A method and device for cleaning grid screen blockage

Through three-dimensional point cloud data processing and voxel filtering technology, the blockages in the mine lattice screen hole are identified and positioned, and automatic crushing is achieved, which solves the problems of high manual operation cost and low efficiency of mining crushers in the existing technology, and improves crushing Efficiency and accuracy.

CN118719554BActive Publication Date: 2024-11-22BEIJING ANCHISES TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411215270.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-02
Publication Date
2024-11-22
Estimated Expiration
2044-09-02

AI Technical Summary

Technical Problem

When crushing ore, existing mining crushers have problems such as high manual operation cost, low efficiency, low degree of automation, high control delay, large visual operation deviation, and inaccurate positioning of crushing points, resulting in poor ore crushing efficiency and effect.

Method used

By obtaining the three-dimensional point cloud data of objects on the grid screen, performing filtering and voxel filtering sampling, identifying and screening blocked grid screen holes, calculating their center to locate fragile points, and using a robotic arm to hit and clean up blocked objects , realize automated breaking.

Benefits of technology

It realizes rapid identification of grid screen holes and accurate positioning of blockages, reduces computing requirements, simplifies the control system, improves crushing efficiency and accuracy, and reduces costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118719554B_ABST
    Figure CN118719554B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and equipment for cleaning a grid screen blockage, and belongs to the technical field of ore processing. Specifically, it includes: obtaining a three-dimensional point cloud of the surface of an object on the grid screen, fitting it to the grid screen position coordinates, and obtaining a mechanical arm data coordinate system; performing voxel filtering; segmenting the voxel point cloud based on the X and Y coordinate axis directions, obtaining the first voxel point, and compiling an index number for each first voxel point; filtering out blocked grid screen holes based on the first voxel point of the grid screen hole; obtaining the centroid corresponding to each projection surface according to the projection of the first voxel point cloud data on the XOY plane, searching for the projection of the first voxel point closest to each centroid, and the mechanical arm data coordinate corresponding to its index number is the vulnerable point of the object. The present invention can identify whether the grid screen hole is blocked, filter out the grid screen holes that are blocked on the periphery and empty in the center, avoid invalid operations on them, and determine the vulnerable points of the object that need to perform crushing operations on the blocked grid screen holes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of ore processing, and in particular relates to a method for locating vulnerable points of a grid screen blocking object, and a method and device for cleaning the grid screen blocking. Background Art

[0002] The large pieces of ore accumulated above the mine chute screen need to be crushed and made to fall into the chute below the screen. The crusher is one of the core production equipment to achieve the crushing of large pieces of ore on the chute screen.

[0003] At present, domestic and foreign mining crushers mainly adopt on-site manual operation. Due to the harsh working environment and high safety risks, it brings problems such as high labor costs, low operating efficiency, and poor construction operation adaptability.

[0004] Although some existing mines have adopted remote control transformation solutions to reduce the number of on-site workers, the on-site ore data collection and data analysis methods use two-dimensional image observation methods, which are affected by factors such as light, dust, and the material and texture of the ore in the on-site environment. The operation is not universal. At the same time, there are still problems such as low degree of automation, high control delay, large visual operation deviation, inaccurate crushing point positioning, and the need for multiple positioning to perform crushing operations. The operation efficiency and results still need to be improved.

[0005] Therefore, the automatic control system of the crusher is the future development trend, and an important part of realizing automatic control is to identify and detect the blockage status of each grid screen hole and accurately locate the vulnerable points where crushing operations are required. Summary of the invention

[0006] The present invention is also based on this technical demand and provides a method and equipment for cleaning grid screen blockage, which at least has the technical effect of being able to quickly identify whether each grid screen hole is blocked, accurately locate the weak points of the ore that needs to be crushed in the blocked grid screen holes, and efficiently clean the blockage.

[0007] In a first aspect, a method for locating a vulnerable point of an object blocked by a sieve grid is provided, wherein the sieve grid has a plurality of sieve grid holes, and the sieve grid plane forms an X-axis and a Y-axis, comprising the following steps:

[0008] S1: Obtain point cloud data of the object surface on the grid screen, generate a three-dimensional point cloud, fit the three-dimensional point cloud to the grid screen position coordinates, and obtain the robot arm data coordinate system;

[0009] S2: The robot data coordinate system is sampled through voxel filtering to calculate and obtain voxel point cloud data with uniform density;

[0010] S3: Segmenting the voxel point cloud data in a direction parallel to the X-coordinate axis and in a direction parallel to the Y-coordinate axis respectively, obtaining a plurality of first voxel points directly above each grid sieve hole, and compiling a corresponding index number for each first voxel point;

[0011] S4: based on the first voxel point of each grid sieve hole, screening out blocked grid sieve holes;

[0012] S5: According to the projection of the plurality of first voxel point cloud data in each blocking grid sieve hole on the XOY plane, the centroid corresponding to each projection surface is calculated, and the first voxel point closest to each of the centroid projections is searched, and the robot arm data coordinate corresponding to the index number of the first voxel point is the vulnerable point of the object on the blocking grid sieve hole;

[0013] The surface refers to all sides of the object that are above the grid screen.

[0014] Furthermore, the screening method of the blocked grid sieve holes in step S4 is:

[0015] The number of first voxel points of the grid sieve hole is greater than or equal to a first preset parameter, and the number of first voxel points within the center radius of the grid sieve hole is greater than or equal to a second preset parameter, and the first preset parameter is greater than the second preset parameter, and the grid sieve hole is a blocked grid sieve hole; wherein the implementation steps of the second preset parameter include:

[0016] S41: Selecting a preset ratio of the width of the grid sieve holes;

[0017] S42: Taking the center of the grid hole as the center of the circle, taking the width of the preset ratio as the radius, and presetting the number of second voxel points within the radius as the second preset parameter.

[0018] Furthermore, the step of calculating and obtaining voxel point cloud data with uniform density in step S2 includes:

[0019] S21: De-noising the point cloud data through a first filter to generate noise-free point cloud data;

[0020] S22: Sampling the noise-free point cloud data through voxel filtering to calculate and obtain a first voxel point with uniform density.

[0021] Furthermore, the voxel filtering sampling method described in step S22 is to divide the noise-free point cloud data into a number of three-dimensional voxel grids, select the point closest to the centroid of each of the three-dimensional voxel grids, and generate the voxel filtering sampling value of the three-dimensional voxel grid.

[0022] Furthermore, the first filtering in step S21 is through filtering and outlier filtering.

[0023] Furthermore, the algorithm for fitting the three-dimensional point cloud and the grid position coordinates is the Euclidean transformation.

[0024] In a second aspect, a method for clearing a grid screen blockage is provided, comprising striking a vulnerable point of an object, wherein the vulnerable point is located by the method described in the first aspect.

[0025] In a third aspect, a storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method for locating vulnerable points of a grid screen blocking object as described in the first aspect above is executed.

[0026] In a fourth aspect, an electronic device is provided, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the method for locating vulnerable points of a grid screen blockage object as described in the first aspect above is performed.

[0027] In a fifth aspect, a stone crushing system is provided, comprising a stone crushing component, wherein the stone crushing component performs a crushing operation using the method for locating vulnerable points of a sieve-blocking object as described in the first aspect.

[0028] The present invention has the following beneficial effects:

[0029] 1. Based on the point cloud of the ore surface, a series of filtering processes are performed to identify whether the grid screen holes are blocked, and the ore vulnerable points where each blocked grid screen hole needs to be crushed are calculated and accurately located.

[0030] 2. After each grid sieve hole is segmented and processed, radius filtering is used for verification to screen out grid sieve holes that are blocked on the periphery and empty in the center to avoid invalid operations on them.

[0031] 3. By performing voxel filtering on point cloud data, the grid screen blockage is transferred from image detection to quantity detection, which reduces the demand for computing power and shortens the response time. Since it is based on three-dimensional equipment and point cloud data, it mainly relies on CPU computing power, and the demand for image computing power is relatively reduced, which simplifies the structure of the control system and reduces costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a structural schematic diagram of a chute grid screen stone crushing operation provided by an embodiment of the present invention;

[0033] Figure 2 is a schematic diagram of the structure of an unblocked grid mesh provided by an embodiment of the present invention;

[0034] Figure 32 is a schematic structural diagram of a first situation of blocked grid sieve holes provided by an embodiment of the present invention;

[0035] Figure 4 2 is a schematic structural diagram of a second situation of blocked grid sieve holes provided by an embodiment of the present invention;

[0036] Figure 5 It is a flow chart of a method for locating vulnerable points of a sieve blocking object provided in an embodiment of the present invention.

[0037] Among them, 1. Depth camera; 2. Well screen; 21. Screen holes. DETAILED DESCRIPTION

[0038] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0039] The terms "first", "second", etc. in the specification and claims of the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0040] In the following, in conjunction with the accompanying drawings, some embodiments and a method for locating vulnerable points of a grid screen blocking object provided by an embodiment of the present invention are described in detail.

[0041] See also Figure 1-Figure 5 A method for locating the vulnerable point of a sieve blocking object comprises the following steps:

[0042] S1: Obtain point cloud data of the object surface on the grid screen, generate a three-dimensional point cloud, fit the three-dimensional point cloud to the grid screen position coordinates, and obtain the robot arm data coordinate system;

[0043] It can be understood that the depth information of the surface of the object on the grid screen, that is, a large amount of point cloud data, is obtained through the three-dimensional data acquisition equipment, and a depth map is obtained from the depth information. Through the depth map, the point cloud reconstruction algorithm is used to convert the depth map into a three-dimensional point cloud, and the three-dimensional point cloud includes X, Y and Z axis coordinates.

[0044] It should be noted that the surface refers to all surfaces of the object that are higher than the grid screen. In the present embodiment, it refers to the surface of the ore that is above the grid screen and exposed to the outside.

[0045] It can be understood that the robot data coordinate system corresponds to the actual physical position coordinates of the object surface on the grid screen.

[0046] In a possible implementation, a depth camera 1 is used to obtain depth information of the ore surface on the grating, that is, a large amount of point cloud data, and a depth map is obtained from the depth information. The depth map is converted into a three-dimensional point cloud using a point cloud reconstruction algorithm. The three-dimensional point cloud is imported into the three-dimensional point cloud processing software, and the three-dimensional point cloud and the grating position coordinates are fitted based on the three-dimensional processing software to obtain the robot arm data coordinate system.

[0047] Preferably, the three-dimensional point cloud processing software is Point Cloud Library.

[0048] In this embodiment, the fitting is achieved by Euclidean transformation.

[0049] Preferably, the Euclidean transformation algorithm uses homogeneous coordinates. It is understandable that the homogeneous coordinate system has a good fitting effect.

[0050] In an embodiment, the robot arm coordinate system may be output to an operating device, and the operating device determines an operating point corresponding to the surface of the ore on the grid screen according to data in the robot arm coordinate system.

[0051] In a possible implementation, the device for acquiring the three-dimensional point cloud of the surface of the object on the chute grid screen 2 is a laser scanner, and the three-dimensional point cloud is fitted into the grid screen position coordinate system through Euclidean transformation to obtain the robot arm coordinate system.

[0052] S2: The robot data coordinate system is sampled through voxel filtering to calculate and obtain voxel point cloud data with uniform density;

[0053] It is understandable that by performing voxel filtering sampling on a 3D point cloud, the density of the point cloud can be reduced while retaining key structural information. The voxel filtering sampling principle is to achieve downsampling by dividing the point cloud into regular voxel grids and then selecting a representative point in each grid.

[0054] In one possible implementation, the surface point cloud of the sieve object is gridded and segmented to generate a three-dimensional voxel grid, and grid voxel sampling is performed. The sampling point (representative point) can be the point closest to the average value of all point coordinates in the three-dimensional voxel grid, or the point closest to the centroid of all points in the grid, thereby obtaining voxel point cloud data with uniform density distribution.

[0055] It should be noted that the above voxel sampling method can be implemented in the PCL (Point Cloud Library) library, which includes a voxel sampling algorithm module.

[0056] It should be noted that the voxel grid size is selected according to the resolution of the depth camera of the point cloud acquisition device and the size of the grid mesh 21. If the voxel grid is too small, the operation processing speed will be affected, and the gridding effect will not be obvious. On the contrary, if the voxel grid is too large, the calculation accuracy will be affected, resulting in a decrease in recognition accuracy, and the accuracy will be reduced when finding the points that need to be crushed.

[0057] In a specific implementation, in combination with the current situation of the mine chute grid screen 2 and the precision requirement of the crushing point in the crushing operation of the rock crusher, the voxel grid size in this embodiment is selected to be 2 to 10 mm.

[0058] S3: Segmenting the voxel point cloud data in a direction parallel to the X-coordinate axis and in a direction parallel to the Y-coordinate axis respectively, obtaining a plurality of first voxel points directly above each grid sieve hole, and compiling a corresponding index number for each first voxel point;

[0059] It can be understood that the straight lines parallel to the X-axis and Y-axis directions divide the voxel point cloud into a plurality of point cloud blocks corresponding to each grid mesh, namely, the first voxel point.

[0060] It should be noted that, after being vertically projected onto the XOY plane, the first voxel point directly above falls into the corresponding grid hole.

[0061] The density of the first voxel points after voxel filtering is evenly distributed. Since the first voxel points are collected on the ore surface above the grid screen, the projection size of the first voxel points on the XOY plane is proportional to the number of the first voxel points. According to the number and distribution of the first voxel points, it can be judged whether the grid screen holes are blocked.

[0062] S4: based on the first voxel point of each grid sieve hole, screening out blocked grid sieve holes;

[0063] It can be understood that after voxel filtering sampling, a certain number of voxel points correspond to the top of each grid sieve hole, and the blocked grid sieve holes can be screened out according to the number of voxel points and the coverage of the grid sieve holes by the voxel points.

[0064] It should be noted that the three-dimensional point cloud processing system has preset method steps for determining whether the grid screen is blocked.

[0065] S5: According to the projection of multiple first voxel point cloud data in each blocked grid sieve hole on the XOY plane, the centroid corresponding to each projection surface is calculated, and the projection of the first voxel point closest to each of the centroids is searched, and the robotic arm data coordinates corresponding to the index number of the first voxel point are the vulnerable points of the object on the blocked grid sieve hole.

[0066] It can be understood that the index number of the first voxel point before and after projection remains unchanged. After the first voxel point of each grid screen hole is projected on the XOY plane, the projection of the first voxel point closest to the centroid of the projection surface is found. Based on its index number, its position coordinates in the Z-axis direction before projection can be determined, that is, the robot arm data coordinates of the data point. In this way, the vulnerable points where the ore covering the blocked grid screen hole is easily crushed are determined.

[0067] It should be noted that the PCL library includes an algorithm module for calculating the centroid of the projection surface.

[0068] Among them, the algorithm module for calculating the centroid of the projection surface includes the following algorithms:

[0069] Because it is projected along the Z axis to the XOY plane, for a point, The coordinates of , then the centroid of the first voxel point in the grid mesh The calculation is as follows:

[0070] , (1)

[0071] in, , is the coordinate value of the first voxel point on the XOY plane, and n represents the number of the first voxel points in the grid sieve.

[0072] Among them, search for the point closest to the centroid , calculate the distance of all the first voxel points in the grid sieve hole by formula (2) , and take the minimum value of the distance to obtain. That is to say, when the value of formula (2) is the smallest, take the set of As . According to the point The index number in the point cloud is used to query the Z-axis coordinate before Z-axis projection, that is, the height information of the vulnerable point from the grid screen.

[0073] (2)

[0074] in, , is the coordinate value of the first voxel point, and n represents the number of the first voxel points in each grid sieve hole.

[0075] Furthermore, the screening method of the blocked grid sieve holes in step S4 is:

[0076] The number of first voxel points of the grid sieve hole is greater than or equal to a first preset parameter, and the number of first voxel points within the center radius of the grid sieve hole is greater than or equal to a second preset parameter, and the first preset parameter is greater than the second preset parameter, and the grid sieve hole is a blocked grid sieve hole; wherein the implementation steps of the second preset parameter include:

[0077] S41: Selecting a preset ratio of the width of the grid sieve holes;

[0078] S42: Taking the center of the grid hole as the center of the circle, taking the width of the preset ratio as the radius, and presetting the number of second voxel points within the radius as the second preset parameter.

[0079] It can be understood that the number of voxel point clouds when the grid sieve hole is blocked is the first preset parameter N1, and the number of first voxel points of the detected grid sieve hole is N2. When N2 is greater than or equal to N1, the detected grid sieve hole meets the blocking condition. However, under this condition, there may be a situation where the grid sieve hole is covered by ore on all sides and the center is empty, such as Figure 2 As shown, although there is a possibility that there are enough voxel point clouds above the grid screen, it is generally considered that this situation is not blocked at the production site, because when the adjacent grid screen is cleared, this kind of grid screen congestion is usually solved. Therefore, there is no need to locate the vulnerable point in the hole. When the number of point clouds within a certain radius of the center is less than a specific number value, there is no need to perform a crushing operation on it. Furthermore, when N2 is greater than or equal to N1, with the center of the grid screen hole as the center of the circle, the number of voxel point clouds within the preset radius R and the corresponding radius R in the grid screen hole is the second preset parameter N3. If the number of point clouds actually detected within the radius R of the grid screen hole is N4, and N4 is greater than or equal to N3, it is determined that the grid screen hole is blocked, and the ore on the grid screen hole needs to be crushed.

[0080] It should be noted that the number of points after voxel filtering is evenly distributed. The number of first voxel points actually distributed directly above each grid sieve hole is counted and recorded as N2. The number of point clouds that fill the grid sieve hole when each grid sieve hole is completely blocked is recorded as N. In a possible implementation, the first preset parameter N1 = 50%N; the center of the grid sieve hole is taken as the center of the circle, and the radius is one-fourth of the width of the grid sieve hole. The number of point clouds within the center radius of the grid sieve hole is set, that is, the second preset parameter is N3, N3 = 20%N, and the number of point clouds actually detected within the radius of the grid sieve hole is N4. If N2 ≥ N1 and N4 ≥ N3, then the grid sieve hole is blocked. The grid sieve holes screened out by this method exclude the grid sieve holes that are blocked on all sides and empty in the middle and do not need to be broken.

[0081] It can be understood that the first preset parameter N1 is The specific value of the second preset parameter N3 needs to be selected according to factors such as the particle size and humidity of the on-site ore and the size of the grid sieve holes.

[0082] In a possible embodiment, the implementation step of the second preset parameter adopts a radius filtering method, and the number of first voxel points corresponding to the selected radius range is obtained through radius filtering. The working principle is as follows: the coordinates of the center point of a grid sieve hole are , to determine whether the first voxel point in the grid sieve hole is at point When R is within the radius range, the following formula (3) is used for judgment. If the condition of formula (3) is met, it means that the first voxel point is within the radius range, and the number of first voxel points within the radius range is recorded and counted. (3)

[0083] in, , and represents the coordinate value of the first voxel point, and n represents the number of the first voxel points.

[0084] In this embodiment, and The value of is 0.

[0085] Furthermore, the step of calculating and obtaining voxel point cloud data with uniform density in step S2 includes:

[0086] S21: De-noising the point cloud data through a first filter to generate noise-free point cloud data;

[0087] S22: Sampling the noise-free point cloud data through voxel filtering to calculate and obtain a first voxel point with uniform density.

[0088] Furthermore, the first filtering in step S21 is through filtering and outlier filtering.

[0089] It can be understood that through-filtering and outlier filtering can effectively remove noise and outliers in point cloud data, and performing through-filtering and outlier filtering before voxel filtering ensures the accuracy and effectiveness of point cloud data.

[0090] It should be noted that the PCL library includes algorithm modules for through-filtering and outlier filtering.

[0091] It can be understood that through filtering is a filtering method in point cloud filtering. Its basic idea is to perform range screening on the coordinate values ​​on a specific axis (such as X, Y or Z axis), that is, to remove points inside or outside the specified range, thereby filtering the point cloud data.

[0092] Outlier filtering,In point cloud processing, the main purpose is to remove points that are obviously different from the surrounding points, which may be caused by noise or errors in the data acquisition process. The principle is that if the number of neighboring points within the radius of a point is less than the set threshold, the point is considered an outlier and is filtered out.

[0093] An embodiment of the present invention further provides a method for clearing a grid screen blockage, comprising striking a weak point of an object, wherein the weak point is located by the above method.

[0094] In one possible implementation, a striking device is used to strike the vulnerable points of the object on the sieve determined by the above method. Since the vulnerable points determined by the above method are essentially the correspondence of the center of mass of the object directly above each sieve hole on the surface of the object, that is, striking the vulnerable points is equivalent to striking the center of mass of the object. The force of this striking will cause a large acceleration of the object, because the center of mass is the center of mass of the object, and the crusher applies the impact force completely in the vertical direction in the direction of the center of mass of the ore. This acceleration will have a great impact on various parts of the object, and the stress inside the object will increase rapidly. In particular, when the force is large enough, the object will be broken because it cannot withstand such a large stress. Therefore, the object on the sieve can be efficiently and accurately crushed, thereby achieving the effect of labor-saving and efficient cleaning of sieve blockages.

[0095] Another embodiment of the present invention further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for locating vulnerable points of a sieve blocking object as described above is executed.

[0096] Another embodiment of the present invention further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the method for locating vulnerable points of an object blocked by a sieve as described above is executed.

[0097] Another embodiment of the present invention further provides a stone crushing system, including a stone crushing component, wherein the stone crushing component uses the method for locating the vulnerable point of a sieve-blocking object as described above to perform a crushing operation.

[0098] That is to say, the stone crushing component is a set of equipment with a crushing function, including but not limited to a striking hammer, a mechanical arm, and a percussion vehicle, and the positioning method adopted by the equipment is the above-mentioned method for locating the vulnerable points of the grid screen blocking object.

[0099] The above embodiments all have the technical effect of a method for cleaning a grid screen blockage provided by an embodiment of the present invention.

[0100] The working principle of the method for locating the vulnerable points of objects blocked by the grid screen of the present embodiment is as follows: point cloud data of the surface of the object on the grid screen is obtained, and after through filtering, outlier filtering and voxel filtering, the first voxel points corresponding to each grid screen hole are generated, and the blocked grid screen holes that need to be crushed are screened out according to the number of first points and their coverage of grid screen holes, and the vulnerable points of the objects on the grid screen holes are determined according to the centroids of the blocked grid screen holes, and then the vulnerable points are hit to achieve the effect of efficiently and accurately cleaning the grid screen blockages.

[0101] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present invention is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0102] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A method for locating a vulnerable point of an object blocked by a grating, wherein the grating has a plurality of grating holes, and the grating plane forms an X-axis and a Y-axis, characterized in that: The following steps are involved: S1: Obtain point cloud data of the object surface on the grid screen, generate a three-dimensional point cloud, fit the three-dimensional point cloud to the grid screen position coordinates, and obtain the robot arm data coordinate system; S2: The robot data coordinate system is sampled through voxel filtering to calculate and obtain voxel point cloud data with uniform density; S3: Segmenting the voxel point cloud data in a direction parallel to the X-coordinate axis and in a direction parallel to the Y-coordinate axis respectively, obtaining a plurality of first voxel points directly above each grid sieve hole, and compiling a corresponding index number for each first voxel point; S4: based on the first voxel point of each grid sieve hole, screening out blocked grid sieve holes; S5: According to the projection of the plurality of first voxel point cloud data in each blocking grid sieve hole on the XOY plane, the centroid corresponding to each projection surface is calculated, and the projection of the first voxel point closest to each of the centroids is searched, and the robot arm data coordinate corresponding to the index number of the first voxel point is the vulnerable point of the object on the blocking grid sieve hole; The surface refers to all the sides of the object that are above the grid screen; The screening method of the blocked grid sieve holes in step S4 is: The number of first voxel points of the grid sieve hole is greater than or equal to a first preset parameter, and the number of first voxel points within the center radius of the grid sieve hole is greater than or equal to a second preset parameter, and the first preset parameter is greater than the second preset parameter, and the grid sieve hole is a blocked grid sieve hole; wherein the implementation steps of the second preset parameter include: S41: Selecting a preset ratio of the width of the grid sieve holes; S42: taking the center of the grid hole as the center of the circle, taking the width of the preset ratio as the radius, and presetting the number of second voxel points within the radius as a second preset parameter; The step S2 of calculating and obtaining voxel point cloud data with uniform density comprises: S21: De-noising the point cloud data through a first filter to generate noise-free point cloud data; S22: Sampling the noise-free point cloud data through voxel filtering to calculate and obtain a first voxel point with uniform density; The voxel filtering sampling method described in step S22 is to divide the noise-free point cloud data into a number of three-dimensional voxel grids, select the point closest to the centroid of each three-dimensional voxel grid, and generate the voxel filtering sampling value of the three-dimensional voxel grid.

2. The method for locating the vulnerable point of a sieve blocking object according to claim 1, characterized in that: The first filtering in step S21 is through filtering and outlier filtering.

3. The method for locating the vulnerable point of a sieve blocking object according to claim 1, characterized in that In, The algorithm for fitting the three-dimensional point cloud and the grid position coordinates is the Euclidean transformation.

4. A method for cleaning a grid screen blockage, characterized in that: It includes a vulnerable point of a striking object, wherein the vulnerable point is located by the method described in any one of claims 1 to 3.

5. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method for locating vulnerable points of a sieve blocking object according to any one of claims 1 to 3 is executed.

6. An electronic device, characterized in that: The electronic device comprises: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the method for locating vulnerable points of a grid screen blockage object as described in any one of claims 1 to 3 is executed.

7. A stone crushing system, comprising a stone crushing component, characterized in that: The stone crushing component performs a crushing operation by using the method for locating the vulnerable point of a sieve blocking object as described in any one of claims 1 to 3.