A Method, Equipment and Medium for Identifying and Conveying Steel Coils in a Steel Mill

Abstract

The present invention discloses a method, device and medium for identifying and transporting steel coils in a steel plant, belonging to the technical field of rail transportation of steel coils, and is used to solve the technical problems that in the short-distance rail transportation of existing inventory steel coils, the manual identification efficiency of various steel coils in the warehouse inventory is low, and the transportation of manually following and controlling the rail vehicle is relatively unsafe, which is likely to affect the transportation safety and efficiency of steel coils. The method includes: identifying the positions of the steel coils stored in the warehouse according to the processing requirement information of the workshop to obtain the steel coil position information; performing feature calibration based on three-dimensional laser scanning on the target steel coils corresponding to the steel coil position information; performing contour recognition and spatial coordinate calculation on the target steel coils to determine the grasping position information of the target steel coils; performing placement area detection on the acquired target steel coil images to obtain area detection result information; and controlling the operation of the rail vehicle according to the environmental factor information to obtain the driving state information of the rail vehicle.

Description

Technical Field

[0001] This application relates to the field of rail transportation of steel coils, and particularly to a method, device and medium for identifying and transporting steel coils in stock in a steel plant. Background Art

[0002] As a traditional industry, the steel industry needs to gradually transform into a smart industry and a digital industry under the promotion of economic globalization and product digitization. The construction of an intelligent steel plant requires intelligent logistics for the steel production process. The transportation of steel coils between various warehouses and workshops in existing steel plants often requires trucks or electric flat cars to achieve the transfer and transportation of steel coils. Between short-distance warehouses and workshops, generally, the corresponding steel coils need to be selected according to the required orders, the steel coils are grabbed by a crane, and then transported by a rail car. With the help of workers, they move along with the rail car in real time to control the vehicle speed and monitor the environmental safety near the transported steel coils. The manual identification and search for steel coils greatly reduce the identification efficiency of each steel coil in the inventory, and at the same time, it is easy to produce deviations. The manual follow-up transportation of the rail car requires a lot of time, and the forward movement of the trolley and the monitoring of roadblocks need to be controlled manually, which further affects the transportation safety and efficiency of the steel coils and is not conducive to protecting the personal safety of the transportation workers. Summary of the Invention

[0003] The embodiments of this application provide a method, device and medium for identifying and transporting steel coils in stock in a steel plant, which are used to solve the following technical problems: In the short-distance rail transportation of existing steel coils in stock, the manual identification efficiency of various steel coils in the warehouse inventory is low, and the transportation of manually following and controlling the rail car is relatively unsafe, which is likely to affect the transportation safety and efficiency of the steel coils.

[0004] The embodiments of this application adopt the following technical solutions:

[0005] On the one hand, an embodiment of the present application provides a method for identifying and transporting steel coils in a steel plant, including: identifying the positions of the steel coils stored in the warehouse according to the processing requirement information of the workshop to obtain the steel coil position information; performing feature calibration based on three-dimensional laser scanning on the target steel coils corresponding to the steel coil position information; and based on the calibrated point cloud feature data, performing contour recognition and spatial coordinate calculation on the target steel coils to determine the grasping position information of the target steel coils; based on the grasping position information, and through a preset electric horizontal coil gripper, placing the target steel coils in a rail car, and performing placement area detection on the acquired target steel coil images to obtain area detection result information; wherein, the area detection result information includes: detection pass information and detection failure information; based on the detection pass information, and according to the environmental factor information around the track, performing operation control on the rail car to obtain the driving state information of the rail car; according to the driving state information, controlling the rail car to perform an alarm response so that the rail car completes automatic transportation.

[0006] In the embodiment of the present application, through laser scanning technology, the positions of various steel coils in the warehouse are identified, and the spatial positions of each steel coil after positioning are accurately determined to obtain the coordinate positions that need to be clamped. Then, through the automatic operation of the rail car and speed control based on the environmental factors around the track, the safe transportation of the rail car is realized, preventing emergencies and dangerous transportation. The automatic identification efficiency of various steel coils in the warehouse inventory is improved, the relatively unsafe manual following and control of the rail car transportation are avoided, the transportation safety and efficiency of the steel coils are enhanced, the degree of manual participation is reduced, and the work safety of the staff is further improved.

[0007] In a feasible implementation manner, identifying the positions of the steel coils stored in the warehouse according to the processing requirement information of the workshop to obtain the steel coil position information specifically includes: obtaining the processing requirement information of the workshop through a warehouse management system; wherein, the processing requirement information at least includes: steel coil model, steel coil quality, steel coil weight, and steel coil size; tabulating the processing requirement information to generate a processing requirement form; inputting the processing requirement form into a preset steel coil storage database, and through the steel coil storage database, querying and processing the steel coil parameters in the processing requirement form to match the steel coil labels and corresponding steel coil row and column positions that meet the requirement parameters; wherein, the steel coil storage database pre-stores the steel coil parameters, steel coil labels, and steel coil row and column positions of each steel coil; based on the steel coil labels and the steel coil row and column positions, determining the steel coil position information corresponding to the processing requirement information.

[0008] In a feasible implementation manner, performing feature calibration based on three-dimensional laser scanning on the target steel coil corresponding to the steel coil position information specifically includes: through a pan-tilt three-dimensional laser scanner installed in a steel mill warehouse, performing surface scanning processing on the storage area of the target steel coil regarding the three-dimensional contours of a number of steel coils to obtain a spherical coordinate set of a number of the target steel coils; determining a rectangular coordinate set of a number of the target steel coils based on the row and column positions of the steel coils in the steel coil storage database; according to the coordinate conversion relationship between the spherical coordinate set and the rectangular coordinate set, collecting point cloud of the surface contour information of a number of the target steel coils to obtain three-dimensional point cloud data; wherein, the surface contour information includes: top-down angle surface information, front-view angle surface information, and side-view angle surface information; according to the preset angle reference lines of the steel mill warehouse, performing feature calibration on the three-dimensional point cloud data under the rotation angle and visual position to obtain calibrated point cloud feature data; wherein, the preset angle reference lines include: heading angle reference line, pitch angle reference line, and roll angle reference line; wherein, the point cloud feature data is the pitch angle calibration feature data, roll angle calibration feature data, heading angle calibration feature data, X-axis position calibration feature data, Y-axis position calibration feature data, and Z-axis position calibration feature data of the target steel coil.

[0009] In a feasible implementation manner, according to the calibrated point cloud feature data, performing contour recognition and spatial coordinate calculation on the target steel coil to determine the grasping position information of the target steel coil, specifically including: through a preset normal vector estimation algorithm, and according to the X-axis position calibration feature data, Y-axis position calibration feature data, and Z-axis position calibration feature data in the point cloud feature data, performing surface normal vector estimation calculation on the target steel coil to obtain surface normal vector data; according to the surface normal vector data, re-labeling the contour features of the target steel coil to obtain contour space coordinate data; wherein, the contour space coordinate data is the space coordinate data of the three-view surface of the contour in the target steel coil; according to the pitch angle calibration feature data, roll angle calibration feature data, and heading angle calibration feature data in the point cloud feature data, performing spatial coordinate calculation on the surface curvature of the target steel coil regarding the spatial coordinates of bending feature points to obtain bending space coordinate data; wherein, the bending space coordinate data is the space coordinate data of the edge surface contour in the target steel coil; fitting the contour space coordinate data and the bending space coordinate data to determine the overall spatial coordinate set of the target steel coil; according to the parameter ratio of the steel coil core and the steel coil edge of the target steel coil, positioning the coordinate position of the core in the overall spatial coordinate set to determine the grasping position information of the target steel coil; wherein, the grasping position information is the clamping position information of the electric horizontal coil gripper.

[0010] In a feasible implementation manner, based on the grasping position information and by using a preset electric horizontal coil gripper, the target steel coil is placed in the rail vehicle, which specifically includes: controlling the bridge crane to move based on the steel coil position information so that the bridge crane moves to the clamping position of the target steel coil; controlling the electric horizontal coil gripper to clamp according to the grasping position information; placing the clamped target steel coil on the saddle of the rail vehicle through the bridge crane; wherein the rail vehicle is located in a designated area of the warehouse; taking a photo of the target steel coil on the rail vehicle by using an industrial camera installed at the top of the warehouse to obtain the target steel coil image; wherein the target steel coil image includes steel coil edge information and platform edge information of the rail vehicle.

[0011] In a feasible implementation manner, performing placement area detection on the obtained target steel coil image to obtain area detection result information, which specifically includes: performing gray processing on the target steel coil image to obtain a gray steel coil image; calculating gradient values for both the steel coil edge information and the platform edge information in the gray steel coil image through an edge detection algorithm to respectively determine the steel coil edge pixels and the platform edge pixels; performing double-threshold processing on the steel coil edge pixels and the platform edge pixels, and respectively connecting the edges of the steel coil edge pixels and the platform edge pixels after the double-threshold processing to respectively obtain a steel coil edge boundary and a platform edge boundary; calculating the minimum line spacing between the coil edge boundary and the platform edge boundary to obtain a first spacing distance; calculating the numerical difference between the first spacing distance and a first preset threshold to obtain a spacing difference; if the spacing difference is greater than a second preset threshold and less than a third preset threshold, determining the area detection result information as passing detection information; otherwise, determining the area detection result information as failing detection information, and re-placing the clamped target steel coil through the bridge crane until the spacing difference is greater than the second preset threshold and less than the third preset threshold.

[0012] In a feasible implementation manner, based on the detected passing information and according to the environmental factor information around the track, the running of the rail vehicle is controlled to obtain the driving state information of the rail vehicle, which specifically includes: when the area detection result information is the detected passing information, starting the rail vehicle; and acquiring the initial running speed of the rail vehicle; wherein, the predetermined constant running speed of the rail vehicle is the initial running speed; by using millimeter-wave radars installed on both sides of the transport track, the movement of various obstacles in the environment of the transport track is recognized to obtain real-time obstacle information; wherein, the real-time obstacle information includes: real-time position coordinate information of the obstacle, real-time movement direction vector information, and real-time movement speed information; based on the real-time obstacle information, determining the dangerous moving area of the obstacle; judging the uniform deceleration of the initial running speed according to the overlapping area between the dangerous moving area and the transport track area; if the overlapping area is less than or equal to a fourth preset threshold, the rail vehicle does not perform uniform deceleration control, and the first driving state information of the rail vehicle is obtained; if the overlapping area is greater than the fourth preset threshold and less than a fifth preset threshold, determining the uniform deceleration acceleration of the rail vehicle according to the overlapping ratio of the overlapping area to the transport track area, and performing uniform deceleration control on the rail vehicle according to the uniform deceleration acceleration to obtain the second driving state information of the rail vehicle; if the overlapping area is greater than or equal to the fifth preset threshold, performing deceleration control on the rail vehicle with the maximum acceleration until the rail vehicle stops moving, and determining it as the third driving state information of the rail vehicle; wherein, the driving state information includes: the first driving state information, the second driving state information, and the third driving state information.

[0013] In a feasible implementation manner, according to the driving state information, controlling the rail vehicle to perform an alarm response so that the rail vehicle completes automatic transportation, which specifically includes: if the driving state information is the first driving state information, the warning frame light of the rail vehicle is a green strobe response; if the driving state information is the second driving state information, the warning frame light of the rail vehicle is a yellow strobe response; by using a voice module installed on the rail vehicle, sending out a voice alarm message and generating a first monitoring log, and sending it to the warehouse management system; if the driving state information is the third driving state information, the warning frame light of the rail vehicle is a red strobe response and a second monitoring log is generated; sending the second monitoring log to the mobile terminal of the staff so that the staff can monitor the running state of the rail vehicle in real time.

[0014] Second aspect, an embodiment of the present application further provides an identification and conveying device for inventory steel coils in a steel plant, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to execute an identification and conveying method for inventory steel coils in a steel plant according to any of the above embodiments.

[0015] Third aspect, an embodiment of the present application further provides a non-volatile computer storage medium, characterized in that the storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each program comprising instructions which, when executed by a terminal, cause the terminal to execute an identification and conveying method for inventory steel coils in a steel plant according to any of the above embodiments.

[0016] The present application provides an identification and conveying method, device and medium for inventory steel coils in a steel plant. Compared with the prior art, the embodiments of the present application have the following beneficial technical effects:

[0017] In the embodiment of the present application, through laser scanning technology, the positions of various steel coils in the warehouse are identified, and the spatial positions of each steel coil after positioning are accurately determined to obtain the coordinate positions that need to be clamped. Then, through the automatic operation of the rail trolley and speed control based on the environmental factors around the rail, safe transportation of the rail trolley is achieved, preventing emergencies and dangerous transportation. The automatic identification efficiency of various steel coils in the warehouse inventory is improved, the relatively unsafe manual following and control of the rail trolley transportation is avoided, the transportation safety and efficiency of the steel coils are enhanced, the degree of manual participation is reduced, and the work safety of the staff is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. In the drawings:

[0019] Figure 1 is a flowchart of an identification and conveying method for inventory steel coils in a steel plant provided by an embodiment of the present application;

[0020] Figure 2 is a schematic structural diagram of an identification and conveying device for inventory steel coils in a steel plant provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To enable those skilled in the art to better understand the technical solutions in this application, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0022] The embodiments of this application provide a method for identifying and conveying steel coils in a steel mill inventory, as Figure 1 shown, the method for identifying and conveying steel coils in a steel mill inventory specifically includes steps S101 - S105:

[0023] It should be noted that when the steel mill transports steel coils, it usually adopts a manual method. This operation method requires the close cooperation between the bridge crane (hereinafter referred to as the bridge machine) driver and the ground commander. The labor intensity of workers is high, and the positioning accuracy depends on the visual inspection and experience judgment of workers, resulting in inaccurate positioning of the positions where the steel coils need to be placed. There are often situations where the placement is not in place and the clamp damages the steel coils, posing safety hazards.

[0024] S101. According to the processing requirement information of the workshop, identify the positions of the steel coils stored in the warehouse to obtain the steel coil position information.

[0025] Specifically, through the warehouse management system, obtain the processing requirement information of the workshop. Among them, the processing requirement information at least includes: steel coil model, steel coil quality, steel coil weight, and steel coil size.

[0026] Furthermore, tabulate the processing requirement information to generate a processing requirement form. Input the processing requirement form into the preset steel coil storage database, and through the steel coil storage database, query and process the steel coil parameters in the processing requirement form to match the steel coil labels and the corresponding steel coil row and column positions that meet the requirement parameters. Among them, the steel coil storage database pre - stores the steel coil parameters, steel coil labels, and steel coil row and column positions of each type of steel coil.

[0027] Furthermore, based on the steel coil label and the steel coil row and column position, determine the steel coil position information corresponding to the processing requirement information.

[0028] In one embodiment, each steel coil in the warehouse has its own steel coil label, and each type of steel coil is arranged in rows and columns for easy classification storage. First, according to the processing requirement information in the processing requirement order of the workshop, identify and locate the suitable type of steel coil, and then, based on the steel coil label and the steel coil row and column position, determine the target steel coil corresponding to the processing requirement information, and generate the steel coil position information of the target steel coil.

[0029] S102. Calibrate the target steel coil corresponding to the steel coil position information based on three-dimensional laser scanning. Then, based on the calibrated point cloud feature data, identify the contour of the target steel coil and calculate its spatial coordinates to determine the grasping position information of the target steel coil.

[0030] Specifically, first, use the pan-tilt three-dimensional laser scanner installed in the steel mill warehouse to perform surface scanning on the storage area of the target steel coil for the three-dimensional contours of several steel coils, and obtain the spherical coordinate sets of several target steel coils.

[0031] Furthermore, based on the row and column positions of the steel coils in the steel coil storage database, determine the rectangular coordinate sets of several target steel coils. According to the coordinate conversion relationship between the spherical coordinate set and the rectangular coordinate set, collect the surface contour information of several target steel coils to obtain three-dimensional point cloud data. Among them, the surface contour information includes: top-down angle surface information, front-view angle surface information, and side-view angle surface information.

[0032] Furthermore, according to the preset angle reference lines in the steel mill warehouse, perform feature calibration on the three-dimensional point cloud data under the rotation angle and visual position to obtain the calibrated point cloud feature data. Among them, the preset angle reference lines include: heading angle reference line, pitch angle reference line, and roll angle reference line. Among them, the point cloud feature data is the pitch angle calibration feature data, roll angle calibration feature data, heading angle calibration feature data, X-axis position calibration feature data, Y-axis position calibration feature data, and Z-axis position calibration feature data of the target steel coil.

[0033] In one embodiment, the Z-axis of the coordinate system in the coordinate positioning and recognition system is perpendicular to the ground upwards. Select an object parallel to the X-axis or Y-axis as the heading angle (α) calibration reference line, and select the horizontal plane of the warehouse as the pitch angle (β) and roll angle (γ) calibration reference plane. Measure the angles α, β, γ between the corresponding visual coordinate system and the system coordinate system, and then implement angle calibration based on the rotation matrix and rotation formula. In the visual coordinate system, select a reference point P0(x0, y0, z0). At the same time, measure the coordinates P(x, y, z) of P0 in the coordinate positioning and recognition system. Calculate the displacement differences ΔX, ΔY, ΔZ from P0 in the visual coordinate system to P in the system coordinate system, and finally obtain the calibrated point cloud feature data under the rotation angle and visual position.

[0034] Furthermore, then use the preset normal vector estimation algorithm, and based on the X-axis position calibration feature data, Y-axis position calibration feature data, and Z-axis position calibration feature data in the point cloud feature data, perform surface normal vector estimation calculation on the target steel coil to obtain surface normal vector data.

[0035] Further, based on the surface normal data, relabel the contour features of the target steel coil to obtain the contour space coordinate data. Among them, the contour space coordinate data are the space coordinate data of the three-view surfaces of the contour in the target steel coil.

[0036] Further, according to the pitch angle calibration feature data, roll angle calibration feature data, and heading angle calibration feature data in the point cloud feature data, calculate the spatial coordinates of the bending feature points related to the surface curvature of the target steel coil to obtain the bending space coordinate data. Among them, the bending space coordinate data are the space coordinate data of the edge surface contour in the target steel coil.

[0037] Further, perform data fitting on the contour space coordinate data and the bending space coordinate data to determine the overall spatial coordinate set of the target steel coil.

[0038] Further, according to the parameter ratio between the coil core and the coil edge of the target steel coil, locate the coordinate position of the coil core in the overall spatial coordinate set to determine the grasping position information of the target steel coil. Among them, the grasping position information is the clamping position information of the electric horizontal coil gripper.

[0039] In one embodiment, the amount of three-dimensional point cloud data of the target surface contour collected by lidar scanning is very large and not easy to directly process. Through normal estimation and surface curvature processing, it is possible to simplify the point cloud data while retaining the geometric features of the point cloud data, greatly reducing the workload of coordinate calculation. Normal estimation is an important geometric property of the target contour. There are two common methods to obtain the surface normal estimation of point cloud data. Calculating the normal of a point on the surface of the point cloud data is approximately the normal of a tangent plane on the surface of the estimated point. Its core is the least squares plane fitting estimation. Then, using the surface normal data after fitting estimation, relabel the contour features of the target steel coil to obtain the contour space coordinate data. Then, calculate the spatial coordinates of the bending feature points related to the surface curvature of the target steel coil to obtain the bending space coordinate data, and finally determine the overall spatial coordinate set of the target steel coil.

[0040] S103. Based on the grasping position information, use the preset electric horizontal coil gripper to place the target steel coil in the rail vehicle, and perform placement area detection on the acquired target steel coil image to obtain the area detection result information. Among them, the area detection result information includes: detection pass information and detection failure information.

[0041] Specifically, based on the steel coil position information, control the bridge crane to move so that the bridge crane moves to the clamping position of the target steel coil. And according to the grasping position information, control the electric horizontal coil gripper to clamp.

[0042] Further, use the bridge crane to place the clamped target steel coil on the saddle of the rail vehicle. Among them, the rail vehicle is located in the designated area of the warehouse.

[0043] Further, an industrial camera installed at the top of the warehouse takes pictures of the target steel coil on the rail car to obtain a target steel coil image. Among them, the target steel coil image includes the steel coil edge information and the platform edge information of the rail car.

[0044] Further, the target steel coil image is subjected to grayscale processing to obtain a grayscale steel coil image. Through an edge detection algorithm, gradient values are calculated for both the steel coil edge information and the platform edge information in the grayscale steel coil image, and the steel coil edge pixels and the platform edge pixels are respectively determined.

[0045] Further, double-threshold processing is performed on the steel coil edge pixels and the platform edge pixels, and the steel coil edge pixels and the platform edge pixels after double-threshold processing are respectively subjected to edge connection to obtain a steel coil edge boundary and a platform edge boundary.

[0046] Further, the minimum line spacing between the coil edge boundary and the platform edge boundary is calculated to obtain a first spacing distance. A numerical difference calculation is performed between the first spacing distance and a first preset threshold to obtain a spacing difference.

[0047] If the spacing difference is greater than a second preset threshold and less than a third preset threshold, the area detection result information is determined as detection passed information.

[0048] Otherwise, the area detection result information is determined as detection failed information, and the target steel coil after being clamped is re-placed by the bridge crane until the spacing difference is greater than the second preset threshold and less than the third preset threshold.

[0049] As a feasible implementation manner, judging the spacing between the steel coil edge boundary and the platform edge boundary in the target steel coil image can better judge the positional relationship of the steel coil placed on the rail car, preventing the target steel coil from tilting or having an unstable center of gravity, etc.

[0050] S104. Based on the detection passed information and according to the environmental factor information around the track, the operation of the rail car is controlled to obtain the driving state information of the rail car.

[0051] Specifically, when the area detection result information is detection passed information, the rail car is started. And the initial running speed of the rail car is obtained. Among them, the predetermined constant running speed of the rail car is the initial running speed.

[0052] Further, millimeter-wave radars installed on both sides of the transport track are used to identify the movement of various obstacles in the environment of the transport track to obtain real-time obstacle information. Among them, the real-time obstacle information includes: the real-time position coordinate information, the real-time movement direction vector information, and the real-time movement speed information of the obstacle.

[0053] Further, based on the real-time obstacle information, determine the dangerous movement area of the obstacle. According to the overlapping area between the dangerous movement area and the transportation track area, perform a uniform deceleration judgment on the initial running speed.

[0054] If the overlapping area is less than or equal to the fourth preset threshold, the rail vehicle does not perform uniform deceleration control, and the first driving state information of the rail vehicle is obtained.

[0055] If the overlapping area is greater than the fourth preset threshold and less than the fifth preset threshold, determine the uniform deceleration acceleration of the rail vehicle according to the overlapping ratio of the overlapping area to the transportation track area, and perform uniform deceleration control on the rail vehicle according to the uniform deceleration acceleration to obtain the second driving state information of the rail vehicle.

[0056] If the overlapping area is greater than or equal to the fifth preset threshold, perform deceleration control on the rail vehicle with the maximum acceleration until the rail vehicle stops moving, and determine it as the third driving state information of the rail vehicle.

[0057] Among them, the driving state information includes: the first driving state information, the second driving state information, and the third driving state information.

[0058] As a feasible implementation method, through the millimeter-wave radars on both sides of the track, it is possible to timely monitor the environmental obstacles on both sides of the track during the operation of the rail vehicle, such as workers walking or transport carts passing by, etc. Judge the overlapping area between the dangerous movement area of the obstacle and the transportation track area. According to the size of the overlapping area, it is possible to well judge the distance between the obstacle and the track, thereby changing the running speed of the rail vehicle, and then obtaining the first driving state information, the second driving state information, and the third driving state information of the rail vehicle, etc., to realize the operation control of the rail vehicle.

[0059] S105. Control the rail vehicle to perform an alarm response according to the driving state information, so that the rail vehicle completes automatic transportation.

[0060] Specifically, if the driving state information is the first driving state information, the warning frame light of the rail vehicle is a green strobe response.

[0061] If the driving state information is the second driving state information, the warning frame light of the rail vehicle is a yellow strobe response. Through the voice module installed on the rail vehicle, send out a voice warning message and generate a first monitoring log, and send it to the warehouse management system.

[0062] If the driving state information is the third driving state information, the warning frame light of the rail vehicle is a red strobe response, and a second monitoring log is generated. Send the second monitoring log to the mobile terminal of the staff so that the staff can monitor the running state of the rail vehicle in real time.

[0063] In addition, the embodiments of the present application also provide an identification and conveying device for the steel coils in the steel mill, such as Figure 2 shown. The identification and conveying device 200 for the steel coils in the steel mill specifically includes:

[0064] At least one processor 201. And, a memory 202 communicatively connected to the at least one processor 201. Wherein, the memory 202 stores instructions that can be executed by the at least one processor 201, so that the at least one processor 201 can execute:

[0065] Based on the processing requirement information of the workshop, identify the positions of the steel coils stored in the warehouse to obtain the steel coil position information;

[0066] Perform feature calibration on the target steel coil corresponding to the steel coil position information based on three-dimensional laser scanning; and based on the calibrated point cloud feature data, perform contour recognition and spatial coordinate calculation on the target steel coil to determine the grasping position information of the target steel coil;

[0067] Based on the grasping position information, and through a preset electric horizontal coil gripper, place the target steel coil in the rail car, and perform placement area detection on the acquired target steel coil image to obtain area detection result information; wherein, the area detection result information includes: detection pass information and detection failure information;

[0068] Based on the detection pass information, and according to the environmental factor information around the track, perform operation control on the rail car to obtain the driving state information of the rail car;

[0069] According to the driving state information, control the rail car to perform alarm response, so that the rail car completes automatic transportation.

[0070] In the present application, through laser scanning technology, the positions of various steel coils in the warehouse are identified, and the spatial positions of each steel coil after positioning are accurately determined to precisely determine the coordinate positions that need to be clamped. Then, through the automatic operation of the rail car and speed control based on the environmental factors around the track, the safe transportation of the rail car is realized, preventing emergencies and dangerous transportation. The automatic identification efficiency of various steel coils in the warehouse inventory is improved, the relatively unsafe manual following and control of the rail car transportation are avoided, the transportation safety and efficiency of the steel coils are enhanced, the degree of manual participation is reduced, and the work safety of the staff is further improved.

[0071] The embodiments in the present application are all described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0072] The device, medium, and method provided by the embodiments of the present application are in one-to-one correspondence. Therefore, the device and the medium also have beneficial technical effects similar to those of their corresponding methods. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device and the medium will not be elaborated here.

[0073] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a dedicated computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0075] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0077] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0078] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0079] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0081] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for identifying and conveying steel coils in a steel plant, characterized in that, The method includes: Identifying the positions of the steel coils stored in the warehouse according to the processing requirement information of the workshop to obtain the steel coil position information; Performing feature calibration on the target steel coils corresponding to the steel coil position information based on three-dimensional laser scanning, specifically including: Performing surface scanning processing on the storage area of the target steel coils regarding the three-dimensional contours of several steel coils through a pan-tilt three-dimensional laser scanner installed in the steel mill warehouse to obtain the spherical coordinate sets of several target steel coils; Determining the rectangular coordinate sets of several target steel coils based on the row and column positions of the steel coils in the steel coil storage database; Collecting point clouds of the surface contour information of several target steel coils according to the coordinate conversion relationship between the spherical coordinate sets and the rectangular coordinate sets to obtain three-dimensional point cloud data; wherein, the surface contour information includes: top-down angle surface information, front-view angle surface information, and side-view angle surface information; Performing feature calibration on the three-dimensional point cloud data under the rotation angle and visual position according to the preset angle reference lines of the steel mill warehouse to obtain the calibrated point cloud feature data; wherein, the preset angle reference lines include: heading angle reference line, pitch angle reference line, and roll angle reference line; wherein, the point cloud feature data is the pitch angle calibration feature data, roll angle calibration feature data, heading angle calibration feature data, X-axis position calibration feature data, Y-axis position calibration feature data, and Z-axis position calibration feature data of the target steel coils; and based on the calibrated point cloud feature data, performing contour recognition and spatial coordinate calculation on the target steel coils to determine the grasping position information of the target steel coils; Based on the grasping position information, placing the target steel coils into the rail vehicle through a preset electric horizontal coil gripper, and performing placement area detection on the obtained target steel coil images to obtain area detection result information; wherein, the area detection result information includes: detection passed information and detection failed information; Based on the detection passed information and according to the environmental factor information around the track, controlling the operation of the rail vehicle to obtain the driving state information of the rail vehicle; According to the driving state information, controlling the rail vehicle to perform an alarm response so that the rail vehicle completes automatic transportation.

2. The method for identifying and conveying steel coils in stock in a steel plant according to claim 1, characterized in that, Identifying the positions of the steel coils stored in the warehouse according to the processing requirement information of the workshop to obtain the steel coil position information, specifically including: Obtaining the processing requirement information of the workshop through the warehouse management system; wherein, the processing requirement information at least includes: steel coil model, steel coil quality, steel coil weight, and steel coil size; Tabulating the processing requirement information to generate a processing requirement form; Inputting the processing requirement form into a preset steel coil storage database, and querying and processing the steel coil parameters in the processing requirement form through the steel coil storage database to match the steel coil labels and corresponding steel coil row and column positions that meet the requirement parameters; wherein, the steel coil storage database pre-stores the steel coil parameters, steel coil labels, and steel coil row and column positions of each type of steel coil; Based on the steel coil label number and the row and column positions of the steel coil, determine the steel coil position information corresponding to the processing requirement information.

3. The identification and conveying method of the steel coils in stock in a steel plant according to claim 1, characterized in that, According to the calibrated point cloud feature data, perform contour recognition and spatial coordinate calculation on the target steel coil to determine the grasping position information of the target steel coil, specifically including: Through a preset normal vector estimation algorithm, and based on the X-axis position calibration feature data, Y-axis position calibration feature data, and Z-axis position calibration feature data in the point cloud feature data, perform surface normal vector estimation calculation on the target steel coil to obtain surface normal vector data; According to the surface normal vector data, re-label the contour features of the target steel coil to obtain contour space coordinate data; wherein, the contour space coordinate data is the spatial coordinate data of the three-view surface of the contour in the target steel coil; According to the pitch angle calibration feature data, roll angle calibration feature data, and heading angle calibration feature data in the point cloud feature data, perform spatial coordinate calculation of the bending feature points on the surface curvature of the target steel coil to obtain bending space coordinate data; wherein, the bending space coordinate data is the spatial coordinate data of the edge surface contour in the target steel coil; Perform data fitting on the contour space coordinate data and the bending space coordinate data to determine the overall spatial coordinate set of the target steel coil; According to the parameter ratio of the steel coil core to the steel coil edge of the target steel coil, perform coordinate position positioning of the core on the overall spatial coordinate set to determine the grasping position information of the target steel coil; wherein, the grasping position information is the clamping position information of the electric horizontal coil gripper.

4. A method for identifying and transporting steel coils in stock in a steel plant according to claim 1, characterized in that, Based on the grasping position information, and through a preset electric horizontal coil gripper, place the target steel coil in the rail car, specifically including: Based on the steel coil position information, control the bridge crane to move so that the bridge crane moves to the clamping position of the target steel coil; and according to the grasping position information, control the electric horizontal coil gripper to clamp; Through the bridge crane, place the clamped target steel coil on the saddle of the rail car; wherein, the rail car is located in the designated area of the warehouse; Take a photo of the target steel coil on the rail car through an industrial camera installed at the top of the warehouse to obtain the target steel coil image; wherein, the target steel coil image includes steel coil edge information and platform edge information of the rail car.

5. A method for identifying and conveying steel coils in stock in a steel plant according to claim 4, characterized in that, Perform placement area detection on the obtained target steel coil image to obtain area detection result information, specifically including: Perform grayscale processing on the target steel coil image to obtain a grayscale steel coil image; Through an edge detection algorithm, calculate the gradient values of both the steel coil edge information and the platform edge information in the grayscale steel coil image to respectively determine the steel coil edge pixels and the platform edge pixels; Perform double-threshold processing on the steel coil edge pixels and the platform edge pixels, and respectively connect the steel coil edge pixels and the platform edge pixels after double-threshold processing to respectively obtain the steel coil edge boundary and the platform edge boundary; Perform the minimum line spacing calculation on the coil edge boundary and the platform edge boundary to obtain the first spacing distance; Perform a numerical difference calculation between the first spacing distance and a first preset threshold to obtain a spacing difference; If the spacing difference distance is greater than a second preset threshold and less than a third preset threshold, determine the area detection result information as passed detection information; Otherwise, determine the area detection result information as failed detection information, and through the bridge crane, re-place the target steel coil after clamping until the spacing difference distance is greater than the second preset threshold and less than the third preset threshold.

6. The method for identifying and conveying steel coils in stock in a steel plant according to claim 1, wherein Based on the passed detection information, and according to the environmental factor information around the track, perform operation control on the rail vehicle to obtain the driving state information of the rail vehicle, specifically including: When the area detection result information is passed detection information, start the rail vehicle; and obtain the initial running speed of the rail vehicle; wherein, the predetermined constant running speed of the rail vehicle is the initial running speed; Through millimeter wave radars installed on both sides of the transport track, perform motion recognition of various obstacles in the environment of the transport track to obtain real-time obstacle information; wherein, the real-time obstacle information includes: real-time position coordinate information of the obstacle, real-time motion direction vector information, and real-time motion speed information; Based on the real-time obstacle information, determine the dangerous moving area of the obstacle; According to the overlapping area between the dangerous moving area and the transport track area, perform a uniform deceleration judgment on the initial running speed; If the overlapping area is less than or equal to a fourth preset threshold, the rail vehicle does not perform uniform deceleration control, and obtain the first driving state information of the rail vehicle; If the overlapping area is greater than the fourth preset threshold and less than a fifth preset threshold, determine the uniform deceleration acceleration of the rail vehicle according to the overlapping ratio of the overlapping area to the transport track area, and perform uniform deceleration control on the rail vehicle according to the uniform deceleration acceleration to obtain the second driving state information of the rail vehicle; If the overlapping area is greater than or equal to the fifth preset threshold, perform deceleration control on the rail vehicle with the maximum acceleration until the rail vehicle stops moving, and determine it as the third driving state information of the rail vehicle; Wherein, the driving state information includes: the first driving state information, the second driving state information, and the third driving state information.

7. A method for identifying and conveying steel coils in stock in a steel plant according to claim 1, characterized in that, According to the driving state information, control the rail vehicle to perform an alarm response so that the rail vehicle completes automatic transportation, specifically including: If the driving state information is the first driving state information, the warning frame light of the rail vehicle is a green strobe response; If the driving state information is the second driving state information, the warning frame light of the rail vehicle is a yellow strobe response; through a voice module installed on the rail vehicle, send out a voice alarm message, and generate a first monitoring log and send it to the warehouse management system; If the driving state information is the third driving state information, the warning frame light of the rail vehicle is a red strobe response, and generate a second monitoring log; send the second monitoring log to the mobile terminal of the staff so that the staff can monitor the running state of the rail vehicle in real time.

8. An identification and conveying device for steel coils in stock in a steel plant, characterized in that, The device includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor to enable the at least one processor to execute a method for identifying and conveying steel coils in stock in a steel mill according to any one of claims 1-7.

9. A non-volatile computer storage medium, characterized in that, The storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, and each program includes instructions which, when executed by a terminal, cause the terminal to execute a method for identifying and conveying steel coils in stock in a steel mill according to any one of claims 1-7.

Images