Phase control method and control system for blasting beads on filter stick forming machine

Abstract

The invention relates to the field of blast bead filter stick production, and discloses a blast bead phase control method and system on a filter stick forming machine. The method is applied to a blasting bead phase control system on a filter stick forming machine, the blasting bead phase control system comprises an image acquisition device and a bead adding device, and the method comprises the steps that a first image of a filter stick is acquired through the image acquisition device, and the filter stick comprises a first blasting bead; determining blasting bead position information of the first blasting bead in the filter stick according to the first image; determining the position offset of the first blasting bead based on the position information of the blasting bead and preset standard position information of the blasting bead; and according to the position offset, generating a pulse signal and sending the pulse signal to the bead adding device. The real-time position and the position offset of the blasting bead are determined by collecting the filter stick image, then the pulse signal is sent to the bead adding device to adjust the bead adding phase of the bead adding device, automatic deviation correction of the position of the blasting bead is achieved, and the qualified rate of the position of the blasting bead in the filter stick is increased.

Description

Technical Field

[0001] This application relates to the field of popping bead filter rod production, and in particular to a popping bead phase control method and control system on a filter rod forming machine. Background Technology

[0002] Currently, the development of capsule cigarettes is very rapid, and this has placed high demands on the insertion of the capsules. The process of inserting the capsules into the cigarette is completed during the filter rod production stage. The tolerance for the axial position of the capsule within the filter rod is becoming increasingly stringent, reaching a maximum of ±1.5mm. Due to the ever-increasing speed of filter rod forming machines, reaching up to 300 meters per minute, coupled with fluctuations in materials and negative pressure, the position of the capsule inserted into the filter rod can fluctuate and change.

[0003] Currently, when the axial position of the burst beads changes within the filter rod, adjustments are typically made manually after periodic inspection. This method suffers from shortcomings in both timeliness and accuracy, leading to a high scrap rate. Furthermore, manual inspection and adjustment cannot meet the demands of increasingly faster production speeds in existing filter rod forming machines. Summary of the Invention

[0004] In view of this, this application provides a method and control system for controlling the phase of bursting beads on a filter rod forming machine. This control method acquires images of the filter rod to determine the real-time position and positional offset of the bursting beads, and then sends pulse signals to the bead-adding device to adjust the bead-adding phase, thereby achieving automatic correction of the bursting bead position and improving the pass rate of the bursting bead position within the filter rod.

[0005] In a first aspect, this application provides a method for controlling the phase of bursting beads on a filter rod forming machine, applied to a bursting bead phase control system on the filter rod forming machine. The bursting bead phase control system includes an image acquisition device and a bead-adding device. The bead-adding device is used to add bursting beads to the filter rod in the filter rod forming machine based on a first bead-adding phase. The method includes: acquiring a first image of the filter rod through the image acquisition device, the filter rod including a first bursting bead; determining the position information of the first bursting bead in the filter rod based on the first image; determining the position offset of the first bursting bead based on the position information and preset standard position information of the bursting bead; generating a pulse signal based on the position offset and sending the pulse signal to the bead-adding device, wherein the pulse signal is used to adjust the bead-adding phase of the bead-adding device to a first phase, the first phase corresponding to the position offset, so that the bead-adding device adjusts the first bead-adding phase to a second bead-adding phase based on the pulse signal, the difference between the second bead-adding phase and the first bead-adding phase being the first phase.

[0006] This solution enables real-time monitoring and automatic correction of the capsule implantation process. Image processing technology is used to detect the actual position of the capsules in the filter rod in real time and compare it with a standard position, ensuring that the capsules are accurately added to the predetermined position, reducing human error and improving capsule positioning accuracy. Furthermore, it achieves automated adjustment of the capsule implantation position without manual intervention. The capsule phase control system automatically generates pulse signals based on the positional offset to adjust the capsule addition phase, improving production efficiency.

[0007] In conjunction with the first aspect, in a possible implementation of the first aspect, the pulse signal consists of a sequence of at least one pulse, each pulse having a pulse direction of either a first direction or a second direction. The pulse in the first direction is used to shift the bead phase to the left, and the pulse in the second direction is used to shift the bead phase to the right.

[0008] This scheme allows for bidirectional adjustment of the bead phase, such as shifting the bead phase to the left or right, thus providing a more flexible correction method to ensure accurate bead placement. Furthermore, the pulse direction setting allows for finer adjustments, avoiding overcorrection that might result from unidirectional adjustments.

[0009] In conjunction with the first aspect, in a possible implementation of the first aspect, sending the pulse signal to the bead-adding device includes: sending the pulse signal to the bead-adding device when it is determined that the position offset is greater than or equal to a preset offset threshold.

[0010] According to this scheme, by setting an offset threshold, unnecessary adjustments for minor deviations can be avoided, reducing frequent system actions and improving stability and lifespan.

[0011] In conjunction with the first aspect, in a possible implementation of the first aspect, the pulse signal consists of a sequence of N pulses, where N is a positive integer greater than or equal to 1. Sending the pulse signal to the bead-adding device includes: obtaining a preset maximum number of pulses for a single adjustment as M, where M is a positive integer greater than or equal to 1; when N is less than or equal to M, sending a first pulse signal to the bead-adding device, the first pulse signal consisting of the N pulses; when N is greater than M, sending a second pulse signal to the bead-adding device, the second pulse signal consisting of M of the N pulses.

[0012] This scheme prevents over-adjustment and system oscillation. By limiting the number of pulses in a single adjustment, it ensures a smooth and controllable adjustment process, thereby improving control accuracy.

[0013] In conjunction with the first aspect, in a possible implementation of the first aspect, the burst bead position information includes the center coordinates of the burst bead, and determining the burst bead position information of the first burst bead in the filter rod forming machine includes: confirming the coordinate information of the burst bead edge of the first burst bead based on the color information of the first burst bead in the first image; and determining the center coordinate value of the first burst bead based on the coordinate information of the burst bead edge of the first burst bead.

[0014] This scheme utilizes color information to identify the edges of the popping beads, reducing image noise interference and improving the accuracy and reliability of position detection. Furthermore, it allows for precise calculation of the center coordinates, providing a high-quality data foundation for offset calculation.

[0015] In conjunction with the first aspect, in a possible implementation of the first aspect, the first burst bead includes multiple burst beads, and the position information of the burst beads includes the center coordinates of the multiple burst beads. Before determining the position offset, the method further includes: obtaining multiple center coordinate values ​​corresponding to the multiple burst beads; removing abnormal data points from the multiple center coordinate values ​​to obtain the corrected center coordinate values ​​of the first burst bead.

[0016] According to this scheme, by cleaning and removing abnormal data points, such as removing erroneous coordinates caused by image blurring or foreign objects, the robustness of the system is improved, ensuring that the position offset calculation is based on valid data and reducing the risk of misadjustment.

[0017] In conjunction with the first aspect, in a possible implementation of the first aspect, removing outlier data points from the plurality of center coordinate values ​​includes: determining a first mean range using the Grubbs algorithm and / or a normal distribution algorithm, wherein data outside the first mean range are outlier data; and removing outlier data points from the plurality of center coordinate values ​​that are outside the first mean range.

[0018] Secondly, this application provides a bead-filling phase control system for a filter rod forming machine, comprising: a bead-filling device for adding bead-filling particles to the filter rod in the filter rod forming machine based on a first bead-filling phase; an image acquisition device for acquiring a first image of the filter rod; and a control device for determining the bead-filling position information of the first bead in the filter rod based on the first image, determining the position offset of the first bead based on a comparison between the bead-filling position information and preset bead-filling standard position information, generating a pulse signal based on the position offset, and sending the pulse signal to the bead-filling device, wherein the pulse signal is used to adjust the first bead-filling phase of the bead-filling device to a second bead-filling phase.

[0019] In conjunction with the second aspect, in a possible implementation of the second aspect, the image acquisition device includes: a camera and / or a laser light source for acquiring bar images corresponding to multiple image frames; the control device is specifically used to stitch together the multiple bar images of the filter rod acquired by the camera and / or the laser light source into the first image based on a scale invariant feature transform (SIFT) image stitching algorithm.

[0020] According to this scheme, the SIFT image stitching algorithm can seamlessly stitch multiple strip images into a complete image, overcoming the limitations of a single camera's field of view and improving the completeness and accuracy of image acquisition. This, in turn, ensures comprehensive detection of the popping bead's location and reduces omissions.

[0021] In conjunction with the second aspect, in a possible implementation of the second aspect, the system further includes: an optocoupler for connecting the control device and the bead-adding device.

[0022] According to this scheme, the optocoupler can prevent electromagnetic interference from affecting the control signal, thereby providing electrical isolation and noise suppression, and ensuring the stability and security of signal transmission.

[0023] Thirdly, a readable storage medium is provided, which includes one or more programs that, when executed on an electronic device, cause the electronic device to implement the first aspect and any possible implementation of any antenna switching method provided by the first aspect.

[0024] Fourthly, a program product is provided that, when run on an electronic device, enables the electronic device to implement the first aspect and any possible implementation of any antenna switching method provided in the first aspect.

[0025] It should be understood that the beneficial effects of the third and fourth aspects mentioned above can be referred to the beneficial effects described in the first aspect, and will not be repeated here. Attached Figure Description

[0026] Figure 1 This is a system architecture diagram of a menthol phase control system provided in an embodiment of this application;

[0027] Figure 2 This is a schematic flowchart of the menthol phase control method provided in the embodiments of this application;

[0028] Figure 3 This is a flowchart of the menthol phase control process provided in the embodiments of this application;

[0029] Figure 4 This is a schematic diagram of filter rod image acquisition provided in an embodiment of this application;

[0030] Figure 5 This is a schematic diagram of the image stitching algorithm provided in an embodiment of this application;

[0031] Figure 6 This is a schematic diagram of the popping bead coordinate acquisition process provided in an embodiment of this application;

[0032] Figure 7 This is a schematic diagram of the coordinates of the burst beads provided in the embodiments of this application;

[0033] Figure 8 This is a schematic diagram of offset smoothing based on proportional integral derivative (PID) provided in an embodiment of this application;

[0034] Figure 9 This is a schematic diagram of the pulse signal provided in the embodiments of this application;

[0035] Figure 10 This is a flowchart of generating pulse signals provided in an embodiment of this application;

[0036] Figure 11 This is a schematic diagram of the interface for generating control pulse signals provided in an embodiment of this application;

[0037] Figure 12 This is a structural schematic diagram of a device provided in an embodiment of this application;

[0038] Figure 13 This is a structural schematic diagram of a system on a chip (SoC) provided in an embodiment of this application. Detailed Implementation

[0039] The terminology used in the following embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to also include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of this application, “at least one” and “one or more” refer to one, two, or more than two. The term “and / or” is used to describe the relationship between related objects, indicating that three relationships may exist; for example, A and / or B can indicate: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character “ / ” generally indicates that the preceding and following related objects are in an “or” relationship.

[0040] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0041] In the embodiments of this application, the bead-adding phase can refer to the specific time or angle point at which the bead is added to the filter rod during the filter rod production process of the filter rod forming machine. For example, each rotation of the main shaft of the filter rod forming machine corresponds to the production of a filter rod of a fixed length. The bead-adding device can be synchronized with the main shaft of the filter rod forming machine, performing a bead-adding action at fixed time intervals or at fixed rotation angles of the main shaft. For example, a bead-adding action is performed every 90° rotation of the main shaft, with bead-adding phases of 0°, 90°, 180°, and 270°.

[0042] The fluctuation in the implantation position of the granules mentioned in the background technology above can refer to a discrepancy between the granule's position in the filter rod and the preset position after the granule-adding device performs the granule-adding action at the corresponding granule-adding phase. For example, when the granule-adding phase is 0°, the preset granule position should be 2 cm from the bottom of the filter rod, but in reality, after the granule-adding device performs the granule-adding action at 0°, the granule position is 2.5 cm from the bottom of the filter rod. In this case, there is a deviation in the granule implantation position.

[0043] As mentioned in the background technology section above, the timeliness and accuracy of manual periodic inspection and adjustment of the bursting bead position are insufficient, resulting in a high scrap rate. This means that manual inspection and adjustment cannot meet the ever-increasing production speed requirements of filter rod forming machines.

[0044] To address the aforementioned issues, this application proposes a method and control system for controlling the phase of bursting beads on a filter rod forming machine. In this control method, images of the filter rod are acquired to determine the real-time position and positional offset of the bursting beads. A pulse signal is then sent to the bead-adding device to adjust the bead-adding phase, thereby achieving automatic correction of the bursting bead position and improving the pass rate of the bursting bead position within the filter rod.

[0045] First, combine Figure 1 The system architecture of the menthol phase control system provided in the embodiments of this application is introduced. Figure 1 A system architecture diagram of the menthol phase control system provided in an embodiment of this application is shown. Figure 1As shown, the popping bead phase control system includes two main modules: a popping bead detection device and a popping bead implantation device. The two modules work together to achieve the detection and precise implantation of popping beads.

[0046] Among them, the capsule detection device is used to acquire images and visually detect the capsule implantation location, and the capsule implantation device is used to accurately implant the capsule into the tobacco bundle of the cigarette.

[0047] Specifically, such as Figure 1 As shown, the popping bead detection device includes a light source system consisting of a light source controller and a high-brightness light source, which can provide a stable lighting environment for image acquisition and visual inspection. For example, the light source can be a laser light source. Figure 1 As shown, the burst bead detection system also includes an image acquisition and detection system composed of an industrial computer, a logic controller, and other devices. The industrial computer connects to the image acquisition device and the display device via Ethernet, receiving filter rod images from the image acquisition device and then transmitting the acquired filter rod images to the display device via a video interface. For example, the image acquisition device can be an industrial camera. The logic controller, as the control core, interacts with the industrial computer via serial communication and simultaneously receives I / O inputs from the shaft encoder and signals from the cutter proximity switch, thereby triggering the image acquisition device to acquire the detection image. Furthermore, the logic controller connects to the motion control system in the burst bead implantation device via an optocoupler to transmit the pulse signals generated by the burst bead detection device based on the filter rod images to the burst bead implantation device.

[0048] Specifically, such as Figure 1 As shown, the menthol capsule implantation device includes a motion control system for receiving signals and outputting control commands. The motion control system receives the host speed signal from the encoder and interacts with the touchscreen, supporting manual parameter setting and status monitoring, and can handle I / O switch signals. Furthermore, the menthol capsule implantation device also includes actuators such as servo motors. The servo motors drive components such as the feeding disc and implantation disc to complete the feeding and implantation of the menthol capsules. The forming cigarette gun, the special tobacco tongue, and the tobacco bundle work together to provide a tobacco bundle carrier for the menthol capsule implantation. The cutting disc, the cutter, and the proximity switch of the cutter in the menthol capsule detection device are linked to realize the cigarette cutting process.

[0049] Subsequently, after the capsule detection device completes the image acquisition of the filter rod and the detection of the capsule position, it transmits the generated pulse signal to the motion control system of the capsule implantation device via an optocoupler. Then, based on the pulse signal and manual commands, the motion control system drives the servo motor and mechanical components to precisely implant the capsule into the filter rod, ultimately forming a capsule cigarette.

[0050] based on Figure 1 The present application proposes a 200 method for controlling the phase of a menthol capsule phase, as shown in the menthol capsule phase control system. Figure 2A schematic flowchart of the menthol phase control method 200 provided in an embodiment of this application is shown. Figure 2 As shown, the method 200 includes steps S210 to S240.

[0051] S210, according to the image acquisition device, acquire the first image of the filter rod.

[0052] Specifically, the filter rod includes one or more popping beads, such as a first popping bead, and the first image includes an image of the one or more popping beads.

[0053] Optionally, the image acquisition device may include a camera and / or a laser light source. This application can acquire multiple bar images corresponding to multiple image frames, and then stitch the multiple bar images of the filter rod acquired by the camera and / or the laser light source into the first image based on the scale invariant feature transform (SIFT) image stitching algorithm.

[0054] For example, taking an image acquisition system including an industrial camera as an example, this application can acquire a bar image through the industrial camera, and then combine it with... Figure 1 The encoder signals in the image are used for image stitching, such as stitching based on the SIFT image stitching algorithm. For example, to meet the high speed and high precision requirements of the production of bursting bead filter rods, and to meet the precision requirement (0.05 mm / pixel) at an equipment operating speed of 200 m / min, this application calculates the line scan frequency as 200000 mm / 0.05 mm / 60 = 66666.67 Hz based on the principle of the line scan camera, and selects a line scan adjustment camera with a horizontal resolution of 2K and a line frequency of 70K as the main industrial camera of the image acquisition system.

[0055] S220, Based on the first image, determine the position information of the first popping bead in the filter rod.

[0056] In embodiments of this application, the burst bead position information may include the center coordinates of the first burst bead. Step S220 can be executed by a control device in the burst bead phase control system, such as the control device may include... Figure 1 The logic controller and industrial computer shown.

[0057] Optionally, in embodiments of this application, determining the position information of the first bursting bead in the filter rod forming machine can be based on the color information of the first bursting bead in the first image. Furthermore, the coordinate information of the edge of the first bursting bead is confirmed based on the color information of the first bursting bead in the first image, and finally the center coordinate value of the first bursting bead is determined.

[0058] For example, after acquiring the first image, this application can preprocess the first image, such as converting the color or grayscale first image into a high-contrast image with only black and white, or using methods such as Gaussian blurring or median filtering to reduce background, noise, and other interference, making the illumination and color of the first burst bead area more uniform. Then, by setting one or more grayscale thresholds, the pixels in the image are divided into two categories, thereby achieving binarization of the burst bead image color. For example, all pixels with grayscale values ​​higher than the set threshold are set to white, and all pixels with grayscale values ​​lower than the set threshold are set to black. Furthermore, after obtaining a high-quality binary image, the edges of the burst bead can be distinguished using edge detection algorithms, and the coordinates of the edges of the first burst bead can be read, thereby obtaining the center coordinates of the first burst bead, and thus obtaining the burst bead position information.

[0059] This scheme utilizes color information to identify the edges of the popping beads, reducing image noise interference and improving the accuracy and reliability of position detection. Furthermore, it allows for precise calculation of the center coordinates, providing a high-quality data foundation for offset calculation.

[0060] Optionally, after collecting the popping bead position information of multiple popping beads, this application can remove abnormal data points. For example, the first popping bead includes multiple popping beads, and the popping bead position information includes the center coordinates of the multiple popping beads. Furthermore, after obtaining the multiple center coordinate values ​​corresponding to the multiple popping beads, abnormal data points among the multiple center coordinate values ​​can be removed to obtain the corrected center coordinate values ​​of the first popping bead. For example, in an embodiment of this application, a first mean range can be determined using the Grubbs algorithm and / or a normal distribution algorithm, wherein data outside the first mean range is abnormal data, and thus data points among the multiple center coordinate values ​​outside the first mean range are abnormal data points, which can be removed.

[0061] According to this scheme, by cleaning and removing abnormal data points, such as removing erroneous coordinates caused by image blurring or foreign objects, the robustness of the system is improved, ensuring that the position offset calculation is based on valid data and reducing the risk of misadjustment.

[0062] S230, based on the burst bead position information and the preset burst bead standard position information, determine the position offset of the first burst bead.

[0063] Specifically, this positional offset indicates the difference between the actual detected position of the burst bead and a preset standard position, quantitatively describing the degree and direction of the first burst bead's deviation from its standard position in space. The preset standard position information of the burst bead indicates the theoretical or designed precise position coordinates where the burst bead should be. In other words, after obtaining the burst bead's position information, such as its center coordinates, the positional offset can be obtained based on the difference between the burst bead's position information and the preset standard position information, such as the difference between the center coordinates and the standard center coordinates.

[0064] The positional offset can include distance and direction. For example, taking the X-axis (horizontal direction) component as an example, the positional offset (ΔX) on the X-axis is the difference between the actual X-coordinate of the popping bead and the standard X-coordinate of the popping bead. The magnitude of ΔX is the distance, and the sign is the direction. For example, when ΔX is positive, it means that the first popping bead is shifted to the left relative to the standard position, and when ΔX is negative, it means that the first popping bead is shifted to the right relative to the standard position.

[0065] Step S230 can be executed by a control device in the menthol phase control system, such as the control device may include... Figure 1 The logic controller and industrial computer shown.

[0066] S240, based on the position offset, generate a pulse signal and send the pulse signal to the bead-adding device.

[0067] Step S240 can be executed by a control device in the menthol phase control system, such as the control device may include... Figure 1 The motion control system shown.

[0068] Specifically, the pulse signal is used to adjust the bead-adding phase of the bead-adding device to a first phase, which corresponds to the position offset, so that the bead-adding device adjusts the first bead-adding phase to a second bead-adding phase based on the pulse signal. The difference between the second bead-adding phase and the first bead-adding phase is the first phase. In other words, after receiving the first phase, the bead-adding device shifts the first bead-adding phase to the left or right by a first phase to obtain the second bead-adding phase. When the bead-adding device adds beads through the second bead-adding phase, the position of the first bursting bead in the filter rod is adjusted to or close to the standard position.

[0069] Optionally, the pulse signal consists of a sequence of at least one pulse, each pulse having a first direction or a second direction. The pulse in the first direction is used to shift the bead phase to the left, and the pulse in the second direction is used to shift the bead phase to the right. For example, if the position offset ΔX is positive, it means that the first bead is deviated to the left relative to the standard position. In this case, the pulse direction is the second direction, so that the first bead moves to the right to approach the standard position. According to this scheme, bidirectional adjustment of the bead phase is allowed, such as shifting the bead phase to the left or right, thereby providing a more flexible correction method and ensuring accurate bead position. In addition, the setting of the pulse direction allows for finer adjustment, avoiding overcorrection that may be caused by unidirectional adjustment.

[0070] Optionally, when sending the pulse signal to the bead-adding device, the pulse signal is sent only if the position offset is determined to be greater than or equal to a preset offset threshold. In other words, this application sets a dead zone range, i.e., a preset offset threshold, so that the bead-adding device will only adjust the bead position when the position exceeds this dead zone range. According to this scheme, by setting an offset threshold, unnecessary adjustments for minor deviations are avoided, reducing frequent system operations and improving stability and lifespan.

[0071] Optionally, the pulse signal consists of a sequence of N pulses, where N is a positive integer greater than or equal to 1. Sending the pulse signal to the bead-adding device includes: obtaining a preset maximum number of pulses for a single adjustment as M, where M is a positive integer greater than or equal to 1; then, if N is less than or equal to M, sending a first pulse signal to the bead-adding device, the first pulse signal consisting of the N pulses; and if N is greater than M, sending a second pulse signal to the bead-adding device, the second pulse signal consisting of M of the N pulses. In other words, this application controls the maximum phase of each adjustment by presetting the maximum number of pulses for a single adjustment as M, so that the correction amount is within the maximum phase range and avoids excessive offset in a single adjustment. This prevents over-adjustment and system oscillation. By limiting the number of pulses in a single adjustment, the adjustment process is ensured to be smooth and controllable, improving control accuracy.

[0072] This application, through method 200, achieves real-time monitoring and automatic correction of the capsule implantation process. On one hand, image processing technology is used to detect the actual position of the capsule in the filter rod in real time and compare it with a standard position, ensuring that the capsule is accurately added to the predetermined position, reducing human error and improving capsule position accuracy. On the other hand, it achieves automated adjustment of the capsule implantation position without manual intervention. The capsule phase control system automatically generates pulse signals based on the position offset to adjust the capsule phase, improving production efficiency.

[0073] To facilitate understanding of the detailed process of method 200, the following is in conjunction with the appendix. Figure 3 To be continued Figure 11 An embodiment of method 200 is described. Wherein, Figure 3 A general flowchart of the method 200 provided in the embodiments of this application is shown.

[0074] like Figure 3 As shown, corresponding to step S210, this application first obtains the first image of the filter rod through machine vision inspection and data preprocessing. Specifically, in the machine vision inspection stage, to accurately obtain the actual position of the popping beads, this application can employ a high-resolution shaft encoder and... Figure 1 The logic controller and motion control system shown are connected, and the image acquisition device, such as an industrial camera, is triggered to take pictures based on the position signal of the shaft encoder, and then the acquired input data x, that is, the first image of the filter rod, is output.

[0075] The following is combined with Figure 4 and Figure 5 This section describes the detailed process of machine vision inspection.

[0076] Figure 4 Image (a) shows a schematic diagram of obtaining the first image of the filter rod. Figure 4 As shown in (a) of the paper, this application can use a line scan camera as an image acquisition device. The line scan camera then acquires multiple frames of strip or bar-shaped images through multiple scans. These strip or bar-shaped images can then be stitched together using the SIFT image stitching algorithm to obtain the image shown in Figure (a). Figure 4 A schematic diagram of the first image of the filter rod shown in (b) of the diagram. Figure 4 As shown in (b) in the image, the first image includes images of four popping beads, that is, the part of the first image that is different from the background color is the position of the popping beads.

[0077] Figure 5 A flowchart of the SIFT image stitching algorithm provided in an embodiment of this application is shown. Figure 5As shown, during the image acquisition stage, a line scan camera acquires images of the silk bundle strips at a frequency of 70 kHz and a resolution of 1×2048 pixels / row, forming an original strip image containing 8 rows (Row 0-Row 7), from which silk bundle texture feature points are identified. Subsequently, feature extraction is performed on the original image to generate SIFT keypoints, each keypoint corresponding to a 128-dimensional descriptor. In the feature matching stage assisted by the random sample consensus (RANSAC) algorithm, the acquired strip images, such as strip i, strip i+1, strip i+2, etc., are paired for feature matching. The RANSAC algorithm is used to filter the matching pairs, requiring more than 12 pairs. The homography matrix H is calculated to further optimize the matching results, eliminate mismatches, and ensure matching accuracy. Finally, through the above SIFT feature extraction and RANSAC feature matching process, accurate feature association of the silk bundle images is achieved, providing a reliable feature foundation for subsequent image stitching, cropping, and offset calculations.

[0078] The following is combined with Figures 6 to 7 This section describes the process of determining the location information of the burst beads.

[0079] Continue to refer to Figure 3 Corresponding to step S220, after obtaining the x input data of the first image through the machine vision detection process, the input data [x], that is, the popping bead position information in the filter rod, can be obtained through the data preprocessing process. As described in the description of step S220 above, this application can obtain the popping bead position information based on the color information in the first image and the process of binarizing the image color.

[0080] Figure 6 This diagram illustrates the method for determining the location information of a burst bead according to an embodiment of this application. It is based on... Figure 4 The first image shown in (b) is shown in the image. Figure 6 Images (a) and (b) in the diagram illustrate the preprocessing of the first image. This application can, based on the binarized image colors, [process the image]. Figure 4 The first color image shown in (b) is converted into a high-contrast image with only black and white colors. For example, as Figure 6 As shown in (a), if the color of the popping bead is darker than the background area, the lower bound of binarization can be set to 0, and the upper bound adjusted until the popping bead is found in the black area. For example, as... Figure 6 As shown in (b), if the color of the popping bead position is whiter than the background area, the upper limit of binarization can be set to 255, and the lower limit can be adjusted until the popping bead position is found in the white area.

[0081] Subsequently, this application can employ edge detection algorithms and other methods to detect, for example... Figure 6 The edge of each popping bead shown in (c) is obtained by optimizing the popping bead edge. Figure 6 The final popping bead edge position is shown in (d) in the diagram. Based on Figure 6 By taking the edge position of the popping bead as shown in (d), we can obtain the coordinates of the edge of each popping bead, and then obtain the center coordinate value of each popping bead, that is, the popping bead position information of each popping bead.

[0082] final, Figure 7 This diagram illustrates the position information of each burst bead provided in an embodiment of this application. For example... Figure 7 As shown, the filter rod contains four popping beads, such as popping beads A to D. Figure 7 As shown, taking the leftmost side of the filter rod as the reference, the position information of burst bead A is S1 distance from the reference, the position information of burst bead B is S2 distance from the reference, the position information of burst bead C is S3 distance from the reference, and the position information of burst bead D is S4 distance from the reference. This burst bead position information is... Figure 3 The input data shown is [x].

[0083] Furthermore, as described in the section on step S220 above, after collecting the popping bead position information of multiple popping beads, this application can remove abnormal data points, such as by using the Grubbs algorithm and / or the normal distribution algorithm to remove abnormal points, thereby obtaining the corrected popping bead position information. This avoids large fluctuations and oscillations in the popping bead position.

[0084] For example, this application can use the Grubbs algorithm to remove outlier data points, such as data with a distance of 0 or too large, to avoid affecting the subsequent data. For instance, a critical value can be obtained based on the Grubbs table. If the P-value in the Grubbs table is selected as 0.95 and the number of measurements is selected as 30, the critical value for the intersection of horizontal and vertical lines indicated in the Grubbs table can be G. 995 (30) = 3.236. Based on this critical value, the aforementioned first mean range can be obtained. That is, if the test statistic corresponding to a data point is less than the critical value, then the data point is within the first mean range; otherwise, it is an outlier. Furthermore, the difference between a data point and the mean is calculated, and the difference is then divided by the standard deviation to obtain the test statistic. If the test statistic is greater than the critical value of 3.236, then the data point is an outlier and needs to be removed.

[0085] For example, this application can use a normal distribution algorithm to obtain the actual deviation value, where the sample data can be calculated using the principle of normal distribution to obtain the mean, variance, and standard deviation. The mean value is obtained as the standard value of the popping beads in the filter rod. Furthermore, when the normal distribution factor is 4.0, 99.99% of the data is standard data, thus obtaining the maximum and minimum allowable standard values; when the normal distribution factor is 2, i.e., (μ-2δ, μ+2δ), 95.45% of the data is standard data; when the normal distribution factor is 3, i.e., (μ-3δ, μ+3δ), 99.73% of the data is standard data; and when the normal distribution factor is 4, i.e., (μ-4δ, μ+4δ), 99.99% of the data is standard data. To ensure that as little data as possible is removed, only outliers that deviate significantly from the mean are removed, this application can choose 99.99% of the data as standard data and a normal distribution factor of 4.0. At this point, the first mean range can be obtained, and data outside this first mean range are outliers.

[0086] The following is combined with Figure 8 This section describes the process of determining the position offset.

[0087] Continue to refer to Figure 3 Corresponding to step S230, after the data preprocessing stage, this application can calculate the position offset. Specifically, as shown in step S230... Figure 3 As shown, during the offset calculation process, the real-time offset is calculated by comparing the [x] input data with a preset standard value. For example, using... Figure 7 Taking the popping bead position information shown as an example, if the standard position information of popping beads A to D are distances from the reference of S1', S2', S3' and S4' respectively, then the position offsets of popping beads A to D are (S1-S1'), (S2-S2'), (S3-S3') and (S4-S4') respectively.

[0088] Furthermore, in the embodiments of this application, the calculated positional offset can be smoothed so that the position of the popping bead after correction based on the positional offset is closer to the standard position, thereby obtaining... Figure 3 The output y shown is the smoothed position offset. In other words, in the embodiments of this application, the position offset also needs to form a closed loop with the actual popping bead position feedback value obtained after position correction, and finally output y to reduce data fluctuations and improve control stability.

[0089] For example, Figure 8 This illustration shows a flowchart of a position offset smoothing process provided in an embodiment of this application. Figure 8As shown, first, the target value, i.e., the standard position information of the popping bead, is input. Then, the feedback signal is acquired; this feedback signal is the measured position information of the popping bead. Next, the deviation signal is obtained by subtracting the target value from the feedback signal, which represents the deviation between the popping bead position information and the standard position information. This deviation signal is then input to the microcontroller's proportional-integral-derivative (PID) controller. The proportional element (K...)... p Instant response to the current deviation, integral element (1 / (T) i ×S)) Accumulate historical deviations and eliminate static errors, so that the system eventually stabilizes at the target value, and the differential element (T) d The PID controller predicts the trend of deviation changes and adjusts the control input in advance to suppress system oscillations. Ultimately, the PID controller outputs an operational input that acts on the motor to adjust its operating state, such as its speed and torque. In this feedback loop, after the actual operating state of the motor changes, a new feedback signal is collected again, compared with the target value, and the closed-loop feedback control process is repeated, ensuring that the actual system state continuously approaches the target value.

[0090] The following is combined with Figures 9 to 11 The process of generating pulse signals is described.

[0091] Continue to refer to Figure 3 After obtaining the y-output through the offset calculation stage, a pulse signal can be generated based on the y-output and pulse parameters. Finally, this pulse signal is sent to the bead-adding device to adjust the bead-adding phase. Figure 9 A schematic diagram of a pulse signal is shown. (For example...) Figure 9 As shown, assuming the length of one pulse period is t1 ms, then within each unit time length t2 ms, a high-level rectangular wave can be generated, meaning the duration of a single pulse is t2 ms, used to indicate an adjustment of the bead phase. In embodiments of this application, the pulse direction may include, for example... Figure 9 The high level 1 and low level -1 indicate a left-shifted beaded phase or a right-shifted beaded phase.

[0092] For example, in the output Figure 3 When outputting data in y, it can be sorted by time to obtain a one-dimensional r column vector such as X = [x1, ..., x2]. r And taking n data points backwards from the current time, such as taking X... t To X t-n Expanding these data row by row results in an r-column, n-row matrix as shown in equation (1):

[0093]

[0094] Among them, X 输入 The phase detection value of the popping beads for each filter rod is given. For example, the phase detection value of 4 popping beads would be a 4-column vector X = [x1, x2, x3, x4]. If there are 30 filter rods, then X... 输入 It is a 4-column, 30-row matrix. For example, Table 1 shows X. 输入 The data consists of a 4-column, 30-row matrix, where each row represents the position (phase) detection value of four popping beads on a filter rod, and the 30 rows represent the data from 30 filter rods.

[0095] Table 1

[0096] Serial Number Exploding beads 1 Exploding beads 2 Exploding beads 3 Exploding beads 4 1 15.66 45.86 74.90 105.63 2 15.12 44.81 75.16 105.01 …… …… …… …… ……

[0097] Based on the data shown in Table 1, the deviation value is calculated, that is, based on X shown in Table 1. 输入 The deviation is determined by comparing the preset standard position information. For example, the standard value can be obtained by manually entering the standard value or by automatically calculating it based on historical data, resulting in a one-dimensional r-column vector W of the standard values. For instance, in a filter rod containing four popping beads, the standard positions corresponding to the four popping beads could be 15, 45, 75, and 105. Furthermore, X... 输入 Subtracting the standard value from the one-dimensional r-column vector W yields the r-column, n-row deviation matrix U. 偏差 The calculation process is shown in equation (2) below:

[0098]

[0099] Among them, W can be automatically expanded using a broadcast mechanism and X 输入 Alignment and broadcasting mechanisms automatically expand smaller tensors (matrices) to match the shape of larger tensors (matrices), enabling them to perform element-level operations (such as addition, subtraction, multiplication, etc.) and matrix operations can only be performed if the matrix operation rules are met.

[0100] Furthermore, based on the results obtained from equation (2), the average value of each column of data can be calculated to obtain y. 输出 As shown in equation (3):

[0101]

[0102] Figure 10 A flowchart illustrating the generation of pulse signals provided in an embodiment of this application is shown.

[0103] As mentioned above, when sending the pulse signal to the bead-adding device, the pulse signal is sent to the bead-adding device only if the position offset is determined to be greater than or equal to a preset offset threshold. For example, as... Figure 10 As shown, assume Z 死区 For offset thresholds, such as Z 死区The value is [0.1 0.1 0.1 0.1] (unit: mm), and then the value of y is determined. 输出 Is the absolute value of the output value of each dimension greater than Z? 死区 The value corresponding to the dimension. If y 输出 Less than Z 死区 If the signal is not output, then no pulse signal will be output and the system will wait for T to control the delay of m filter rods. Otherwise, the following will occur: Figure 10 As shown, calculate the number of control pulses N, i.e. Figure 9 The number of pulses shown. Where N takes the value y 输出 Divide by u, where u is the minimum adjustment increment, i.e., the base number of the bead phase adjusted per pulse, such as 0.02mm.

[0104] Furthermore, such as Figure 10 As shown, when N>1, the popping beads deviate to the right, and this application can output N such... Figure 9 The pulse width shown indicates that the left deviation control is achieved. When N < -1, the jelly bead deflects to the left. This application can output N pulses as shown. Figure 9 The pulse width shown indicates that the right-side correction control is performed.

[0105] As mentioned above, this application controls the maximum phase of the bead-adding device in each adjustment by presetting the maximum number of pulses for a single adjustment to M, thereby ensuring that the correction amount is within the maximum phase range and avoiding excessive offset in a single adjustment. For example, as Figure 10 As shown, this application can set S 单次调整最大脉冲数 Furthermore, when the absolute value of N is greater than S 单次调整最大脉冲数 When, output S pulses; if the absolute value of N is less than S... 单次调整最大脉冲数 At that time, output the absolute value of N pulses. After the output is complete, wait for parameter T. 控制延迟 Then, sampling is activated again to form a continuous closed-loop control. Wherein, T 控制延迟 The input parameters are fixed and determined by the response time of the control system.

[0106] For example, suppose Z 死区 The value is 1 mm, u is 0.2 mm, and then based on the y shown in equation (3) 输出 We can obtain N. If we take the first popping bead as the basis for correction and the first popping bead is in y 输出 The corresponding value in the middle is 2 mm, then y 输出 Greater than Z 死区 And N is 10. Therefore, the first explosive bead is deflected to the right, requiring 10 pulses for adjustment. If S... 单次调整最大脉冲数 If the value of N is 1, then only one pulse is output for each adjustment, up to a total of 10 pulses output after 10 adjustments. In some other embodiments of this application, the average offset of the four popping beads can also be used as the basis for calculating the value of N.

[0107] Figure 11 A schematic diagram of the interface for generating control pulse signals provided in an embodiment of this application is shown.

[0108] In some embodiments of this application, the user can manually control the position of the burst bead to shift left or right. For example, the user can... Figure 11 The "Manual trigger for left shift" and "Manual trigger for right shift" controls left shift with 6 pulses and right shift with 7 pulses. Furthermore, the user can adjust the number of pulses, such as changing the left shift from 6 pulses to 7 pulses.

[0109] In other embodiments of this application, the user can achieve automatic correction of the popping bead position using the aforementioned method 200. Exemplarily, the sampling position and sampling period are used to set the sampling timing and frequency of visual detection, such as... Figure 11 The sampling position shown is the preset filter rod position 1, and the sampling period is 2 microseconds; the control delay is used to control the delay time of the action, such as... Figure 11 The control delay shown is 2 microseconds; the adjustment base per pulse is the aforementioned u, as shown. Figure 11 The 0.2 mm shown indicates that the dead zone for adjustment is the aforementioned Z. 死区 ,like Figure 11 The 1 mm shown indicates that the control pulse width is... Figure 9 The time length of t2 shown is as follows: Figure 11 The 300 milliseconds shown; the minimum pulse interval is... Figure 9 The time length of t3 shown is as follows: Figure 11 The 200 milliseconds shown; the maximum number of pulses adjusted in a single operation is the aforementioned S. 单次调整最大脉冲数 ,like Figure 11 As shown in 1. Furthermore, as... Figure 11 As shown, the warning trigger continuous correction cycle can be used to set the number of consecutive abnormal cycles to trigger the correction warning, and the warning reset continuous normal cycle can be used to set the number of consecutive normal cycles required for the warning reset.

[0110] This application provides a computer program product that, when run on an electronic device, causes the electronic device to execute the technical solutions described in the above embodiments. Its implementation principle and technical effects are similar to those of the related embodiments described above, and will not be repeated here.

[0111] This application provides a readable storage medium containing instructions that, when executed by an electronic device, cause the electronic device to perform the technical solutions described in the above embodiments. The implementation principle and technical effects are similar and will not be repeated here.

[0112] This application provides a chip for executing instructions. When the chip is running, it executes the technical solutions described in the above embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0113] The following describes the hardware module of this application, which can be used to implement the aforementioned method 300, and can also implement... Figures 3 to 11 The functions described above.

[0114] Now for reference Figure 12 The diagram shows a block diagram of a device 1200 according to one embodiment of this application. Device 1200 may include one or more processors 1201 coupled to a controller hub 1203. In at least one embodiment, the controller hub 1203 communicates with the processor 1201 via a multi-branch bus such as a front side bus (FSB), a point-to-point interface such as a quick path interconnect (QPI), or a similar connection 1210. The processor 1201 executes instructions controlling general types of data processing operations. In one embodiment, the controller hub 1203 includes, but is not limited to, a graphics memory controller hub (GMCH) (not shown) and an input / output hub (IOH) (which may be on a separate chip) (not shown), wherein the GMCH includes memory and a graphics controller and is coupled to the IOH.

[0115] Device 1200 may also include a coprocessor 1202 and a memory 1204 coupled to a controller hub 1203. Alternatively, one or both of the memory and the GMCH may be integrated within the processor, with memory 1204 and coprocessor 1202 directly coupled to processor 1201 and controller hub 1203, which resides on a single chip with the IOH. Memory 1204 may be, for example, dynamic random access memory (DRAM), phase change memory (PCM), or a combination of both. In one embodiment, coprocessor 1202 is a dedicated processor, such as, for example, a high-throughput MIC processor (many integrated core, MIC), a network or communication processor, a compression engine, a graphics processor, a general-purpose computing on GPU (GPGPU), or an embedded processor, etc. Optional properties of coprocessor 1202 are indicated by dashed lines. Figure 12 middle.

[0116] As a computer-readable storage medium, memory 1204 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. For example, memory 1204 may include any suitable non-volatile memory such as flash memory and / or any suitable non-volatile storage device such as one or more hard-disk drives (HDD(s)), one or more compact disc (CD) drives, and / or one or more digital versatile disc (DVD) drives.

[0117] In one embodiment, device 1200 may further include a network interface controller (NIC) 1206. NIC 1206 may include a transceiver for providing a radio interface to device 1200, thereby enabling communication with any other suitable device (such as a front-end module, antenna, etc.). In various embodiments, NIC 1206 may be integrated with other components of device 1200. NIC 1206 can implement the functions of the communication unit in the above embodiments.

[0118] Device 1200 may further include input / output (I / O) device 1205. I / O 1205 may include: a user interface designed to enable a user to interact with device 1200; a peripheral component interface designed to enable peripheral components to also interact with device 1200; and / or sensors designed to determine environmental conditions and / or location information related to device 1200.

[0119] It is worth noting that, Figure 12 This is merely an example. That is, although... Figure 12 The diagram shows that device 1200 includes multiple devices such as processor 1201, controller hub 1203, and memory 1204. However, in actual applications, devices using the methods of this application may include only a portion of the devices in device 1200. For example, it may include only processor 1201 and NIC 1206. Figure 12 The properties of the optional devices are shown in dashed lines. According to some embodiments of this application, the memory 1204, which is a computer-readable storage medium, stores instructions that, when executed on a computer, cause the device 1200 to perform the methods according to the above embodiments. Specific details can be found in the methods of the above embodiments, and will not be repeated here.

[0120] Now for reference Figure 13 The diagram shown is a block diagram of a system-on-chip (SoC) 1300 according to an embodiment of this application. Figure 13In the diagram, similar components share the same reference numerals. Additionally, dashed boxes are an optional feature for more advanced SoCs. Figure 13 In this embodiment, SoC 1300 includes: an interconnect unit 1350 coupled to an application processor 1310; a system proxy unit 1380; a bus controller unit 1390; an integrated memory controller unit 1340; a group or one or more coprocessors 1320, which may include integrated graphics logic, an image processor, an audio processor, and a video processor; a static random access memory (SRAM) unit 1330; and a direct memory access (DMA) unit 1360. In one embodiment, the coprocessor 1320 includes a dedicated processor, such as, for example, a network or communication processor, a compression engine, a GPGPU, a high-throughput MIC processor, or an embedded processor.

[0121] The static random-access memory (SRAM) cell 1330 may include one or more computer-readable media for storing data and / or instructions. The computer-readable storage medium may store instructions, specifically, temporary and permanent copies of those instructions. These instructions may include, when executed by at least one unit in the processor, causing the SoC 1300 to perform the attention training method according to the above embodiments, as detailed in the methods described above, which will not be repeated here.

[0122] Various embodiments of the mechanisms disclosed in this application can be implemented in hardware, software, firmware, or combinations of these implementation methods. Embodiments of this application can be implemented as computer programs or program code executable on a programmable system, the programmable system including at least one processor, a storage system (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device.

[0123] Program code can be applied to input instructions to execute the functions described in this application and generate output information. The output information can be applied to one or more output devices in a known manner. For the purposes of this application, the processing system includes any system having a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application-specific integrated circuit (ASIC), or a microprocessor.

[0124] The program code can be implemented using a high-level procedural language or an object-oriented programming language to communicate with the processing system. Assembly language or machine language can also be used when needed. In fact, the mechanisms described in this application are not limited to any particular programming language. In either case, the language can be a compiled language or an interpreted language.

[0125] In some cases, the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof. The disclosed embodiments may also be implemented as instructions carried or stored thereon on one or more temporary or non-temporary machine-readable (e.g., computer-readable) storage media, which may be read and executed by one or more processors. For example, the instructions may be distributed via a network or through other computer-readable media. Therefore, machine-readable media may include any mechanism for storing or transmitting information in a machine-readable (e.g., computer-readable) form, including but not limited to floppy disks, optical disks, CD-ROMs, compact disc read-only memory (CD-ROMs), magneto-optical disks, read-only memory (ROM), random-access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic cards or optical cards, flash memory, or tangible machine-readable storage for transmitting information (e.g., carrier waves, infrared signals, digital signals, etc.) using the Internet in the form of electrical, optical, acoustic, or other forms of propagated signals. Therefore, machine-readable media includes any type of machine-readable medium suitable for storing or transmitting electronic instructions or information in a machine-readable (e.g., computer-readable) form.

[0126] In the accompanying drawings, some structural or methodological features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be necessary. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the accompanying drawings. Furthermore, including structural or methodological features in a particular figure does not imply that such features are required in all embodiments, and in some embodiments, these features may be omitted or may be combined with other features.

[0127] It should be noted that all units / modules mentioned in the device embodiments of this application are logical units / modules. Physically, a logical unit / module can be a physical unit / module, a part of a physical unit / module, or a combination of multiple physical units / modules. The physical implementation of these logical units / modules themselves is not the most important factor; the combination of functions implemented by these logical units / modules is the key to solving the technical problems proposed in this application. Furthermore, to highlight the innovative aspects of this application, the above-described device embodiments of this application have not introduced units / modules that are not closely related to solving the technical problems proposed in this application. This does not mean that the above-described device embodiments do not contain other units / modules.

[0128] It should be noted that in the examples and description of this patent, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0129] Although this application has been illustrated and described with reference to certain preferred embodiments thereof, those skilled in the art should understand that various changes in form and detail may be made thereto without departing from the spirit and scope of this application.

Claims

1. A method for controlling the phase of bursting beads on a filter rod forming machine, characterized in that, A bursting bead phase control system applied to a filter rod forming machine, the bursting bead phase control system including an image acquisition device and a bead adding device, the bead adding device being used to add bursting beads to the filter rods in the filter rod forming machine based on a first bead adding phase, including: The image acquisition device acquires a first image of the filter rod, which includes a first burst bead. Based on the first image, determine the position information of the first popping bead in the filter rod; Based on the burst bead position information and the preset burst bead standard position information, the position offset of the first burst bead is determined; Based on the position offset, a pulse signal is generated and sent to the bead-adding device. The pulse signal is used to adjust the bead-adding phase of the bead-adding device to a first phase, which corresponds to the position offset, so that the bead-adding device adjusts the first bead-adding phase to a second bead-adding phase based on the pulse signal. The difference between the second bead-adding phase and the first bead-adding phase is the first phase.

2. The method according to claim 1, characterized in that, The pulse signal consists of a sequence of at least one pulse, each pulse having a first direction or a second direction. The pulse in the first direction is used to shift the beaded phase to the left, and the pulse in the second direction is used to shift the beaded phase to the right.

3. The method according to claim 1 or 2, characterized in that, Sending the pulse signal to the bead-adding device includes: If the position offset is determined to be greater than or equal to a preset offset threshold, the pulse signal is sent to the bead-adding device.

4. The method according to any one of claims 1 to 3, characterized in that, The pulse signal consists of a sequence of N pulses, where N is a positive integer greater than or equal to 1. Sending the pulse signal to the bead-adding device includes: Get the preset maximum number of pulses per adjustment as M, where M is a positive integer greater than or equal to 1; When N is less than or equal to M, a first pulse signal is sent to the bead-adding device, the first pulse signal being composed of the N pulses; When N is greater than M, a second pulse signal is sent to the bead-adding device, the second pulse signal being composed of M of the N pulses.

5. The method according to any one of claims 1 to 4, characterized in that, The burst bead position information includes the center coordinates of the burst bead, and determining the burst bead position information of the first burst bead in the filter rod forming machine includes: Based on the color information of the first burst bead in the first image, the coordinate information of the edge of the first burst bead is confirmed; The center coordinates of the first burst bead are determined based on the coordinate information of the edge of the first burst bead.

6. The method according to claim 5, characterized in that, The first burst bead includes multiple burst beads, and the burst bead position information includes the center coordinates of the multiple burst beads. Before determining the position offset, the method further includes: Obtain the center coordinate values ​​corresponding to the multiple burst beads; Abnormal data points are removed from the multiple center coordinate values ​​to obtain the corrected center coordinate values ​​of the first popping bead.

7. The method according to claim 6, characterized in that, The removal of outlier data points from the plurality of center coordinate values ​​includes: A first mean range is determined using the Grubbs algorithm and / or the normal distribution algorithm, wherein data outside the first mean range are considered outliers. Remove outlier data points from the plurality of center coordinate values ​​that are not within the range of the first mean.

8. A phase control system for bursting beads on a filter rod forming machine, characterized in that, include: Bead-adding device for adding popping beads to the filter rods in the filter rod forming machine based on a first bead-adding phase; An image acquisition device is used to acquire a first image of the filter rod, wherein the filter rod includes a first burst bead. A control device is configured to determine the position information of the first popping bead in the filter rod based on the first image, and to determine the position offset of the first popping bead based on a comparison between the popping bead position information and preset popping bead standard position information. The device also generates a pulse signal based on the position offset and sends the pulse signal to the bead-adding device. The pulse signal is used to adjust the bead-adding phase of the bead-adding device to a first phase, the first phase corresponding to the position offset, so that the bead-adding device adjusts the first bead-adding phase to a second bead-adding phase based on the pulse signal. The difference between the second bead-adding phase and the first bead-adding phase is the first phase.

9. The system according to claim 8, characterized in that, The image acquisition device includes: A camera and / or laser light source are used to acquire bar images corresponding to multiple image frames; The control device is specifically used to stitch together multiple bar images of the filter rod acquired by the camera and / or the laser light source into the first image based on the SIFT image stitching algorithm.

10. The system according to claim 8 or 9, characterized in that, The system also includes: An optocoupler is used to connect the control device and the bead-adding device.

Images