Detection method, device and equipment for sintering machine wheels and medium
By acquiring the 3D point cloud of the sintering machine wheel and performing planar fitting and clustering, the problem of automated oil injection was solved, enabling precise positioning and damage detection of the oil injection nozzle, thus improving oil injection efficiency and equipment reliability.
Patent Information
- Application Number
- CN202310498147.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-05
- Publication Date
- 2024-11-05
AI Technical Summary
In the existing technology, the oil injection process of sintering machine wheels has not been automated, resulting in low oil injection efficiency and frequent accidents. How to provide oil injection nozzle information to automated oil injection equipment to ensure smooth oil injection is an urgent problem to be solved.
By acquiring the three-dimensional point cloud of the sintering machine wheel, performing plane fitting and clustering, extracting the point cloud of the oil injection nozzle, determining the height and edge damage of the oil injection nozzle, and providing accurate positioning and detection results of the oil injection nozzle.
It enables precise positioning and damage detection of wheel grease nozzles, ensuring the normal operation of automated grease filling equipment, improving grease filling efficiency, and reducing maintenance costs and equipment damage risks.
Smart Images

Figure CN118896500A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of sintering machine detection, and in particular to a detection method, device, equipment and medium for a sintering machine wheel. Background Art
[0002] Sintering is a key link in the steel industry, providing high-quality raw materials for iron making. The sintering process is a process in which the iron-containing raw materials are batched, mixed, and granulated, and then subjected to the exhaust effect of the main exhaust fan and high-temperature roasting on the sintering machine, so that the materials undergo a series of physical and chemical changes. Among them, the sintering machine is usually composed of more than 100 trolleys with a width of about 2 meters and drive wheels. The trolley plays a vital core role in the sintering process. Its stable operation can ensure the continuity of the sintering process. During the sintering process, the wheels of the trolley will repeatedly withstand harsh working conditions such as alternating high and low temperatures, alternating light and heavy loads, etc., so abnormal conditions such as breakage, deviation, wear, and shedding may occur. Once the equipment is shut down due to a fault, it may cause serious economic losses. In order to avoid the above situation and ensure that the wheels can adapt to the harsh environment, the axle needs to be regularly lubricated through the oil nozzle on the side of the wheel. When oiling manually, the condition of the oil nozzle can be judged manually. When oiling automatically by machine, the condition of the oil filling plate is very important. Once the oil filling plate is damaged, it will affect the position identification of the oil filling nozzle and whether the oiling can be successful.
[0003] At present, machine oiling is limited by various technical problems and has not been effectively implemented. How to realize the automation of oiling, provide the oiling nozzle information for the automatic oiling equipment, and ensure smooth oiling is the problem that needs to be solved at present. Summary of the invention
[0004] In view of this, the purpose of this application is to provide a sintering machine wheel detection method, device, equipment and medium, which can provide oiling nozzle information for automatic oiling equipment to ensure smooth oiling. The specific scheme is as follows:
[0005] In a first aspect, the present application discloses a method for detecting a sintering machine wheel, comprising:
[0006] During the operation of the sintering machine, the three-dimensional point cloud of the wheel of the sintering machine is obtained;
[0007] Performing plane fitting based on the three-dimensional point cloud of the wheel to obtain a bottom plane of the oiling nozzle;
[0008] Extracting a grease nozzle point cloud from the wheel three-dimensional point cloud;
[0009] A height detection result of the oiling nozzle is determined based on the oiling nozzle point cloud and the bottom plane of the oiling nozzle.
[0010] Optionally, extracting the oiling nozzle point cloud from the wheel three-dimensional point cloud includes:
[0011] Acquire a point cloud around the oiling nozzle from the three-dimensional point cloud of the wheel based on a three-dimensional region of interest of a preset size;
[0012] The point cloud around the oiling nozzle is clustered to obtain a point cloud of the oiling nozzle.
[0013] Optionally, the step of determining a height detection result of the oiling nozzle based on the oiling nozzle point cloud and the bottom plane of the oiling nozzle includes:
[0014] Determine the mean coordinates of the oil filling nozzle point cloud to obtain a mean point;
[0015] The distance from the mean point to the bottom plane of the oil filling nozzle is calculated to obtain the height detection result of the oil filling nozzle.
[0016] Optionally, also include:
[0017] Performing plane fitting based on the three-dimensional point cloud of the wheel to obtain an oil filling pan plane;
[0018] Extracting a boundary point cloud of the oil filling pan plane;
[0019] The oil filling pan edge damage detection result is determined based on the distance between adjacent points in the boundary point cloud.
[0020] Optionally, determining the oil filling pan edge damage detection result based on the distance between adjacent points in the boundary point cloud includes:
[0021] Filtering points that meet preset conditions from the boundary point cloud to obtain a valid point set;
[0022] Calculate the distance between two adjacent points in the effective point set;
[0023] An oil fill pan edge damage detection result is determined based on the distance.
[0024] Optionally, the step of selecting points satisfying a preset condition from the boundary point cloud to obtain a valid point set includes:
[0025] Determine the wheel center of the sintering machine;
[0026] Determine the distance between each point in the boundary point cloud and the center of the wheel, and determine the mean of the distances;
[0027] Determine a distance range based on the distance mean and a preset distance threshold;
[0028] Points whose distances from the center of the wheel are within the distance range are determined as points that meet a preset condition to obtain a valid point set.
[0029] Optionally, during the operation of the sintering machine, obtaining a three-dimensional point cloud of a wheel of the sintering machine includes:
[0030] When point cloud data of a continuous preset number of frames are collected, the point cloud data of the continuous preset number of frames and the point cloud data of subsequent frames are saved until the continuous preset number of frames of empty data are collected, then the collection is stopped to obtain the three-dimensional point cloud of the wheel of the sintering machine.
[0031] In a second aspect, the present application discloses a detection device for a sintering machine wheel, comprising:
[0032] The wheel point cloud acquisition module is used to obtain the three-dimensional point cloud of the wheel of the sintering machine during the operation of the sintering machine;
[0033] A plane fitting module, used for performing plane fitting based on the three-dimensional point cloud of the wheel to obtain a bottom plane of the oiling nozzle;
[0034] A grease nozzle point cloud extraction module, used to extract the grease nozzle point cloud from the wheel three-dimensional point cloud;
[0035] The detection result determination module is used to determine the height detection result of the oil filling nozzle based on the oil filling nozzle point cloud and the bottom plane of the oil filling nozzle.
[0036] In a third aspect, the present application discloses an electronic device, including a memory and a processor, wherein:
[0037] The memory is used to store the computer program;
[0038] The processor is used to execute the computer program to implement the aforementioned sintering machine wheel detection method.
[0039] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program, wherein the computer program implements the aforementioned sintering machine wheel detection method when executed by a processor.
[0040] It can be seen that the present application first obtains the three-dimensional point cloud of the wheel of the sintering machine during the operation of the sintering machine, then performs plane fitting based on the three-dimensional point cloud of the wheel to obtain the bottom plane of the oiling nozzle, and extracts the oiling nozzle point cloud from the three-dimensional point cloud of the wheel, and finally determines the height detection result of the oiling nozzle based on the oiling nozzle point cloud and the bottom plane of the oiling nozzle. That is, the present application performs plane fitting based on the three-dimensional point cloud of the wheel to obtain the bottom plane of the oiling nozzle, and extracts the oiling nozzle point cloud, and then uses the oiling nozzle point cloud and the bottom plane of the oiling nozzle to determine the height detection result of the oiling nozzle, so that the oiling nozzle information can be provided to the automated oiling equipment to ensure smooth oiling. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0042] Figure 1 A flow chart of a method for detecting a sintering machine wheel disclosed in the present application;
[0043] Figure 2 This is a schematic diagram of the installation of a line structured light device disclosed in this application;
[0044] Figure 3 A specific point cloud data collection flow chart disclosed in this application;
[0045] Figure 4 A plane fitting flow chart disclosed in this application;
[0046] Figure 5 A specific oil filling plate edge damage detection flow chart disclosed in the present application;
[0047] Figure 6 This is a schematic diagram of the structure of a detection device for a sintering machine wheel disclosed in the present application;
[0048] Figure 7 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION
[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0050] At present, most lubrication methods are manual oiling, which is inefficient, difficult to oil and often causes accidents. How to realize oiling automation, provide oiling nozzle information for automatic oiling equipment, and ensure smooth oiling is a problem that needs to be solved at present. To this end, the present application provides a detection scheme for sintering machine wheels, which can provide oiling nozzle information for automatic oiling equipment to ensure smooth oiling.
[0051] See also Figure 1 As shown, the embodiment of the present application discloses a method for detecting a sintering machine wheel, comprising:
[0052] Step S11: during the operation of the sintering machine, a three-dimensional point cloud of a wheel of the sintering machine is obtained.
[0053] In a specific implementation, an industrial CCD camera and a line laser emitter are used to form a line structured light, and each wheel passing through the position is detected in real time within a preset range (such as one meter) near the sintering trolley. The measurement process of the line structured light equipment belongs to non-contact measurement. The main structure of the line structured light equipment includes a camera, a straight line laser and related brackets. For example, see Figure 2 As shown, Figure 2 A schematic diagram of the installation of a line structured light device provided for this application, wherein (a) is a top view and (b) is a left view. In the embodiment of the present application, a red line laser is used. After capturing the image, the camera first extracts the laser line, and then converts the two-dimensional pixel points on the laser line into three-dimensional points in the camera coordinate system through the previous line plane calibration. The distance between the camera and the line laser varies according to the distance to the object being measured, and the spacing is usually in the range of 50mm-2000mm. The angle between the laser and the camera is usually about [20°-50°]. For example, the angle between the camera and the laser is selected to be 45°. The mounting bracket requires stability, the camera and the laser can be fixed by multiple screws, the laser can adjust the mounting angle, and the camera can adjust the translation position on the bracket. The movement of the sintered wheel is relatively slow, so the camera frame rate is set to 10-15 frames to obtain a relatively dense point cloud, and it can meet the requirements of real-time measurement. The spacing between the sintered wheels is relatively large, and the gaps are invalid data, so it is necessary to determine when the required wheel data has been collected.
[0054] In a specific implementation, when point cloud data of a preset number of consecutive frames is collected, the point cloud data of the preset number of consecutive frames and the point cloud data of subsequent frames are saved until the preset number of consecutive frames of empty data are collected, then the collection is stopped to obtain the three-dimensional point cloud of the wheel of the sintering machine. That is, the point cloud data before the empty data can be used as the three-dimensional point cloud of a wheel.
[0055] For example, see Figure 3 As shown, Figure 3 This is a specific point cloud data collection flow chart disclosed in the embodiment of this application. The scanning is started and stopped by judging whether there are 10 consecutive frames of data. After the process is completed, a complete wheel point cloud is collected and the next step of processing can be carried out.
[0056] It should be pointed out that the existing wheel detection technology mostly uses point lasers to emit lasers vertically to obtain partial features of the wheel. This technology is difficult to install, and the installation environment needs to be close to the sintering trolley. If the temperature is too high, equipment failure is likely to occur. In addition, the point laser can only collect three-dimensional information of a single point during the movement of the wheel. Therefore, the features obtained are limited. It can obtain partial wheel features, but cannot obtain the state of the entire wheel, and cannot measure the complete size of the wheel. In addition, the sintered wheel is constantly rotating during operation, and the oiling nozzle cannot be fixed in position every time at the inspection station. The point laser equipment cannot measure the height of the oiling nozzle and detect damage to the oiling nozzle. The embodiment of the present application can obtain the precise size of each wheel, whether the oiling tray is damaged, and the height parameter data of the oiling nozzle by means of line structured light. These geometric dimensions and damage information can ensure the precise positioning of the oiling nozzle for automatic oiling and achieve the goal of unmanned oiling.
[0057] Step S12: performing plane fitting based on the three-dimensional point cloud of the wheel to obtain the bottom plane of the oil filling nozzle.
[0058] In a specific implementation, RANSAC may be used to perform plane fitting to obtain the bottom plane of the oil filling nozzle.
[0059] Step S13: extracting the oiling nozzle point cloud from the wheel three-dimensional point cloud.
[0060] In a specific implementation, a point cloud around the oiling nozzle can be obtained from the three-dimensional point cloud of the wheel based on a three-dimensional region of interest of a preset size; the point cloud around the oiling nozzle is clustered to obtain the oiling nozzle point cloud. The point cloud around the oiling nozzle can be clustered by using a Euclidean clustering method to obtain the oiling nozzle point cloud.
[0061] Step S14: determining a height detection result of the oiling nozzle based on the oiling nozzle point cloud and the bottom plane of the oiling nozzle.
[0062] In a specific implementation, the mean coordinates of the oil filling nozzle point cloud may be determined to obtain a mean point; and the distance from the mean point to the bottom plane of the oil filling nozzle may be calculated to obtain a height detection result of the oil filling nozzle.
[0063] Furthermore, the embodiments of the present application can also perform plane fitting based on the three-dimensional point cloud of the wheel to obtain the oil filling pan plane; extract the boundary point cloud of the oil filling pan plane; and determine the oil filling pan edge damage detection result based on the distance between adjacent points in the boundary point cloud.
[0064] Among them, points that meet preset conditions can be screened out from the boundary point cloud to obtain a valid point set; the distance between two adjacent points in the valid point set is calculated; and the oil filling plate edge damage detection result is determined based on the distance. If the distance is greater than a preset threshold, it is determined that damage has occurred, and the presence or absence of damage and the amount of damage can be output.
[0065] Furthermore, the specific process of selecting points satisfying preset conditions from the boundary point cloud to obtain a valid point set may include: determining the wheel center of the sintering machine; determining the distance between each point in the boundary point cloud and the wheel center, and determining the distance mean; determining a distance range based on the distance mean and a preset distance threshold; and determining points whose distances to the wheel center are within the distance range as points satisfying the preset conditions to obtain a valid point set.
[0066] In a specific implementation, plane fitting can be performed based on the three-dimensional point cloud of the wheel to obtain the wheel disc plane, and ellipse fitting can be performed on the wheel disc plane to obtain the wheel center.
[0067] The embodiment of the present application can perform plane fitting and ellipse fitting based on the three-dimensional point cloud of the wheel using the RANSAC algorithm to obtain circle parameters such as the bottom plane of the oiling nozzle, the plane of the wheel disc, the plane of the oiling disc, and the center of the wheel. Figure 4 As shown, Figure 4 A plane fitting flow chart disclosed in an embodiment of the present application. First, determine the number of iterations N and the threshold value of in-place points Mthreshold; randomly select 3 points, and calculate the sampling plane formed by the 3 points, calculate the distance from all points to the plane according to the sampling plane, and divide the points into in-place points and out-place points according to the parameter (threshold of the distance); count the in-place points, if the number of in-place points is greater than Mthreshold, it means that this round of Ransac fitting is completed; repeat the above process until the number of iterations is reached, output the plane parameters with the most in-place points, if Ransac is unsuccessful, output the initial plane parameters; save the out-place points of this round for the next round of segmentation. The Ransac fitting method can effectively remove discrete points and fit the point cloud plane with the largest area. After each fitting, the extracted in-plane points are removed, and the out-of-place points are continued to be fitted until the remaining points do not meet the fitting conditions (the number of extracted planes meets the requirements or the number of remaining point sets cannot meet the requirements). After this segmentation process, the plane space equations and plane point clouds such as the bottom plane of the oiling nozzle, the oiling plate, and the wheel disc plane can be obtained. Then, by judging the depth of the point cloud, the plane can be distinguished.
[0068] Furthermore, size detection can be performed, including the diameter measurement of the wheel disc and the diameter measurement of the edge circle of the oil nozzle. The fitted plane point cloud set is processed separately. Any three-dimensional circle can be represented as the intersection of a plane and a three-dimensional sphere. The Ransac algorithm is continued to be used to segment the three-dimensional circle, and the number of iterations N is set: 1. For any plane point cloud, three points are randomly selected from the original point set of the plane point cloud, and the parameters of the initial circle, the center (Ox, Oy, Oz) and the radius R0 are solved through these three points. 2. Calculate the distance d from other points in the point set to the center of the circle. If d-R0≤Threshold (distance threshold), the point is added to the internal point set, otherwise it is added to the external point set. 3. After all points in the point set are calculated, if the number of internal points M is greater than the internal point threshold Mmin, the segmentation is considered to be completed, and the internal points and the number of internal points are recorded, and the next step is continued. Otherwise, continue to the first step. 4. Repeat steps 1, 2, and 3 until the number of iterations is equal to N. The iteration result with the largest number of points in the above iteration process is selected, and the parameter model of the circle is recalculated using the least square method for all points in the point set to obtain the final result. After completion, the coordinates of the center, radius, and normal direction of the three-dimensional circle can be obtained.
[0069] It should be pointed out that the oiling nozzle will have oil residue after each oiling, and it is impossible to obtain a regular geometric shape every time. Therefore, the ROI in the x, y, and z directions (that is, the three dimensions of the three-dimensional point cloud) is limited to obtain the point cloud set around the oiling nozzle, and then the oiling nozzle point cloud is extracted by Euclidean clustering. The spatial equation of the plane at the bottom of the oiling nozzle is Ax+By+Cz=D, where A, B, and C are the coefficients of the spatial plane equation. The average coordinates of the oiling nozzle point cloud obtained by Euclidean clustering are taken to obtain the average point (a, b, c), and the distance from the point to the plane is calculated. The distance d obtained in this step is the height data of the oil nozzle.
[0070] In addition, the damage detection target is the edge of the oiling nozzle plate. If there is damage, the wheel oiling device will not be able to oil normally, and timely maintenance is required. The damage detection is based on the straight-through filtering of the original point cloud. Because the installation position of the equipment is fixed, the position of each scanned wheel will also be fixed in the camera coordinate system. From the previous size detection process, the center coordinates of the entire wheel and the plane point cloud of the oiling plate can be obtained. The boundary points of the plane point cloud of the oiling plate are extracted, and the boundary contour of the oiling plate can be obtained after extraction. The average distance R between each point in the boundary point cloud and the center of the wheel is obtained, and the distance threshold DT is set. The points with a distance greater than R+DT and R-DT in the boundary points are eliminated, and the remaining points are valid points on the oiling plate. Finally, the interval between adjacent points in the valid point set is calculated. If the interval is greater than the threshold DT, it is judged that there is damage. The presence or absence of damage and the amount of damage are output to the automatic oiling control system, which can avoid damage to the oiling equipment due to damage. If the oiling plate is not damaged, the radius size of the oiling plate can also be calculated. For example, see Figure 5 As shown, an embodiment of the present application discloses a specific flow chart for detecting damage to the edge of an oil filling pan.
[0071] In this way, a detection system consisting of a laser, a camera and a bracket is installed on both sides of the sintering trolley. The detection system can detect the size, oil nozzle height and edge damage of each trolley wheel in real time, providing real-time measurement data for the automatic oiling of the wheel. The oil nozzle height and the size of the wheel oil pan can be used to guide the automatic oiling equipment to oil. The detection of damage can allow the control system to control the operation of the oiling machine in time to avoid equipment damage. This method has a simple structure, easy installation, high detection accuracy, low maintenance cost and high robustness.
[0072] See also Figure 6 As shown, the embodiment of the present application discloses a detection device for a sintering machine wheel, comprising:
[0073] The wheel point cloud acquisition module 11 is used to acquire the three-dimensional point cloud of the wheel of the sintering machine during the operation of the sintering machine;
[0074] A plane fitting module 12 is used to perform plane fitting based on the three-dimensional point cloud of the wheel to obtain a bottom plane of the oiling nozzle;
[0075] A grease nozzle point cloud extraction module 13, used to extract a grease nozzle point cloud from the wheel three-dimensional point cloud;
[0076] The detection result determination module 14 is used to determine the height detection result of the oil filling nozzle based on the oil filling nozzle point cloud and the bottom plane of the oil filling nozzle.
[0077] It can be seen that the embodiment of the present application first obtains the three-dimensional point cloud of the wheel of the sintering machine during the operation of the sintering machine, then performs plane fitting based on the three-dimensional point cloud of the wheel to obtain the bottom plane of the oiling nozzle, and extracts the oiling nozzle point cloud from the three-dimensional point cloud of the wheel, and finally determines the height detection result of the oiling nozzle based on the oiling nozzle point cloud and the bottom plane of the oiling nozzle. That is, the embodiment of the present application performs plane fitting based on the three-dimensional point cloud of the wheel to obtain the bottom plane of the oiling nozzle, and extracts the oiling nozzle point cloud, and then uses the oiling nozzle point cloud and the bottom plane of the oiling nozzle to determine the height detection result of the oiling nozzle, so that the oiling nozzle information can be provided to the automated oiling equipment to ensure smooth oiling.
[0078] The oiling nozzle point cloud extraction module 13 is specifically used to obtain a point cloud around the oiling nozzle from the three-dimensional point cloud of the wheel based on a three-dimensional region of interest of a preset size; and cluster the point cloud around the oiling nozzle to obtain a point cloud of the oiling nozzle.
[0079] Furthermore, the detection result determination module 14 is specifically used to determine the mean coordinates of the oil filling nozzle point cloud to obtain a mean point; calculate the distance from the mean point to the bottom plane of the oil filling nozzle to obtain a height detection result of the oil filling nozzle.
[0080] In addition, the plane fitting module 12 is also used to perform plane fitting based on the three-dimensional point cloud of the wheel to obtain the oil filling pan plane.
[0081] Furthermore, the device also includes an oil filling pan boundary point cloud extraction module, which is used to extract the boundary point cloud of the oil filling pan plane;
[0082] Correspondingly, the device further comprises an oil filling tray edge damage detection module, which is used to determine the oil filling tray edge damage detection result based on the distance between adjacent points in the boundary point cloud.
[0083] In a specific implementation, the oil filling plate edge damage detection module specifically includes:
[0084] An effective point set screening submodule, used to screen out points that meet preset conditions from the boundary point cloud to obtain a valid point set;
[0085] A distance calculation submodule, used to calculate the distance between two adjacent points in the effective point set;
[0086] The damage detection result determination submodule is used to determine the damage detection result of the oil filling plate edge based on the distance.
[0087] Among them, the effective point set screening submodule is specifically used to determine the wheel center of the sintering machine; determine the distance between each point in the boundary point cloud and the wheel center, and determine the distance mean; determine the distance range based on the distance mean and a preset distance threshold; determine the points whose distance to the wheel center is within the distance range as points that meet the preset conditions to obtain a valid point set.
[0088] The wheel point cloud acquisition module 11 is specifically used to save the point cloud data of the continuous preset number of frames and the point cloud data of subsequent frames when the point cloud data of the continuous preset number of frames is collected, until the empty data of the continuous preset number of frames is collected, then stop collecting to obtain the three-dimensional point cloud of the wheel of the sintering machine.
[0089] See also Figure 7 As shown, an embodiment of the present application discloses an electronic device 20, including a processor 21 and a memory 22; wherein the memory 22 is used to store a computer program; the processor 21 is used to execute the computer program, the sintering machine wheel detection method disclosed in the above embodiment.
[0090] The specific process of the above-mentioned sintering machine wheel detection method can refer to the corresponding content disclosed in the above-mentioned embodiment, and will not be repeated here.
[0091] Furthermore, the memory 22 as a carrier for storing resources may be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., and the storage method may be temporary storage or permanent storage.
[0092] In addition, the electronic device 20 also includes a power supply 23, a communication interface 24, an input / output interface 25 and a communication bus 26; wherein the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input / output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.
[0093] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the sintering machine wheel detection method disclosed in the aforementioned embodiment.
[0094] The specific process of the above-mentioned sintering machine wheel detection method can refer to the corresponding content disclosed in the above-mentioned embodiment, and will not be repeated here.
[0095] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.
[0096] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0097] The above is a detailed introduction to the detection method, device, equipment and medium for a sintering machine wheel provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A method for detecting a sintering machine wheel, characterized in that: include: During the operation of the sintering machine, the three-dimensional point cloud of the wheel of the sintering machine is obtained; Performing plane fitting based on the three-dimensional point cloud of the wheel to obtain a bottom plane of the oiling nozzle; Extracting a grease nozzle point cloud from the wheel three-dimensional point cloud; A height detection result of the oiling nozzle is determined based on the oiling nozzle point cloud and the bottom plane of the oiling nozzle.
2. The method for detecting a sintering machine wheel according to claim 1, characterized in that: The step of extracting the oiling nozzle point cloud from the wheel three-dimensional point cloud comprises: Acquire a point cloud around the oiling nozzle from the three-dimensional point cloud of the wheel based on a three-dimensional region of interest of a preset size; The point cloud around the oiling nozzle is clustered to obtain a point cloud of the oiling nozzle.
3. The method for detecting a sintering machine wheel according to claim 1, characterized in that: The step of determining the height detection result of the oiling nozzle based on the oiling nozzle point cloud and the bottom plane of the oiling nozzle includes: Determine the mean coordinates of the oil filling nozzle point cloud to obtain a mean point; The distance from the mean point to the bottom plane of the oil filling nozzle is calculated to obtain the height detection result of the oil filling nozzle.
4. The method for detecting a sintering machine wheel according to claim 1, characterized in that: Also includes: Performing plane fitting based on the three-dimensional point cloud of the wheel to obtain an oil filling pan plane; Extracting a boundary point cloud of the oil filling pan plane; The oil filling pan edge damage detection result is determined based on the distance between adjacent points in the boundary point cloud.
5. The method for detecting a sintering machine wheel according to claim 4, characterized in that: The step of determining the oil filling pan edge damage detection result based on the distance between adjacent points in the boundary point cloud comprises: Filtering points that meet preset conditions from the boundary point cloud to obtain a valid point set; Calculate the distance between two adjacent points in the effective point set; An oil fill pan edge damage detection result is determined based on the distance.
6. The method for detecting a sintering machine wheel according to claim 5, characterized in that: The step of selecting points satisfying preset conditions from the boundary point cloud to obtain a valid point set includes: Determine the wheel center of the sintering machine; Determine the distance between each point in the boundary point cloud and the center of the wheel, and determine the mean of the distances; Determine a distance range based on the distance mean and a preset distance threshold; Points whose distances from the center of the wheel are within the distance range are determined as points that meet a preset condition to obtain a valid point set.
7. The method for detecting a sintering machine wheel according to any one of claims 1 to 6, characterized in that: The method of obtaining a three-dimensional point cloud of a wheel of the sintering machine during operation of the sintering machine includes: When point cloud data of a preset number of consecutive frames are collected, the point cloud data of the preset number of consecutive frames and the point cloud data of subsequent frames are saved until the preset number of consecutive frames of empty data are collected, then the collection is stopped to obtain the three-dimensional point cloud of the wheel of the sintering machine.
8. A detection device for a sintering machine wheel, characterized in that: include: The wheel point cloud acquisition module is used to obtain the three-dimensional point cloud of the wheel of the sintering machine during the operation of the sintering machine; A plane fitting module, used for performing plane fitting based on the three-dimensional point cloud of the wheel to obtain a bottom plane of the oiling nozzle; A grease nozzle point cloud extraction module, used to extract the grease nozzle point cloud from the wheel three-dimensional point cloud; The detection result determination module is used to determine the height detection result of the oil filling nozzle based on the oil filling nozzle point cloud and the bottom plane of the oil filling nozzle.
9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store the computer program; The processor is used to execute the computer program to implement the sintering machine wheel detection method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, the method for detecting a sintering machine wheel according to any one of claims 1 to 7 is implemented.
