Robot control system, method and equipment for saggar loading and unloading and medium

Abstract

The invention provides a robot control system, method and equipment for saggar loading and unloading and a medium. The problem that in the prior art, an integrated system covering the whole process of grabbing, carrying, cleaning, loading and unloading cannot be provided for saggars is effectively solved. The system comprises a visual module used for identifying position information of a target to-be-processed saggar from a plurality of to-be-processed saggars in a to-be-operated area; the robot is used for grabbing the target to-be-processed saggar in the operation area in cooperation with a preset moving module according to the position information to generate a grabbing result, and transmitting the target to-be-processed saggar to the cleaning module for cleaning; the cleaning module is used for generating a cleaning result when the target to-be-treated saggar is cleaned, and controlling the robot to place the target to-be-treated saggar to a designated area; and the uploading module is used for receiving and uploading the grabbing result, the cleaning result and equipment state data obtained by operation of the monitoring control system so as to complete online and offline of the target to-be-processed saggar.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automation control, in particular to a robot control system, method, device and medium for sagger online and offline. BACKGROUND

[0002] In the fields of new energy positive electrode material manufacturing, chemical industry and ceramic production, sagger online and offline and cleaning transfer are key production links. At present, the industry relies on manual operation or single-link automation equipment for this link, which has significant drawbacks: manual operation is low in efficiency, high in labor cost, and prone to sagger damage and unstable cleaning and demagnetization effect; the existing automation equipment is single in function, lacks a visual guidance system, resulting in insufficient positioning accuracy, poor collaboration between devices, fragmented processes, low automation level of cleaning and demagnetization technology, high maintenance cost and insufficient stability.

[0003] In summary, the prior art lacks an integrated system covering the whole process of grabbing, carrying, cleaning and online and offline, which is difficult to meet the production needs of high efficiency, high quality and low cost, and an intelligent and collaborative solution is urgently needed. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a robot control system, method, device and medium for sagger online and offline, which effectively solves the problem that the prior art cannot provide an integrated system covering the whole process of grabbing, carrying, cleaning and online and offline for sagger.

[0005] In a first aspect, an embodiment of the present application provides a robot control system for sagger online and offline, the system comprising: a visual module configured to identify position information of a target sagger to be processed from a plurality of saggertobe-processed in a to-be-processed area; a robot configured to, according to the position information, cooperate with a preset movement module to grab the target sagger to be processed in the to-be-processed area to generate a grabbing result, and transfer the target sagger to be processed to a cleaning module for cleaning; a cleaning module configured to, when the cleaning for the target sagger to be processed is completed, generate a cleaning result, and control the robot to place the target sagger to be processed in a designated area; an uploading module configured to receive and upload the grabbing result, the cleaning result and equipment state data obtained by monitoring the control system running, to complete the online and offline of the target sagger to be processed, and generate processing information for the control system.

[0006] In combination with the first aspect, an embodiment of the present application provides a first possible implementation manner of the first aspect, wherein the robot, according to the position information, cooperates with the preset movement module to grab the target sagger to be processed in the to-be-processed area to generate the grabbing result, comprising: Based on the location information and the production environment where the multiple crucibles to be processed are located, the robot dynamically plans the global path and the local offset path. Based on the global path and the local offset path, the robot and the mobile module are controlled to cooperate in grasping the target crucible to be processed.

[0007] In conjunction with the first aspect, this application provides a second possible implementation of the first aspect, wherein controlling the robot and the mobile module to cooperate in grasping the target crucible to be processed includes: Based on the global path, the mobile module is controlled to move the robot to the work area; Upon reaching the work area, the robot dynamically adjusts its gripping force to grasp the target crucible based on various parameter data of the target crucible and the local offset path.

[0008] In conjunction with the first aspect, this application provides a third possible implementation of the first aspect, wherein dynamically adjusting the gripping force of the robot to grasp the target crucible includes: Calculate the difference between the attitude angle of the target crucible and a preset threshold, and determine whether the difference is under tilt conditions; If so, the spatial state of the robot's end effector is adjusted according to the difference to grasp the target crucible.

[0009] In conjunction with the first aspect, this application provides a fourth possible implementation of the first aspect, wherein the vision module is used to identify the position information of a target crucible from among a plurality of crucibles to be processed in the work area, including: Capture stacked point cloud data of multiple crucibles to be processed, and dynamically segment the stacked point cloud data to obtain crucible point cloud data corresponding to each of the multiple crucibles to be processed. The spatial coordinates of the crucible point cloud data are calculated to generate the position information of the target crucible to be processed.

[0010] In conjunction with the first aspect, this application provides a fifth possible implementation of the first aspect, wherein dynamically segmenting the stacked point cloud data to obtain multiple crucible point cloud data corresponding to each crucible to be processed includes: Sample point cloud data of saggers under stacking, tilting, and occlusion conditions in actual production are collected in advance, and various features are constructed based on the sample point cloud data; A point cloud segmentation model is trained based on the aforementioned features, and the stacked point cloud data is dynamically segmented based on the point cloud segmentation model.

[0011] With reference to the first aspect, the embodiments of the present application provide a sixth possible implementation manner of the first aspect, and the method further includes: The cleaning module is configured in advance based on the permanent magnet adsorption assembly, the negative pressure dust collection assembly, and the iron scrap automatic separation module. The cleaning module is controlled to clean the target kiln based on the permanent magnet adsorption assembly, the negative pressure dust collection assembly, and the iron scrap automatic separation module.

[0012] In the second aspect, the embodiments of the present application provide a robot control method for kiln online and offline, and the method includes: The position information of a target kiln to be processed is recognized from a plurality of kilns to be processed in a to-be-worked region by a vision module; A robot cooperates with a preset movement module to grab the target kiln to be processed in the working region according to the position information to generate a grabbing result, and the target kiln to be processed is transported to a cleaning module for cleaning; When the cleaning for the target kiln to be processed is completed, the cleaning module generates a cleaning result, and the robot is controlled to place the target kiln to be processed in a designated region; The grabbing result, the cleaning result, and equipment state data obtained by monitoring and controlling a system are received and uploaded to complete the online and offline of the target kiln to be processed, and processing information for the control system is generated.

[0013] In the third aspect, the embodiments of the present application provide an electronic device, which includes a processor, a memory, and a bus. The memory stores machine readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory through the bus. The machine readable instructions are executed by the processor to perform the steps of the robot control method for kiln online and offline.

[0014] In the fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program. When the computer program is run by a processor, the steps of the robot control method for kiln online and offline are executed.

[0015] The embodiment of the present application provides a robot control system for the upline and downline of a sagger, the system comprises: a vision module, which is used for identifying position information of a target sagger to be processed from a plurality of saggertobe-processed in a to-be-operated region; a robot, which is used for generating a grabbing result by grabbing the target sagger to be processed in the operating region according to the position information and in cooperation with a preset moving module, and transmitting the target sagger to be processed to a cleaning module for cleaning; a cleaning module, which is used for generating a cleaning result when the cleaning for the target sagger to be processed is completed, and controlling the robot to place the target sagger to be processed to a specified region; and an uploading module, which is used for receiving and uploading the grabbing result, the cleaning result and equipment state data obtained by monitoring the control system running, so as to complete the upline and downline of the target sagger to be processed and generate processing information for the control system. Based on the above system, the present application not only realizes an integrated system for the whole process of covering grabbing, carrying, cleaning and upline and downline of the sagger, eliminates inefficient links such as manual carrying, cleaning and collaborative waiting, and solves the process interruption problem caused by independent operation of the traditional equipment through the collaborative processing of the vision module, the robot, the moving module, the cleaning module and the uploading module, realizes real-time monitoring of running states such as torque, temperature and vibration, realizes automatic triggering of maintenance prompt or degradation operation mode, reduces unplanned downtime, solves the core pain points of the prior art in efficiency, quality, collaboration and operation and maintenance, and forms a whole-process intelligent and collaborative solution. BRIEF DESCRIPTION OF DRAWINGS In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0016] Figure 1 A schematic diagram of a robot control system for the upline and downline of a sagger provided by the embodiment of the present application is shown; Figure 2 A schematic diagram of a robot and a moving module provided by the embodiment of the present application is shown; Figure 3 A structural schematic diagram of a cleaning module provided by the embodiment of the present application is shown; Figure 4 A structural schematic diagram of a negative air pressure pipe provided by the embodiment of the present application is shown; Figure 5 A structural schematic diagram of automatic iron filings shedding provided by the embodiment of the present application is shown; Figure 6 A flow chart of a robot control method for the upline and downline of a sagger provided by the embodiment of the present application is shown; Figure 7 A structural block diagram of an electronic device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It should be understood that the drawings in the present application serve merely to illustrate and describe the present application, and are not intended to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts show the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can not be implemented in sequence, and the steps that have no logical context relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flowcharts or one or more operations can be removed from the flowcharts under the guidance of the content of the present application.

[0018] In addition, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0019] It should be noted that the term “comprise” will be used in the embodiments of the present application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0020] The prior art lacks an integrated system covering the whole process of grabbing, carrying, cleaning, and on-off line, and it is difficult to meet the production requirements of high efficiency, high quality, and low cost, and an intelligent and collaborative solution is urgently needed.

[0021] Based on this, the embodiments of the present application provide a robot control system, method, device, and medium for on-off line of sagger, which are described below through embodiments.

[0022] Embodiment 1 To facilitate the understanding of the present embodiment, first, a robot control system for on-off line of sagger disclosed by the embodiments of the present application is introduced in detail. As shown in a schematic diagram of a robot control system for on-off line of sagger, the present application provides a robot control system for on-off line of sagger, which comprises: Figure 1 ​a visual module configured to identify position information of a target to-be-processed sagger from a plurality of to-be-processed saggers in a to-be-processed area; a robot configured to, in cooperation with a preset movement module, grasp the target to-be-processed sagger in the to-be-processed area according to the position information to generate a grasping result, and transfer the target to-be-processed sagger to a cleaning module for cleaning; a cleaning module configured to, when the cleaning for the target to-be-processed sagger is completed, generate a cleaning result, and control the robot to place the target to-be-processed sagger to a designated area; an uploading module configured to receive and upload the grasping result, the cleaning result, and equipment state data obtained by monitoring the control system to complete on- and off-line of the target to-be-processed sagger, and generate processing information for the control system.

[0023] In the present application, the visual module can be a high-precision binocular speckle 3D camera, the robot can be a 6-axis collaborative robot, the end of the 6-axis collaborative robot is provided with a torque-adjustable servo electric claw to perform a grasping action such as clamping, and the movement module can be a movable AGV, and the robot is arranged on the movable AGV included in the movement module, as shown in Figure 2 When the movement module moves, the robot moves along with the movement module, and there is also a communication module between the visual module, the robot, the cleaning module, and the uploading module, and the uploading module and the MES system perform data interaction through an OPC UA protocol. The visual module is configured to identify position information of a target to-be-processed sagger from a plurality of to-be-processed saggers in a to-be-processed area; wherein the plurality of to-be-processed saggers in the to-be-processed area are pre-transported, and in an actual production process, the plurality of to-be-processed saggers are generally stacked together, that is, the visual module scans the plurality of to-be-processed saggers in a stacked form to obtain stacked point cloud data of the plurality of to-be-processed saggers in the stacked form, and the robot can only grasp a single sagger and cannot grasp multiple saggers at the same time when grasping the sagger, so it is necessary to identify position information of a target to-be-processed sagger from a plurality of to-be-processed saggers in a to-be-processed area, and the position information is transmitted to the robot through a TCP / IP protocol to be grasped based on a torque-adjustable servo electric claw at the end of the robot to realize adaptive grasping (positioning error <0.1 mm) in a dynamic environment.

[0024] In some embodiments, the visual module is configured to identify position information of a target to-be-processed sagger from a plurality of to-be-processed saggers in a to-be-processed area, including: capturing stacked point cloud data of the plurality of to-be-processed saggers, and dynamically segmenting the stacked point cloud data to obtain sagger point cloud data corresponding to the plurality of to-be-processed saggers, respectively; The spatial coordinates of the saggar point cloud data are calculated to generate the position information of the target saggar to be processed.

[0025] In this embodiment, the vision module captures stacked point cloud data of multiple saggars to be processed, the stacked point cloud data densely covers the surface of the saggars, including the edge, bottom surface, and side wall, and dynamically segments the stacked point cloud data by a pre-trained point cloud segmentation model to obtain saggar point cloud data corresponding to the multiple saggars to be processed respectively. The point cloud segmentation model is trained based on a deep learning algorithm, that is, saggar point cloud data corresponding to each saggar is obtained. The spatial coordinates of the saggar point cloud data are calculated by edge processing and point cloud calculation on the saggar point cloud data corresponding to each saggar respectively, so as to generate the position information of the target saggar to be processed. The position information is represented by coordinates (X, Y, Z, Rz), wherein Rz is a rotation angle. If the target saggar to be processed is in an inclined working condition, the output position information further includes (Rx, Ry, Rz). The edge processing eliminates noise points in the stacked point cloud data, such as isolated points caused by camera errors and interference points formed by surface dust reflection, and retains effective point clouds of the saggar body. Then, the characteristic edges of the saggar are identified, such as the upper edge contour points, specifically the four corner points of the saggar upper opening and the contour points of the four edges; the bottom edge contour points, such as the edge points of the saggar bottom surface in contact with the ground; and the side wall edge points, such as the vertical edge points of the four side surfaces of the saggar. Based on the key edge points obtained after the edge processing, the unified spatial coordinates (X, Y, Z, Rz) of the entire saggar of the target saggar to be processed are derived by geometric fitting and pose solving operations, that is, the position information of the target saggar to be processed is obtained, rather than calculating the coordinates of a single point. The original X, Y, and Z of a single point are directly collected by a 3D camera, wherein X is the horizontal left and right, Y is the horizontal front and back, and Z is the vertical height.

[0026] In some embodiments, the dynamic segmentation of the stacked point cloud data to obtain saggar point cloud data corresponding to the multiple saggars to be processed respectively includes: The sample point cloud data of the saggars in the actual production under the stacking, tilting, and shielding conditions is pre-collected to construct multiple features based on the sample point cloud data. The point cloud segmentation model is trained based on the multiple features to dynamically segment the stacked point cloud data based on the point cloud segmentation model.

[0027] In this embodiment, the application pre-acquires sample point cloud data of the sagger in the actual production under the stacking, tilting and shielding working conditions, and carries out denoising, alignment and labeling on the sample point cloud data. Based on the denoising, isolated points caused by camera errors and environmental interference points (such as ground dust and air reflection) are deleted. Based on the alignment, the point cloud data of the same sagger collected at different angles is aligned in coordinates to form a complete sagger point cloud model. Based on the labeling, the boundary between the effective point cloud of the sagger and the interference point cloud (such as the point cloud of the shielding object) in each sample point cloud is determined to avoid learning of incorrect features. Based on the sample point cloud data, a plurality of features are constructed, including edge contour features, size features and surface texture features. Based on the edge contour features, size features and surface texture features, a stacking working condition feature set, a tilting working condition feature set and a shielding working condition feature set are constructed. The stacking working condition feature set includes the extraction of the layering rule of the sagger point cloud in the stacking state, such as the difference between the bottom point cloud of the upper sagger and the top point cloud of the lower sagger in the Z coordinate being equal to the sagger height. When the stacking is offset, the offset amount of the edge point cloud of the upper and lower sagger in the X / Y coordinate. The tilting working condition feature is the extraction of the posture correlation rule of the sagger point cloud in the tilting state, such as when tilting forward and backward, the Z coordinate of the front edge point cloud of the sagger is lower than the rear end (or vice versa), and the difference in the Z coordinate is positively correlated with the tilting angle. When tilting left and right, the difference between the Z coordinate of the left edge point cloud of the sagger and the right side is positively correlated with the tilting angle. The shielding working condition feature is the extraction of the incomplete feature of the sagger point cloud in the shielding state, such as when partially shielding, the edge point cloud of the sagger not shielded still maintains the inherent contour proportion. When adjacent shielding, the density of the point cloud of the two sagger in the overlapping area will increase significantly. Based on the plurality of features constituting the stacking working condition feature set, the tilting working condition feature set and the shielding working condition feature set, a point cloud segmentation model is trained to enable the point cloud segmentation model to correctly identify the above three working conditions and calculate accurate spatial coordinates and attitude angles to provide a basis for robot adaptive grabbing. Therefore, the position information of the target sagger to be processed is obtained by dynamically segmenting the stacking point cloud data based on the point cloud segmentation model. Through transfer learning to optimize the deep learning model, the robustness of the vision module in complex environments is improved, and the success rate of the robot grabbing is > 99.5%.

[0028] The edge profile feature is to extract the point cloud distribution of the upper edge, lower edge and side wall edge of the sagger from the sample point cloud. The ideal state of the upper edge is a rectangle, and when it is inclined, it is a trapezoid, but the length ratio of the four sides and the included angle range of the corners are fixed. The side wall edge is a straight line, which still maintains the straight line feature when it is inclined, only the spatial angle changes. The size feature is to extract the key size parameters of the sagger, such as the upper edge length, lower edge length, height, wall thickness, etc. (calculated by the coordinates of the points in the point cloud), which are inherent properties of the sagger and can be used as an important basis for identifying the sagger. The surface texture feature is the point cloud density distribution of the extracted sagger surface (such as the fine concave-convex formed on the sagger surface due to material and use marks, which reflects the density change in the point cloud), which further enhances the unique identification of the sagger.

[0029] The robot is used to design a path for the target sagger to be processed based on the adaptive path planning algorithm, and the path includes a global path and a local offset path. The global path is for the saggertobe-processed area, and the local offset path is for the target sagger to be processed. Thus, the robot can grasp the target sagger to be processed in the saggertobe-processed area. The robot can generate a grasping result based on the robot grasping the target sagger to be processed in the saggertobe-processed area. The grasping result includes success and failure. The hardware structure of the mobile module is provided with a standardized clamp interface, which can be connected with robots of different types or different functions. Thus, the robot can automatically adapt to different sagger specifications of different production lines, and one or two robots can cover the operation demand of multiple workshops. The robot can transmit the target sagger to be processed to the cleaning module for cleaning. Thus, the robot can feed the cleaning module. If the cleaning module lacks saggertobe-processed in the normal working state, the cleaning module sends a lack of material signal to the robot. The robot can immediately grasp the target sagger to be processed based on the lack of material signal. Thus, the cleaning module can normally perform the cleaning operation. After feeding is completed, the robot feeds back a completion signal to the cleaning module. The cleaning module detects whether there is material in the entrance to perform reconfirmation. The robot interacts with the automatic door.

[0030] In some embodiments, the robot is used to generate a grasping result based on the position information and the preset mobile module in the saggertobe-processed area. According to the position information and the production environment of the saggertobe-processed, the robot dynamically plans a global path and a local offset path. Based on the global path and the local offset path, the robot and the mobile module are controlled to cooperatively grab the target to-be-processed saggar.

[0031] In this embodiment, the application collects real-time production environment of multiple to-be-processed saggars, specifically including fixed constraints and dynamic constraints. The fixed constraints include production line equipment layout such as kiln and conveying line position, workshop passage boundary, and obstacle position such as column and tool rack. The dynamic constraints include real-time position of mobile AGV of the mobile module, working state of other robots, and temporary obstacles such as ground material and personnel. The dynamic constraints are the rule boundary of path planning, ensuring that the mobile module does not collide and interfere when moving the robot to the to-be-worked region. The global path is the macro route of the robot from the current position to the to-be-processed saggar in the to-be-worked region. The core target is to efficiently and safely reach the target range. The mobile module searches for the optimal route from the current position to the to-be-worked region in the built-in electronic map of the mobile module through the preset adaptive path planning algorithm, and generates a global path including global path nodes. The local offset path is the micro route of the robot from the to-be-worked region to the precise grabbing point of the target to-be-processed saggar after reaching the target region. The core target is to adapt to the position and posture of the target to-be-processed saggar, realize precise docking, and write the position information (X, Y, Z, Rz) of the target to-be-processed saggar into the local offset path, thereby generating the local offset path, and controlling the servo electric claw at the end of the robot to grab the target to-be-processed saggar.

[0032] The vision module outputs multiple saggar coordinates at a time, the robot is moved by the mobile module to above the whole-layer grabbing point, a global variable coordinate is used to plan an offset path in real time, and the target is grabbed in turn in descending order.

[0033] In some embodiments: the robot and the mobile module are controlled to cooperatively grab the target to-be-processed saggar, including: Based on the global path, the mobile module is controlled to move the robot to the to-be-worked region. After reaching the to-be-worked region, the clamping force of the robot is dynamically adjusted based on the multiple parameter data of the target to-be-processed saggar and the local offset path to grab the target to-be-processed saggar.

[0034] In this embodiment, the mobile module generates the global path, moves according to the global path nodes in the global path to move the robot to the work area, triggers the sagger online start signal after reaching the work area, and at the same time, the robot adjusts the joint angle and end execution posture of the robot in real time based on the local offset variable, the millisecond level response between devices, forms a continuous work flow, reduces the waiting time, and if the X / Y coordinates of the sagger and the center of the work area have deviation, the local path will fine-tune the horizontal position of the robot, so that the servo electric claw is aligned with the target sagger to be processed. According to the Z coordinate of the target sagger to be processed, the height of the robot execution end is adjusted to ensure that the electric claw and the target sagger to be processed are consistent in height; according to the Rz (horizontal rotation) angle, the rotation angle of the electric claw is adjusted to align the sagger edge, and in the process of grabbing, the servo electric claw starts the clamping action according to the preset multiple parameter data such as sagger weight and material parameters, real-time acquisition of clamping force data and real-time feedback of clamping force data through the torque detection unit, dynamic adjustment of clamping force, until the stable clamping state is reached and the sagger is not damaged. Specifically, the real-time clamping force data is compared with the preset clamping force safety threshold value, if the real-time clamping force is less than the safety threshold value and the sagger clamping requirement is not reached, the servo electric claw is controlled to gradually increase the clamping force; if the real-time clamping force reaches the safety threshold value or the sagger is detected to be stably clamped, the servo electric claw is controlled to stop increasing the force, and the current clamping force is maintained until the grabbing action is completed, so as to realize the adaptive grabbing of the target sagger to be processed by the robot.

[0035] In some embodiments: dynamically adjusting the clamping force of the robot to grab the target sagger to be processed includes: calculating the difference between the attitude angle of the target sagger to be processed and the preset threshold value, and determining whether the difference is in the inclined working condition; If yes, adjust the spatial state of the execution end of the robot according to the difference to grab the target sagger to be processed.

[0036] In this embodiment, if the visual module determines that the Rx angle and the Ry angle of the target to-be-processed saggar exceed the horizontal reference threshold value, that is, the preset allowable deviation range, it is determined that the target to-be-processed saggar is in a tilted working condition, and the visual module calculates the attitude angle (Rx, Ry, Rz) of the target to-be-processed saggar, wherein the Rx angle is the rotation angle of the target to-be-processed saggar around the X axis, specifically, the front and back inclination, such as the front end is high and the rear end is low; the Ry angle is the rotation angle of the saggar around the Y axis, specifically, the left and right inclination, such as the left end is high and the right end is low; and the Rz angle is the rotation angle of the saggar around the Z axis, specifically, the horizontal rotation, which is the core of the non-inclined working condition, but needs to assist in judging the overall attitude. The robot adjusts the spatial attitude of the execution end, such as the spatial state of the servo electric claw, to be synchronized with the saggar, so as to realize the grabbing of the target to-be-processed saggar in the tilted working condition.

[0037] In some embodiments: the target to-be-processed saggar is transported to the cleaning module for cleaning, comprising: The cleaning module is configured in advance based on the permanent magnet adsorption assembly, the negative pressure dust suction assembly, and the iron filings automatic separation module; The cleaning module is controlled to clean the target to-be-processed saggar based on the permanent magnet adsorption assembly, the negative pressure dust suction assembly, and the iron filings automatic separation module.

[0038] In this embodiment, the cleaning module described in the present application is configured in advance based on the permanent magnet adsorption assembly, the negative pressure dust suction assembly, and the iron filings automatic separation module, as shown in Figure 3 , so that the cleaning module can realize the functions of absorbing iron filings and impurities at the same time, and automatically collect the iron filings without manual disassembly and washing. Specifically, the permanent magnet adsorption assembly and the negative pressure dust suction assembly are configured in the same cleaning and demagnetizing machine, and the permanent magnet adsorption assembly and the negative pressure dust suction assembly are installed on the same XYZ axis lifting mechanism. The negative pressure dust suction assembly includes a negative pressure air pipe, a negative pressure motor, and a filter bag, as shown in Figure 4 . The XYZ axis lifting mechanism drives the negative pressure air pipe suction nozzle to enter the saggar cavity to suck and remove impurities, and simultaneously completes the iron filings adsorption (permanent magnet adsorption assembly) and the impurity suction (negative pressure dust suction assembly), avoiding manual step-by-step operation and eliminating cleaning blind spots. When the cleaning module is in a non-working state, the permanent magnet is driven by an electric cylinder to separate from the adsorption surface, realizing the automatic falling of the iron filings into the collection box, as shown in Figure 5 . The cleaning and demagnetizing machine is also provided with an iron filings automatic separation device, and the cleaning module further includes an automatic door mechanism. The opening and closing of the automatic door mechanism is in real-time synchronization with the action of the robot, and the automatic door mechanism and the robot and the moving module realize action synchronization through the communication protocol of the modbus TCP protocol.

[0039] The cleaning module is configured to generate a cleaning result when the cleaning of the target to-be-cleaned saggar is completed, the cleaning result including a pass or a fail, which is determined based on preset detection means, specifically including iron filings residue detection means, non-magnetic impurity detection means, and cleaning coverage rate detection means. If any of the three detection means fails, the cleaning result is a fail; otherwise, the cleaning result is a pass. When the cleaning result is a pass, the robot is controlled to place the target to-be-cleaned saggar in a specified area; or to transfer a saggar taken off a kiln line to a specified area, the specified area including a next work station, a temporary buffer area, a stacking area, and the like. If the cleaning result is a fail, a secondary cleaning instruction is automatically triggered, and the cleaning process is restarted by the sweeping and demagnetizing machine until the pass standard is met.

[0040] Iron filings residue detection means: a built-in magnetic flux sensor in a permanent magnet adsorption assembly of the sweeping and demagnetizing machine detects the change in magnetic flux before and after adsorption to determine the amount of iron filings adsorbed; at the same time, a collection box of an automatic iron filings separation device is equipped with a weight sensor to quantify the weight of collected iron filings, indirectly reflecting the iron filings residue in the saggar; non-magnetic impurity detection: a particulate matter sensor is arranged in the air pipe of the negative pressure dust suction assembly to detect the particle size and concentration of impurities in real time during the dust suction process; at the same time, an air pressure sensor at the outlet end of the filter bag monitors the change in air pressure to determine the amount of impurities accumulated in the filter bag, thereby assisting in evaluating the impurity removal effect; cleaning coverage rate detection: after cleaning is completed, the 3D vision system collects three-dimensional point cloud data inside the saggar again, compares the point cloud differences before and after cleaning through an AI algorithm, identifies blind areas (such as saggar corners and inner wall grooves) that are not cleaned, and calculates the cleaning coverage rate.

[0041] The uploading module described in the present application is used to receive and upload the grabbing result, the cleaning result, and the equipment state data obtained by monitoring the operation of the control system. The equipment state data includes joint temperature, current, vibration data of the mechanical arm, feedback data of the servo motor torque sensor, and fault alarm information such as joint temperature exceeding the standard and abnormal clamping force. Through real-time monitoring of the state of key components, combined with dynamic optimization of the task of the MES, potential faults are warned in advance, unplanned downtime is reduced, and the overall equipment utilization rate is improved. The grabbing result, the cleaning result, and the equipment state data obtained by monitoring the operation of the control system are uploaded to the MES system connected by the OPC UA protocol of the control system. The MES system completes the on- and off-line of the target to-be-processed saggar based on the cleaning result, and performs multi-dimensional analysis through a preset algorithm and rules, thereby generating processing information for the control system, such as calculating production effect, production quality, and equipment health analysis and task load analysis. Through adjusting the task priority, triggering abnormal early warning, and optimizing parameter setting, dynamic self-adaptation of the production process is realized, such as real-time display of the real-time running temperature and current of the robot. The running heat dissipation state and load state of the robot can be monitored in real time through data, and abnormal state of the robot can be observed in advance. When it is detected that the equipment state data is abnormal, a maintenance prompt or a degraded operation mode is automatically triggered. When the cleaning coverage rate of three consecutive saggars is less than 99%, the system analyzes that it is power attenuation of the negative pressure motor, immediately sends a negative pressure motor maintenance warning to the operator, and automatically adjusts the cleaning time (extends by 10 seconds) to temporarily ensure the cleaning effect. When the task is interrupted, the feeding task is preferentially allocated, and if the buffer on the saggar side exceeds the threshold value, an emergency saggar unloading task is allocated to realize traceability and intelligent decision-making of the whole production process.

[0042] The system described in the present application achieves the following effects: 1. Fundamental improvement of work efficiency Full-process automation closed loop eliminates manual handling, cleaning and other nodes, and the work cycle is shortened to less than 1 / 3 of the traditional mode.

[0043] 2. Quality risk source control Adaptive grabbing force and high-precision positioning avoid saggar collision and damage, and eliminate the risk of mixing fragments into products from the source.

[0044] 3. Breakthrough optimization of equipment collaboration Multi-device millisecond-level response forms a seamless operation chain, solving the efficiency loss caused by collaboration fragmentation in traditional solutions.

[0045] 4. Significant reduction in operation and maintenance cost Self-diagnosis system reduces sudden failures, modular design prolongs calibration period, and comprehensive operation and maintenance cost is reduced.

[0046] 5. Revolutionary enhancement of production flexibility AGV cross workshop scheduling and fixture quick switching, realize "one machine multi-line", adapt to the production demand of using different types of box.

[0047] 6. The quality leap of cleaning effect The composite cleaning module integrates the coverage of the inner wall of the box, and the impurity removal rate is close to complete, far exceeding the effect of manual step-by-step operation.

[0048] Embodiment 2 The application also provides a robot control method for box online and offline, as shown in Figure 6 As shown in a flowchart of a robot control method for box online and offline, the function realized by the robot control method for box online and offline corresponds to the above-mentioned robot control system for box online and offline implemented on a terminal device. The robot control method for box online and offline provided by the application, the method comprises: S601, identifying the position information of a target to-be-processed box from a plurality of to-be-processed boxes in a to-be-worked region through a vision module; S602, the robot cooperates with the preset movement module to generate a grabbing result by grabbing the target to-be-processed box in the working area according to the position information, and transmits the target to-be-processed box to the cleaning module for cleaning; S603, when the cleaning for the target to-be-processed box is completed, the cleaning module generates a cleaning result, and controls the robot to place the target to-be-processed box to a designated area; S604, receiving and uploading the grabbing result, the cleaning result and the equipment state data obtained by monitoring the control system to complete the online and offline of the target to-be-processed box, and generating processing information for the control system.

[0049] The effect realized by the robot control method for box online and offline corresponds to the effect produced by the above-mentioned robot control system for box online and offline implemented on a terminal device, which will not be described here.

[0050] Embodiment 3 The application also provides an electronic device, as shown in Figure 7 The electronic device comprises a processor 701, a memory 702 and a bus 703, the memory 702 stores machine readable instructions executable by the processor 701, when the electronic device is running, the processor 701 and the memory 702 communicate through the bus 703, and the machine readable instructions are executed by the processor 701 to execute the steps of the robot control method for box online and offline.

[0051] Embodiment 4 The application further provides a computer readable storage medium, which stores a computer program, and the computer program performs the steps of the robot control method for sagger online and offline when executed by a processor.

[0052] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in the application. In the several embodiments provided in the application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the modules is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual elements can be indirect coupling or communication connection through some communication interface, device or module, and can be electrical, mechanical or other forms.

[0053] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, i.e. can be located in one place or distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0054] In addition, the functional units in each embodiment of the application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0055] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the application essentially or the part of the prior art or the part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a platform server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the application. The foregoing storage medium includes: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk and various program code storage media.

[0056] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A robot control system for sagger loading and unloading, characterized by, The system comprises: a vision module configured to identify position information of a target to-be-processed saggar from a plurality of to-be-processed saggars in a to-be-processed region; a robot configured to, according to the position information, cooperate with a preset moving module to grab the target to-be-processed saggar in the to-be-processed region to generate a grabbing result, and transport the target to-be-processed saggar to a cleaning module for cleaning; the cleaning module configured to, when the cleaning for the target to-be-processed saggar is completed, generate a cleaning result, and control the robot to place the target to-be-processed saggar to a designated region; an uploading module configured to receive and upload the grabbing result, the cleaning result, and equipment state data obtained by monitoring the control system to complete the on- and off-line of the target to-be-processed saggar, and generate processing information for the control system.

2. The system of claim 1, wherein, The robot configured to, according to the position information, cooperate with a preset moving module to grab the target to-be-processed saggar in the to-be-processed region to generate a grabbing result, comprises: According to the position information and a production environment in which the plurality of to-be-processed saggars are located, the robot dynamically plans a global path and a local offset path; Based on the global path and the local offset path, the robot is controlled to cooperate with the moving module to grab the target to-be-processed saggar.

3. The system of claim 2, wherein, The control of the robot and the moving module to cooperate to grab the target to-be-processed saggar comprises: Based on the global path, the moving module is controlled to move the robot to the to-be-processed region; After reaching the to-be-processed region, based on a plurality of parameter data of the target to-be-processed saggar and the local offset path, the clamping force of the robot is dynamically adjusted to grab the target to-be-processed saggar.

4. The system of claim 3, wherein, The dynamic adjustment of the clamping force of the robot to grab the target to-be-processed saggar comprises: A difference between an attitude angle of the target to-be-processed saggar and a preset threshold value is calculated to determine whether the difference is in an inclined working condition; If yes, the spatial state of an execution end of the robot is adjusted according to the difference to grab the target to-be-processed saggar.

5. The system of claim 1, wherein, The vision module configured to identify position information of a target to-be-processed saggar from a plurality of to-be-processed saggars in a to-be-processed region comprises: Stacked point cloud data of the plurality of to-be-processed saggars is captured, and the stacked point cloud data is dynamically segmented to obtain saggar point cloud data corresponding to the plurality of to-be-processed saggars respectively; The spatial coordinates of the saggar point cloud data are calculated to generate the position information of the target to-be-processed saggar.

6. The system of claim 5, wherein, The dynamic segmentation of the stacked point cloud data to obtain saggar point cloud data corresponding to the plurality of to-be-processed saggars respectively comprises: Sample point cloud data of saggars in actual production under stacking, tilting, and shielding working conditions is pre-collected to construct a plurality of features based on the sample point cloud data; A point cloud segmentation model is trained based on the plurality of features to dynamically segment the stacked point cloud data based on the point cloud segmentation model.

7. The system of claim 1, wherein, The transportation of the target to-be-processed saggar to the cleaning module for cleaning comprises: The cleaning module is pre-configured based on a permanent magnet adsorption assembly, a negative pressure dust suction assembly, and a ferrous metal automatic separation module; The cleaning module controlled to complete cleaning of the target kiln based on the permanent magnet adsorption assembly, the negative pressure dust collection assembly, and the iron scrap automatic separation module.

8. A robot control method for sagger loading and unloading, characterized by, The method comprises: identifying position information of a target kiln to be processed from a plurality of kilns to be processed in a to-be-operated area by a vision module; a robot cooperates with a preset movement module to grab the target kiln to be processed in the operation area according to the position information to generate a grabbing result, and transfers the target kiln to be processed to a cleaning module for cleaning; when the cleaning of the target kiln to be processed is completed, the cleaning module generates a cleaning result, and controls the robot to place the target kiln to be processed to a designated area; receiving and uploading the grabbing result, the cleaning result, and equipment state data obtained by monitoring and controlling the system to complete the on- and off-line of the target kiln to be processed, and generate processing information for the control system.

9. An electronic device, comprising: comprises: a processor, a memory, and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating through the bus when the electronic device is running, and the machine-readable instructions being executed by the processor to perform the steps of the robot control method for on- and off-line of kilns according to claim 8.

10. A computer-readable storage medium, characterized in that, The computer program stored on the computer readable storage medium is executed by the processor to perform the steps of the robot control method for on- and off-line of kilns according to claim 8.

Images