Method, device, equipment and readable storage medium for detecting the positioning of raw material billets entering a furnace

Abstract

The present invention is a method, device, equipment and readable storage medium for detecting the position of raw material blanks entering a furnace. The method comprises the following steps: collecting point cloud data in a preset area in a three-dimensional coordinate system, wherein the preset area includes point cloud data at the location of the entrance of a heating furnace; detecting point cloud data corresponding to the end face of the raw material blank in the length direction; and determining whether the raw material blank moves to a predetermined position in the heating furnace. The present invention solves the technical problem that it is impossible to accurately detect whether the raw material blank has moved to the predetermined position after entering the heating furnace.

Description

Technical Field

[0001] The present invention relates to the technical field of rod and wire production, and further to a method, device, equipment and readable storage medium for detecting the positioning of a raw material billet entering a furnace, and in particular to a method, device, equipment and readable storage medium for detecting the positioning of a raw material billet entering a furnace based on point cloud analysis. Background Art

[0002] The raw material billet of rod and wire is usually a square billet with a cross-sectional side length of about 200mm and a length of about 10 meters. During the production process, the raw material billet needs to pass through a section of conveyor rollers before entering the heating furnace for heating. At present, after the raw material billet enters the furnace, it is difficult to determine whether the raw material billet is in place due to the lack of corresponding detection means. Once subsequent actions are performed without being in place, production abnormalities and other situations will occur. In severe cases, it may even cause equipment damage, resulting in huge losses.

[0003] At present, most of the rod and wire production lines are manually inspected by operators through monitoring videos to determine whether the raw material billets are in place, but this method has the following disadvantages:

[0004] 1. The work intensity is high, time-consuming and labor-intensive;

[0005] Second, the accuracy of visual inspection is limited, the error is large, and the accuracy rate is low;

[0006] 3. Unable to achieve automated closed-loop control, reducing production efficiency;

[0007] 4. It does not conform to the expected goal of reducing staff and increasing efficiency.

[0008] With regard to the problem in the related art that it is impossible to accurately detect whether the raw material blanks have been properly moved after entering the heating furnace, no effective solution has been given so far.

[0009] Therefore, the inventor, relying on many years of experience and practice in related industries, proposes a method, device, equipment and readable storage medium for detecting the positioning of raw material billets entering a furnace to overcome the defects of the prior art. Summary of the invention

[0010] The purpose of the present invention is to provide a method, device, equipment and readable storage medium for detecting the positioning of raw material billets entering the furnace. By using three-dimensional point cloud analysis technology, a laser radar is placed near the transport roller in front of the furnace to collect three-dimensional point cloud data of the raw material billets entering the heating furnace, and the position of the end of the raw material billet is automatically detected. Then, it can be determined whether the raw material billet has been put into place, thereby improving the accuracy and efficiency of raw material billet detection, and forming a closed-loop feedback control to complete subsequent operation control.

[0011] The purpose of the present invention can be achieved by adopting the following technical solutions:

[0012] The present invention provides a method for detecting the positioning of a raw material billet entering a furnace, comprising the following steps:

[0013] Collecting point cloud data within a preset area in a three-dimensional coordinate system, wherein the preset area includes point cloud data of a location where an entrance of a heating furnace is located;

[0014] Detecting point cloud data corresponding to the end surface of the raw material blank in the length direction;

[0015] It is determined whether the raw material blank moves to a predetermined position in the heating furnace.

[0016] In a preferred embodiment of the present invention, the point cloud data collected within a preset area in the three-dimensional coordinate system is a coordinate set of multiple position points in the three-dimensional coordinate system.

[0017] In a preferred embodiment of the present invention, the point cloud data within a preset area in the three-dimensional coordinate system is collected, and the preset area includes the point cloud data at the location of the heating furnace entrance and the point cloud data corresponding to the end face of the raw material blank in the length direction, and further includes:

[0018] Performing horizontal rotation correction on the three-dimensional coordinate system where the point cloud data in a preset area is located;

[0019] The coordinate origin of the three-dimensional coordinate system is transformed, rotated and corrected.

[0020] In a preferred embodiment of the present invention, the horizontal rotation correction of the three-dimensional coordinate system where the point cloud data in the preset area is located includes:

[0021] Selecting point cloud data of a horizontal reference object from the point cloud data within a preset area;

[0022] The three-dimensional coordinate system is horizontally rotated and corrected so that the point cloud data of the horizontal reference object is within the xy plane of the three-dimensional coordinate system or within a plane parallel to the xy plane of the three-dimensional coordinate system.

[0023] In a preferred embodiment of the present invention, the horizontal rotation correction of the three-dimensional coordinate system includes:

[0024] Detecting the plane where the horizontal reference object in the point cloud data within the preset area is located by a plane detection algorithm;

[0025] Obtaining a plane equation of the plane where the horizontal reference object is located;

[0026] According to the plane equation of the plane where the horizontal reference object is located and the rotation matrix solution algorithm, a rotation matrix for horizontal rotation correction of the three-dimensional coordinate system is obtained, and the rotation matrix is ​​the correction parameter;

[0027] The point cloud data in the preset area is multiplied by the correction parameter to obtain the point cloud data in the preset area after horizontal rotation correction.

[0028] In a preferred embodiment of the present invention, the coordinate origin of the three-dimensional coordinate system after the transformation and rotation correction includes: a vertical projection of the initial coordinate origin on the plane where the horizontal reference object is located as the changed coordinate origin.

[0029] In a preferred embodiment of the present invention, the coordinate origin of the three-dimensional coordinate system after the transformation and rotation correction includes:

[0030] When obtaining the initial coordinate origin, the height difference h between the acquisition position of the point cloud data and the plane where the horizontal reference object is located;

[0031] The coordinates (x, y, z) of each point cloud data in the three-dimensional coordinate system after rotation correction are transformed into (x, y, hz).

[0032] In a preferred embodiment of the present invention, the point cloud data corresponding to the end face of the raw material blank in the length direction detected in the three-dimensional coordinate system after the origin is calibrated includes:

[0033] The preset area is deleted and a screening area is retained, wherein the raw material blank is located in the screening area;

[0034] Segmenting the point cloud data in the screening area to separate the point cloud data representing different objects in the screening area and form a set of multiple sub-point clouds;

[0035] Traversing the set of each sub-point cloud;

[0036] If the quantity of the point cloud data in the set of sub-point clouds is greater than or equal to a preset first quantity threshold, it is determined that the point cloud data in the set of sub-point clouds is the point cloud data corresponding to the raw material blank.

[0037] In a preferred embodiment of the present invention, segmenting the point cloud data within the screening area includes:

[0038] Preset distance threshold;

[0039] Points corresponding to two point cloud data whose distance is less than the distance threshold are divided into the same set of sub-point clouds.

[0040] In a preferred embodiment of the present invention, determining whether the raw material blank moves to a predetermined position in the heating furnace includes:

[0041] Obtaining an x-coordinate set of all the point cloud data corresponding to the raw material blank;

[0042] Preset area division value;

[0043] Performing region division at the region division value in the x-coordinate set, and obtaining a plurality of sub-regions;

[0044] Counting the number of x-coordinate values ​​in each of the sub-areas;

[0045] If the number of the x-coordinate values ​​is greater than a second number threshold, it is determined that the sub-region is located on the end surface of the raw material blank in the length direction;

[0046] Setting a positioning value within the area division value;

[0047] If the positioning value is greater than or equal to the standard value, the raw material blank moves to a predetermined position in the heating furnace.

[0048] The present invention provides a raw material blank entering a furnace positioning detection device, comprising:

[0049] A point cloud data acquisition unit, used to acquire point cloud data in a preset area in a three-dimensional coordinate system, wherein the preset area includes point cloud data at a location where an entrance of the heating furnace is located;

[0050] A raw material blank position detection unit, used to detect point cloud data corresponding to the end face of the raw material blank in the length direction;

[0051] The position determination unit is used to determine whether the raw material blank moves to a predetermined position in the heating furnace.

[0052] In a preferred embodiment of the present invention, the raw material blank entering the furnace positioning detection device further includes:

[0053] A rotation correction unit, used for performing horizontal rotation correction on the three-dimensional coordinate system where the point cloud data in a preset area is located;

[0054] The origin transformation unit is used to transform the coordinate origin of the three-dimensional coordinate system after rotation correction.

[0055] In a preferred embodiment of the present invention, the point cloud data acquisition unit is a laser radar, which is arranged on the upper side of the transport roller that transports the raw material billet. The laser radar is aimed at the entrance of the heating furnace to collect point cloud data at the location of the entrance of the heating furnace.

[0056] The present invention provides a computer device, including a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for detecting the positioning of raw material billets entering a furnace when executing the computer program.

[0057] The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the above-mentioned raw material billet positioning detection method.

[0058] As described above, the characteristics and advantages of the raw material blank entering the furnace positioning detection method, device, equipment and readable storage medium of the present invention are: in the process of conveying the raw material blank to the heating furnace, by collecting point cloud data in a preset area in the three-dimensional coordinate system, and by detecting the point cloud data corresponding to the end face of the raw material blank in the length direction, it is possible to accurately detect whether the raw material blank has run to the preset position after entering the heating furnace. This method can replace manual detection, realize unmanned production, and greatly improve detection and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The following drawings are only intended to illustrate and explain the present invention, and are not intended to limit the scope of the present invention.

[0060] in:

[0061] Figure 1 : is one of the flow charts of the raw material blank entering the furnace positioning detection method of the present invention.

[0062] Figure 2 : This is the second flow chart of the raw material blank entering furnace positioning detection method of the present invention.

[0063] Figure 3 : It is a schematic diagram of the arrangement position of the equipment in the method for detecting the positioning of raw material billets entering the furnace according to the present invention.

[0064] Figure 4 : It is a schematic diagram of the point cloud data collected in the raw material blank entering the furnace positioning detection method of the present invention.

[0065] Figure 5 : This is the third flow chart of the raw material blank entering furnace positioning detection method of the present invention.

[0066] Figure 6 : This is the fourth flow chart of the raw material blank entering the furnace positioning detection method of the present invention.

[0067] Figure 7 : This is the fifth flow chart of the raw material blank entering the furnace positioning detection method of the present invention.

[0068] Figure 8 : This is the sixth flow chart of the raw material blank entering the furnace positioning detection method of the present invention.

[0069] Fig. 9 : This is the seventh flow chart of the method for detecting the positioning of raw material billets entering the furnace according to the present invention.

[0070] Fig.10 : It is a schematic diagram of the principle of positioning the raw material billet in the raw material billet entering the furnace positioning detection method of the present invention.

[0071] Fig.11 : This is the eighth flow chart of the method for detecting the positioning of raw material billets entering the furnace according to the present invention.

[0072] Fig.12 : is one of the structural block diagrams of the raw material blank entering the furnace positioning detection device of the present invention.

[0073] Fig.13 : This is the second structural block diagram of the raw material blank entering furnace positioning detection device of the present invention.

[0074] Fig.14 : It is the third structural block diagram of the raw material blank entering furnace positioning detection device of the present invention.

[0075] The accompanying drawings in the present invention are:

[0076] 1. Raw material blank; 2. Transport roller;

[0077] 3. Heating furnace entrance; 4. LiDAR. DETAILED DESCRIPTION

[0078] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described with reference to the accompanying drawings.

[0079] Implementation Method 1

[0080] like Figure 1 , Figure 2 As shown, the present invention provides a method for detecting the positioning of a raw material blank into a furnace, and the method for detecting the positioning of a raw material blank into a furnace comprises the following steps:

[0081] Step S1: collecting point cloud data within a preset area in a three-dimensional coordinate system, where the preset area includes point cloud data of the location of the heating furnace entrance 3;

[0082] Furthermore, the collected point cloud data is a coordinate set of multiple position points in a three-dimensional coordinate system.

[0083] Specifically, Figure 3 As shown, in the process of collecting point cloud data in a preset area, a laser radar 4 is arranged on the upper side of the transport roller 2, and the scanning port of the laser radar 4 is aligned with the heating furnace entrance 3 to collect point cloud data. Among them, the point cloud data scanned by the laser radar 4 is a collection of a series of (x, y, z) coordinates in a three-dimensional coordinate system (the (x, y, z) coordinates here are only used to describe the format of the point cloud data returned by the laser radar 4, and do not specifically refer to the specific detection position. Of course, in actual measurement, it is necessary to scan the point cloud data near the heating furnace entrance 4). According to the scanning accuracy of the selected laser radar 4, point cloud data of different accuracies can be collected (the coordinate accuracy of the point cloud data can be accurate to millimeters). The point cloud data obtained by scanning is shown as follows. Figure 4 As shown, the rectangular white frame contains the point cloud data collected within the preset area, including the point cloud data of the location of the heating furnace entrance and the point cloud data of the end face of the raw material billet 1 in the length direction.

[0084] Step S2: performing horizontal rotation correction on the three-dimensional coordinate system where the point cloud data in the preset area is located;

[0085] In actual operation scenarios, it is difficult to ensure that the installation of the laser radar 4 is completely horizontal, and the ground may also have a certain tilt angle. In order to facilitate point cloud analysis, when the installation angle of the laser radar 4 and / or the ground has a tilt angle, the three-dimensional coordinate system where the point cloud data is located needs to be rotated and corrected.

[0086] In an optional embodiment of the present invention, Figure 5 As shown, step S2 includes:

[0087] Step S201: selecting point cloud data of a horizontal reference object from point cloud data within a preset area;

[0088] Step S202: Perform horizontal rotation correction on the three-dimensional coordinate system so that the point cloud data of the horizontal reference object is in the xy plane of the three-dimensional coordinate system or in a plane parallel to the xy plane of the three-dimensional coordinate system.

[0089] Among them, the horizontal reference object can be the ground (the ground needs to be horizontal and there is no tilt angle). The horizontal plane correction mainly uses the point cloud data of the ground to perform rotation correction on the three-dimensional coordinate system. When the ground has a tilt angle or the point cloud data of the ground cannot be collected due to occlusion, etc., a horizontal marking plate can be placed in the field of view as a horizontal reference object, and the three-dimensional coordinate system can be rotated and corrected using the point cloud data of the marking plate.

[0090] Further, such as Figure 6 As shown, step S202 includes:

[0091] Step S2021: Detecting the plane P (corresponding to the horizontal ground or the horizontal marking plate) where the horizontal reference object is located in the point cloud data within the preset area by using a plane detection algorithm;

[0092] Step S2022: In the three-dimensional coordinate system, obtain the plane equation of the plane P where the horizontal reference object is located:

[0093] ax+by+cz+d=0;

[0094] The specific value of d is automatically calculated by the plane detection algorithm. In the present invention, the normal vector (a, b, c) of the plane P is sufficient, which has nothing to do with the value of d. Since (a, b, c) is the normal vector of the plane P, and the vertical vector in the conventional three-dimensional coordinate system should be (0, 0, 1), it is necessary to calculate the rotation matrix R from the normal vector (a, b, c) of the plane P to the vertical vector (0, 0, 1).

[0095] Step S2023: According to the plane equation of the plane where the horizontal reference object is located and the rotation matrix solution algorithm, a rotation matrix for horizontal rotation correction of the three-dimensional coordinate system is obtained, and the rotation matrix is ​​the correction parameter;

[0096] Among them, the plane detection algorithm and rotation matrix solution algorithm required for the above-mentioned horizontal correction are existing calculation methods, which can be directly called through point cloud data processing libraries such as Halcon and PCL (Point Cloud Library), so the specific calculation method will not be described here.

[0097] Step S2024: multiplying the point cloud data in the preset area by the correction parameter to obtain the point cloud data in the preset area after horizontal rotation correction.

[0098] When the installation position of the laser radar 4 is determined, the above rotation correction operation only needs to be performed once, and the obtained rotation matrix R is the correction parameter. In the subsequent work process, it is only necessary to multiply the original point cloud data Pori in the preset area measured by the laser radar 4 by the rotation matrix R to obtain the point cloud data Padjust in the preset area after rotation correction, where: Padjust in the preset area = Pori × R

[0099] Step S3: transforming the coordinate origin of the three-dimensional coordinate system after rotation correction;

[0100] Furthermore, step S3 includes: taking the vertical projection of the initial coordinate origin on the plane where the horizontal reference object is located as the changed coordinate origin.

[0101] Specifically, the point cloud data obtained by the laser radar 4 usually uses the position of the laser radar 4 itself as the origin of the three-dimensional coordinate system. Therefore, it is necessary to transform the origin of the three-dimensional coordinate system. The vertical projection point of the laser radar 4 on the horizontal ground (or horizontal marking board) is used as the 0 point of the Z-axis coordinate in the three-dimensional coordinate system, which can facilitate data processing.

[0102] In an optional embodiment of the present invention, Figure 7 As shown, step S3 includes:

[0103] Step S301: When obtaining the initial coordinate origin, acquire the height difference h between the acquisition position of the point cloud data (i.e., the position where the lidar 4 is set) and the plane where the horizontal reference object (i.e., the horizontal ground or the horizontal marker board) is located; among them, h can be obtained by on-site measurement.

[0104] Step S302: Transform the coordinates (x, y, z) of each point cloud data in the rotation-corrected three-dimensional coordinate system into (x, y, h - z).

[0105] Step S4: Detect the point cloud data corresponding to the end face of the raw material blank 1 in the length direction in the three-dimensional coordinate system after calibrating the origin (i.e., the x coordinate of the end face of the raw material blank 1 in the length direction in the three-dimensional coordinate system);

[0106] In an alternative embodiment of the present invention, as Figure 8 、 Fig.10 shown, Step S4 includes:

[0107] Step S401: Delete the preset area and retain the screening area, where the raw material blank is located within the screening area;

[0108] In the present invention, since the scanning range of the lidar 4 is relatively large, it is necessary to剔除 the points outside the area where the raw material blank 1 is located. Select the area where the raw material blank 1 appears according to the value range of the point cloud data collected in the three-dimensional coordinate system, that is, retain the point cloud data within the area where x1 < x < x2, y1 < y < y2, z1 < z < z2. Among them, the selection of x1, x2, y1, y2, z1, z2 can be obtained by on-site measurement. The principle of selection is to ensure that the raw material blank 1 will appear in the selected area A, and the smaller the range of this area A, the better. Through the screening of the area, most of the background noise data (i.e., the point cloud data that does not contain the raw material blank 1) can be filtered out, and it can also be ensured that the main part within the selected area A is the raw material blank 1 itself. After screening, a set P of point cloud data can be obtained A .

[0109] Step S402: Segment the point cloud data within the screening area to separate the point cloud data representing different objects within the screening area and form multiple subsets of point clouds;

[0110] Furthermore, as Fig. 9 shown, Step S402 includes:

[0111] Step S4021: Preset a distance threshold;

[0112] Step S4022: Divide the points corresponding to two point cloud data with a distance less than the distance threshold into the same subset of point clouds.

[0113] Specifically, in the selected area A, the main part of the point cloud data is the raw material blank 1 itself, and the point cloud data set P A Perform point cloud segmentation operation (which can be achieved through operators in point cloud analysis libraries such as PCL and Halcon), and divide two point cloud data with a distance less than a preset distance threshold (which can be 1 cm) into the same sub-point cloud set to achieve the segmentation of different objects in the point cloud data. After segmentation, a set Ps of multiple sub-point clouds will be formed.

[0114] Step S403: screening the sets Ps of the plurality of sub-point clouds and traversing the sets Ps of the sub-point clouds;

[0115] Step S404: If the number of point cloud data in the set Ps of the sub-point cloud is greater than or equal to the preset first quantity threshold (which can be 1000), it can be determined that the point cloud data in the set Ps of the sub-point cloud is the point cloud data Pt corresponding to the raw material blank 1, and the other filtered out point cloud data is noise; if the number of point cloud data in the set Ps of the sub-point cloud is less than the preset first quantity threshold, it can be determined that the current point cloud data is not on the raw material blank 1 and the raw material blank 1 is not detected.

[0116] Step S5: Determine whether the raw material blank moves to a predetermined position in the heating furnace.

[0117] In an optional embodiment of the present invention, Fig.11 As shown, step S5 includes:

[0118] Step S501: obtaining the x-coordinate set of all point cloud data Pt corresponding to the raw material blank 1 (ie, the coordinate set in the length direction of the raw material blank 1);

[0119] Step S502: preset area division value (5 cm is acceptable);

[0120] Step S503: performing region division in the x-coordinate set according to the region division value, and obtaining a plurality of sub-regions An;

[0121] Step S504: Count the number n of x-coordinate values ​​in each sub-area An;

[0122] Step S505: if the number n of x-coordinate values ​​is greater than a second number threshold θ (the value of θ can be determined according to actual conditions, and can be 200), it is determined that the sub-area An is located on the end surface of the raw material blank 1 in the length direction (because the points on the raw material blank 1 are the most dense);

[0123] Step S506: setting the positioning value within the area division value;

[0124] Specifically, a value within the preset area division value (such as the middle position d within a range of 5 cm) may be selected as the positioning value.

[0125] Step S507: If the positioning value is greater than or equal to the standard value, the raw material blank 1 moves to a predetermined position in the heating furnace.

[0126] Specifically, after the raw material blank 1 moves into the heating furnace, when d>d0 (d0 is actually measured), it can be determined that the raw material blank 1 has entered the furnace; if d<d0, it can be determined that the raw material blank 1 has not entered the preset position of the heating furnace, and the raw material blank 1 needs to be adjusted.

[0127] The characteristics and advantages of the raw material blank entering the furnace positioning detection method of the present invention are:

[0128] 1. The method for detecting the positioning of the raw material billet entering the furnace can accurately detect whether the raw material billet 1 has run to the preset position after entering the heating furnace by collecting point cloud data within a preset area in a three-dimensional coordinate system and detecting the point cloud data corresponding to the end face of the raw material billet 1 in the length direction. This method can replace manual detection, realize unmanned production, greatly improve detection and production efficiency, and achieve the purpose of reducing staff and increasing efficiency.

[0129] 2. In the method for detecting the positioning of raw material billets entering the furnace, after collecting the point cloud data in a preset area in the three-dimensional coordinate system, the position of the three-dimensional coordinate system can be adjusted by means of horizontal rotation correction and transformation of the coordinate origin, thereby improving the accuracy of the detection and facilitating calculation.

[0130] Implementation Method 2

[0131] like Fig.12 As shown, the present invention provides a raw material blank into the furnace positioning detection device, the raw material blank into the furnace positioning detection device includes a point cloud data acquisition unit 100, a rotation correction unit 200, an origin transformation unit 300, a raw material blank position detection unit 400 and a position determination unit 500, wherein:

[0132] The point cloud data acquisition unit 100 is used to acquire point cloud data in a preset area in a three-dimensional coordinate system, and the preset area includes point cloud data at the location of the heating furnace entrance 3;

[0133] In an optional embodiment of the present invention, Figure 3 As shown, the point cloud data acquisition unit 100 is a laser radar 4, which is fixedly arranged on the upper side of the transport roller 2 that transports the raw material billet 1. The laser radar 4 is aimed at the entrance 3 of the heating furnace, so that the laser radar 4 can collect point cloud data at the location of the entrance 3 of the heating furnace.

[0134] Specifically, Figure 3As shown, in the process of collecting point cloud data in a preset area, a laser radar 4 is arranged on the upper side of the transport roller 2, and the scanning port of the laser radar 4 is aligned with the heating furnace entrance 3 to collect point cloud data. Among them, the point cloud data scanned by the laser radar 4 is a collection of a series of (x, y, z) coordinates in a three-dimensional coordinate system (the (x, y, z) coordinates here are only used to describe the format of the point cloud data returned by the laser radar 4, and do not specifically refer to the specific detection position. Of course, in actual measurement, it is necessary to scan the point cloud data near the heating furnace entrance 4). According to the scanning accuracy of the selected laser radar 4, point cloud data of different accuracies can be collected (the coordinate accuracy of the point cloud data can be accurate to millimeters). The point cloud data obtained by scanning is shown as follows. Figure 4 As shown, the rectangular white frame contains the point cloud data collected within the preset area, including the point cloud data of the location of the heating furnace entrance and the point cloud data of the end face of the raw material billet 1 in the length direction.

[0135] The rotation correction unit 200 is used to perform horizontal rotation correction on the three-dimensional coordinate system where the point cloud data in the preset area is located. In actual operation scenarios, since it is difficult to ensure that the installation of the laser radar 4 is completely horizontal, and the ground may also have a certain inclination angle, in order to facilitate point cloud analysis, when the installation angle of the laser radar 4 and / or the ground has an inclination angle, the three-dimensional coordinate system where the point cloud data is located needs to be rotated and corrected.

[0136] The origin transformation unit 300 is used to transform the coordinate origin of the three-dimensional coordinate system after rotation correction, and use the vertical projection of the initial coordinate origin on the plane where the horizontal reference object is located as the changed coordinate origin.

[0137] Specifically, the point cloud data obtained by the laser radar 4 usually uses the position of the laser radar 4 itself as the origin of the three-dimensional coordinate system. Therefore, it is necessary to transform the origin of the three-dimensional coordinate system. The vertical projection point of the laser radar 4 on the horizontal ground (or horizontal marking board) is used as the 0 point of the Z-axis coordinate in the three-dimensional coordinate system, which can facilitate data processing.

[0138] The raw material blank position detection unit 400 is used to detect the point cloud data corresponding to the end face of the raw material blank 1 in the length direction;

[0139] Further, such as Fig.13 As shown, the raw material blank position detection unit 400 includes:

[0140] The area deletion module 4001 is used to delete the preset area and retain the screening area, and the raw material blank is located in the screening area;

[0141] The region segmentation module 4002 is used to segment the point cloud data in the screening region to separate the point cloud data representing different objects in the screening region and form a set of multiple sub-point clouds;

[0142] A screening module 4003 is used to screen the sets of multiple sub-point clouds and traverse the sets of each sub-point cloud;

[0143] The first judgment module 4004 is used to determine that the point cloud data in the set of sub-point clouds is the point cloud data corresponding to the raw material blank 1 if the number of point cloud data in the set of sub-point clouds is greater than or equal to the preset first number threshold; if the number of point cloud data in the set of sub-point clouds is less than the preset first number threshold, it can be determined that the current point cloud data is not on the raw material blank 1 and the raw material blank 1 is not detected.

[0144] The position determination unit 500 is used to determine whether the raw material blank 1 moves to a predetermined position in the heating furnace.

[0145] Further, such as Fig.14 As shown, the position determination unit 500 includes:

[0146] An x-coordinate set acquisition module 5001 is used to acquire an x-coordinate set of all point cloud data corresponding to the raw material blank 1;

[0147] A first preset module 5002, used for presetting area division values;

[0148] A sub-region division module 5003 is used to perform region division in the x-coordinate set according to the region division value and obtain multiple sub-regions;

[0149] A quantity counting module 5004 is used to count the number of x-coordinate values ​​in each sub-area A;

[0150] The second judgment module 5005 is used to determine that the sub-region is located on the end surface of the raw material blank 1 in the length direction if the number of x-coordinate values ​​is greater than a second number threshold;

[0151] A second preset module 5006, used to set a positioning value within the area division value;

[0152] The third judgment module 5007 is used to move the raw material blank 1 to a predetermined position in the heating furnace if the positioning value is greater than or equal to the standard value.

[0153] The characteristics and advantages of the raw material blank entering the furnace positioning detection device of the present invention are:

[0154] The raw material blank entering the furnace positioning detection device can accurately detect whether the raw material blank 1 has run to the preset position after entering the heating furnace. This method can replace manual detection, realize unmanned production, greatly improve detection and production efficiency, and achieve the purpose of reducing staff and increasing efficiency.

[0155] Implementation Method 3

[0156] The present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for detecting the positioning of raw material billets entering a furnace is implemented.

[0157] Specifically, the computer device may be a computer terminal, a server or a similar computing device.

[0158] Implementation Method 4

[0159] The present invention provides a computer-readable storage medium, which stores a computer program for executing the above-mentioned raw material billet positioning detection method.

[0160] Specifically, computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable 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 tape 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 storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0161] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0162] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0163] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0165] The above description is only an illustrative embodiment of the present invention and is not intended to limit the scope of the present invention. Any equivalent changes and modifications made by any person skilled in the art without departing from the concept and principle of the present invention shall fall within the scope of protection of the present invention.

Claims

1. A method for detecting the positioning of raw material billets entering a furnace, characterized in that: The steps include: Collecting point cloud data within a preset area in a three-dimensional coordinate system, wherein the preset area includes point cloud data of a location where an entrance of a heating furnace is located; Performing horizontal rotation correction on the three-dimensional coordinate system where the point cloud data in a preset area is located; The coordinate origin of the three-dimensional coordinate system after transformation, rotation and correction; Detecting point cloud data corresponding to the end face of the raw material blank in the length direction; detecting point cloud data corresponding to the end face of the raw material blank in the length direction in the three-dimensional coordinate system after calibrating the origin includes: The preset area is deleted and a screening area is retained, wherein the raw material blank is located in the screening area; Segmenting the point cloud data in the screening area to separate the point cloud data representing different objects in the screening area and form a set of multiple sub-point clouds; Preset distance threshold; The points corresponding to the two point cloud data whose distance is less than the distance threshold are divided into the same set of sub-point clouds. Traversing the set of each sub-point cloud; If the number of the point cloud data in the set of sub-point clouds is greater than or equal to a preset first number threshold, determining that the point cloud data in the set of sub-point clouds is the point cloud data corresponding to the raw material blank; Determining whether the raw material blank moves to a predetermined position in the heating furnace; Obtaining an x-coordinate set of all the point cloud data corresponding to the raw material blank; Preset area division value; Performing region division at the region division value in the x-coordinate set, and obtaining a plurality of sub-regions; Counting the number of x-coordinate values ​​in each of the sub-areas; If the number of the x-coordinate values ​​is greater than a second number threshold, it is determined that the sub-region is located on the end surface of the raw material blank in the length direction; Setting a positioning value within the area division value; If the positioning value is greater than or equal to the standard value, the raw material blank moves to a predetermined position in the heating furnace.

2. The method for detecting the positioning of raw material billets entering a furnace according to claim 1, characterized in that: The point cloud data collected within a preset area in the three-dimensional coordinate system is a coordinate set of multiple position points in the three-dimensional coordinate system.

3. The method for detecting the positioning of raw material billets entering a furnace according to claim 1, characterized in that: The performing horizontal rotation correction on the three-dimensional coordinate system where the point cloud data in the preset area is located comprises: Selecting point cloud data of a horizontal reference object from the point cloud data within a preset area; The three-dimensional coordinate system is horizontally rotated and corrected so that the point cloud data of the horizontal reference object is within the xy plane of the three-dimensional coordinate system or within a plane parallel to the xy plane of the three-dimensional coordinate system.

4. The method for detecting the positioning of raw material billets entering a furnace according to claim 3, characterized in that: The horizontal rotation correction of the three-dimensional coordinate system comprises: Detecting the plane where the horizontal reference object in the point cloud data within the preset area is located by a plane detection algorithm; Obtaining a plane equation of the plane where the horizontal reference object is located; According to the plane equation of the plane where the horizontal reference object is located and the rotation matrix solution algorithm, a rotation matrix for horizontal rotation correction of the three-dimensional coordinate system is obtained, and the rotation matrix is ​​the correction parameter; The point cloud data in the preset area is multiplied by the correction parameter to obtain the point cloud data in the preset area after horizontal rotation correction.

5. The method for detecting the positioning of raw material billets entering a furnace according to claim 3, characterized in that: The coordinate origin of the three-dimensional coordinate system after the transformation and rotation correction includes: a vertical projection of the initial coordinate origin on the plane where the horizontal reference object is located as the changed coordinate origin.

6. The method for detecting the position of raw material billets entering a furnace according to claim 3, characterized in that: The coordinate origin of the three-dimensional coordinate system after the transformation and rotation correction includes: When obtaining the initial coordinate origin, the height difference h between the acquisition position of the point cloud data and the plane where the horizontal reference object is located; The coordinates (x, y, z) of each point cloud data in the three-dimensional coordinate system after rotation correction are transformed into (x, y, hz).

7. A device for detecting the position of a raw material billet entering a furnace, which uses the method for detecting the position of a raw material billet entering a furnace as claimed in any one of claims 1 to 6 to detect the position of a raw material billet entering a furnace, characterized in that: The raw material blank entering the furnace positioning detection device comprises: A point cloud data acquisition unit, used to acquire point cloud data in a preset area in a three-dimensional coordinate system, wherein the preset area includes point cloud data at a location where an entrance of the heating furnace is located; A rotation correction unit, used for performing horizontal rotation correction on the three-dimensional coordinate system where the point cloud data in a preset area is located; An origin transformation unit, used for transforming the coordinate origin of the three-dimensional coordinate system after rotation correction; A raw material blank position detection unit, used to detect point cloud data corresponding to the end face of the raw material blank in the length direction; The position determination unit is used to determine whether the raw material blank moves to a predetermined position in the heating furnace.

8. The raw material blank entering furnace positioning detection device according to claim 7, characterized in that: The point cloud data acquisition unit is a laser radar, which is arranged on the upper side of the transport roller conveying the raw material billet. The laser radar is aimed at the entrance of the heating furnace to collect point cloud data at the location of the entrance of the heating furnace.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for detecting the positioning of the raw material billet entering the furnace as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the method for detecting the positioning of raw material billets entering a furnace as claimed in any one of claims 1 to 6.

Images