A steel coil yard material identification and automatic loading and unloading system and method

Abstract

This invention discloses a material identification and automatic loading / unloading system and method suitable for steel coil yards, including a first one-dimensional gimbal, a second one-dimensional gimbal, a first laser scanner, a second laser scanner, and first and second industrial control computers. The industrial control computers include an OPEN3D point cloud processing algorithm module and a gimbal and laser scanning control module. The first one-dimensional gimbal and the first laser scanner are responsible for collecting point cloud information of the steel coil warehouse in the yard, and the first industrial control computer processes the point cloud data to obtain the steel coil diameter and center coordinates. The second one-dimensional gimbal and the second scanner are responsible for collecting point cloud information of the truck parking area in the yard, and the second industrial control computer processes the point cloud data to obtain the vehicle type, the diameter and center coordinates of the steel coil on the vehicle, and the placement position, thus completing the automatic warehousing and loading / unloading of steel coils. This invention can be applied to the automated warehousing and positioning calculation of steel coils on vehicles during warehousing and the placement position calculation during unloading in steel coil yards, realizing automated warehousing and loading / unloading of steel coils.

Description

Technical Field

[0001] This invention relates to a stockyard management system, and more particularly to a material identification and automatic loading and unloading system and method suitable for steel coil stockyards. Background Technology

[0002] Currently, most steel companies need to store the produced steel coils in the yard instead of using them directly. Due to the large variety of steel coil specifications and the complex yard environment, steel coil management is prone to chaos and is difficult to identify.

[0003] The current methods for handling steel coils in stockpiles mainly rely on the following: Manual measurement by workers, who then communicate the specifications, handling information, and placement details of the steel coils to be handled to the truck driver. This requires real-time communication between truck drivers and drivers, resulting in high labor costs, high risks, and excessively long working hours. Image processing recognition methods are also used to obtain two-dimensional information about the steel coils and provide this information to workers for handling and placement. However, this method relies on worker expertise, and the images are easily affected by lighting conditions, leading to significant errors in recognition. Summary of the Invention

[0004] In view of this, the present invention provides a material identification and automatic loading and unloading system and method suitable for steel coil yards, which can be used for the identification and positioning of steel coils, saddles, and loading and unloading trucks in steel coil yards. It uses point cloud method for identification and positioning to realize the automated entry and exit of steel coils by grabbing and placing.

[0005] Therefore, the present invention provides the following technical solutions, including:

[0006] A material identification and automated loading / unloading system suitable for steel coil yards includes:

[0007] Install the first one-dimensional gimbal and laser scanner at an appropriate location on the road to collect point cloud information of the storage yard;

[0008] Install a second 1D gimbal and laser scanner at an appropriate location on the road to load and unload point cloud information from the truck;

[0009] The industrial control computer receives task instructions from the on-site WMS system, categorizes the tasks, controls the 1D pan-tilt unit and laser scanner to collect 3D point cloud data of the yard and loading / unloading trucks, uses the POIINTNET++ model to segment the vehicles and saddles in the yard, and uses the region growing algorithm to segment the steel coils.

[0010] A method for material identification and automated loading and unloading in steel coil yards includes:

[0011] Commands are sent from the industrial control computer to control the first and second pan-tilt units and the first and second laser scanners to collect yard data;

[0012] The recognition module is based on Convert two-dimensional polar coordinate point cloud data into three-dimensional point cloud data, where x, y, z are three-dimensional coordinate values, and r is the radial distance from the point to the origin in polar coordinates, provided by the lidar message; The polar angle is provided by the lidar message; The azimuth angle represents the angular resolution of the gimbal.

[0013] For the point cloud information of the stockyard, the recognition module uses a pass-through filtering algorithm to extract the region of interest A from the 3D point cloud data. Region A contains all the steel coils in the stockyard.

[0014] The radius filtering algorithm is used to filter region A to remove noise points in the point cloud data, thereby improving processing speed and point cloud accuracy.

[0015] The K-nearest neighbor algorithm is used to traverse all points, and in conjunction with the region growing algorithm, the curvature change between each point is calculated. Points with a change less than a threshold are considered to be the same steel coil. This process continues until all points have been traversed, and then the point cloud data of each steel coil can be obtained.

[0016] The point cloud of each steel coil is cylindrically fitted using the cylindrical equation and the RANSAC algorithm to obtain the center coordinates, radius, and orientation of each steel coil, thus completing the steel coil identification task.

[0017] For the point cloud information of loading and unloading trucks, the recognition module uses a pass-through filtering algorithm to extract the region of interest B from the 3D point cloud data. Region B contains the vehicle, saddle, and steel coils on the vehicle.

[0018] The radius filtering algorithm is used to filter region B, remove noise points in the point cloud data, and improve processing speed and point cloud accuracy.

[0019] The K-nearest neighbor algorithm is used to traverse all points, and RANSAC coarse registration and ICP fine registration are used to register the vehicles in region B with the vehicles in the dataset to obtain the current vehicle type and information.

[0020] The vehicle was segmented using a point cloud segmentation model in POINTNET++ to obtain the loading and unloading area C, which contains the point cloud of each saddle and each steel coil.

[0021] For the point cloud data of steel coils in region C, the cylindrical equation and RANSAC algorithm are used to perform cylindrical fitting on the point cloud of each steel coil to obtain the center coordinates, radius and orientation of each steel coil, thus completing the steel coil identification.

[0022] For the saddle point cloud data in region C, plane fitting is performed using the plane equation Ax+By+Cz+D=0 and the RANSAC algorithm to obtain the two plane equations of the saddle V-groove and the normal vectors L1 and L2 of the plane.

[0023] Find the intersection point A of L1 and L2, which is the estimated placement position of the steel coil, and complete the loading and unloading of the truck.

[0024] In addition, the yard material identification and automatic loading and unloading system needs to be calibrated once before use;

[0025] Three reflectors are placed below the gimbal and laser scanner. A plumb bob is placed on the trolley to measure the X1Y1Z1;X2Y2Z2;X3Y3Z3 coordinates of the reflectors using the trolley's Gramm-line system. The laser scanner is used to collect point cloud data of the reflectors. The point cloud data is processed to find the three point sets with the highest reflectivity. The centroids of these three point sets are calculated as x1y1z1; x2y2z2; x3y3z3. The three XYZ coordinates and the three xyz coordinates are transformed to obtain the calibration transformation matrix, thus completing the calibration task.

[0026] Advantages and positive effects of the present invention: The present invention provides a material identification and automatic loading and unloading system and method for steel coil yards. Without changing the original site and equipment, it adds a laser scanner, a pan-tilt unit and an industrial control computer, which reduces labor costs, improves work efficiency, shortens the work cycle, increases the safety factor, and realizes rapid and accurate steel coil identification, positioning and grabbing, and placement, thereby realizing intelligent management of steel coil yards. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of the 3D vision installation for data retrieval in an example of the present invention;

[0029] Figure 2 This is a schematic diagram of the 3D vision installation for outbound data retrieval in an example of the present invention;

[0030] Figure 3 This is a flowchart of the steel coil yard scanning process in an example of the present invention;

[0031] In the diagram, 1 represents the first 1D gimbal; 2 represents the first laser scanner; 3 represents the on-site crane; 4 represents the second 1D gimbal; 5 represents the second laser scanner; and 6 represents the on-site crane. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] This invention relates to a scanning and identification system and scanning method for a "smart electromagnetic crane" used in steel coil yard material handling equipment. The system is designed to enable unmanned, fully automated operation and autonomous sensing of the actual on-site conditions during production operations.

[0035] like Figure 1 and Figure 2 As shown, this invention proposes a material identification and automatic loading / unloading system suitable for steel coil yards, including a first one-dimensional gimbal, a second one-dimensional gimbal, a first laser scanner, a second laser scanner, and first and second industrial control computers. The industrial control computers include an OPEN3D point cloud processing algorithm module and a gimbal and laser scanning control module. The first one-dimensional gimbal and the first laser scanner are responsible for collecting point cloud information from the steel coil storage area in the yard, and the first industrial control computer processes the point cloud data to obtain the steel coil diameter and center coordinates. The second one-dimensional gimbal and the second scanner are responsible for collecting point cloud information from the truck parking area in the yard, and the second industrial control computer processes the point cloud data to obtain the vehicle type, the diameter and center coordinates of the steel coil on the vehicle, and its placement position, thus completing the automatic storage and loading / unloading of steel coils. The scanners need to be installed in a location with a wide field of vision to ensure that the vehicles in the yard and parking area are completely scanned during scanning.

[0036] A one-dimensional gimbal is a stabilizer that turns a laser scanner into a three-dimensional data generator. It stabilizes the laser scanner and generates three-axis data. After the laser scanner is installed, its horizontal position can be adjusted.

[0037] The industrial control computer includes an identification module that can communicate with the field PLC. The first industrial control computer's OPEN3D point cloud processing algorithm module processes the 3D point cloud data to provide the steel coil diameter and center coordinates. The second industrial control computer's OPEN3D point cloud processing algorithm module processes the 3D point cloud data to provide the vehicle type, steel coil diameter, center coordinates, and placement coordinates.

[0038] The above embodiments provide a material identification and automatic loading and unloading system suitable for steel coil yards. Without changing the original site and equipment, by adding equipment such as laser scanners, one-dimensional pan-tilt units and industrial control computers, labor costs are reduced, work efficiency is improved, work cycles are shortened, and safety factors are increased, so as to achieve fast and accurate steel coil identification, positioning, grabbing and placement, and realize intelligent management of steel plate yards.

[0039] like Figure 3 As shown, a method for material identification and automatic loading / unloading in steel coil yards includes the following specific steps:

[0040] Step S1: Receive the task sent by the PLC through the industrial control computer, and control the pan-tilt unit and laser scanner to collect 3D point cloud data on site;

[0041] Step S2: The industrial control computer's identification module processes the 3D point cloud data collected from the yard, providing the target steel coil diameter and center coordinate information, identifying the vehicle type, saddle position information, and providing steel coil placement information.

[0042] Step S3: The industrial control computer sends the above information to the field PLC, which controls the crane to move to the designated position to start grabbing and placing.

[0043] The industrial control computer identification module aims to identify the diameter, center coordinates, vehicle type, and placement location of the steel coil. This includes: using pass-through point cloud filtering to obtain the region of interest; using radius filtering to remove noise from the data; using RANSAC to segment and obtain point clouds of the steel coil library, vehicle, and saddle; using a region growing algorithm to segment the steel coil library point cloud to obtain the point cloud of each steel coil; using the cylinder equation to fit the point cloud of each steel coil to obtain the diameter and center coordinates of the steel coil; using RANSAC plane fitting to perform plane fitting on the saddle point cloud to obtain the plane equations and normal vectors on both sides of the saddle; and calculating the intersection of the normal vectors of the two planes to obtain the center coordinates of the steel coil.

[0044] In this embodiment of the invention, the RANSAC method is used to fit a straight line to the contour. RANSAC is an abbreviation for Random Sample Consensus, which is an algorithm that calculates the mathematical model parameters of a dataset containing outliers to obtain valid sample data. Compared with other methods for plane fitting, the RANSAC method can effectively remove outliers, select the global optimum for fitting, and reduce the error of the fitted straight line.

[0045] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A material identification and automatic loading / unloading system suitable for steel coil stockpiles, characterized in that, include: The first one-dimensional gimbal and the first laser scanner installed on the overhead crane above the steel coil warehouse in the stockyard are used to collect point cloud data of the steel coil warehouse. The second one-dimensional gimbal and the second laser scanner, installed above the parking area of ​​the yard, are used to collect point cloud data of the vehicles. An industrial control computer installed next to the first one-dimensional gimbal and the first laser scanner is used to acquire the steel coil radius, center position and control the first one-dimensional gimbal and the first laser scanner. An industrial control computer installed next to the second 1D gimbal and the second laser scanner is used to acquire vehicle type, radius and center coordinates of steel coil on the vehicle, placement position and control the second 1D gimbal and the second laser scanner. Based on point cloud data, information about the steel coil and its location were identified, including: The first gimbal and the first laser scanner for acquiring steel coils in the stockyard need to be moved to the preset parking area to perform coordinate calibration of the target area; The reflector is placed under the gimbal and laser scanner. A plumb bob is placed on the crane to measure the XYZ coordinates of the reflector. The laser scanner is used to collect point cloud data of the reflector. The industrial control computer processes the point cloud data to find the xyz of the point with the highest reflectivity. The XYZ coordinates and xyz coordinates are transformed to obtain the calibrated transformation matrix.

2. The material identification and automatic loading / unloading system for steel coil yards according to claim 1, characterized in that, Dustproof and waterproof protective covers are installed above the first and second laser scanners.

3. A method for material identification and automatic loading / unloading in steel coil yards, applied to the material identification and automatic loading / unloading system for steel coil yards as described in any one of claims 1-2, characterized in that, The method includes: The industrial control computer receives task instructions from the on-site PLC, and the gimbal and laser scanning control module of the industrial control computer controls the gimbal and laser scanner to collect data according to the task. The first industrial control computer's OPEN3D point cloud processing algorithm module processes 3D point cloud data to provide the steel coil's radius and center coordinates. The second industrial control computer's OPEN3D point cloud processing algorithm module processes the 3D point cloud data to provide the vehicle type, steel coil radius, center coordinates, and placement coordinates.

4. The method for material identification and automatic loading and unloading in steel coil yards according to claim 3, characterized in that, The RANSA segmentation method was used to extract targets of interest from the steel coil warehouse and parking area.

Images