Apparatus and method for determining presence or absence of component using deep learning model

Abstract

Embodiments of the present invention relate to an apparatus and a method for determining the presence or absence of a component using a deep learning model. The apparatus for determining the presence or absence of a component according to an embodiment of the present invention for achieving the objective described above comprises: a camera mounted on a chip mounter; and a processor. The processor may obtain, from the camera, an image of the pocket provided in a component supply reel supplied through a feeder, and determine the presence or absence of a component in the pocket on the basis of the image of the pocket using a pre-trained deep learning model.

Description

Device and method for checking the presence or absence of a component using a deep learning model

[0001] Embodiments of the present invention relate to a device and method for checking the presence or absence of a component using a deep learning model.

[0002] The chip mounter picks up components from the component feeder and mounts them onto the PCB. The component feeder's mechanical position is fixed, and components are stored in pockets within it. The location of the pockets and the presence of components within them can be determined in various ways. If a component is picked up without a pocket, the camera recognition process may generate an error indicating a failure to pick up the component. However, this requires the head to move again to pick it up, increasing production time. If a component is detected as missing from a pocket, the next component is fed, resulting in component waste.

[0003] The present invention aims to address various issues, including those described above, by providing a device and method for verifying the presence or absence of components using a deep learning model. However, these tasks are exemplary and do not limit the scope of the present invention.

[0004] According to one aspect of the present invention, a device for checking the presence or absence of a part in a pocket is provided, comprising a camera mounted on a chip mounter, and a processor, wherein the processor obtains an image of the pocket provided on a part supply reel supplied through a feeder from the camera, and checks the presence or absence of a part in the pocket using a deep learning model learned in advance based on the image of the pocket.

[0005] The camera is mounted on the head of the chip mounter, and the processor can obtain an image of the upper surface of the component provided on the upper surface of the pocket from the camera.

[0006] The above processor can train a deep learning model based on an image when there is no part in the pocket and an image when there is a part in the pocket.

[0007] The above processor can train different deep learning models according to the shape of the pocket, and use the deep learning model corresponding to the shape of the pocket to check the presence or absence of a component in the pocket.

[0008] According to one aspect of the present invention, a method for confirming the presence or absence of a component in a pocket, performed by a computing device, is provided, comprising the steps of: obtaining an image of the pocket provided in a component supply reel supplied through a feeder using a camera mounted on a chip mounter; and confirming the presence or absence of a component in the pocket using a deep learning model learned in advance based on the image of the pocket.

[0009] The step of acquiring an image of the pocket may include a step of acquiring an image of the upper surface of the component provided on the upper surface of the pocket using the camera mounted on the head of the chip mounter.

[0010] The step of checking whether there is a part in the pocket may include a step of training a deep learning model based on an image when there is no part in the pocket and an image when there is a part in the pocket.

[0011] The step of checking whether there is a part in the pocket may include a step of training different deep learning models according to the shape of the pocket, and a step of checking whether there is a part in the pocket using a deep learning model corresponding to the shape of the pocket.

[0012] According to one aspect of the present invention, a computer program stored in a recording medium is provided to execute the above-described method using a computer.

[0013] Other aspects, features and advantages other than those described above will become apparent from the following detailed description, claims and drawings for carrying out the invention.

[0014] According to one embodiment of the present invention, as described above, a device and method for effectively identifying the presence of a component can be implemented using a deep learning model. Of course, the scope of the present invention is not limited by these effects.

[0015] FIG. 1 is a drawing for explaining the configuration and operation of a device for checking the presence or absence of a component according to one embodiment of the present invention.

[0016] Figure 2 is a flowchart for explaining a method for checking the presence or absence of a part according to one embodiment of the present invention.

[0017] Figure 3 is a flowchart for explaining a method for checking the presence or absence of a part according to another embodiment of the present invention.

[0018] FIG. 4 and FIG. 5 are drawings for explaining a method for checking the presence or absence of a part according to one embodiment of the present invention.

[0019] The present invention is capable of various modifications and embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. The effects and features of the present invention, as well as the methods for achieving them, will become clearer with reference to the embodiments described in detail below, along with the drawings. However, the present invention is not limited to the embodiments disclosed below and can be implemented in various forms.

[0020] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals and redundant descriptions thereof will be omitted.

[0021] In the following examples, terms such as "first" and "second" are not used in a limiting sense, but rather to distinguish one component from another. Furthermore, singular expressions include plural expressions unless the context clearly dictates otherwise. Furthermore, terms such as "include" and "have" imply the presence of features or components described in the specification, but do not exclude the possibility that one or more other features or components may be added.

[0022] For convenience of explanation, the sizes of components in the drawings may be exaggerated or reduced. For example, the sizes and thicknesses of each component shown in the drawings are arbitrarily indicated for convenience of explanation, and thus the present invention is not necessarily limited to what is shown.

[0023] In the following embodiments, when a part such as an area, component, sub-part, block or module is said to be on or above another part, this includes not only the case where it is directly on top of the other part, but also the case where another area, component, sub-part, block or module is interposed therebetween. And when it is said that an area, component, sub-part, block or module is connected, this includes not only the case where the areas, components, sub-parts, blocks or modules are directly connected, but also the case where another area, component, sub-part, block or module is interposed therebetween and is indirectly connected therebetween.

[0024] Hereinafter, various embodiments of the present invention will be described in detail with reference to the attached drawings so that a person having ordinary skill in the art to which the present invention pertains can easily practice the present invention.

[0025] FIG. 1 is a drawing for explaining the configuration and operation of a device for checking the presence or absence of a component according to one embodiment of the present invention.

[0026] Referring to FIG. 1, a device (100) for checking the presence or absence of a component according to an embodiment of the present invention may include a memory (110), a processor (120), and a communication module (130). In addition, the device (100) for checking the presence or absence of a component according to an embodiment of the present invention may further include a camera (140). However, the present invention is not limited thereto, and the device (100) for checking the presence or absence of a component may further include other components, or some components may be omitted. Some components of the device (100) for checking the presence or absence of a component may be separated into multiple devices, or multiple components may be merged into one device.

[0027] The memory (110) is a computer-readable storage medium and may include a non-perishable mass storage device such as a random access memory (RAM), a read-only memory (ROM), and a disk drive. In addition, a program code and a deep learning model for controlling the component presence / absence checking device (100) may be temporarily or permanently stored in the memory (110).

[0028] The processor (120) controls the overall operation of the component presence / absence detection device. For example, the processor (120) may be implemented in a form that selectively includes a processor, an application-specific integrated circuit (ASIC), another chipset, a logic circuit, a register, a communication modem, and / or a data processing device known in the art to perform the above-described operations. For example, the processor (120) may perform basic arithmetic, logic, and input / output operations, and may execute program codes stored in, for example, the memory (110). The processor (120) may store data in the memory (110) or load data stored in the memory (110).

[0029] The camera (140) may be a camera mounted on a chip mounter. Additionally, the camera (140) may be a downward camera mounted on the head of the chip mounter to photograph components within a pocket.

[0030] The processor (120) obtains an image of a pocket provided in a parts supply reel supplied through a feeder from a camera, and can check the presence or absence of a part in the pocket using a deep learning model learned in advance based on the image of the pocket.

[0031] The communication module (130) may provide a function for communicating with an external server via a network. For example, a request generated by the processor (120) of the component presence / absence checking device (100) according to a program code stored in a recording device such as a memory (110) may be transmitted to an external server via a network under the control of the communication module (130). Conversely, control signals, commands, contents, files, etc. provided under the control of the processor of the external server may be received by the component presence / absence checking device (100) via the network through the communication module (130). For example, control signals or commands from an external server received via the communication module (130) may be transmitted to the processor (120) or the memory (110).

[0032] The communication method is not limited, and may include not only a communication method that utilizes a communication network that the network may include (e.g., a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network), but also short-range wireless communication between devices. For example, the network may include any one or more of a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), and the Internet. In addition, the network may include any one or more of a network topology including, but not limited to, a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree, or a hierarchical network.

[0033] Additionally, the communication module (130) can communicate with an external server via a network. The communication method is not limited, but the network may be a short-range wireless communication network. For example, the network may be a Bluetooth, BLE (Bluetooth Low Energy), or Wi-Fi communication network.

[0034] In addition, the device (100) for checking the presence or absence of components according to the present invention may include an input / output interface. The input / output interface may be a means for interfacing with an input / output device. For example, the input device may include a device such as a keyboard or a mouse, and the output device may include a device such as a display for displaying a communication session of an application. As another example, the input / output interface may be a means for interfacing with a device that integrates input and output functions, such as a touchscreen. As a more specific example, the processor (120) of the device (100) for checking the presence or absence of components may display a service screen or content configured using data provided by an external server on the display through the input / output interface when processing commands of a computer program loaded in the memory (110).

[0035] Additionally, in other embodiments, the component presence / absence checking device (100) may include more components than those of FIG. 1. For example, it may be implemented to include at least some of the input / output devices described above, or may further include other components such as a battery and charging device for supplying power to internal components, various sensors, a database, etc.

[0036] The processor (120) can control the component presence / absence confirmation device (100) to perform steps included in the component presence / absence confirmation method of FIGS. 2 and 3. For example, the processor (120) can be implemented to execute instructions according to the code of the operating system included in the memory (110) and the code of at least one program. Here, the components of the processor (120) can be expressions of different functions of the processor (120) performed by the processor (120) according to instructions provided by the program code stored in the component presence / absence confirmation device (100). The specific operation of the processor (120) will be described with reference to the flowchart of the component presence / absence confirmation method of FIG. 2.

[0037] Figure 2 is a flowchart for explaining a method for checking the presence or absence of a part according to one embodiment of the present invention.

[0038] Referring to FIG. 2, in step S110, the processor (120) can obtain an image of the pocket using a camera mounted on the chip mounter.

[0039] For example, the processor (120) can obtain an image of the upper surface of a component provided on the upper surface of a pocket using a camera mounted on the head of a chip mounter.

[0040] In step S120, the processor (120) can use a pre-trained deep learning model based on an image of the pocket to determine whether a component is present in the pocket. For example, the processor (120) can train the deep learning model based on an image of a pocket without a component and an image of a pocket with a component.

[0041] Additionally, the processor (120) can train different deep learning models depending on the shape of the pockets provided on the parts supply reel supplied through the feeder. For example, the parts supply reel may have a belt shape. Furthermore, the processor (120) can use a deep learning model corresponding to the shape of the pocket to determine the presence or absence of parts within the pocket.

[0042] Figure 3 is a flowchart illustrating a method for confirming the presence or absence of a component according to another embodiment of the present invention. For example, a tape feeder may be used as the feeder according to one embodiment of the present invention. For example, a tape feeder may refer to a feeder that supplies components to a pickup location of a component mounting device by pitch-transferring a carrier tape using a gear unit. In addition, the reel used in the tape feeder may be classified into a paper reel and an emboss reel depending on the type.

[0043] Referring to FIG. 3, a flowchart of a method for training a deep learning model according to one embodiment of the present invention is illustrated.

[0044] In step S210, the processor (120) can classify pocket images of the feeder by reel type. For example, the reel type may include a paper reel and an emboss reel.

[0045] In step S220, the processor (120) can classify images based on the presence or absence of a component within the pocket. For example, the processor (120) can classify images when a component is within the pocket and images when a component is not within the pocket.

[0046] In step S230, the processor (120) can generate deep learning input data by cutting out an area larger than the component size by a preset ratio (e.g., 1.1 times) based on the center of the pocket within the classified images.

[0047] In step S240, the processor (120) can input the generated deep learning input data into a deep learning model to train the deep learning model. For example, a component presence / absence classifier including a deep learning model can be created through deep learning training.

[0048] For example, the reels of components used in a tape feeder include paper reels and emboss reels, and the shapes of pocket images differ accordingly. The processor (120) according to one embodiment of the present invention can train deep learning models corresponding to the types of reels. For example, a first deep learning model corresponding to a paper reel and a second deep learning model corresponding to an emboss reel can be trained and used to confirm the presence or absence of components. In this case, the presence or absence of components can be confirmed with high accuracy even with a small amount of training data.

[0049] FIG. 4 and FIG. 5 are drawings for explaining a method for checking the presence or absence of a part according to one embodiment of the present invention.

[0050] First, referring to FIG. 4, an image of a pocket in a paper reel according to one embodiment of the present invention is illustrated.

[0051] For example, as illustrated in FIG. 4, when a part (420) is supplied in the part supply direction (440), the presence or absence of a part in each pocket can be confirmed based on images of a pocket (410) without a part and a pocket (415) with a part. In this case, since the size of the part (420) is small compared to the size of the pocket (415), a space of a certain size can be created between one side of the pocket (415) and the part (420) within the pocket (415). For example, the pocket (410) without a part and the pocket (415) with a part can be arranged at an interval of the inter-pocket pitch (430).

[0052] The processor (120) can generate deep learning input data by cropping an area within the classified images to a size that is a preset ratio (e.g., 1.1 times) larger than the component size, based on the center of the pocket. According to the present invention, by training a deep learning model by cropping an area larger than the component size, the accuracy of determining the presence or absence of a component can be improved.

[0053] Referring to FIG. 5, the presence or absence of a component within a pocket is confirmed in an emboss reel according to one embodiment of the present invention. FIG. 5(a) shows an image of a pocket with a component, and FIG. 5(b) shows an image of a pocket without a component.

[0054] For example, referring to FIG. 5(a), it can be confirmed that a part (520) is present within a pocket (510) containing a part. Furthermore, referring to FIG. 5(b), it can be confirmed that a pocket (530) does not contain a part. According to the present invention, the accuracy and speed of component presence detection can be improved by training a deep learning model using pocket images according to the presence or absence of parts for each reel type.

[0055] The devices and / or systems described above may be implemented as hardware components, software components, and / or a combination of hardware components and software components. The devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0056] Software may include computer programs, codes, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may, independently or collectively, command the processing device. The software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage media or device, or transmitted signal waves, for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

[0057] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the embodiment or may be those known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of the program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The above-mentioned hardware devices may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0058] Although the embodiments described above have been described by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above teachings. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0059] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims described below.

Claims

1. In a device for checking the presence or absence of a part in a pocket, Camera mounted on chip mounter; and Contains a processor, The above processor is a device for checking the presence or absence of a part, which obtains an image of the pocket provided in the pocket supplied through the feeder from the camera, and checks the presence or absence of a part in the pocket using a deep learning model learned in advance based on the image of the pocket.

2. In paragraph 1, The above camera is mounted on the head of the chip mounter, The above processor is a device for checking the presence or absence of a component, which obtains an image of the upper surface of the component provided on the upper surface of the pocket from the camera.

3. In paragraph 1, The above processor is a device for checking the presence or absence of a part, which trains a deep learning model based on an image when there is no part in the pocket and an image when there is a part in the pocket.

4. In paragraph 1, The above processor is a device for checking the presence or absence of a part in the pocket, which trains different deep learning models according to the shape of the pocket and checks the presence or absence of a part in the pocket using the deep learning model corresponding to the shape of the pocket.

5. A method for checking the presence or absence of a part in a pocket performed by a computing device, A step of obtaining an image of the pocket provided on the component supply reel supplied through the feeder using a camera mounted on the chip mounter; and A step of checking whether there is a part in the pocket using a pre-trained deep learning model based on an image of the pocket; A method for checking the presence or absence of a part, including:

6. In paragraph 5, A method for confirming the presence or absence of a component, wherein the step of obtaining an image of the pocket includes the step of obtaining an image of the upper surface of the component provided on the upper surface of the pocket using the camera mounted on the head of the chip mounter.

7. In paragraph 5, A method for checking whether there is a part in the pocket, wherein the step of checking whether there is a part in the pocket includes the step of training a deep learning model based on an image when there is no part in the pocket and an image when there is a part in the pocket.

8. In paragraph 5, The step of checking the presence or absence of a part in the above pocket is: A step of training different deep learning models according to the shape of the above pocket; and A method for confirming the presence or absence of a part, comprising a step of confirming the presence or absence of a part in a pocket using a deep learning model corresponding to the shape of the pocket.

9. A computer program stored in a recording medium for executing the method of any one of claims 5 to 8 using a computing device.

Images