless network, so that they can be operated in conjunction with each other.

At this time, in the PC control panel 420 , the vision module 422 interlocked with the machine vision camera 320 interacts with the artificial intelligence module 421 and is executed, and defective products are detected by learning by the artificial intelligence module 421 . It can classify defective items more precisely, faster and more precisely than classifying defective items with a simple vision module.

More specifically, when acquiring a shot image of an injection product with the machine vision camera 320 , the artificial intelligence module 421 controls the camera exposure time and illuminance through the control of the machine vision camera 320 and the lighting device 340 , etc. It is possible to generate various kinds of image data by adjusting, and collect the data sets for learning and verification as a control value most suitable for the artificial intelligence module 421 .

Thereafter, the collected data set can be pre-processed. In this process, light reflection due to the curved characteristics of the product can be processed with the vision module 422, and the artificial intelligence module 421 can be used for the pre-processed image data. By labeling the defective locations such as dark spots, browning, and scratches, it is possible to distinguish normal products from defective products more precisely, quickly and precisely.

That is, the artificial intelligence module 421 collects the image taken from the machine vision camera 320 in the image collection step (S10) and in the image collection step (S10), if the image does not meet the learning and verification requirements, the machine vision camera The images collected after the control step (S20) and the control step (S20) that meet the learning and verification requirements by controlling the 320 and the lighting device 340 are removed using the vision module 422 to remove light reflections, etc. Learning step (S40), learning step (S40) to learn the bad locations such as black spots, browning, scratches, etc. while comparing the image preprocessed in the image preprocessing step (S30), the image preprocessing step (S30) with the normal image Defective products can be classified by including a defective product determination step (S50) of discriminating and labeling the learned defective positions and classifying defective items.

Here, the artificial intelligence module 421 is not limited to any specific form, but preferably, as an example, a deep learning model of PaDiM may be used, and the operation of the control analysis unit 400 to classify defective products or control the operation with the naked eye. To confirm, the PC control panel 420 may be connected to the monitor 425 .

The defective product detection unit 500 may be provided in the conveying direction of the injection-molded material conveyed by the image acquisition unit 300 . In addition, the defective product retrieval unit 500 may be controlled by the control analysis unit 400 to detect the divided defective products.

To this end, the defective product detection unit 500 may include a punching unit 510 and a collection device 520 .

Specifically, the punching means 510 may be provided on one side in the transport direction of the injection-molded material transported by the image acquisition unit 300 . In addition, the punching means 510 may be configured to receive a control signal from the control analysis unit 400 to push the defective product from the provided position to the other side.

The recovery device 520 may be provided at a position opposite to the punching means 510 . That is, the punching means 510 and the recovery device 520 may be provided on both sides of the transfer conveyor 310 with the transfer conveyor 310 interposed therebetween, and may be formed at positions facing each other.

Through this, the recovery device 520 may recover defective products pushed out by the punching means 510 from the opposite side of the punching means 510 , and good products except for the recovered defective products are continuously transported along the transfer conveyor 310 . can be

On the other hand, the high-speed artificial intelligence-based injection molding quality inspection system according to an embodiment of the present invention, as shown in FIG. 13, receives the information of the divided defective product from the control analysis unit 400 and performs a re-analysis of the defective product cloud server 600 may further include.

The cloud server 600 may receive the defective product information to perform the defective product reanalysis and separately store the reanalyzed result, and at the same time transmit the defective product reanalysis information to the control analysis unit 400 .

The control analysis unit 400 that has received the defective product reanalysis information from the cloud server 600 compares the defective product information analyzed by itself with the defective product reanalysis information transmitted from the cloud server 600 and performs artificial intelligence learning, Defective products can be judged more accurately.

In addition, the artificial intelligence-based high-speed quality inspection system for injection molding according to an embodiment of the present invention is provided in the transport direction of the injection-molded material transported by the image acquisition unit 300 to the rear of the defective product detection unit 500 as shown in FIG. 12 . It may further include a non-defective product counter 700 for counting the injection product of the non-defective product.

The non-defective counter unit 700 may be provided with a photosensor, etc., and may image and count the transferred injection product, and may determine a defective rate and the like by comparing the supply amount using the supply unit 100 .

Although the embodiments of the present invention have been described above with reference to the accompanying drawings, those of ordinary skill in the art to which the present invention pertains can implement the present invention in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Accordingly, the embodiments described above are illustrative in all respects and not restrictive.

100: supply
110: input hopper
112: inlet
114: safety door
120: supply conveyor
125: movement barrier
200: alignment transfer unit
210: rotary feeder
212: accommodating space
214: information board
214a: escape barrier
220: straight feeder
222: constant speed straight feeder
222a: power generating means
222b: guide film
224: high-speed straight feeder
224a: power generating means
224b: guide film
230: escape roller
230a : link
300: image acquisition unit
310: transfer conveyor
311: separator
315: guide curtain
317: rotation generating means
320: machine vision camera
330: means for preventing multi-stage loading
331: fixed plate
332: fixed rod
332a: mounting groove
340: lighting device
400: control analysis unit
410: PLC control panel
415 : HMI
420: PC control panel
421: artificial intelligence module
422: vision module
425 : monitor
500: defective product detection unit
510: punching means
520: recovery device
600: cloud server
700: good product counter part
TO: injection molding

Claims (12)

a supply unit for supplying an injection molding product;
an alignment transfer unit for aligning and conveying the injection product supplied from the supply unit;
an image acquisition unit configured to acquire an image by capturing the conveyed injection material while receiving the injection material transferred from the alignment transfer unit and transferring it to one side;
A control analysis unit that analyzes based on an artificial intelligence module and a vision module using the image of the injection product obtained from the image acquisition unit, classifies defective products, and controls each unit; and
Comprising a defective product retrieval unit provided in the conveying direction of the injection-molded material conveyed by the image acquisition unit to detect the divided defective products,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
The method of claim 1,
The alignment transfer unit,
An accommodating space is provided inside to accommodate the injection-molded material supplied from the supply unit, and a guide plate extending spirally from the lower end to the upper end of the accommodation space is formed, and the injection-molded material received while rotating by power is arranged in a line along the guide plate and transported. rotary feeder and
Forming a straight line length from the guide plate end of the rotary feeder to the image acquisition unit, comprising a linear feeder that delivers the injection product transferred from the rotation feeder to the image acquisition unit,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
3. The method of claim 2,
The straight feeder,
A constant-speed linear feeder that receives the injection product from the rotary feeder and transfers it at a constant speed; and
and a high-speed linear feeder that receives the injection material transferred from the constant-speed linear feeder and transfers it to the image acquisition unit at a faster speed than the constant-speed linear feeder,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
4. The method of claim 3,
The straight feeder,
Further comprising an escape roller for separating the injection product transferred from the constant-speed linear feeder to the high-speed linear feeder,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
The method of claim 1,
The image acquisition unit,
A transfer conveyor in which a plurality of separation membranes are regularly installed at intervals sufficient to accommodate one injection-molded product, and receive and load the injection-molded product from the alignment transfer unit, and transport it in one direction;
A machine vision camera that is installed on the upper side of the conveying conveyor to acquire an image by capturing the transported injection product, and transmits the acquired image to the control analysis unit,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
6. The method of claim 5,
The transfer conveyor is
It is formed with a width smaller than the length of the loaded injection-molded product so that at least one end of both ends of the injection-molded product protrudes to the outside,
A rotation generating means for rotating the injection-molded product is provided in the center between both sides or both sides in the conveying direction of the injection-molded product,
Characterized in that the machine vision camera can acquire the entire image of the injection-molded product by rotating and moving the injection-molded material conveyed by the conveying conveyor,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
6. The method of claim 5,
The image acquisition unit,
Further comprising a multi-stage loading prevention means provided on the upper side of the transfer conveyor in front of the position of the machine vision camera to prevent the multi-stage loading of the transferred injection product,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
6. The method of claim 5,
The image acquisition unit,
Further comprising a lighting device installed on both sides of the conveying conveyor on which the machine vision camera is located and emitting light to further enhance the clarity of the image acquired by the machine vision camera,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
9. The method of claim 8,
The artificial intelligence module is
an image collection step of collecting images captured by the machine vision camera;
a control step of controlling the machine vision camera and lighting device to meet the learning and verification requirements when the image does not meet the learning and verification requirements in the image acquisition step;
an image pre-processing step of pre-processing the images collected after the control step to remove light reflection using a vision module;
A learning step of learning a defective position while comparing the image preprocessed in the image preprocessing step with a normal product image; and
Characterized in that, including a defective product determination step of discriminating and labeling the defective position learned through the learning step, and classifying the defective product,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
The method of claim 1,
The defective product detection unit,
Punching means provided on one side of the conveying direction of the injection-molded material conveyed by the image acquisition unit, receiving a control signal from the control analysis unit, and pushing the defective product from the provided position to the other side;
and a recovery device provided at a position opposite to the punching means and recovering defective products pushed out by the punching means;
Artificial intelligence-based high-speed quality inspection system for injection moldings.
The method of claim 1,
Further comprising a cloud server for receiving the defective product information divided from the control analysis unit, performing a defective product reanalysis, and transmitting the performed defective product reanalysis information to the control analysis unit,
Artificial intelligence-based high-speed quality inspection system for injection moldings.
The method of claim 1,
Further comprising a non-defective counter unit provided in the conveying direction of the injection-molded material transported by the image acquisition unit to the rear of the defective product detection unit and counting the non-defective product injection product,
Artificial intelligence-based high-speed quality inspection system for injection moldings.

Images