Control method and system based on multi-area multi-material mounting

Abstract

The invention discloses a control method and system based on multi-area multi-material mounting, relates to the technical field of automatic mounting, is applied to a chip mounter, and comprises a chip mounter control system, a multi-area flexible vibration disc, a top camera, a mechanical arm and a mounting head. The control method based on multi-area multi-material mounting comprises the following steps that S10, a chip mounter control system controls a multi-area flexible vibration disc to vibrate so as to adjust the positions and angles of various materials in all independent areas in the multi-area flexible vibration disc; s20, receiving a material image, collected by the top camera, in the multi-area flexible vibration disc, and preprocessing the material image; s30, carrying out image segmentation on the preprocessed material image, and identifying an element with an upward front side in the segmented image by adopting a target detection algorithm; and S40, controlling a mechanical arm to grab the element identified in the step S30, and controlling a mounting head to mount the element. The method has the beneficial effects that the production quality is guaranteed, the production cost is saved, and the production efficiency is optimized.

Description

Technical Field

[0001] This invention relates to the field of automated chip mounting technology, and more specifically, to a control method and system for multi-area, multi-material mounting. Background Technology

[0002] Currently, in the electronics manufacturing field, with the increasing miniaturization and multifunctionality of electronic products, surface mount technology (SMT) faces an urgent need to handle multiple materials simultaneously and improve mounting accuracy and efficiency. Traditional mounting equipment typically handles only one type of material per unit. In multi-material assembly scenarios, sequential operation is required, necessitating manual intervention for material switching, which is slow and cannot meet the demands of high-precision, high-efficiency production. Consequently, it cannot achieve rapid and accurate material identification and mounting.

[0003] Therefore, this invention provides a control method and system based on multi-region multi-material mounting, which can reduce manual intervention, meet the production requirements of high precision and high efficiency, thereby ensuring production quality, saving production costs, and optimizing production efficiency. Summary of the Invention

[0004] To overcome the shortcomings of existing technologies, this invention provides a control method and system based on multi-region multi-material mounting, which can reduce manual intervention, meet the production requirements of high precision and high efficiency, thereby ensuring production quality, saving production costs, and optimizing production efficiency.

[0005] The technical solution adopted by this invention to solve its technical problem is: a control method based on multi-region multi-material placement, applied to a pick-and-place machine, wherein the pick-and-place machine includes at least a pick-and-place machine control system, a multi-region flexible vibratory feeder, a top camera, a robotic arm, and a placement head, wherein the pick-and-place machine control system is respectively connected to the multi-region flexible vibratory feeder, the top camera, the robotic arm, and the placement head via industrial communication; the improvement lies in that the control method based on multi-region multi-material placement includes the following steps: S10, the chip mounter control system controls the vibration of the multi-zone flexible vibratory feeder to adjust the position and angle of various materials in each independent zone of the multi-zone flexible vibratory feeder; S20, the chip mounter control system receives material images from the multi-area flexible vibrating plate captured by the top camera and preprocesses the material images; S30, the chip mounter control system performs image segmentation on the pre-processed material image and uses target detection algorithm to identify the components facing up in the segmented image; S40, the pick-and-place machine control system controls the robotic arm to grasp the components identified in S30, and controls the placement head to place the components.

[0006] Furthermore, in step S10, during the vibration of the multi-zone flexible vibratory feeder, the pick-and-place machine control system dynamically adjusts the vibration parameters of the multi-zone flexible vibratory feeder through a PID control algorithm. The vibration parameters include vibration frequency, amplitude, and vibration waveform. The vibration frequency is adjustable between 200Hz and 500Hz, the amplitude is adjustable between 0.1 and 0.5mm, and the vibration waveform is selected between square wave and sine wave.

[0007] Furthermore, in step S20, the specific steps for preprocessing the material image include: S201, Grayscale Conversion: Converting the material image from a color image to a grayscale image; S202, Gaussian filtering noise reduction: The Gaussian function is used to perform a weighted average on the grayscale image to smooth the image and suppress noise; S203, Histogram Equalization: Redistributes the gray values ​​of the grayscale image after Gaussian filtering and denoising, stretching the relatively concentrated grayscale range to a uniform distribution across the entire grayscale range.

[0008] Furthermore, in step S201, the specific method for converting the material image from a color image to a grayscale image is as follows: Read the R, G, and B components of each pixel in a color image; Use formula Calculate the grayscale value of each pixel, where R represents the red component of each pixel in the color image, G represents the green component of each pixel in the color image, B represents the blue component of each pixel in the color image, and Y represents the grayscale value. The calculated grayscale values ​​are assigned to the corresponding positions in the new image to form a grayscale image.

[0009] Furthermore, in step S202, the specific method of using a Gaussian function to perform a weighted average on the grayscale image to smooth the image and suppress noise is as follows: Determine the size and standard deviation of the Gaussian kernel. ; The weight of each position within the Gaussian kernel is calculated based on a two-dimensional Gaussian function and then normalized; wherein the calculation expression of the two-dimensional Gaussian function is: In the formula, This represents the x-coordinate of each position within the Gaussian kernel relative to the center point of the Gaussian kernel. This represents the x-coordinate of each position within the Gaussian kernel relative to the center point of the Gaussian kernel, where the coordinates of the center point of the Gaussian kernel are (0,0). Slide a Gaussian kernel across the grayscale image and perform a convolution operation on each pixel and its neighborhood to obtain a smoothed grayscale image.

[0010] Furthermore, in step 203, the specific method for redistributing the grayscale values ​​of the grayscale image after Gaussian filtering and denoising, and stretching the relatively concentrated grayscale range to a uniform distribution across the entire grayscale range, is as follows: The gray-level histogram of the smoothed gray-level image is calculated using the formula p(r_k)=n_k / N to count the probability of each gray level appearing. In the formula, r_k represents the k-th gray level, and k is an integer greater than or equal to 0; N represents the total number of pixels in the smoothed gray-level image; p(r_k) represents the probability of gray level r_k appearing; and L represents the total number of gray levels. The cumulative distribution function of gray-level probability is calculated using the following formula: In the formula, Let R represent the possible values ​​of the random variable R; j represents the index, which is an integer between 0 and k; p(r_j) is the probability mass function of the random variable R, representing the probability that R = r_j; The formula T(r_k)=round((L-1)×cdf(r_k)) maps each gray level to a new gray level, making the new histogram tend to be uniformly distributed. In the formula, T(r_k) represents the transformation function of the new gray level after mapping, round() means rounding to the nearest integer, and L-1 represents the maximum gray value.

[0011] Furthermore, in step S30, before performing image segmentation on the preprocessed material image, the pick-and-place machine control system also needs to calculate the gradient magnitude and gradient direction angle of each pixel in the preprocessed material image. The formula for calculating the gradient magnitude is: The formula for calculating the gradient direction angle is: In the formula, Indicates the gradient magnitude; This represents the gradient of each pixel in the material image in the horizontal direction. This represents the gradient of each pixel in the material image in the vertical direction. This indicates the gradient direction angle.

[0012] Furthermore, the preprocessed material image is segmented, and the specific method for identifying face-up components in the segmented image using target detection is as follows: The coordinates of each independent region of the multi-region flexible vibratory feeder are marked in the material image, and the material image is cut into sub-images corresponding to each independent region of the multi-region flexible vibratory feeder according to the marked region coordinates. Each sub-image is then preprocessed again, its contour extracted, and its features extracted. A pre-trained classifier is used to determine whether there are any face-up elements in each sub-image.

[0013] Furthermore, the specific method by which the chip mounter control system controls the robotic arm to grasp the identified components in S30 is as follows: the chip mounter and control system uses visual positioning data collected by the top camera and employs a nonlinear compensation algorithm to perform center offset compensation, angle compensation, and flatness compensation on the identified components in order to accurately grasp the identified components.

[0014] A control system based on multi-region multi-material mounting is applied to the control method for multi-region multi-material mounting described above. The improvement lies in that the control system for multi-region multi-material mounting includes: The central control and scheduling module is used to send control commands to schedule and coordinate the work of other modules; A multi-zone material vibration module is used to classify and load various materials and adjust the angle and position of the materials through vibration; The image acquisition module is used to acquire material images and transmit them to the central control and scheduling module for processing. The image processing module is used to preprocess, segment, and detect targets in the material image in sequence to identify the components facing upwards in the material image. The component placement module is used to pick up and identify components according to control commands and accurately place them in designated positions.

[0015] The beneficial effects of this invention are as follows: This invention controls the vibration of a multi-region flexible vibratory feeder through a pick-and-place machine control system to adjust the position and angle of various materials in each independent region of the multi-region flexible vibratory feeder, facilitating subsequent material identification; the pick-and-place machine control system sequentially receives material images from the multi-region flexible vibratory feeder captured by a top camera, preprocesses the material images, performs image segmentation on the preprocessed material images, and uses target detection algorithms to identify face-up components in the segmented images, thereby achieving high-precision identification and positioning of multiple materials simultaneously; the pick-and-place machine control system controls a robotic arm to grasp the identified components and controls the placement head to place the components, thereby achieving high-precision grasping and placement of materials; in this process, various materials only need to be loaded into the independent regions of the multi-region flexible vibratory feeder manually or by a feeding device. Compared with the prior art, which requires manual intervention to switch materials, this invention significantly reduces manual intervention and enables high-precision identification, grasping, and placement of multiple materials, meeting the needs of high-precision and high-efficiency production, thereby ensuring production quality, saving production costs, and optimizing production efficiency. Attached Figure Description

[0016] Figure 1 This is an overall flowchart of a control method for multi-region multi-material mounting according to the present invention; Figure 2 This is a block diagram of a control system based on multi-region multi-material mounting according to the present invention; Figure 3 This is a hardware structure diagram of an electronic device as an example embodiment; Figure 4 This is a block diagram illustrating an electronic device as an example embodiment. Detailed Implementation

[0017] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0018] The following will clearly and completely describe the concept, specific structure, and technical effects of the present invention in conjunction with embodiments and accompanying drawings, so as to fully understand the purpose, features, and effects of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are all within the scope of protection of the present invention. Furthermore, all connections / linkages involved in the patent do not simply refer to direct contact between components, but rather to the ability to form a better connection structure by adding or reducing connecting accessories according to specific implementation conditions. The various technical features in this invention can be combined interactively without contradicting each other.

[0019] Reference Figure 1 As shown, this invention discloses a control method for multi-region, multi-material placement, applied to a pick-and-place machine. The pick-and-place machine includes at least a pick-and-place machine control system, a multi-region flexible vibratory feeder, a top camera, a robotic arm, and a placement head. The pick-and-place machine control system is connected via industrial communication to the multi-region flexible vibratory feeder, the top camera, the robotic arm, and the placement head. The control method for multi-region, multi-material placement includes the following steps: S10, the chip mounter control system controls the vibration of the multi-zone flexible vibratory feeder to adjust the position and angle of various materials in each independent zone of the multi-zone flexible vibratory feeder; It should be noted that in this embodiment, various materials are first classified and loaded into the independent areas of the multi-zone flexible vibratory feeder by manual or automatic feeding devices. Then, the pick-and-place machine control system controls the vibration of the multi-zone flexible vibratory feeder to adjust each material to a suitable position and angle for subsequent identification. This method of pre-classifying and placing various materials into the independent areas of the multi-zone flexible vibratory feeder eliminates the need for feeding devices or manual material switching, avoiding the problem of slow switching speed affecting production efficiency in the prior art. Therefore, this embodiment can optimize production efficiency. In addition, during the vibration of the multi-zone flexible vibratory feeder, the pick-and-place machine control system dynamically adjusts the vibration parameters of the multi-zone flexible vibratory feeder through a PID control algorithm. The vibration parameters include vibration frequency, amplitude, and vibration waveform. The vibration frequency is adjusted within the range of 200Hz-500Hz, the amplitude is adjusted within the range of 0.1-0.5mm, and the vibration waveform is selected between square wave and sine wave. The dynamic adjustment of the vibration parameters of the multi-zone flexible vibratory feeder by the PID control algorithm is a conventional technique in the art, and its specific principle will not be elaborated here. It should also be noted that vibration frequency mainly affects the vibration speed and stability of materials in the vibratory feeder. The higher the vibration frequency, the greater the vibration energy, and the faster the material vibrates, but it is also more prone to instability. When the feeding speed cannot keep up with the placement head's rhythm, the vibration frequency needs to be increased, especially when placing large batches of large-sized LED chips. Due to the weight and inertia of the components, a lower frequency may not be able to vibrate them to the pick-up surface, causing the placement head to wait or fail to pick up the components. In this case, the frequency can be gradually increased until the feeding speed stably matches the placement rhythm. However, if the components bounce, flip, splash, or accumulate in the feed channel; for example, when placing tiny 0402 or 0201 packaged resistors and capacitors, the components are very light, and an excessively high frequency will cause them to splash in the feed channel or even jump out of the feed tray. In this case, it is necessary to appropriately lower the frequency. Frequency is adjusted to achieve stability; amplitude is the main factor affecting component separation and the ability to overcome friction. The larger the amplitude, the stronger the force of each vibration, which helps to separate tightly fitted components, but it also makes components more prone to overshoot or damage. When components cannot be flipped smoothly in the vibratory feeder due to increased friction caused by static electricity or oil, the amplitude needs to be increased. For example, when mounting IC chips with adhesive packaging, the components may not be easy to flip from the vibratory feeder. When the system detects that there are no available quantities for several consecutive times, the PID algorithm will judge it as "insufficient feeding force" and increase the amplitude to provide a stronger "push" to successfully flip the components. However, when the components are too fragile, the amplitude needs to be reduced. For example, when mounting QFP packaged chips with thin leads, an excessive amplitude may cause the leads to collide with the feed tray during vibration and bend. Alternatively, after increasing the frequency for small components, the amplitude needs to be reduced simultaneously to avoid excessive speed, achieving a fine "high frequency, low amplitude" flipping mode. The vibration waveform determines the vibration mode. A sine wave provides a smooth, continuous driving force, resulting in gentle motion; a square wave provides an instantaneous impact force, decisive start and stop, and strong driving force. For most standard components, a sine wave is sufficient, such as ceramic capacitors and SOT components. A gentle sine wave can minimize internal stress and prevent micro-cracks from forming during vibration flipping. If it is necessary to overcome large static friction or sticky components, a square wave should be selected, especially when mounting IC chips with adhesive backing. The components may be stuck tightly in the vibratory feeder, and a smooth sine wave may not be able to flip them, while the instantaneous impact force of a square wave can effectively vibrate them. S20, the pick-and-place machine control system receives material images from a multi-area flexible vibrating plate captured by a top camera and preprocesses the material images; specifically, the preprocessing steps for the material images include: S201, Grayscale Conversion: Converting the material image from a color image to a grayscale image; further, the specific method for converting the material image from a color image to a grayscale image is as follows: Read the R, G, and B components of each pixel in a color image; Use formula Calculate the grayscale value of each pixel, where R represents the red component of each pixel in the color image, G represents the green component of each pixel in the color image, B represents the blue component of each pixel in the color image, and Y represents the grayscale value. The calculated grayscale values ​​are assigned to the corresponding positions in the new image to form a grayscale image; S202, Gaussian filtering noise reduction: A weighted average of the grayscale image is applied using a Gaussian function to smooth the image and suppress noise; furthermore, the specific method of applying a weighted average of the grayscale image using a Gaussian function to smooth the image and suppress noise is as follows: Determine the size and standard deviation of the Gaussian kernel. ; The weight of each position within the Gaussian kernel is calculated based on a two-dimensional Gaussian function and then normalized; wherein the calculation expression of the two-dimensional Gaussian function is: In the formula, This represents the x-coordinate of each position within the Gaussian kernel relative to the center point of the Gaussian kernel. This represents the x-coordinate of each position within the Gaussian kernel relative to the center point of the Gaussian kernel, where the coordinates of the center point of the Gaussian kernel are (0,0). Slide the Gaussian kernel across the grayscale image and perform a convolution operation on each pixel and its neighborhood to obtain a smoothed grayscale image. S203, Histogram equalization: This involves redistributing the grayscale values ​​of the Gaussian-filtered denoised grayscale image, stretching relatively concentrated grayscale ranges to a uniform distribution across the entire grayscale range; further, the specific method for redistributing the grayscale values ​​of the Gaussian-filtered denoised grayscale image and stretching relatively concentrated grayscale ranges to a uniform distribution across the entire grayscale range is as follows: The gray-level histogram of the smoothed gray-level image is calculated using the formula p(r_k)=n_k / N to count the probability of each gray level appearing. In the formula, r_k represents the k-th gray level, and k is an integer greater than or equal to 0; N represents the total number of pixels in the smoothed gray-level image; p(r_k) represents the probability of gray level r_k appearing; and L represents the total number of gray levels. The cumulative distribution function of gray-level probability is calculated using the following formula: In the formula, Let R represent the possible values ​​of the random variable R; j represents the index, which is an integer between 0 and k; p(r_j) is the probability mass function of the random variable R, representing the probability that R = r_j; The formula T(r_k)=round((L-1)×cdf(r_k)) maps each gray level to a new gray level, making the new histogram tend to be uniformly distributed; where T(r_k) represents the transformation function of the new gray level after mapping, round() means rounding to the nearest integer, and L-1 represents the maximum gray value. It should be noted that, in this embodiment, the grayscale conversion process converts the color image into a grayscale image using a weighted average method, which significantly reduces the amount of data while preserving brightness information and improves processing efficiency; the Gaussian filtering denoising process uses a Gaussian function to generate a convolution kernel and performs a weighted average on the grayscale image, effectively smoothing the image and suppressing high-frequency noise generated during acquisition and transmission, providing a "cleaner" image for subsequent processing; the histogram equalization process calculates the cumulative distribution function of grayscale probability, remapping the concentrated grayscale range in the image to the entire grayscale range of 0-255, thereby enhancing the overall contrast of the image and making the edges and contours of the components more prominent, facilitating accurate identification and positioning of target components in the material image; S30, the pick-and-place machine control system performs image segmentation on the preprocessed material image and uses target detection algorithms to identify components facing upwards in the segmented image; furthermore, in performing image segmentation on the preprocessed material image, the pick-and-place machine control system also needs to calculate the gradient magnitude and gradient direction angle of each pixel in the preprocessed material image, wherein the formula for calculating the gradient magnitude is: The formula for calculating the gradient direction angle is: In the formula, Indicates the gradient magnitude; This represents the gradient of each pixel in the material image in the horizontal direction, i.e., the rate of change of the pixel in the horizontal direction. It can be obtained by convolving the image with a horizontal edge detection operator (such as the x-direction kernel of the Sobel operator). The gradient of each pixel in the material image in the vertical direction, i.e. the rate of change of the pixel in the vertical direction, can be obtained by convolving the image with an edge detection operator in the vertical direction (such as the Y-direction kernel of the Sobel operator); This represents the gradient direction angle; specifically, the method for segmenting the preprocessed material image and using target detection to identify face-up components in the segmented image is as follows: The coordinates of each independent region of the multi-region flexible vibratory feeder are marked in the material image, and the material image is cut into sub-images corresponding to each independent region of the multi-region flexible vibratory feeder according to the marked region coordinates. Each sub-image is then preprocessed again, its contour extracted, and its features extracted. Specifically, the preprocessing refers to further preprocessing of each sub-image, such as binarization and morphological operations. Contour extraction involves using edge detection and contour finding algorithms to identify all possible candidate regions. Feature extraction involves extracting features from each candidate region, such as area, perimeter, convex hull, Hue moment, and color features. Use a pre-trained classifier to determine whether there are any face-up elements in each sub-image; S40, the pick-and-place machine control system controls the robotic arm to grasp the components identified in S30, and then controls the placement head to place the components. Specifically, the pick-and-place machine control system grasps the components identified in S30 by controlling the robotic arm as follows: the pick-and-place and control system uses visual positioning data collected by the top camera and a nonlinear compensation algorithm to perform center offset compensation, angle compensation and flatness compensation on the identified components in order to accurately grasp the identified components.

[0020] It should be noted that, in this embodiment, the purpose of the center offset compensation is to correct the positional deviation of the component center in the X-axis and Y-axis directions. The X-axis and Y-axis directions refer to the directions corresponding to the two right-angled sides of each independent region (square) of the multi-region flexible vibratory feed. The angle compensation is to correct the rotational deviation of the component, which may be caused by camera installation tilt, perspective distortion during image acquisition, or asymmetry in the shape of the component itself. The flatness compensation is to correct the height deviation of the component in the Z-axis direction and the tilt caused by unevenness of the worktable or warping of the component. The Z-axis direction is the direction perpendicular to the plane where the multi-region vibratory feed is located. The specific compensation process is as follows: Two-dimensional positioning using a top camera: The top camera captures images of BGA components, and through image processing algorithms (such as extracting solder ball contours and calculating their center coordinates), the precise center coordinates (X_m, Y_m) and rotation angle θ_m of the components in the XY plane are obtained; Laser sensors perform 3D topography scanning: A line laser scanner scans the surface of a BGA component to obtain 3D point cloud data of its surface, thereby obtaining a real-time planar height map of the BGA component surface. The pick-and-place machine control system, based on the precise center coordinates (X_m, Y_m) and rotation angle θ_m of the component in the XY plane, and the real-time planar height map of the BGA component surface, calls the compensation algorithm F_compensate to calculate the required offset. Specifically: center offset compensation and angle compensation: calculate the offset (Δx, Δy, Δθ) between the actual position and orientation of the component and the theoretical value; flatness compensation: calculate a "tilt compensation vector" for the real-time height map of the BGA; for example, if the lower right corner is found to be tilted by 30μm, then the placement head needs to be lowered by an additional 30μm in the lower right corner direction. The pick-and-place machine control system generates a final target pose that includes XYZ translation and XY rotation based on center offset compensation, angle compensation, and flatness compensation. Then, it controls the robotic arm to pick up components according to this compensated target pose and place the components through the placement head.

[0021] Reference Figure 2 As shown, the present invention also discloses a control system 600 based on multi-region multi-material mounting, applied to the control method based on multi-region multi-material mounting described above. The control system 600 based on multi-region multi-material mounting includes: The central control and scheduling module 601 is used to send control commands to schedule and coordinate the work of other modules; The multi-zone material vibration module 602 is used to classify and load multiple materials and adjust the angle and position of the materials through vibration. The image acquisition module 603 is used to acquire material images and transmit them to the central control and scheduling module 601 for processing. The image processing module 604 is used to preprocess, segment, and detect targets in the material image in sequence to identify the face-up components in the material image. The component placement module 605 is used to pick up and identify components according to control commands and accurately place them in designated positions.

[0022] It should be noted that the control strategy based on multi-region multi-material mounting provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed. That is, the internal structure of the control system 600 based on multi-region multi-material mounting will be divided into different functional modules to complete all or part of the functions described above. Furthermore, the control system 600 based on multi-region multi-material mounting provided in the above embodiments and the embodiments of the control method based on multi-region multi-material mounting belong to the same concept. The specific way in which each module performs operations has been described in detail in the method embodiments, and will not be repeated here.

[0023] Figure 3 A schematic diagram of the structure of an electronic device according to an exemplary embodiment is shown.

[0024] It should be noted that this electronic device is merely an example adapted to the present invention and should not be construed as providing any limitation on the scope of use of the present invention. Furthermore, this electronic device should not be interpreted as requiring or depending on having... Figure 3 One or more components of the exemplary electronic device 2000 shown.

[0025] The hardware structure of electronic devices 2000 can vary significantly due to differences in configuration or performance, such as... Figure 3 As shown, the electronic device 2000 includes: a power supply 210, an interface 230, at least one memory 250, and at least one central processing unit (CPU) 270.

[0026] Specifically, power supply 210 is used to provide operating voltage for various hardware devices on electronic device 2000.

[0027] Interface 230 includes at least one wired or wireless network interface 231 for interacting with external devices. Of course, in other examples adapted to this invention, interface 230 may further include at least one serial-to-parallel conversion interface 233, at least one input / output interface 235, and at least one USB interface 237, etc. Figure 3 As shown, this does not constitute a specific limitation.

[0028] The memory 250 serves as a carrier for resource storage and can be a read-only memory, random access memory, disk, or optical disk, etc. The resources stored on it include the operating system 251, application programs 253, and data 255, etc., and the storage method can be temporary storage or permanent storage.

[0029] The operating system 251 is used to manage and control the various hardware devices and application programs 253 on the electronic device 2000, so as to enable the central processing unit 270 to perform calculations and processing on the massive data 255 in the memory 250. It can be Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0030] Application 253 is a computer-readable instruction based on operating system 251 that performs at least one specific task, and may include at least one module ( Figure 3 (Not shown), each module may contain computer-readable instructions for the electronic device 2000. For example, a device for prioritizing tasks may be considered as an application program 253 deployed on the electronic device 2000.

[0031] Data 255 may be signal information, etc., and is stored in memory 250.

[0032] The central processing unit 270 may include one or more processors and is configured to communicate with the memory 250 via at least one communication bus to read computer-readable instructions stored in the memory 250, thereby enabling the computation and processing of massive amounts of data 255 in the memory 250. For example, a control method based on multi-region multi-material mounting can be implemented by the central processing unit 270 reading a series of computer-readable instructions stored in the memory 250.

[0033] Furthermore, the present invention can also be implemented through hardware circuits or a combination of hardware circuits and software. Therefore, the implementation of the present invention is not limited to any specific hardware circuit, software, or combination thereof.

[0034] Please see Figure 4 This invention provides an electronic device 4000, which may include: a desktop computer, a laptop computer, a server, etc., with sensor recognition capabilities.

[0035] exist Figure 4 In this context, the electronic device 4000 includes at least one processor 4001 and at least one memory 4003.

[0036] The data interaction between the processor 4001 and the memory 4003 can be achieved through at least one communication bus 4002. This communication bus 4002 may include a path for transmitting data between the processor 4001 and the memory 4003. The communication bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 4002 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0037] Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0038] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0039] The memory 4003 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program instructions or code in the form of instructions or data structures and accessible by the electronic device 4000, but not limited thereto.

[0040] The memory 4003 stores computer-readable instructions, and the processor 4001 can read the computer-readable instructions stored in the memory 4003 through the communication bus 4002.

[0041] The computer-readable instructions are executed by one or more processors 4001 to implement the control method based on multi-region multi-material mounting in the above embodiments.

[0042] Furthermore, this embodiment of the invention provides a storage medium storing computer-readable instructions, which are executed by one or more processors to implement the control method based on multi-region multi-material mounting as described above.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. By pre-classifying and placing various materials in the independent areas of the multi-zone flexible vibrating plate, there is no need for a feeding device or manual material switching. This avoids the problem of slow switching speed affecting production efficiency in existing technologies, thereby saving labor costs and optimizing production efficiency. 2. The pick-and-place machine control system sequentially receives material images from a multi-area flexible vibrating plate captured by a top camera, preprocesses the material images, segments the preprocessed material images, and uses target detection algorithms to identify components facing upwards in the segmented images. This achieves high-precision identification and positioning of multiple materials simultaneously. The system then controls a robotic arm to grasp the identified components and controls the placement head to place the components, thereby achieving high-precision material grasping and placement. This meets the requirements of high-precision and high-efficiency production, ensuring production quality and optimizing production efficiency.

[0044] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A control method for multi-region, multi-material placement, applied to a pick-and-place machine, wherein the pick-and-place machine includes at least a pick-and-place machine control system, a multi-region flexible vibratory feeder, a top camera, a robotic arm, and a placement head, wherein the pick-and-place machine control system is connected via industrial communication to the multi-region flexible vibratory feeder, the top camera, the robotic arm, and the placement head; characterized in that... The control method based on multi-region multi-material mounting includes the following steps: S10, the chip mounter control system controls the vibration of the multi-zone flexible vibratory feeder to adjust the position and angle of various materials in each independent zone of the multi-zone flexible vibratory feeder; S20, the chip mounter control system receives material images from the multi-area flexible vibrating plate captured by the top camera and preprocesses the material images; S30, the chip mounter control system performs image segmentation on the pre-processed material image and uses target detection algorithm to identify the components facing up in the segmented image; S40, the pick-and-place machine control system controls the robotic arm to grasp the components identified in S30, and controls the placement head to place the components.

2. The control method based on multi-region multi-material mounting according to claim 1, characterized in that, In step S10, during the vibration of the multi-zone flexible vibratory feeder, the pick-and-place machine control system dynamically adjusts the vibration parameters of the multi-zone flexible vibratory feeder through a PID control algorithm. The vibration parameters include vibration frequency, amplitude, and vibration waveform. The vibration frequency is adjustable between 200Hz and 500Hz, the amplitude is adjustable between 0.1 and 0.5mm, and the vibration waveform is selected between square wave and sine wave.

3. The control method based on multi-region multi-material mounting according to claim 1, characterized in that, In step S20, the specific steps for preprocessing the material image include: S201, Grayscale Conversion: Converting the material image from a color image to a grayscale image; S202, Gaussian filtering noise reduction: The Gaussian function is used to perform a weighted average on the grayscale image to smooth the image and suppress noise; S203, Histogram Equalization: Redistributes the gray values ​​of the grayscale image after Gaussian filtering and denoising, stretching the relatively concentrated grayscale range to a uniform distribution across the entire grayscale range.

4. The control method based on multi-region multi-material mounting according to claim 3, characterized in that, In step S201, the specific method for converting the material image from a color image to a grayscale image is as follows: Read the R, G, and B components of each pixel in a color image; Use formula Calculate the grayscale value of each pixel, where R represents the red component of each pixel in the color image, G represents the green component of each pixel in the color image, B represents the blue component of each pixel in the color image, and Y represents the grayscale value. The calculated grayscale values ​​are assigned to the corresponding positions in the new image to form a grayscale image.

5. The control method based on multi-region multi-material mounting according to claim 4, characterized in that, In step S202, the specific method of using a Gaussian function to perform a weighted average on the grayscale image to smooth the image and suppress noise is as follows: Determine the size and standard deviation of the Gaussian kernel. ; The weight of each position within the Gaussian kernel is calculated based on a two-dimensional Gaussian function and then normalized; wherein the calculation expression of the two-dimensional Gaussian function is: In the formula, This represents the x-coordinate of each position within the Gaussian kernel relative to the center point of the Gaussian kernel. This represents the x-coordinate of each position within the Gaussian kernel relative to the center point of the Gaussian kernel, where the coordinates of the center point of the Gaussian kernel are (0,0). Slide a Gaussian kernel across the grayscale image and perform a convolution operation on each pixel and its neighborhood to obtain a smoothed grayscale image.

6. The control method based on multi-region multi-material mounting according to claim 5, characterized in that, In step 203, the specific method for redistributing the grayscale values ​​of the Gaussian-filtered denoised grayscale image, stretching the relatively concentrated grayscale range to a uniform distribution across the entire grayscale range, is as follows: The gray-level histogram of the smoothed gray-level image is calculated using the formula p(r_k)=n_k / N to count the probability of each gray level appearing. In the formula, r_k represents the k-th gray level, and k is an integer greater than or equal to 0; N represents the total number of pixels in the smoothed gray-level image; p(r_k) represents the probability of gray level r_k appearing; and L represents the total number of gray levels. The cumulative distribution function of gray-level probability is calculated using the following formula: In the formula, Let R represent the possible values ​​of the random variable R; j represents the index, which is an integer between 0 and k; p(r_j) is the probability mass function of the random variable R, representing the probability that R = r_j; The formula T(r_k)=round((L-1)×cdf(r_k)) maps each gray level to a new gray level, making the new histogram tend to be uniformly distributed. In the formula, T(r_k) represents the transformation function of the new gray level after mapping, round() means rounding to the nearest integer, and L-1 represents the maximum gray value.

7. The control method based on multi-region multi-material mounting according to claim 1, characterized in that, In step S30, before performing image segmentation on the preprocessed material image, the pick-and-place machine control system also needs to calculate the gradient magnitude and gradient direction angle of each pixel in the preprocessed material image. The formula for calculating the gradient magnitude is: The formula for calculating the gradient direction angle is: In the formula, Indicates the gradient magnitude; This represents the gradient of each pixel in the material image in the horizontal direction. This represents the gradient of each pixel in the material image in the vertical direction. This indicates the gradient direction angle.

8. The control method based on multi-region multi-material mounting according to claim 7, characterized in that, The specific method for segmenting the preprocessed material image and identifying face-up components in the segmented image using target detection algorithms is as follows: The coordinates of each independent region of the multi-region flexible vibratory feeder are marked in the material image, and the material image is cut into sub-images corresponding to each independent region of the multi-region flexible vibratory feeder according to the marked region coordinates. Each sub-image is then preprocessed again, its contour extracted, and its features extracted. A pre-trained classifier is used to determine whether there are any face-up elements in each sub-image.

9. The control method based on multi-region multi-material mounting according to claim 8, characterized in that, The specific method by which the chip mounter control system controls the robotic arm to grasp the identified components in S30 is as follows: the chip mounter and control system uses visual positioning data collected by the top camera and employs a nonlinear compensation algorithm to perform center offset compensation, angle compensation, and flatness compensation on the identified components in order to accurately grasp the identified components.

10. A control system based on multi-region multi-material mounting, applied to the control method based on multi-region multi-material mounting as described in any one of claims 1-9, characterized in that, The control system based on multi-region, multi-material mounting includes: The central control and scheduling module is used to send control commands to schedule and coordinate the work of other modules; A multi-zone material vibration module is used to classify and load various materials and adjust the angle and position of the materials through vibration; The image acquisition module is used to acquire material images and transmit them to the central control and scheduling module for processing. The image processing module is used to preprocess, segment, and detect targets in the material image in sequence to identify the components facing upwards in the material image. The component placement module is used to pick up and identify components according to control commands and accurately place them in designated positions.

Images