A method and system for adaptive adjustment of the adsorption force of cleaning equipment

Through visual inspection and spiral airflow control, the cleaning equipment can accurately identify and stably adsorb flaky particles, solving the problem of low adsorption efficiency of cleaning equipment for irregularly shaped particles, improving cleaning efficiency and reducing energy consumption.

CN123113364APending Publication Date: 2026-11-17TUOXIN ANZHIJIE POWER (SHAOGUAN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611418692.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-14
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing cleaning equipment has low adsorption efficiency when dealing with particles of various shapes, especially flat, flaky particles. These particles are prone to tumbling, slipping, or bouncing off, resulting in a low success rate for single adsorption and increased energy consumption and noise.

Method used

Visual detection identifies flaky particles, generating a rotating airflow along a spiral path. The deflection angle of the guide vanes is adjusted in real time, and combined with vortex enhancement, to ensure stable movement and effective desorption of flaky particles along the centerline of the dust collection channel.

Benefits of technology

It improves the single-use adsorption success rate of flaky particles, reduces the number of times cleaning equipment needs to operate repeatedly in the same area, and lowers energy consumption and time costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123113364A_ABST
    Figure CN123113364A_ABST
Patent Text Reader

Abstract

This application relates to the field of cleaning equipment technology, specifically a method and system for adaptive adjustment of the adsorption force of cleaning equipment. The method includes: acquiring an image of the cleaning area and identifying flaky particles; controlling the deflection of guide vanes to generate a rotating airflow; acquiring the real-time position of the flaky particles and calculating their offset relative to the centerline of the dust collection channel; if the offset is greater than a preset deviation threshold, adjusting the angle of the guide vanes to change the direction of the rotating airflow; if the offset is less than or equal to the preset deviation threshold, acquiring the surface adhesion force of the flaky particles when they enter the dust collection channel inlet; if the surface adhesion force is greater than a preset desorption threshold, performing vortex enhancement until the surface adhesion force is no greater than the preset desorption threshold. This application achieves accurate classification of flaky particles through morphological recognition, provides a spin stabilization effect to the particles through rotating airflow, ensures centered particle movement through real-time correction, and ensures smooth desorption through vortex enhancement, thereby improving the adsorption success rate and cleaning efficiency of the cleaning equipment for flaky particles.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application belongs to the field of cleaning equipment technology, specifically relating to a method and system for adaptive adjustment of the adsorption force of cleaning equipment. Background Technology

[0002] As a core tool for maintaining modern home and industrial environments, the adsorption efficiency of cleaning equipment directly affects the quality of cleaning operations and energy consumption control. With the increasing complexity of usage scenarios, the forms of ground pollutants exhibit significant diversity, ranging from regular dust particles to irregularly shaped solid particles such as food scraps and paper fragments.

[0003] Current cleaning equipment generally employs a constant adsorption force operating mode. This fixed-parameter airflow organization method exhibits significant limitations in adaptability when dealing with particles of varying shapes. For smooth, spherical particles, standard airflow can form an effective envelope for adsorption. However, when encountering irregularly shaped particles with uneven structures, sharp edges, or flat shapes, traditional straight airflow struggles to establish a stable pressure distribution on the particle surface. This mismatch between the airflow and the particle's geometry causes irregularly shaped particles to roll, slide, or even bounce off near the suction port, significantly reducing the success rate of single-pass adsorption. The equipment then needs to repeatedly pass through the same area to complete the cleaning task.

[0004] Therefore, how to improve the cleaning efficiency of cleaning equipment has become an urgent technical problem to be solved. Summary of the Invention

[0005] To address the above problems, this application provides a method and system for adaptive adjustment of the adsorption force of cleaning equipment, which achieves stable adsorption of flaky particles by identifying flaky particles and generating a rotating airflow.

[0006] To achieve the above objectives, this application provides a method for adaptive adjustment of the adsorption force of a cleaning device, comprising: Image data of the cleaning area of ​​the cleaning equipment is acquired, and flaky particles are identified from the image data. The flaky particles are irregularly shaped particles whose ratio of major axis to minor axis is greater than a preset flatness threshold. The guide vanes at the suction port of the cleaning device are deflected to generate a rotating airflow with a spiral flow path; The real-time position of the flake particles during their movement is obtained, and the offset of the flake particles relative to the center line of the dust collection channel of the cleaning equipment is calculated based on the real-time position. In response to the offset being greater than a preset deviation threshold, the deflection angle of the guide vanes is adjusted to change the direction of the rotating airflow; In response to the offset being less than or equal to the preset deviation threshold, the surface adhesion value of the flaky particles when they enter the dust collection channel inlet is obtained; In response to the surface adhesion value being greater than a preset desorption threshold, an eddy current enhancement operation is performed until the surface adhesion value is less than or equal to the preset desorption threshold.

[0007] On one hand, this application provides a cleaning equipment adsorption force adaptive adjustment system, comprising: The image acquisition module is used to acquire image data of the cleaning area of ​​the cleaning equipment and identify flaky particles from the image data. The flaky particles are irregularly shaped particles with a major-minor axis ratio greater than a preset flatness threshold. An airflow control module is used to control the deflection of the guide vanes at the suction port of the cleaning equipment to generate a rotating airflow with a spiral flow path. The position acquisition and offset calculation module is used to acquire the real-time position of the flake particles during the movement process, and calculate the offset of the flake particles relative to the center line of the dust collection channel of the cleaning equipment based on the real-time position. An angle adjustment module is used to adjust the deflection angle of the guide vanes in response to the offset being greater than a preset deviation threshold, so as to change the direction of the rotating airflow. An adhesion acquisition module is used to acquire the surface adhesion value of the flaky particles when they enter the dust collection channel inlet in response to the offset being less than or equal to the preset deviation threshold. The eddy current control module is used to perform eddy current enhancement operation in response to the surface adhesion value being greater than a preset desorption threshold, until the surface adhesion value is less than or equal to the preset desorption threshold.

[0008] The embodiments of this application have the following beneficial effects: In the embodiments of this application, image data of the cleaned area is acquired, irregularly shaped particles are identified from the image data, and their contour information is extracted. Then, based on the comparison between the ratio of the major and minor axes and a preset flatness threshold, the irregularly shaped particles are distinguished into sheet-like particles and block-like particles. For sheet-like particles, this embodiment further controls the deflection of the guide vanes at the suction port to generate a rotating airflow with a spiral flow path.

[0009] Compared with the cleaning equipment in related technologies that uses a constant adsorption force or a single airflow mode to process all particles, the embodiments of this application realize the quantitative classification and identification of particle morphology through visual detection, and actively reconstruct the straight airflow into a spiral airflow based on the flat morphological characteristics of the flake particles. This allows the cleaning equipment to adopt differentiated adsorption strategies according to the actual morphological characteristics of the particles, avoiding the phenomenon that flake particles roll, slide or even bounce away near the suction port due to the mismatch between the airflow pattern and the geometric characteristics of the particles, thus improving the single adsorption success rate of flake particles.

[0010] In the embodiments of this application, after generating the rotating airflow, the real-time position of the sheet-like particles during their movement is obtained through a position sensing component, and their offset relative to the centerline of the dust collection channel is calculated. When the offset exceeds a preset deviation threshold, the deflection angle of the guide vanes is adjusted to change the direction of the rotating airflow. This closed-loop adjustment mechanism based on real-time position feedback allows the direction of the rotating airflow to dynamically adapt to changes in the actual trajectory of the sheet-like particles, ensuring stable movement of the sheet-like particles along the centerline of the dust collection channel. This avoids the particles from impacting the pipe wall or falling out of the airflow due to deviation from the channel centerline, thus guaranteeing the stability and reliability of the conveying process.

[0011] Furthermore, in this embodiment, the surface adhesion value of the flaky particles is acquired when they move to the dust collection channel inlet. When the surface adhesion value is greater than a preset desorption threshold, a vortex enhancement operation is performed until the surface adhesion value is less than or equal to the preset desorption threshold. By acquiring the surface adhesion value of the flaky particles when they enter the dust collection channel inlet and comparing it with the preset desorption threshold, accurate judgment of the desorption state of the flaky particles is achieved. The vortex enhancement operation dynamically increases the rotation intensity of the airflow to reduce the surface adhesion, so that the flaky particles obtain sufficient desorption force at the moment they enter the dust collection channel.

[0012] In summary, the embodiments of this application enable the cleaning equipment to accurately distinguish flaky particles and activate a specialized airflow control mode through visual detection and morphological classification. The rotating airflow establishes a tangential pressure gradient on the surface of the flaky particles and generates aerodynamic torque, giving the particles a spin stabilizing effect. This solves the problem of unstable force and easy tumbling and bouncing of flaky particles in straight airflow. Simultaneously, position feedback and guided vane linkage ensure that the flaky particles maintain stable movement along the centerline of the dust collection channel during their spiral ascent. The vortex-enhanced dynamic desorption mechanism precisely eliminates surface adhesion when the flaky particles enter the dust collection channel inlet. This embodiment improves the single-pass adsorption success rate and overall cleaning efficiency of the cleaning equipment for flaky particles, effectively reducing the number of times the equipment operates repeatedly in the same area, and lowering the time cost and energy consumption of cleaning operations. Attached Figure Description

[0013] Figure 1This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the first embodiment of this application; Figure 2 This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the second embodiment of this application; Figure 3 This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the third embodiment of this application; Figure 4 This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the fourth embodiment of this application; Figure 5 This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the fifth embodiment of this application; Figure 6 This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the sixth embodiment of this application; Figure 7 This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the seventh embodiment of this application; Figure 8 This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the eighth embodiment of this application; Figure 9 This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the ninth embodiment of this application; Figure 10 This is a flowchart illustrating a method for adaptive adjustment of the adsorption force of a cleaning device provided in the tenth embodiment of this application; Figure 11 This is a schematic diagram of a cleaning equipment adsorption force adaptive adjustment system provided in the embodiments of this application. Detailed Implementation

[0014] To enable those skilled in the art to better understand the technical solution, the present application will be described in detail below with reference to the embodiments. The description in this section is only exemplary and explanatory, and should not be used to limit the scope of protection of the present application in any way.

[0015] Current cleaning equipment exhibits significant limitations in adapting to particulate matter of varying shapes. Specifically, while the airflow of cleaning equipment can effectively envelop and adsorb smooth, spherical particles, it struggles to establish a stable pressure distribution on the particle surface when encountering irregularly shaped particles with uneven structures, sharp edges, or flat shapes. Further analysis reveals that the streamline direction of linear airflow is singular, limiting the adhesion area on the particle surface and preventing the formation of a comprehensive envelopment around the particle's irregular features. When the airflow impacts the particle surface, the drastic changes in surface curvature cause airflow separation at sharp corners or edges, creating localized vortices and low-pressure zones. This results in the force direction on the particle fluctuating dramatically with its orientation. This mismatch between the airflow and the particle's geometry causes irregularly shaped particles to roll, slide, or even bounce off near the suction port, significantly reducing the success rate of single-pass adsorption. The equipment must repeatedly pass through the same area to complete the cleaning task.

[0016] In related technologies, some products attempt to improve adsorption by increasing the constant suction power to enhance the adsorption effect. However, this method has significant limitations. First, simply increasing the suction power only changes the amplitude of the airflow velocity and still cannot establish an effective envelope pressure field on the flat surface of the flake particles. Second, for lighter flake particles such as paper, plastic film, or dry blades, the increased vertical airflow will actually create a high-pressure zone at the bottom of the particles, generating an aerodynamic lift effect that blows the particles away or exacerbates their escape, rather than guiding them into the dust collection channel. Furthermore, continuous high-power operation leads to a significant increase in energy consumption and noise, seriously affecting the equipment's battery life and user experience.

[0017] Therefore, how to adjust the working parameters of cleaning equipment in real time based on particulate matter morphology information to keep the adsorption process stable and controllable has become a key issue in improving the intelligence level of cleaning equipment.

[0018] For the above technical issues, please refer to [link / reference]. Figure 1 One or more embodiments of this application and combinations thereof provide a method for adaptive adjustment of the adsorption force of a cleaning device, comprising the following steps: Step S100: Acquire image data of the cleaning area of ​​the cleaning equipment, and identify flaky particles from the image data. Flaky particles are irregularly shaped particles whose major and minor axis ratios are greater than a preset flatness threshold.

[0019] Step S120: Control the deflection of the guide vanes at the suction port of the cleaning equipment to generate a rotating airflow with a spiral flow path.

[0020] Step S140: Obtain the real-time position of the flake particles during their movement, and calculate the offset of the flake particles relative to the center line of the dust collection channel of the cleaning equipment based on the real-time position.

[0021] Step S160: In response to the offset being greater than a preset deviation threshold, adjust the deflection angle of the guide vanes to change the direction of the rotating airflow.

[0022] Step S180: In response to the offset being less than or equal to a preset deviation threshold, obtain the surface adhesion value when the flaky particles enter the dust collection channel inlet.

[0023] Step S200: In response to the surface adhesion value being greater than the preset desorption threshold, perform eddy current enhancement operation until the surface adhesion value is less than or equal to the preset desorption threshold.

[0024] In step S100, the cleaning device can be an intelligent vacuum cleaner with visual perception and airflow regulation functions, including a device body, a vacuum port located at the bottom of the device body, a dust collection channel connected to the vacuum port, a flow guiding component located inside the vacuum port, an image acquisition component, a position sensing component, an airflow driving component, and a central control unit located on the device body.

[0025] The cleaning area refers to the floor area in the working environment where the cleaning equipment is currently located and cleaning operations need to be performed. Image data refers to the data obtained by the image acquisition component from taking pictures of the cleaning area, including images of the floor background and irregularly shaped particles on the floor.

[0026] After acquiring image data of the cleaning area through its image acquisition component, the cleaning equipment can process the acquired image data to identify irregularly shaped particles. Specifically, by performing grayscale conversion on the image data, a grayscale image containing the grayscale values ​​of each pixel is obtained. The edge pixels in the image are then determined based on the grayscale differences between adjacent pixels. The area enclosed by these closed edge pixels is identified as the contour region of the irregularly shaped particles, thus allowing the particles to be identified from the image data.

[0027] After identifying irregularly shaped particles, their contour information can be further extracted, and their shape can be determined based on this information to determine whether they are sheet-like particles. Sheet-like particles are irregularly shaped particles whose major-minor axis ratio is greater than a preset flattening threshold. The preset flattening threshold can be stored in the central control unit in advance. Furthermore, during the research and development phase of the cleaning equipment, several sample particles, including known sheet-like and block-like particles, can be collected first. Then, the major-minor axis ratio of each sample particle is calculated. Finally, the preset flattening threshold is determined by using the calculated major-minor axis ratios of multiple known sheet-like particles. For example, the preset flattening threshold can be 1.5, 1.8, 2.0, 2.5, 3.0, etc.

[0028] It can be understood that the ratio of the major axis to the minor axis of the equivalent ellipse of irregularly shaped particles can be considered as the ratio of the length of the major axis to the length of the minor axis. The larger this ratio is, the more the particles tend to be slender or flat; the closer the ratio is to 1, the more the particles tend to be an isotropic block or spherical shape.

[0029] If the ratio of the major and minor axes of the irregularly shaped particles is less than or equal to the preset flatness threshold, the irregularly shaped particles are determined to be block particles. For block particles, the cleaning equipment maintains the current adsorption force working mode.

[0030] If the ratio of the major and minor axes of the irregularly shaped particles is greater than the preset flatness threshold, then the irregularly shaped particles are determined to be sheet-like particles.

[0031] In step S120, after the cleaning equipment determines that the irregularly shaped particles are flaky particles, it generates a corresponding control command. This control command is used to drive the guide vanes at the suction port to deflect. The deflection of the guide vanes changes the direction of the airflow passing through the suction port, thereby creating a spiral flow path along the inside of the suction port and obtaining a rotating airflow.

[0032] It can be understood that the guide vanes are airflow guiding structures installed inside the suction port, which change the flow direction and path distribution of the airflow by altering their deflection angle. Rotating airflow refers to the airflow organization form in which the airflow moves along a spiral path inside the suction port, possessing both a flow component along the axial direction of the suction port and a rotational component along the tangential direction. Preset spiral angle values ​​can be stored in the cleaning equipment beforehand, determined through fluid dynamics simulation or experimental testing before the equipment leaves the factory. For example, during the R&D phase, a three-dimensional fluid dynamics simulation model of the suction port and guide vanes is established. The flow state of the airflow is simulated at multiple candidate deflection angles, and the vorticity intensity and tangential velocity component of the airflow corresponding to each candidate deflection angle are calculated. With the goal of the vorticity intensity exceeding a preset vorticity threshold and the tangential velocity component exceeding a preset velocity threshold, one or more angle values ​​satisfying the above conditions are selected from multiple candidate deflection angles and set as the preset spiral angle value. For example, the preset spiral angle value can be 30 degrees, 45 degrees, 50 degrees, 60 degrees, etc.

[0033] Through the above process, the cleaning equipment generates a rotating airflow with a spiral flow path at the suction port, which is used to act on the surface of the flaky particles.

[0034] In step S140, the cleaning device obtains the real-time position of the flake particles during their movement through a position sensing component, and calculates the offset of the flake particles relative to the center line of the dust collection channel of the cleaning device based on the real-time position.

[0035] Specifically, the position sensing component can use a non-contact sensing method to acquire the position coordinates of the sheet-like particles in three-dimensional space and output these coordinates as real-time position data. The centerline of the dust collection channel refers to the geometric central axis of the dust collection channel along its extension direction, and the spatial position of this centerline is predetermined. The offset refers to the spatial distance of the real-time position of the sheet-like particles from the centerline of the dust collection channel. It is specifically calculated by using the centerline of the dust collection channel as a reference point to calculate the deviation distance of the sheet-like particles in the direction perpendicular to the centerline of the dust collection channel.

[0036] It is understandable that the offset can include information about the direction of deviation, which indicates the specific direction in which the flaky particles deviate from the centerline of the dust collection channel.

[0037] In step S160, the cleaning equipment compares the offset calculated in step S140 with a preset deviation threshold. The preset deviation threshold can be stored in the cleaning equipment beforehand, determined through experimental testing or simulation analysis before the equipment leaves the factory or during the R&D phase. Specifically, the trajectory distribution of the flake particles within the dust collection channel can be obtained through experimental testing or simulation analysis. The maximum offset value when the flake particles can enter the dust collection channel entrance on their own is statistically analyzed, and this maximum offset value is set as the preset deviation threshold. Alternatively, the maximum offset value can be multiplied by a safety factor less than 1 to obtain the preset deviation threshold. For example, the preset deviation threshold can be 3 mm, 5 mm, 8 mm, 10 mm, etc. If the offset is greater than the preset deviation threshold, it indicates that the movement direction of the flake particles has deviated from the centerline of the dust collection channel and the degree of deviation exceeds the allowable range, then the cleaning equipment performs an adjustment operation.

[0038] Specifically, the adjustment operation refers to the cleaning equipment adjusting the deflection angle of the guide vanes at the suction port based on the directional component of the offset. The directional component of the offset is used to indicate the direction of deviation of the flaky particles relative to the centerline of the dust collection channel, and the cleaning equipment determines the deflection direction of the guide vanes based on this deviation direction.

[0039] By adjusting the deflection angle of the guide vanes, the tangential flow direction of the rotating airflow is changed, which in turn changes the tangential pressure gradient direction vector acting on the surface of the flake particles. This causes the lateral aerodynamic force on the flake particles to change, pushing the flake particles toward the centerline of the dust collection channel.

[0040] It is understood that the adjustment operation in step S160 can be repeatedly performed during the movement of the flaky particles. That is, the cleaning equipment continuously acquires the real-time position of the flaky particles and calculates the offset at a preset sampling period. After each calculation, the offset is compared with a preset deviation threshold. If the offset is still greater than the preset deviation threshold, the deflection angle of the guide vanes is adjusted until the offset is less than or equal to the preset deviation threshold.

[0041] Through the above process, the cleaning equipment achieves real-time correction of the movement trajectory of the flake particles, enabling the flake particles to move along the center line of the dust collection channel and enter the dust collection channel.

[0042] In step S180, when the offset determined in step S160 is less than or equal to a preset deviation threshold, it indicates that the flake particles have moved along the centerline of the dust collection channel to the vicinity of the dust collection channel inlet. At this time, the cleaning equipment acquires the surface adhesion force value when the flake particles enter the dust collection channel inlet. Surface adhesion force refers to the magnitude of the adhesion effect generated between the surface of the flake particles and the airflow due to aerodynamic forces. This surface adhesion force value can be calculated by detecting the motion state parameters of the flake particles when they enter the dust collection channel inlet.

[0043] It can be understood that the moment when flaky particles enter the dust collection channel inlet can refer to the time when the flaky particles and the dust collection channel inlet plane reach a specific relative spatial position. The criteria for determining this moment can be either the moment when the centroid coordinates of the flaky particles coincide with the coordinates of the dust collection channel inlet plane, or the moment when the leading edge of the flaky particles first reaches the dust collection channel inlet plane. The cleaning equipment continuously acquires the spatial coordinates of the flaky particles through position sensing components and compares these coordinates with the pre-stored position coordinates of the dust collection channel inlet plane in real time. When both meet any of the above criteria, the current moment is determined to be the moment when the flaky particles enter the dust collection channel inlet.

[0044] Subsequently, the cleaning equipment acquires the particle spin angular velocity and airflow velocity components at the moment the flaky particles enter the dust collection channel inlet. The particle spin angular velocity reflects the speed at which the flaky particles rotate around their own center of mass under the influence of the rotating airflow. The airflow velocity component refers to the decomposition of the velocity of the rotating airflow at the dust collection channel inlet in different directions, which may include one or more of the tangential, axial, and radial velocity components. The cleaning equipment acquires these two parameters through a velocity sensing component or a vision sensing component installed at the dust collection channel inlet. After acquiring the particle spin angular velocity and airflow velocity components, the cleaning equipment calculates the surface adhesion force of the flaky particles based on these two parameters. Surface adhesion force refers to the magnitude of the adhesion effect generated between the surface of the flaky particles and the airflow due to aerodynamic forces, which can be obtained by substituting the particle spin angular velocity and airflow velocity components into a preset fluid dynamics equation.

[0045] The cleaning equipment uses the calculated surface adhesion value as the output of step S180 for use in subsequent step S200.

[0046] In step S200, the cleaning equipment obtains the surface adhesion value calculated in step S180 and compares it with a preset desorption threshold. The preset desorption threshold can be stored in the cleaning equipment in advance. This preset desorption threshold is determined through experimental testing before the cleaning equipment leaves the factory or during the research and development stage. Specifically, several known sheet-like particle samples can be collected, and the surface adhesion of the sheet-like particles can be measured under different airflow vortex intensity conditions, and the corresponding desorption effect can be recorded. The maximum surface adhesion value that enables the sheet-like particles to be smoothly desorbed from the dust collection channel inlet and enter the dust collection channel is set as the preset desorption threshold. For example, the preset desorption threshold can be 4.5 micronewtons, 5.0 micronewtons, 6.0 micronewtons, 8.0 micronewtons, etc.

[0047] If the surface adhesion value is less than or equal to the preset desorption threshold, it means that the current surface adhesion is insufficient to prevent the flake particles from smoothly entering the dust collection channel, and the cleaning equipment maintains the current airflow operation state.

[0048] If the surface adhesion value exceeds the preset desorption threshold, it indicates that the current surface adhesion is too high, and flaky particles may adhere to the dust collection channel inlet and be unable to enter smoothly. In this case, the cleaning equipment performs a vortex enhancement operation. Specifically, the cleaning equipment calculates a compensation coefficient based on the difference between the surface adhesion value and the preset desorption threshold. This compensation coefficient indicates the required increase in vortex intensity; a larger difference indicates a larger increase, and a smaller difference indicates a smaller increase. The compensation coefficient can be calculated by multiplying the difference between the surface adhesion value and the preset desorption threshold by a preset proportionality coefficient. This preset proportionality coefficient can be stored in the cleaning equipment in advance and is determined through experimental testing or empirical formulas. It is used to convert the dimension of the adhesion difference into the dimension of vortex intensity adjustment.

[0049] Vorticity intensity is a physical quantity that characterizes the rotational intensity of airflow. The greater the vorticity intensity, the stronger the rotational effect of the airflow. Cleaning equipment increases the vorticity intensity of the rotating airflow according to a compensation coefficient to enhance the aerodynamic force of the rotating airflow on the surface of flaky particles, thereby reducing the surface adhesion of the flaky particles.

[0050] It is understandable that the eddy current enhancement operation can be repeatedly performed during the process of flaky particles entering the dust collection channel inlet. That is, the cleaning equipment continuously acquires the surface adhesion value of flaky particles at the dust collection channel inlet at a preset sampling period. After each acquisition, the surface adhesion value is compared with the preset desorption threshold. If the surface adhesion value is still greater than the preset desorption threshold, the compensation coefficient is calculated based on the new difference and the eddy current intensity is further increased until the surface adhesion value is less than or equal to the preset desorption threshold, so that the flaky particles can be successfully desorbed and enter the dust collection channel.

[0051] Through the above process, the cleaning equipment dynamically optimizes the vortex intensity of the rotating airflow when the flaky particles enter the dust collection channel inlet, ensuring that the surface adhesion of the flaky particles is reduced to below the desorption threshold, thereby achieving efficient desorption and collection of the flaky particles.

[0052] Of course, in response to the detection that the flaky particles have completely passed through the dust collection channel inlet and entered the dust collection channel, the vortex enhancement operation is stopped and the guide vanes are restored to the deflection angle before step S120.

[0053] In this embodiment, image data of the cleaned area is acquired, irregularly shaped particles are identified from the image data, and their contour information is extracted. Then, based on the comparison between the ratio of the major and minor axes and a preset flatness threshold, the irregularly shaped particles are classified into sheet-like particles and block-like particles. For sheet-like particles, this embodiment further controls the deflection of the guide vanes at the suction port to generate a rotating airflow with a spiral flow path.

[0054] Compared with the cleaning equipment in related technologies that uses constant adsorption force or a single airflow mode to process all particles, this embodiment achieves quantitative classification and identification of particle morphology through visual detection. Based on the flat morphological characteristics of flaky particles, it actively reconstructs the straight airflow into a spiral airflow, enabling the cleaning equipment to adopt differentiated adsorption strategies according to the actual morphological characteristics of the particles. This avoids the phenomenon of flaky particles rolling, sliding, or even bouncing away near the suction port due to the mismatch between airflow morphology and particle geometry, thereby improving the single-pass adsorption success rate of flaky particles.

[0055] In this embodiment, after generating the rotating airflow, the real-time position of the sheet-like particles during their movement is obtained through a position sensing component, and their offset relative to the centerline of the dust collection channel is calculated. When the offset exceeds a preset deviation threshold, the deflection angle of the guide vanes is adjusted to change the direction of the rotating airflow. This closed-loop adjustment mechanism based on real-time position feedback allows the direction of the rotating airflow to dynamically adapt to changes in the actual trajectory of the sheet-like particles, ensuring stable movement of the particles along the centerline of the dust collection channel. This avoids the particles from impacting the pipe wall or falling out of the airflow due to deviation from the channel centerline, thus guaranteeing the stability and reliability of the conveying process.

[0056] Furthermore, in this embodiment, the surface adhesion value of the flaky particles is acquired when they move to the dust collection channel inlet. When the surface adhesion value is greater than a preset desorption threshold, a vortex enhancement operation is performed until the surface adhesion value is less than or equal to the preset desorption threshold. By acquiring the surface adhesion value of the flaky particles when they enter the dust collection channel inlet and comparing it with the preset desorption threshold, accurate judgment of the desorption state of the flaky particles is achieved. The vortex enhancement operation dynamically increases the rotation intensity of the airflow to reduce the surface adhesion, so that the flaky particles obtain sufficient desorption force at the moment they enter the dust collection channel.

[0057] In summary, this embodiment enables the cleaning equipment to accurately distinguish flaky particles and activate a specialized airflow control mode through visual detection and morphological classification. The rotating airflow establishes a tangential pressure gradient on the surface of the flaky particles and generates aerodynamic torque, giving the particles a spin-stabilizing effect. This solves the problem of unstable force and easy tumbling and bouncing of flaky particles in straight airflow. Simultaneously, position feedback and guided vane linkage ensure that the flaky particles maintain stable movement along the centerline of the dust collection channel during their spiral ascent. The vortex-enhanced dynamic desorption mechanism precisely eliminates surface adhesion when the flaky particles enter the dust collection channel inlet. This embodiment improves the single-pass adsorption success rate and overall cleaning efficiency of the cleaning equipment for flaky particles, effectively reducing the number of times the equipment operates repeatedly in the same area, and lowering the time and energy costs of cleaning operations.

[0058] In one embodiment, see Figure 2 Step S100 includes: Step S101: Perform edge detection processing on the image data and extract the coordinate sequence of sampling points for irregular contours.

[0059] Step S102: Calculate the rate of curvature change between adjacent sampling points based on the coordinate sequence of the irregular contour sampling points.

[0060] Step S103: Based on the rate of curvature change, smooth the coordinate sequence of the sampling points of the irregular contour to obtain the coordinate sequence of the target contour.

[0061] Step S104: Calculate the area value and perimeter of the closed region enclosed by the target contour coordinate sequence.

[0062] Step S105: Fit the major and minor axis ratio of the irregular contour based on the area of ​​the closed region and the perimeter of the contour.

[0063] Step S106: In response to the ratio of major and minor axes being greater than a preset flatness threshold, the irregular contour is determined to be sheet-like particles.

[0064] In step S101, after the cleaning device acquires image data of the cleaning area through the image acquisition component, it processes the acquired image data to identify irregularly shaped particles from the image data. Specifically, the image data can be converted to grayscale to obtain a grayscale image containing the grayscale values ​​of each pixel. The edge pixels in the image are determined based on the grayscale differences between adjacent pixels in the grayscale image. The area enclosed by the closed edge pixels is determined as the contour region of the irregularly shaped particles, thereby identifying the irregularly shaped particles from the image data.

[0065] After identifying irregularly shaped particles, the cleaning equipment performs edge detection processing on the contour of the particles and extracts the coordinate sequence of sampling points on the irregular contour. The coordinate sequence of sampling points on the irregular contour refers to the sequence of coordinates on the image plane formed by multiple sampling points collected along the edge of the irregular particle contour at a preset step size. This sequence is used to describe the shape information of the irregular particle contour.

[0066] In step S102, after the cleaning equipment obtains the coordinate sequence of the sampling points of the irregular contour, it calculates the rate of curvature change between adjacent sampling points based on this sequence. Specifically, the tangent direction angle at each sampling point can be calculated first, the curvature value at each sampling point can be calculated based on the difference in tangent direction angles between adjacent sampling points, and then the rate of curvature change can be calculated based on the difference in curvature between adjacent sampling points. The rate of curvature change reflects the change in the degree of curvature of the irregular particle contour at different positions, and its magnitude and positive / negative changes can reflect the concave and convex characteristics of the contour surface.

[0067] In step S103, the cleaning equipment smooths the coordinate sequence of the sampling points of the irregular contour according to the calculated rate of curvature change, thereby obtaining the target contour coordinate sequence. Locations with a large rate of curvature change usually correspond to bumps or noise points on the contour. By identifying sampling points with a rate of curvature change exceeding a preset threshold and smoothing them, local burrs and noise interference on the contour can be eliminated, making the contour smoother and more continuous.

[0068] The specific method of smoothing can be to identify sampling points whose curvature change rate is greater than a preset curvature threshold, and perform mean filtering or Gaussian filtering on the sampling point and its neighboring sampling points to reduce the curvature change rate of the region, thereby obtaining a smooth and continuous target contour coordinate sequence.

[0069] In step S104, after obtaining the target contour coordinate sequence, the cleaning equipment calculates the area and perimeter of the closed region enclosed by the target contour coordinate sequence. Specifically, the area can be obtained by integrating the target contour coordinate sequence using Green's formula, and the perimeter can be obtained by summing the Euclidean distances between adjacent sampling points in the target contour coordinate sequence. The area and perimeter are fundamental geometric parameters describing the size and shape of irregularly shaped particles.

[0070] In step S105, the cleaning equipment fits the major-minor axis ratio of the irregularly shaped particles based on the area and perimeter of the enclosed region. The major-minor axis ratio is the ratio of the major axis length to the minor axis length of the equivalent ellipse.

[0071] For example, the major axis length *a* and minor axis length *b* of the equivalent ellipse can be solved as follows: Let the area of ​​the closed region be *S* and the perimeter of the contour be *L*. According to the ellipse area formula *S* = πab and the approximate ellipse perimeter formula *L* ≈ π[3(a+b) / 2 - √(ab)], substituting the known area value *S* and perimeter value *L* into the above two formulas, we obtain a system of two nonlinear equations about *a* and *b*. Solving this system of equations using numerical methods yields numerical solutions for the major axis length *a* and minor axis length *b*. Of course, other equivalent ellipse fitting methods can also be used, such as calculating the principal axis direction and major and minor axis lengths using image moments, or using the least squares method to fit the contour sampling points to an ellipse. This embodiment is not limited to the specific fitting methods described above.

[0072] After obtaining the major axis length 'a' and the minor axis length 'b', calculate their ratio a / b to obtain the major-minor axis ratio. The larger this ratio is, the more elongated or flattened the particles tend to be; the closer the ratio is to 1, the more homogeneous the particles tend to be blocky or spherical.

[0073] In step S106, if the ratio of the major axis to the minor axis is greater than a preset flatness threshold, the cleaning device determines that the irregular particle is a sheet-like particle.

[0074] In this embodiment, the coordinate sequence of sampling points for the irregular contour is extracted through edge detection, and the contour is smoothed based on the rate of curvature change between adjacent sampling points, eliminating local burrs and noise interference on the contour and improving the accuracy of contour representation. Furthermore, by calculating the area value of the closed region enclosed by the target contour coordinate sequence and the contour perimeter, and fitting the major and minor axis ratios, a quantitative description of the irregular particle morphology is achieved. This enables accurate differentiation between sheet-like and block-like particles, laying the foundation for improving the adsorption success rate of sheet-like particles.

[0075] In one embodiment, see Figure 3 and Figure 4 Step S102 includes: Step S1020: Calculate the tangent direction angle between adjacent sampling points based on the coordinate sequence of the irregular contour sampling points.

[0076] Step S1021: Calculate the curvature value between adjacent sampling points based on the tangent direction angle.

[0077] Step S1022: Calculate the rate of change of curvature between adjacent sampling points based on the curvature value.

[0078] And, step S103 includes: Step S1030: In response to the curvature change rate being greater than the preset curvature threshold, the corresponding sampling point is determined to be a candidate concave-convex point, and a set of candidate concave-convex points is obtained.

[0079] Step S1031: Obtain the coordinate values ​​of each candidate concave / convex point in the candidate concave / convex point set.

[0080] Step S1032: Determine the location markers of the irregular particles based on the coordinate values ​​of each candidate concave and convex point.

[0081] Step S1033: Based on the concave and convex point position marks, perform local smoothing on the sampling points and neighboring points corresponding to the concave and convex point position marks in the irregular contour sampling point coordinate sequence to obtain the target contour coordinate sequence.

[0082] In step S1020, for any two adjacent sampling points in the coordinate sequence of the irregular contour sampling points, the tangent direction angle can be determined according to the direction of the line connecting the two adjacent sampling points. For example, the direction angle of the line can be used as an approximation of the tangent direction angle of the contour segment corresponding to the two adjacent points, thereby obtaining the tangent direction angle value at each sampling point.

[0083] In step S1021, the curvature value is used to characterize the degree of curvature of the irregular particle profile at a certain position. It can be calculated by the ratio of the change in the tangent direction angle between adjacent sampling points to the corresponding arc length. The larger the curvature value, the more severe the curvature of the profile at that position; the smaller the curvature value, the closer the profile at that position is to a straight line.

[0084] In step S1022, the curvature change rate is used to characterize the variation of the curvature degree of the irregular particle contour along the contour distribution. It can be calculated by the ratio of the difference in curvature values ​​between adjacent sampling points to the corresponding arc length. The magnitude and positive / negative change of the curvature change rate can reflect the concavity and convexity features of the contour surface. For example, the peak position where the curvature change rate changes from a positive value to a negative value corresponds to a convex point on the contour, and the valley position where the curvature change rate changes from a negative value to a positive value corresponds to a concave point on the contour, thus providing an accurate basis for subsequent contour smoothing and morphology classification.

[0085] In step S1030, the cleaning device compares the calculated rate of curvature change at each sampling point with a preset curvature threshold. The preset curvature threshold can be stored in the cleaning device beforehand. During the research and development phase of the cleaning device, several sample particles containing known surface irregularities are collected, and the rate of curvature change at the contour sampling points of each sample particle is calculated. The threshold is determined with the goal of effectively distinguishing between irregular points and normal contour points. For example, the preset curvature threshold can be 0.5, 0.8, 1.0, 1.5, etc. If the rate of curvature change at a certain sampling point is greater than the preset curvature threshold, the cleaning device determines that sampling point as a candidate irregular point. After traversing all sampling points, a set of candidate irregular points is obtained.

[0086] In step S1031, the cleaning device obtains the coordinate value of each candidate bump in the candidate bump set, which is used to indicate the position of the candidate bump on the image plane.

[0087] In step S1032, it can be understood that since the same concave-convex feature region may contain multiple adjacent candidate concave-convex points, the cleaning device can perform clustering processing on the candidate concave-convex points according to the coordinate values ​​of the candidate concave-convex points (for example, using density-based clustering algorithm or hierarchical clustering algorithm), classify the candidate concave-convex points belonging to the same concave-convex feature region into one category, and extract the representative position in the category (for example, the mean position of the coordinates of each candidate concave-convex point in the category) as the concave-convex point position marker, thereby determining the accurate position of the concave-convex points on the profile of the irregular particle.

[0088] In step S1033, the sampling points corresponding to the concave / convex point location markers and their adjacent neighboring sampling points (e.g., several sampling points before and after) constitute the region with drastic curvature changes on the contour. Local smoothing of the sampling points within this region can eliminate local contour distortion caused by concave / convex features or noise. Specifically, the local smoothing process can involve applying mean filtering or Gaussian filtering to the sampling points corresponding to the concave / convex point location markers and their neighboring points, using the weighted average of the coordinates of all sampling points within this region as the smoothed coordinate values, thereby obtaining a smooth and continuous target contour coordinate sequence. This target contour coordinate sequence preserves the overall shape characteristics of the irregular particle contour while eliminating local burrs and noise interference.

[0089] In this embodiment, by calculating the tangent direction angle between adjacent sampling points, and then calculating the curvature value based on the tangent direction angle, and finally calculating the rate of change of curvature based on the curvature value, the precise quantification of the curvature degree and its variation law of the irregular particle contour is achieved. Furthermore, by comparing the rate of change of curvature with a preset curvature threshold, candidate concave and convex points are identified and their location markers are determined, accurately distinguishing between real concave and convex features and noise interference on the contour. Based on this, local smoothing processing is performed on the corresponding sampling points and neighboring points according to the concave and convex point location markers. This eliminates local burrs and noise interference while retaining the effective shape information corresponding to the concave and convex features, avoiding the problem of losing effective features due to smoothing the entire contour. The resulting target contour coordinate sequence retains both the real geometric features of the irregular particles and a smooth and continuous contour shape, laying the foundation for accurate fitting of the major and minor axis ratios and accurate identification of sheet-like particles.

[0090] In one embodiment, see Figure 5 Step S120 includes: Step S121: Generate a rotating airflow control command and obtain the current deflection angle of the guide vanes inside the suction port.

[0091] Step S122: Calculate the angle difference between the current deflection angle and the preset helix angle value, and generate a pulse signal for the stepper motor of the cleaning equipment based on the angle difference.

[0092] Step S123: Drive the stepper motor according to the rotating airflow control command and pulse signal to synchronously adjust the guide vanes from the current deflection angle to the preset spiral angle value, so that the airflow forms a turbulent state inside the dust suction port and obtains a rotating airflow with a spiral flow path.

[0093] In step S121, the rotating airflow control command instructs the cleaning equipment to switch the airflow from the current flow mode to a rotating airflow mode with a spiral flow path. The current deflection angle of the guide vanes is the position angle of the guide vanes before the adjustment operation is performed. This angle can be obtained in real time by an angle sensor or read from the control register of the cleaning equipment.

[0094] In step S122, the preset spiral angle value can be stored in the cleaning equipment in advance. This value is determined through fluid dynamics simulation or experimental testing before the equipment leaves the factory. Specifically, a three-dimensional fluid dynamics simulation model of the suction port and guide vanes can be established. The airflow state is simulated at multiple candidate deflection angles, and the vortex intensity and tangential velocity component of the airflow corresponding to each candidate deflection angle are calculated. With the goal of the vortex intensity exceeding a preset vortex threshold and the tangential velocity component exceeding a preset velocity threshold, one or more angle values ​​satisfying the above conditions are selected from the multiple candidate deflection angles and set as the preset spiral angle value. For example, the preset spiral angle value can be 30 degrees, 45 degrees, 50 degrees, 60 degrees, etc. The larger the absolute value of the angle difference, the greater the required rotation amplitude of the guide vanes; the positive or negative sign of the angle difference indicates the rotation direction of the guide vanes. The cleaning equipment generates a corresponding pulse signal based on this angle difference value. The number and frequency of the pulse signals are related to the magnitude of the angle difference and the desired rotation speed.

[0095] In step S123, a stepper motor is driven according to the rotating airflow control command and pulse signal to deflect the guide vanes to a preset spiral angle value. At this time, the direction of the airflow passing through the suction port changes, and the airflow forms a turbulent state inside the suction port, obtaining a rotating airflow with a spiral flow path. The turbulent state refers to the disordered and mixed flow state of the airflow inside the suction port, which has a high vortex intensity and tangential velocity component, and can generate a sufficient tangential pressure gradient to act on the surface of the sheet particles, thereby driving the sheet particles to obtain a spin angular velocity.

[0096] Multiple guide vanes can be used, evenly distributed circumferentially inside the suction port. A stepper motor drives these vanes to deflect synchronously via a transmission mechanism, ensuring the symmetry and stability of the airflow. Through this process, the cleaning equipment generates a rotating airflow based on the geometric shape data of the flaky particles and precisely controls the deflection angle of the guide vanes, achieving targeted airflow regulation for the flaky particles.

[0097] In this embodiment, by acquiring the geometric morphology data of the sheet-like particles and generating a rotating airflow control command accordingly, a precise match between the airflow pattern and the particle morphology is achieved. Simultaneously, by calculating the angle difference between the current deflection angle and a preset helical angle value and generating a pulse signal to drive a stepper motor, precise closed-loop control of the guide vane deflection angle is achieved, enabling the guide vane to quickly and accurately adjust from the current deflection angle to the preset helical angle value. After the guide vane deflects to the preset helical angle value, the airflow forms a turbulent state inside the suction port and obtains a rotating airflow with a helical flow path. This rotating airflow has high vorticity intensity and tangential velocity components, generating a sufficient tangential pressure gradient acting on the surface of the sheet-like particles.

[0098] In one embodiment, see Figure 6 Step S180 includes: Step S181: Obtain the particle spin angular velocity and airflow velocity components at the moment the flaky particles enter the dust collection channel inlet. The airflow velocity components include at least one of the tangential velocity component, axial velocity component, and radial velocity component.

[0099] Step S182: Calculate the drag force on the sheet-like particles in the airflow based on the airflow velocity component and the equivalent diameter of the sheet-like particles.

[0100] Step S183: Calculate the lift generated by the spin of the plate-like particles based on the particle spin angular velocity, the airflow velocity component, and the equivalent diameter of the plate-like particles.

[0101] Step S184: Vector superposition of drag and lift to obtain the resultant force of airflow on the surface of the sheet-like particles, and use the resultant force of airflow as the surface adhesion force value.

[0102] In step S181, the cleaning equipment obtains the particle spin angular velocity and airflow velocity components at the moment the flaky particles enter the dust collection channel inlet using a speed sensing component or a vision sensing component installed at the dust collection channel inlet.

[0103] Specifically, for acquiring the particle spin angular velocity, a high-speed vision sensor can be deployed at the dust collection channel inlet. This sensor continuously acquires image sequences of the moment when the sheet-like particles enter the dust collection channel inlet at a preset sampling frequency. Using particle image velocimetry algorithms or optical flow methods, feature points on the surface of the sheet-like particles in adjacent frames are matched and tracked to extract the angular displacement of the sheet-like particles over a continuous time interval. The particle spin angular velocity is then calculated based on the ratio of the angular displacement to the time interval. Alternatively, a laser displacement sensor or photoelectric sensor array can be used to calculate the particle spin angular velocity by detecting the periodic positional changes of preset marker points on the surface of the sheet-like particles. For acquiring the airflow velocity components, velocity sensing components such as hot-wire anemometers or laser Doppler velocimeters can be installed at the dust collection channel inlet. These components can acquire at least one of the tangential, axial, and radial velocity components of the airflow in real time. Particle image velocimetry technology can also be used to obtain the airflow velocity field distribution by tracking the motion trajectory of tracer particles in the airflow, thereby extracting the velocity components in each direction at the dust collection channel inlet. It is understood that the above-described sensing components and algorithms are merely illustrative examples, and those skilled in the art can select appropriate measurement methods to obtain the particle spin angular velocity and airflow velocity components according to actual needs.

[0104] In step S182, it can be understood that the drag force is the force exerted by the airflow on the sheet-like particles along the airflow direction, and its magnitude is related to the airflow velocity, particle size, and the relative velocity between the airflow and the particles. For example, the airflow velocity component and the equivalent diameter of the sheet-like particles can be substituted into the Stokes drag force formula to calculate the drag force value.

[0105] The equivalent diameter of the sheet-like particles can be obtained as follows: After the cleaning equipment acquires image data of the sheet-like particles through its image acquisition component, it extracts the contour information of the particles, calculates the contour area or perimeter of the particles based on the contour information, and converts the contour area or perimeter into the diameter of an equivalent circle. The diameter of this equivalent circle is the equivalent diameter of the sheet-like particles. The equivalent diameter is then stored in the cleaning equipment's memory for subsequent calculations of drag and lift.

[0106] In step S183, it can be understood that the lift is a lateral force generated by the difference in airflow velocity on both sides of the plate-like particle due to its spin, and its magnitude is related to the particle's spin angular velocity, airflow velocity, and particle size. For example, the particle's spin angular velocity, airflow velocity component, and the equivalent diameter of the plate-like particle can be substituted into the Magnus effect model for calculation to obtain the lift value.

[0107] In step S184, the vector superposition of drag and lift is specifically as follows: the direction of drag is the same as the airflow direction, and the direction of lift is perpendicular to the plane determined by the rotation plane of the sheet-like particles and the airflow direction (i.e., the direction of the lateral force generated by the Magnus effect). The cleaning equipment determines the direction vector of drag based on the airflow direction at the dust collection channel inlet, and determines the direction vector of lift based on the direction of particle spin angular velocity and airflow direction (for example, by cross-product of the particle spin angular velocity vector and the airflow velocity vector to obtain the direction vector of lift). The magnitudes of drag and lift are decomposed into force components in three-dimensional space along their respective direction vectors, and then the force components in the same direction in three-dimensional space are added together to obtain the component values ​​of the resultant force in three-dimensional space, thereby obtaining the resultant force of drag and lift.

[0108] For example, in the two-dimensional simplification case, if the airflow direction is taken as the horizontal direction and the lift direction is taken as the vertical direction, then the magnitude of the resultant force is the square root of the sum of the squares of the drag force and the lift force, and the direction of the resultant force is the vector composition direction of the drag force and the lift force.

[0109] Since both drag and lift are aerodynamic forces exerted by rotating airflow on the surface of sheet-like particles, and both originate from the same source—the interaction between airflow and particle surface—the resultant force obtained by superimposing them is the airflow resultant force. The airflow resultant force is used to quantify the overall driving effect of rotating airflow on sheet-like particles, and its magnitude directly reflects the airflow's ability to overcome the adhesion resistance on the particle surface. When the airflow resultant force is greater than a preset desorption threshold, it indicates that the overall driving effect of the airflow on the particles is sufficient to overcome the adhesion resistance between the particles and the wall, and the particles can detach smoothly. When the airflow resultant force is less than or equal to the preset desorption threshold, it indicates that the driving effect of the airflow is insufficient to overcome the adhesion resistance, and the particles cannot detach smoothly. Therefore, the airflow resultant force is directly compared with the preset desorption threshold as the surface adhesion force value to determine whether vorticity enhancement operation needs to be performed.

[0110] In this embodiment, by acquiring the particle spin angular velocity and airflow velocity components at the moment the sheet-like particles enter the dust collection channel inlet, and calculating the drag and lift based on the Stokes drag formula and the Magnus effect model respectively, the drag and lift are then vectorively superimposed to obtain the resultant force as the surface adhesion force value. This achieves precise quantification of the adhesion state of sheet-like particles at the dust collection channel inlet. Compared with related technologies that cannot obtain the particle adhesion state and can only rely on experience or passive waiting, this embodiment indirectly calculates and characterizes the surface adhesion force, which is difficult to measure directly, by converting it into motion parameters (particle spin angular velocity, airflow velocity components) that can be obtained by sensors. This provides a precise judgment basis for subsequent eddy current-enhanced desorption operations, thereby improving the accuracy and reliability of desorption control.

[0111] In one embodiment, see Figure 7 Step S140 includes: Step S141: Collect the initial coordinate sequence of the sheet-like particles during their movement.

[0112] Step S142: Perform noise reduction on the initial coordinate sequence to obtain the target coordinate sequence.

[0113] Step S143: Calculate the real-time centroid coordinates of the sheet-like particles based on the target coordinate sequence.

[0114] Step S144: Based on the real-time centroid coordinates and the centerline coordinates of the dust collection channel, calculate the vertical distance between the real-time centroid coordinates and the centerline coordinates of the dust collection channel to obtain the offset.

[0115] In step S141, the cleaning equipment collects the initial coordinate sequence of the sheet-like particles during their movement using a position sensing component. The position sensing component can be installed at the entrance of the dust collection channel or on the inner wall of the dust collection channel. It uses a non-contact sensing method to sample the position of the sheet-like particles in three-dimensional space in real time, obtaining the spatial coordinates of the sheet-like particles at different times. Arranging these coordinates in chronological order constitutes the initial coordinate sequence. The initial coordinate sequence reflects the original position information of the sheet-like particles during their movement.

[0116] In step S142, the cleaning equipment performs noise reduction processing on the initial coordinate sequence to obtain the target coordinate sequence. It is understood that the position sensing component may be affected by environmental vibration, electromagnetic interference, or sensor noise during the coordinate data acquisition process, resulting in random noise components in the initial coordinate sequence. The purpose of noise reduction processing is to eliminate or reduce these noise components to obtain smoother and more accurate coordinate data. Specifically, noise reduction processing can be performed by using filtering algorithms on the initial coordinate sequence, such as mean filtering, median filtering, or Kalman filtering, to filter out high-frequency noise components and obtain a smooth and continuous target coordinate sequence.

[0117] In step S143, the cleaning device calculates the real-time centroid coordinates of the sheet-like particles based on the target coordinate sequence. The centroid coordinates characterize the position of the sheet-like particles in three-dimensional space and can be obtained by spatial integration of the contour point coordinates of the sheet-like particles. For the obtained target coordinate sequence, which contains the coordinates of multiple edge contour points of the sheet-like particles in three-dimensional space, the cleaning device averages the abscissas of these edge contour points as the centroid abscissa, averages the ordinates as the centroid ordinate, and averages the vertical coordinates as the centroid vertical coordinate, thus obtaining the real-time centroid coordinates. Since the target coordinate sequence has undergone noise reduction processing, the centroid coordinates obtained by averaging these coordinates accurately reflect the actual position of the sheet-like particles in three-dimensional space.

[0118] In step S144, the cleaning equipment calculates the vertical distance between the real-time centroid coordinates and the centerline coordinates of the dust collection channel, based on the real-time centroid coordinates and the centerline coordinates of the dust collection channel, thus obtaining the offset. The centerline coordinates of the dust collection channel refer to the spatial coordinates of the geometric central axis along the extension direction of the dust collection channel; the spatial position of this centerline is predetermined. The offset refers to the spatial distance of the real-time centroid position of the flaky particles from the centerline of the dust collection channel. Specifically, it is calculated by using the centerline of the dust collection channel as a reference, calculating the deviation distance of the real-time centroid coordinates in the direction perpendicular to the centerline of the dust collection channel; this deviation distance is the offset. The offset may include directional information, which indicates the specific direction in which the flaky particles deviate from the centerline of the dust collection channel, such as deviating to the left or right.

[0119] In this embodiment, by acquiring the initial coordinate sequence of the sheet-like particles during their movement and performing noise reduction processing on the initial coordinate sequence, interference from environmental vibration and sensor noise on the position data is eliminated, resulting in a smooth and accurate target coordinate sequence. Based on this, the real-time centroid coordinates are calculated according to the target coordinate sequence, and the offset is calculated based on the real-time centroid coordinates and the centerline coordinates of the dust collection channel, achieving precise quantification of the deviation degree of the sheet-like particles' movement trajectory. This embodiment obtains accurate offset data through noise reduction processing and centroid calculation. This offset data simultaneously includes information on the deviation distance and deviation direction, thus providing a reliable basis for ensuring the stable movement of the sheet-like particles along the centerline of the dust collection channel.

[0120] In one embodiment, see Figure 8 Step S160 includes: Step S161: Extract the direction component and amplitude component corresponding to the offset.

[0121] Step S162: Determine the deviation direction of the flaky particles from the center line of the dust collection channel based on the directional component, and determine the deviation distance level based on the amplitude component.

[0122] Step S163: Obtain the coarse angle adjustment value based on the deviation direction and deviation distance level.

[0123] Step S164: Obtain the current deflection angle of the guide vane, and generate the fine-tuning angle value based on the difference between the coarse-adjustment value and the current deflection angle.

[0124] Step S165: Generate the target deflection angle based on the sum of the coarse angle adjustment value and the fine angle adjustment value.

[0125] Step S166: Generate a pulse width modulation signal based on the target deflection angle to drive the stepper motor of the cleaning equipment to adjust the guide vanes to the target deflection angle.

[0126] In step S161, the direction component indicates the direction of deviation of the flake particles relative to the centerline of the dust collection channel, and the amplitude component indicates the magnitude of the distance the flake particles deviate from the centerline of the dust collection channel. The offset includes both a direction component and an amplitude component. The direction component can be determined based on the deviation direction of the real-time centroid coordinates relative to the centerline coordinates of the dust collection channel. For example, if the real-time centroid coordinates are to the left of the centerline of the dust collection channel, the direction component is left; if they are to the right, the direction component is right. Furthermore, the absolute value of the vertical distance between the real-time centroid coordinates and the centerline coordinates of the dust collection channel can be used as the amplitude component, which is the magnitude of the offset.

[0127] In step S162, the deviation direction can be leftward or rightward, which determines which direction the guide vanes should deflect to generate the opposite aerodynamic force for correction. The deviation distance level characterizes the severity of the deviation and is determined by comparing the amplitude component with multiple preset level thresholds. These preset level thresholds can be stored in the cleaning equipment in advance and are set as follows: During the research and development phase of the cleaning equipment, trajectory data of several sheet-like particles at different distances from the centerline of the dust collection channel are collected. The aerodynamic force required for successful correction at each deviation distance is statistically analyzed, and multiple level thresholds are set accordingly. For example, when the amplitude component is less than the first level threshold (e.g., 3 mm), it is determined to be a slight deviation; when the amplitude component is between the first and second level thresholds (e.g., 8 mm), it is determined to be a moderate deviation; and when the amplitude component is greater than the second level threshold, it is determined to be a severe deviation.

[0128] In step S163, the coarse angle adjustment value refers to the angle value used to roughly adjust the guide vane from the current deflection angle to within the target deflection angle range. It is determined based on the deviation direction and the deviation distance level. Different deviation directions and deviation distance levels correspond to different coarse angle adjustment values. For example, when the flaky particles deviate to the right and the deviation distance level is severe, the guide vane needs to be deflected to the left by a large angle to generate sufficient aerodynamic force for correction; when the deviation distance level is mild, only a small angle deflection to the left is needed.

[0129] In step S164, the fine-tuning angle value refers to the angle value used to precisely fine-tune the deflection angle of the guide vanes based on the coarse-tuning angle value. The difference between the coarse-tuning angle value and the current deflection angle reflects the remaining adjustment margin between the guide vanes from the current position and the coarse-tuning target position. The cleaning equipment generates the fine-tuning angle value based on this difference to achieve fine correction of the deflection angle.

[0130] In step S165, the cleaning equipment adds the coarse angle adjustment value and the fine angle adjustment value, and the sum is the target deflection angle, which is the final deflection angle value that the guide vane should achieve after adjustment.

[0131] In step S166, the pulse width modulation signal is an electrical signal used to control the rotation of the stepper motor. It controls the rotation angle and speed of the stepper motor by adjusting the pulse width or duty cycle. The cleaning equipment generates a corresponding pulse width modulation signal based on the target deflection angle and sends this signal to the stepper motor's drive circuit. Driven by the pulse width modulation signal, the stepper motor rotates by the corresponding angle, and through the transmission mechanism, it drives the guide vanes to adjust from the current deflection angle to the target deflection angle. After the guide vanes are adjusted to the target deflection angle, the flow direction of the rotating airflow changes, and the direction of the aerodynamic force on the flake particles also changes, thereby pushing the flake particles towards the centerline of the dust collection channel.

[0132] In this embodiment, by extracting the directional and amplitude components of the offset, the deviation direction is determined based on the directional component, the deviation distance level is determined based on the amplitude component, and a coarse angle adjustment value is obtained based on the deviation direction and deviation distance level, thus achieving rapid coarse adjustment of the guide vane deflection angle. Based on this, by acquiring the current deflection angle of the guide vane and generating a fine angle adjustment value based on the difference between the coarse and fine angle adjustment values, the target deflection angle is obtained by adding the coarse and fine angle adjustment values, thus achieving precise fine-tuning of the guide vane deflection angle. This embodiment, through a two-stage adjustment mechanism of coarse and fine adjustment, improves adjustment accuracy while ensuring adjustment speed, enabling the guide vane to be quickly and accurately adjusted to the target deflection angle. This ensures the speed and accuracy of adjusting the direction of the rotating airflow, allowing flaky particles to be corrected to the centerline direction of the dust collection channel in a timely and accurate manner.

[0133] In one embodiment, see Figure 9 Step S200 includes: Step S201: Obtain the current vorticity intensity value and calculate the target vorticity intensity increment based on the difference between the surface adhesion force value and the preset desorption threshold.

[0134] Step S202: Generate the target vorticity value based on the sum of the current vorticity intensity value and the target vorticity intensity increment.

[0135] Step S203: Gradually increase the current vorticity intensity value with a preset step size until the target vorticity intensity value is reached.

[0136] In step S201, the cleaning equipment obtains the vorticity intensity value at the current moment. Vorticity intensity is a physical quantity that characterizes the rotation intensity of airflow. It can be obtained in real time by a vorticity sensor set at the inlet of the dust collection channel, or it can be calculated by a preset fluid dynamics model based on operating parameters such as the current fan speed, the deflection angle of the guide vanes, and the gap height between the dust suction port and the cleaning surface.

[0137] Meanwhile, the cleaning equipment calculates the target vorticity intensity increment based on the difference between the surface adhesion value and the preset desorption threshold. The target vorticity intensity increment refers to the amount by which the vorticity intensity of the rotating airflow needs to be increased from the current level in order to reduce the surface adhesion of the flaky particles to below the preset desorption threshold. It can be obtained by multiplying the difference by a preset proportional coefficient. The larger the difference, the greater the increase required, and the smaller the difference, the smaller the increase required.

[0138] In step S202, the cleaning device adds the current vorticity intensity value to the target vorticity intensity increment, and uses the sum of the two as the target vorticity intensity value. The target vorticity intensity value is the final vorticity intensity value that the rotating airflow should reach after the guide vane undergoes vorticity enhancement operation.

[0139] In step S203, the cleaning equipment gradually increases the current vorticity intensity value with a preset step size until the target vorticity intensity value is reached. The preset step size can be stored in the cleaning equipment in advance and is determined through experimental testing or simulation analysis before the cleaning equipment leaves the factory or during the research and development stage. For example, a fluid dynamics simulation model can be established to simulate the vorticity intensity increase process under multiple candidate step size conditions. A suitable step size value is selected with the vorticity intensity overshoot being less than a preset overshoot threshold and the settling time being less than a preset time threshold as the target, and this step size value is set as the preset step size. Alternatively, testing can be conducted on an actual prototype, and the maximum step size value that enables the flaky particles to desorb smoothly and maintain a stable motion state can be set as the preset step size. For example, the preset step size can be 15 seconds, 20 seconds, 25 seconds, etc.

[0140] During the eddy power enhancement process, the cleaning equipment continuously acquires the surface adhesion value of the flaky particles at a preset sampling period and compares it with a preset desorption threshold. If the surface adhesion value is less than or equal to the preset desorption threshold before the eddy power reaches the target eddy power value, the eddy power enhancement is stopped. If the eddy power has reached the target eddy power value but the surface adhesion value is still greater than the preset desorption threshold, the target eddy power increment is recalculated based on the new difference and the target eddy power value is updated. The eddy power is then enhanced until the surface adhesion value is less than or equal to the preset desorption threshold.

[0141] In this embodiment, by acquiring the current vorticity intensity value and calculating the target vorticity intensity increment based on the difference between the surface adhesion force and the desorption threshold, the adjustment range of the vorticity intensity is precisely matched with the degree of adhesion force exceeding the threshold. By using the sum of the current vorticity intensity and the target vorticity intensity increment as the target vorticity intensity value, precise quantification of the adjustment target is achieved. The vorticity intensity is gradually increased with a preset step size, making the adjustment process of the vorticity intensity smooth and controllable.

[0142] In one embodiment, see Figure 10Step S200 includes: Step S204: Increase the fan speed of the cleaning equipment to increase the overall velocity of the rotating airflow.

[0143] And / or, Step S205: Increase the deflection angle of the guide vanes at the dust inlet to enhance the tangential velocity component of the rotating airflow.

[0144] And / or, Step S206: Reduce the gap height between the suction port and the cleaning surface to compress the cross-sectional area of ​​the airflow channel and increase the vortex intensity of the rotating airflow.

[0145] In step S204, the cleaning equipment increases the overall velocity of the rotating airflow by increasing the fan speed. The increased fan speed increases the gas flow rate through the suction port per unit time, thereby increasing the velocity components of the rotating airflow in both the axial and tangential directions, and thus enhancing the aerodynamic force of the airflow on the surface of the flake particles.

[0146] In step S205, the cleaning equipment enhances the tangential velocity component of the rotating airflow by increasing the deflection angle of the guide vanes at the suction port. As the deflection angle of the guide vanes increases, the degree of deflection of the airflow in the tangential direction intensifies, resulting in an increase in the tangential velocity component of the airflow and a stronger rotational effect of the rotating airflow, thereby improving the shearing effect of the airflow on the surface of the flake-like particles.

[0147] In step S206, the cleaning device compresses the cross-sectional area of ​​the airflow channel and increases the vortex intensity of the rotating airflow by reducing the gap height between the suction port and the cleaning surface. It can be understood that, with the fan speed remaining constant, a reduced gap height between the suction port and the cleaning surface means a reduced cross-sectional area of ​​the airflow channel. This increases the airflow velocity as it passes through this narrow area, and simultaneously enhances the rotational effect of the airflow, thereby increasing the vortex intensity.

[0148] The three methods described above can be implemented independently; that is, increasing the fan speed, increasing the deflection angle of the guide vanes, or reducing the gap height between the suction port and the cleaning surface can all enhance vorticity intensity. These three methods can also be combined, i.e., simultaneously increasing the fan speed, increasing the deflection angle of the guide vanes, and reducing the gap height between the suction port and the cleaning surface to further increase the enhancement of vorticity intensity. The cleaning equipment can select one or more of these methods for combination based on actual operating conditions and the required enhancement of vorticity intensity. This embodiment provides multiple optional enhancement methods, allowing the cleaning equipment to flexibly select appropriate enhancement methods or combinations according to actual operating conditions, thereby adapting to different adhesion states of flaky particles and different cleaning environment conditions. Furthermore, by reducing the gap height between the suction port and the cleaning surface to compress the cross-sectional area of ​​the airflow channel, vorticity intensity can be increased without increasing fan power consumption, which helps reduce energy consumption and improves the energy utilization efficiency of the cleaning equipment.

[0149] For the same purpose, referring to Figure 1, in one embodiment, a cleaning device adsorption force adaptive adjustment system is provided, comprising: The image acquisition module is used to acquire image data of the cleaning area of ​​the cleaning equipment and identify flaky particles from the image data. Flaky particles are irregularly shaped particles whose major and minor axis ratios are greater than a preset flatness threshold.

[0150] The airflow control module is used to control the deflection of the guide vanes at the suction port of the cleaning equipment to generate a rotating airflow with a spiral flow path.

[0151] The position acquisition and offset calculation module is used to acquire the real-time position of the flake particles during their movement and calculate the offset of the flake particles relative to the center line of the dust collection channel of the cleaning equipment based on the real-time position.

[0152] An angle adjustment module is used to adjust the deflection angle of the guide vanes in response to an offset exceeding a preset deviation threshold, thereby changing the direction of the rotating airflow.

[0153] The adhesion acquisition module is used to acquire the surface adhesion value of flaky particles when they enter the dust collection channel inlet in response to an offset amount less than or equal to a preset deviation threshold.

[0154] The vorticity control module is used to perform vorticity enhancement operation in response to the surface adhesion value being greater than the preset desorption threshold, until the surface adhesion value is less than or equal to the preset desorption threshold.

[0155] The specific implementation methods and working principles of each module included in the above system correspond to the steps in the aforementioned method embodiments, and will not be repeated here.

[0156] For those skilled in the art, the above division of functional modules is merely an exemplary logical division. In practical applications, modules can be merged, split, or recombined according to specific needs. Each module can be integrated into a single processor or distributed across different processors or computing nodes. The operations performed by each module, the algorithmic steps involved, and the data processing flow adopted are all fully and clearly described in the foregoing method embodiments. Based on reading the foregoing method embodiments, those skilled in the art can implement the method steps into corresponding functional modules without creative effort and deploy them on general-purpose or special-purpose computing devices using programming languages ​​and software development tools.

[0157] This application also provides an electronic device, which includes one or more processors and memory resources represented by memory for storing instructions executable by the processor, such as application programs. The application programs stored in the memory may include one or more modules, each corresponding to a set of instructions.

[0158] The electronic device may also include a power supply component configured to perform power management of the electronic device, a wired or wireless network interface configured to connect the electronic device to a network, and an input / output (I / O) interface. The electronic device can be operated based on operating devices stored in memory, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0159] In one embodiment, a computer device, which may be a server, is also provided. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device stores data. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection.

[0160] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. The display unit of the computer device is used to form a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0161] This application also provides a non-transitory computer-readable storage medium, which, when the instructions in the storage medium are executed by the processor of the electronic device, enables the electronic device to perform one of the above embodiments.

[0162] This application may take the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information may be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to: phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0163] It should be noted that although the steps of the method in this application are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps, such as omitting certain steps, combining multiple steps into one step, and / or breaking down one step into multiple steps, should all be considered part of this application.

[0164] It should be understood that this application is not limited to the detailed data of the methods presented in this specification. This application is capable of other implementations and can be implemented and performed in various ways. The foregoing variations and modifications fall within the scope of this application. It should be understood that the disclosure and definition of this application extend to all alternative combinations of two or more individual features mentioned or apparent in the text and / or drawings. All these different combinations constitute multiple alternative aspects of this application. The embodiments described in this specification illustrate the best known mode for implementing this application and will enable those skilled in the art to utilize this application.

Claims

1. A method for adaptive adjustment of the adsorption force of a cleaning device, characterized in that, include: Image data of the cleaning area of ​​the cleaning equipment is acquired, and flaky particles are identified from the image data. The flaky particles are irregularly shaped particles whose ratio of major axis to minor axis is greater than a preset flatness threshold. The guide vanes at the suction port of the cleaning device are deflected to generate a rotating airflow with a spiral flow path; The real-time position of the flake particles during their movement is obtained, and the offset of the flake particles relative to the center line of the dust collection channel of the cleaning equipment is calculated based on the real-time position. In response to the offset being greater than a preset deviation threshold, the deflection angle of the guide vanes is adjusted to change the direction of the rotating airflow; In response to the offset being less than or equal to the preset deviation threshold, the surface adhesion value of the flaky particles when they enter the dust collection channel inlet is obtained; In response to the surface adhesion value being greater than a preset desorption threshold, an eddy current enhancement operation is performed until the surface adhesion value is less than or equal to the preset desorption threshold.

2. The method according to claim 1, characterized in that, The step of identifying sheet-like particles from the image data includes: Edge detection processing is performed on the image data to extract the coordinate sequence of sampling points for irregular contours; Calculate the rate of curvature change between adjacent sampling points based on the coordinate sequence of the irregular contour sampling points; Based on the curvature change rate, the coordinate sequence of the sampling points of the irregular contour is smoothed to obtain the target contour coordinate sequence; Calculate the area and perimeter of the closed region enclosed by the target contour coordinate sequence; Based on the area of ​​the closed region and the perimeter of the contour, fit the ratio of the major and minor axes of the irregular contour; In response to the major-minor axis ratio being greater than the preset flatness threshold, the irregular contour is determined to be the sheet-like particle.

3. The method according to claim 2, characterized in that, The step of calculating the rate of curvature change between adjacent sampling points based on the coordinate sequence of the irregular contour sampling points includes: Calculate the tangent direction angle between adjacent sampling points based on the coordinate sequence of the irregular contour sampling points; Calculate the curvature value between adjacent sampling points based on the tangent direction angle; Based on the curvature value, calculate the rate of change of curvature between adjacent sampling points; The step of smoothing the coordinate sequence of the irregular contour sampling points according to the curvature change rate to obtain the target contour coordinate sequence includes: In response to the curvature change rate being greater than a preset curvature threshold, the corresponding sampling point is determined to be a candidate concave / convex point, and a set of candidate concave / convex points is obtained; Obtain the coordinate values ​​of each candidate concave / convex point in the candidate concave / convex point set; The position markings of the irregular particles are determined based on the coordinate values ​​of each candidate concave and convex point; Based on the concave and convex point position marks, the sampling points and neighboring points corresponding to the concave and convex point position marks in the irregular contour sampling point coordinate sequence are locally smoothed to obtain the target contour coordinate sequence.

4. The method according to claim 1, characterized in that, The method of controlling the deflection of the guide vanes at the suction port of the cleaning device to generate a rotating airflow with a spiral flow path includes: Generate rotating airflow control commands and obtain the current deflection angle of the guide vanes inside the suction port; Calculate the angle difference between the current deflection angle and the preset helix angle value, and generate a pulse signal for the stepper motor of the cleaning device based on the angle difference; The stepper motor is driven according to the rotating airflow control command and the pulse signal to synchronously adjust the guide vanes from the current deflection angle to the preset spiral angle value, so that the airflow forms a turbulent state inside the dust suction port and obtains the rotating airflow with a spiral flow path.

5. The method according to claim 1, characterized in that, The step of obtaining the surface adhesion value of the flaky particles when they enter the dust collection channel inlet includes: The particle spin angular velocity and airflow velocity components at the moment when the flaky particles enter the dust collection channel inlet are obtained. The airflow velocity components include at least one of tangential velocity component, axial velocity component and radial velocity component. The drag force experienced by the sheet-like particles in the airflow is calculated based on the airflow velocity component and the equivalent diameter of the sheet-like particles. The lift generated by the spin of the plate-like particles is calculated based on the particle spin angular velocity, the airflow velocity component, and the equivalent diameter of the plate-like particles. The drag force and the lift force are vector-superimposed to obtain the resultant force of the airflow on the surface of the sheet-like particles, and the resultant force of the airflow is used as the value of the surface adhesion force.

6. The method according to claim 1, characterized in that, The step of acquiring the real-time position of the flake-like particles during their movement and calculating the offset of the flake-like particles relative to the center line of the dust collection channel of the cleaning equipment based on the real-time position includes: Collect the initial coordinate sequence of the sheet-like particles during their movement; The initial coordinate sequence is denoised to obtain the target coordinate sequence; Calculate the real-time centroid coordinates of the sheet-like particles based on the target coordinate sequence; Based on the real-time centroid coordinates and the centerline coordinates of the dust collection channel, the vertical distance between the real-time centroid coordinates and the centerline coordinates of the dust collection channel is calculated to obtain the offset.

7. The method according to claim 1, characterized in that, The step of adjusting the deflection angle of the guide vanes to change the direction of the rotating airflow in response to the offset being greater than a preset deviation threshold includes: Extract the directional and amplitude components corresponding to the offset; Based on the directional component, the deviation direction of the flaky particles from the center line of the dust collection channel is determined, and the deviation distance level is determined based on the amplitude component. Based on the deviation direction and the deviation distance level, the coarse angle adjustment value is obtained; Obtain the current deflection angle of the guide vane, and generate a fine-tuning angle value based on the difference between the coarse-tuning angle value and the current deflection angle. The target deflection angle is generated based on the sum of the coarse angle adjustment value and the fine angle adjustment value. A pulse width modulation signal is generated based on the target deflection angle to drive the stepper motor of the cleaning device to adjust the guide vanes to the target deflection angle.

8. The method according to claim 1, characterized in that, The vorticity enhancement operation includes: Obtain the current vorticity intensity value, and calculate the target vorticity intensity increment based on the difference between the surface adhesion force value and the preset desorption threshold. The target vorticity value is generated based on the sum of the current vorticity intensity value and the target vorticity intensity increment. The current vorticity intensity value is gradually increased by a preset step size until the target vorticity intensity value is reached.

9. The method according to claim 1, characterized in that, The vorticity enhancement operation includes: Increase the fan speed of the cleaning equipment to increase the overall velocity of the rotating airflow; And / or, Increase the deflection angle of the guide vanes at the dust inlet to enhance the tangential velocity component of the rotating airflow; And / or, The gap height between the suction port and the cleaning surface is reduced to compress the cross-sectional area of ​​the airflow channel and increase the vortex intensity of the rotating airflow.

10. A self-adaptive adjustment system for the adsorption force of a cleaning device, characterized in that, include: The image acquisition module is used to acquire image data of the cleaning area of ​​the cleaning equipment and identify flaky particles from the image data. The flaky particles are irregularly shaped particles with a major-minor axis ratio greater than a preset flatness threshold. An airflow control module is used to control the deflection of the guide vanes at the suction port of the cleaning equipment to generate a rotating airflow with a spiral flow path. The position acquisition and offset calculation module is used to acquire the real-time position of the flake particles during the movement process, and calculate the offset of the flake particles relative to the center line of the dust collection channel of the cleaning equipment based on the real-time position. An angle adjustment module is used to adjust the deflection angle of the guide vanes in response to the offset being greater than a preset deviation threshold, so as to change the direction of the rotating airflow. An adhesion acquisition module is used to acquire the surface adhesion value of the flaky particles when they enter the dust collection channel inlet in response to the offset being less than or equal to the preset deviation threshold. The eddy current control module is used to perform eddy current enhancement operation in response to the surface adhesion value being greater than a preset desorption threshold, until the surface adhesion value is less than or equal to the preset desorption threshold.