CN113639657B

CN113639657B - Square billet bending detection method and device and bar and wire raw material billet bending detection system

Info

Publication number: CN113639657B
Application number: CN202110890863.0A
Authority: CN
Inventors: 张希元; 冯建标; 温志强; 李凡; 万振涛; 王云波
Original assignee: Ceristar Electric Co ltd; Capital Engineering & Research Inc Ltd
Current assignee: Ceristar Electric Co ltd; Capital Engineering & Research Inc Ltd
Priority date: 2021-08-04
Filing date: 2021-08-04
Publication date: 2024-02-27
Anticipated expiration: 2041-08-04
Also published as: CN113639657A

Abstract

The embodiment of the application provides a square billet bending detection method and device and a bar and wire stock billet bending detection system, wherein the method comprises the following steps: collecting target three-dimensional point cloud data corresponding to a square billet from the upper part of the square billet placed horizontally; respectively projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane to obtain a corresponding target point set; judging whether abnormal points exist at all edge points on one long side of the square billet in the target point set, and if so, determining that the square billet is bent on the horizontal plane. The method and the device can realize automatic bending detection of the square billets, can effectively improve the bending detection precision of the square billets and the accuracy of the bending detection result, and further can effectively save labor cost and time cost, and improve the bending detection efficiency of the square billets.

Description

Square billet bending detection method and device and bar and wire raw material billet bending detection system

Technical Field

The application relates to the technical field of bending detection, in particular to a square billet bending detection method and device and a bar and wire raw material billet bending detection system.

Background

The square billets are common raw materials in the production process, and because the length of the square billets is long, bending phenomena can occur in the process of transportation or processing of individual square billets, and particularly, the situation that the square billets bend left and right or the cross section bends up and down on the horizontal plane can exist. The square billets bent up and down can naturally collapse in the follow-up process such as heating processing and the like, the influence on production is small, the square billets bent horizontally left and right are difficult to smoothly move out of heating equipment in the follow-up process such as heating processing and the like, equipment damage of the heating equipment and the like is easy to cause, the generation efficiency is influenced, and the square billet cost is wasted, so that the square billets bent horizontally left and right need to be found in time.

At present, most of the modes for detecting the square billets bent horizontally and leftwards are manually checked by operators beside a production line, and whether the square billets are bent or not is manually observed, so that the existing square billet bending detection mode has the problems of long time consumption, high working strength of personnel, low accuracy, low production efficiency and the like.

Disclosure of Invention

To the problem among the prior art, this application provides a square billet bending detection method and device, stick wire rod raw materials base bending detection system, can realize the automatic bending detection to the square billet, can effectively improve the accuracy of the bending detection precision and the bending detection result of square billet, and then can effectively use manpower sparingly cost and time cost, improves the bending detection efficiency of square billet.

In order to solve the technical problems, the application provides the following technical scheme:

in a first aspect, the present application provides a method for detecting bending of a square billet, including:

collecting target three-dimensional point cloud data corresponding to a square billet from the upper part of the square billet placed horizontally;

respectively projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane to obtain a corresponding target point set;

judging whether abnormal points exist at all edge points on one long side of the square billet in the target point set, and if so, determining that the square billet is bent on the horizontal plane.

Further, the collecting the target three-dimensional point cloud data corresponding to the square billet from the upper part of the square billet placed horizontally comprises the following steps:

collecting three-dimensional point cloud data of a scene in which a square billet is positioned from above the square billet which is horizontally placed;

performing rotation correction processing on the three-dimensional point cloud data of the scene to obtain rotation corrected three-dimensional point cloud data of the scene;

performing origin calibration processing on the rotation corrected three-dimensional point cloud data of the scene to obtain origin calibrated three-dimensional point cloud data of the scene;

and extracting target three-dimensional point cloud data corresponding to the square billet from the scene three-dimensional point cloud data calibrated by the origin.

Further, the performing rotation correction processing on the three-dimensional point cloud data of the scene to obtain rotation corrected three-dimensional point cloud data of the scene includes:

obtaining a prestored rotation matrix, wherein the obtaining mode of the rotation matrix comprises the following steps: the method comprises the steps of collecting background three-dimensional point cloud data in advance, calculating a ground plane equation corresponding to the background three-dimensional point cloud data according to a preset plane detection algorithm, and determining a rotation matrix rotated from a normal vector in the ground plane equation to (0, 1);

and taking the rotation matrix as a current correction parameter, and carrying out rotation correction processing on the three-dimensional scene point cloud data based on the correction parameter so as to obtain the three-dimensional scene point cloud data after rotation correction.

Further, the performing origin calibration processing on the rotation corrected three-dimensional point cloud data of the scene to obtain origin calibrated three-dimensional point cloud data of the scene includes:

acquiring the vertical height from the acquisition point of the three-dimensional point cloud data of the scene to the ground;

and respectively replacing the numerical value of the Z axis in each point coordinate in the three-dimensional point cloud data of the scene according to the vertical height to obtain the three-dimensional point cloud data of the scene after the origin calibration.

Further, extracting the target three-dimensional point cloud data corresponding to the square billet from the three-dimensional point cloud data of the scene after the origin calibration comprises the following steps:

extracting regional three-dimensional point cloud data of the region where the square billet is located from the scene three-dimensional point cloud data calibrated by the origin;

performing point cloud segmentation processing on the three-dimensional point cloud data of the region to obtain a plurality of point cloud sets;

and selecting a point cloud set with the total number of point coordinates larger than a point number threshold value from the point cloud sets, and determining the point cloud set with the total number of the point coordinates larger than the point number threshold value as target three-dimensional point cloud data corresponding to the square billet.

Further, the determining whether an abnormal point exists at each edge point on a long side of the square billet in the target point set, if yes, determining that the square billet is bent on the horizontal plane includes:

Aligning and de-duplicating the coordinates of each point in the target point set;

selecting each edge point on one long side of the square billet from the target point set subjected to alignment and de-duplication treatment to form an edge point set;

selecting an X-axis maximum value and an X-axis minimum value from the edge point set;

acquiring a linear equation of the maximum X-axis value and the minimum X-axis value;

sequentially calculating the distances between each edge point of the edge point set and the linear equation except the edge point corresponding to the maximum X-axis value and the edge point corresponding to the minimum X-axis value;

judging whether abnormal points with the distance between the edge points and the linear equation being greater than a distance threshold exist in all edge points except the edge point corresponding to the maximum value of the X axis and the edge point corresponding to the minimum value of the X axis in the edge point set, if so, determining that the square billet is bent on the horizontal plane;

and outputting alarm information for indicating that the square billet bends on the horizontal plane, and/or controlling transportation equipment where the square billet is positioned to stop running.

In a second aspect, the present application provides a billet bending detection device, comprising:

The three-dimensional acquisition module is used for acquiring target three-dimensional point cloud data corresponding to a square billet from above the square billet placed horizontally;

the data projection module is used for respectively projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane to obtain a corresponding target point set;

and the edge detection module is used for judging whether each edge point on one long side of the square billet in the target point set has an abnormal point, and if so, determining that the square billet is bent on the horizontal plane.

In a third aspect, the present application provides a bar and wire stock bloom bending detection system comprising: the device comprises a square billet bending detection device and a laser radar fixedly arranged above a conveying roller way in a production line;

the transportation roll table is used for transporting the square billet horizontally placed on the transportation roll table, and the square billet comprises: raw material billets of the rod wires;

the square billet bending detection device is used for executing the square billet bending detection method, is in communication connection with the laser radar and is used for receiving the three-dimensional point cloud data acquired by the laser radar.

In a fourth aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the billet bending detection method when executing the program.

In a fifth aspect, the present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the billet bending detection method.

According to the technical scheme, the square billet bending detection method and device and the bar wire raw material billet bending detection system provided by the application comprise the following steps: collecting target three-dimensional point cloud data corresponding to a square billet from the upper part of the square billet placed horizontally; respectively projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane to obtain a corresponding target point set; judging whether each edge point on one long side of the square billet in the target point set has an abnormal point, if so, determining that the square billet is bent on the horizontal plane, and respectively projecting each point coordinate in the target three-dimensional point cloud data onto the horizontal plane by applying the target three-dimensional point cloud data corresponding to the square billet, and then judging whether each edge point on one long side of the square billet in the target point set has an abnormal point, so that automatic bending detection of the square billet can be realized, the bending detection precision of the square billet and the accuracy of a bending detection result can be effectively improved, further, the labor cost and the time cost can be effectively saved, the bending detection efficiency of the square billet can be improved, the automatic closed-loop control of the square billet in a production line can be effectively realized, the production efficiency of the square billet in the production line can be effectively improved, and the user experience of production staff can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic illustration of a raw blank of rod and wire being charged in a production line.

Fig. 2 is a schematic view of the bending of a raw blank of rod and wire material up and down.

Fig. 3 is a schematic view of the left-right bending of the raw material billet of the rod-wire material in the horizontal plane.

Fig. 4 is a schematic diagram of a relationship between the billet bending detection apparatus in the embodiment of the present application and the laser radar, the controller, the alarm device, and the client device, respectively.

Fig. 5 is a schematic diagram of a first flow of a method for detecting bending of a billet in an embodiment of the present application.

Fig. 6 is a schematic diagram of a second flow chart of a method for detecting bending of a square billet in an embodiment of the present application.

Fig. 7 is a schematic diagram of a third flow chart of a method for detecting bending of a square billet in an embodiment of the present application.

Fig. 8 is a fourth flow chart of a method for detecting bending of a square billet in the embodiment of the present application.

Fig. 9 is a fifth flowchart of the billet bending detection method in the embodiment of the present application.

Fig. 10 is a sixth flowchart of the billet bending detection method in the embodiment of the present application.

Fig. 11 is a schematic structural view of a billet bending detection device in the embodiment of the present application.

Fig. 12 is a schematic diagram of a field device arrangement provided by an example application of the present application.

Fig. 13 is an exemplary schematic diagram of three-dimensional point cloud data obtained by scanning provided in the application example of the present application.

Fig. 14 is a schematic view of horizontal plane rotation correction scanning provided by an application example of the present application.

Fig. 15 is a flow chart of rotation correction provided by an application example of the present application.

Fig. 16 is a schematic diagram of a point cloud according to a high degree of screening provided by an application example of the present application.

Fig. 17 is a flow chart for extracting the upper surface of a raw blank provided in an application example of the present application.

Fig. 18 is a schematic view of point cloud projection provided by an application example of the present application.

Fig. 19 is a schematic diagram of point cloud collection before alignment deduplication provided by an application example of the present application.

Fig. 20 is a schematic view of a point cloud collection effect before performing aligned deduplication provided by an application example of the present application.

Fig. 21 is a schematic diagram of coordinates of an edge point of an obtained raw blank provided in an application example of the present application.

Fig. 22 is a flowchart of the bending detection provided by the application example of the present application.

Fig. 23 is a schematic structural diagram of an electronic device in an embodiment of the present application.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

Taking the raw material blanks of the rod wires in the square blank as an example, the cross section of the raw material blanks of the rod wires is generally square, the side length of the cross section is about 200mm, the length of the cross section is about 10 meters, and the raw material blanks need to enter a heating furnace through a section of conveying roller table in the production process, as shown in fig. 1.

Individual blanks may be bent for various reasons. Since the raw material blanks are mostly lifted to a conveying roller way by a crane, some raw material blanks are bent up and down on the roller way, see fig. 2; some of the blanks exhibit a horizontal bending, see fig. 3, wherein it is noted that the bending states shown in fig. 2 and 3 are shown for more visual description only, and the actual bending degree may not be achieved in the bending states shown in fig. 2 and 3 by appropriate exaggeration.

After the raw material blanks bent up and down are heated in the heating furnace, the raw material blanks can naturally collapse, so that the influence on production is small; and the raw material blank of horizontal bending, after heating in the heating furnace, hardly go out the stove smoothly, influence production rhythm, can cause equipment to damage even, consequently this application detects to the square billet of bending about taking place.

Because most of the existing bar production lines are manually inspected by operators beside the production lines, when raw material blanks are found to be bent, manual control equipment performs blank removal. Therefore, the existing square billet bending detection mode has the following problems:

(1) The working strength of operators is very high and is influenced by noise for a long time;

(2) The long-time on-site work can cause the reduction of the visual inspection accuracy of operators;

(3) The raw material blank is longer, and the visual inspection precision is limited;

(4) Automatic closed-loop control cannot be realized, and production efficiency is reduced;

(5) Is not in line with the expected goal of human reduction and synergy.

Therefore, aiming at the problems that whether a blank needs to be detected to bend before being fed into a furnace in the production process, but an effective detection means is lacking and closed-loop control cannot be formed, and the current method is finished in a manual visual inspection mode, the method for detecting the bending of the square blank based on the point cloud analysis is provided in a three-dimensional point cloud analysis mode, the accuracy and the efficiency of detection are improved, and a technical means is provided for realizing unmanned automatic production.

Based on the above, the embodiment of the application provides a method for detecting the bending of a square billet, which is characterized by collecting target three-dimensional point cloud data corresponding to the square billet from the upper part of the square billet horizontally placed; respectively projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane to obtain a corresponding target point set; judging whether each edge point on one long side of the square billet in the target point set has an abnormal point, if so, determining that the square billet is bent on the horizontal plane, and respectively projecting each point coordinate in the target three-dimensional point cloud data onto the horizontal plane by applying the target three-dimensional point cloud data corresponding to the square billet, and then judging whether each edge point on one long side of the square billet in the target point set has an abnormal point, so that automatic bending detection of the square billet can be realized, the bending detection precision of the square billet and the accuracy of a bending detection result can be effectively improved, further, the labor cost and the time cost can be effectively saved, the bending detection efficiency of the square billet can be improved, the automatic closed-loop control of the square billet in a production line can be effectively realized, the production efficiency of the square billet in the production line can be effectively improved, and the user experience of production staff can be improved.

Based on the foregoing, the present application further provides a billet bending detection device for implementing the billet bending detection method provided in one or more embodiments of the present application, where the billet bending detection device may be a server or a controller, see fig. 4, and the billet bending detection device may be connected by itself or through a third party server, and may be sequentially in communication with a laser radar, a controller of a transport device such as a transport roller way, each alarm device, and each client device, where the billet bending detection device may receive a billet bending detection instruction sent by the client device, and control, according to the billet bending detection instruction, the laser radar to collect target three-dimensional point cloud data corresponding to a billet from above the horizontally placed billet; respectively projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane to obtain a corresponding target point set; judging whether each edge point on one long side of the square billet in the target point set has an abnormal point, if so, determining that the square billet is bent on the horizontal plane, sending alarm information for indicating that the square billet is bent on the horizontal plane to the client device, and controlling alarm equipment arranged in a scene where a production line is located to carry out alarm prompt.

In another practical application, the foregoing portion of the billet bending detection device that performs the billet bending detection may be executed in the server as described above, or all operations may be completed in the client device. Specifically, the selection may be made according to the processing capability of the client device, and restrictions of the use scenario of the user. The present application is not limited in this regard. If all operations are performed in the client device, the client device may further include a processor for specific processing of billet bending detection.

It is understood that the mobile terminal may include any mobile device capable of loading applications, such as a smart phone, a tablet electronic device, a network set top box, a portable computer, a Personal Digital Assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Wherein, intelligent wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..

The mobile terminal may have a communication module (i.e. a communication unit) and may be in communication connection with a remote server, so as to implement data transmission with the server. The server may include a server on the side of the task scheduling center, and in other implementations may include a server of an intermediate platform, such as a server of a third party server platform having a communication link with the task scheduling center server. The server may include a single computer device, a server cluster formed by a plurality of servers, or a server structure of a distributed device.

Any suitable network protocol may be used for communication between the server and the mobile terminal, including those not yet developed at the filing date of this application. The network protocols may include, for example, TCP/IP protocol, UDP/IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol ), REST protocol (Representational State Transfer, representational state transfer protocol), etc. used above the above-described protocol.

The following embodiments and application examples are described in detail.

In order to solve the problems that most of the existing square billet bending detection modes are manually visually inspected by operators beside a production line, and whether the square billets are bent or not is manually observed, so that the existing square billet bending detection modes have long time consumption, high working strength of personnel, low accuracy, low production efficiency and the like, the application provides an embodiment of a square billet bending detection method, and referring to fig. 5, the square billet bending detection method based on the execution of the square billet bending detection device specifically comprises the following steps:

step 100: and collecting target three-dimensional point cloud data corresponding to the square billet from the upper part of the square billet which is horizontally placed.

In step 100, an acquisition device capable of acquiring three-dimensional point cloud data of an object, such as a laser radar fixedly arranged in a scene where a square billet is located, may be used to acquire three-dimensional point cloud data in the scene where the laser radar is located, and the laser radar may be fixedly installed above the horizontally placed square billet, for example, at a ceiling of a generating workshop, where the laser radar may send the acquired three-dimensional point cloud data to a square billet bending detection device, and the square billet bending detection device determines target three-dimensional point cloud data corresponding to the square billet therein according to the three-dimensional point cloud data.

It can be understood that, in addition to obtaining the target three-dimensional point cloud data corresponding to the square billet to perform square billet bending detection, in the embodiment of the present application, an image recognition machine learning model or the like may be used to perform image processing on the collected square billet image to perform image recognition or the like, so as to obtain a square billet bending detection result.

Step 200: and respectively projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane to obtain a corresponding target point set.

In step 200, since the three-dimensional point cloud data is composed of a plurality of point coordinates, each point coordinate has values in three directions, i.e., (x, y, z), and the horizontal plane mentioned in step 200 refers to a plane in which (x, y), i.e., an abscissa (x-axis coordinate) and an ordinate (y-axis coordinate), are composed.

Taking a square billet as a raw material billet of a rod wire as an example, the point cloud P is formed on the upper surface of the obtained raw material billet _t Based on the above, a bending determination is performed. First, the point cloud P _t Projection onto the XY plane, i.e. point cloud P _t Only the X-axis, Y-axis coordinates, i.e., (X, Y, Z) =are retained>(X, Y) acquiring a set P of projected points _project 。

Step 300: judging whether abnormal points exist at all edge points on one long side of the square billet in the target point set, and if so, determining that the square billet is bent on the horizontal plane.

In step 300, the top side length or the bottom side length of the square billet in the point cloud image formed by the current target point set may be selected to perform the outlier determination, and in order to facilitate the statistical determination, the bottom side length is preferably used to perform the outlier determination in the specific example of the present application.

It will be understood that the abnormal point is specifically a point that is abnormal in each edge point on a long side of the square billet, and may be specifically determined according to a distance between each edge point and a certain basic boundary.

As can be seen from the foregoing description, in the method for detecting bending of a square billet provided in the embodiments of the present application, by applying the three-dimensional point cloud data of the target corresponding to the square billet, and projecting each point coordinate in the three-dimensional point cloud data of the target onto a horizontal plane, and then determining whether each edge point on one long side of the square billet in the target point set has an abnormal point, automatic bending detection of the square billet can be achieved, bending detection precision of the square billet and accuracy of a bending detection result can be effectively improved, further labor cost and time cost can be effectively saved, bending detection efficiency of the square billet can be improved, automatic closed-loop control of the square billet in a production line can be effectively realized, production efficiency of the square billet in the production line can be effectively improved, and user experience of production personnel can be improved.

In order to improve accuracy and reliability of acquiring target three-dimensional point cloud data of a square billet, in one embodiment of the square billet bending detection method provided in the present application, referring to fig. 6, step 100 of the square billet bending detection method specifically includes the following steps:

step 110: and acquiring scene three-dimensional point cloud data of a scene where the square billet is located from above the square billet which is horizontally placed.

It can be understood that the three-dimensional point cloud data of the scene refers to three-dimensional point cloud data of a space in which a generated line is located, and a current square billet is also located in the space.

Step 120: and performing rotation correction processing on the three-dimensional point cloud data of the scene to obtain the three-dimensional point cloud data of the scene after rotation correction.

In step 120, since the installation of the lidar is difficult to ensure complete level, and the ground may have a certain inclination angle, in order to facilitate the analysis of the point cloud, the coordinate system of the point cloud is first rotationally corrected, so as to ensure that the corrected coordinate of the ground point cloud is parallel to the xy plane of the xyz coordinate system, so that the rotational correction processing can be performed on the three-dimensional point cloud data of the scene by adopting preset correction parameters.

Step 130: and performing origin calibration processing on the rotation corrected three-dimensional point cloud data of the scene to obtain origin calibrated three-dimensional point cloud data of the scene.

In step 130, the point cloud data acquired by the lidar usually uses its own position as the origin of the coordinate system, so that the origin of the coordinate system needs to be transformed, and the perpendicular projection point of the lidar on the ground is used as the 0 coordinate point of the Z axis, so that the data processing can be more conveniently performed.

Step 140: and extracting target three-dimensional point cloud data corresponding to the square billet from the scene three-dimensional point cloud data calibrated by the origin.

As can be seen from the above description, the method for detecting the bending of the square billet provided by the embodiment of the application can effectively improve the accuracy and reliability of acquiring the target three-dimensional point cloud data corresponding to the square billet, can effectively improve the degree of automation and the efficiency of acquiring the target three-dimensional point cloud data, provides an accurate and effective data basis for the subsequent bending detection of the square billet, and further can further improve the bending detection precision and the accuracy of the bending detection result of the square billet and improve the bending detection efficiency of the square billet.

In order to improve the accuracy and reliability of the rotation correction, in one embodiment of the method for detecting a square billet bending provided in the present application, referring to fig. 7, step 120 of the method for detecting a square billet bending specifically includes the following steps:

Step 121: obtaining a prestored rotation matrix, wherein the obtaining mode of the rotation matrix comprises the following steps: the method comprises the steps of collecting background three-dimensional point cloud data in advance, calculating a ground plane equation corresponding to the background three-dimensional point cloud data according to a preset plane detection algorithm, and determining a rotation matrix rotated from a normal vector in the ground plane equation to (0, 1).

Step 122: and taking the rotation matrix as a current correction parameter, and carrying out rotation correction processing on the three-dimensional scene point cloud data based on the correction parameter so as to obtain the three-dimensional scene point cloud data after rotation correction.

Specifically, the basic procedure of the horizontal plane rotation correction is to detect a plane P existing in the point cloud by a plane detection algorithm, and to obtain a plane equation ax+by+cz+d=0 of P. Where (a, b, c) is the normal vector of plane P and the vertical vector in the radar coordinate system should be (0, 1), it is therefore necessary to calculate the rotation matrix R rotated from the normal vector of plane (a, b, c) to the vertical vector (0, 1).

The plane detection algorithm and the rotation matrix solving algorithm which are needed in the horizontal correction are standard algorithms of point cloud processing libraries such as Halcon and PCL (Point Cloud Library) and the like, and can be directly called.

After the installation position of the laser radar is determined, the initial correction operation is only required to be executed once, and the obtained matrix R is the correction parameter. In the subsequent application, the point cloud data P after rotation correction can be obtained by multiplying the original point cloud data Pori measured by the laser radar by the rotation matrix R _adjust ：

P _adjust ＝P _ori ·R

As can be seen from the foregoing description, in the method for detecting the bending of the square billet according to the embodiment of the present application, a ground plane equation corresponding to the background three-dimensional point cloud data is obtained by calculating according to a preset plane detection algorithm, a rotation matrix rotated from a normal vector in the ground plane equation to (0, 1) is determined, and then the rotation matrix is used as a correction parameter to perform rotation correction processing on the three-dimensional point cloud data of the scene, so that accuracy and reliability of rotation correction can be effectively improved, automation degree and efficiency of rotation correction can be effectively improved, an accurate and effective data base is provided for subsequent bending detection of the square billet, and further bending detection precision and accuracy of a bending detection result of the square billet can be further improved, and bending detection efficiency of the square billet is improved.

In order to improve accuracy and reliability of the origin calibration process, in one embodiment of the method for detecting a square billet bending provided in the present application, referring to fig. 8, step 130 of the method for detecting a square billet bending specifically includes the following:

Step 131: and acquiring the vertical height from the acquisition point of the three-dimensional point cloud data of the scene to the ground.

Step 132: and respectively replacing the numerical value of the Z axis in each point coordinate in the three-dimensional point cloud data of the scene according to the vertical height to obtain the three-dimensional point cloud data of the scene after the origin calibration.

The specific transformation method is to make P _adjust The coordinates (x, y, z) of each point are transformed into (x, y, h-z), where h is the height of the lidar to the ground, which can be measured in the field.

As can be seen from the foregoing description, according to the method for detecting bending of a square billet provided in the embodiments of the present application, the values of the Z axis in each point coordinate in the three-dimensional point cloud data of the scene are replaced according to the vertical height, so that the accuracy and reliability of origin calibration processing can be effectively improved, the degree of automation and efficiency of origin calibration can be effectively improved, an accurate and effective data basis is provided for subsequent bending detection of the square billet, and further the bending detection precision of the square billet and the accuracy of the bending detection result can be further improved, and the bending detection efficiency of the square billet is improved.

In order to improve accuracy and reliability of extracting target three-dimensional point cloud data corresponding to the square billet from scene three-dimensional point cloud data, in an embodiment of the square billet bending detection method provided in the present application, referring to fig. 9, step 140 of the square billet bending detection method specifically includes the following contents:

Step 141: and extracting regional three-dimensional point cloud data of the region where the square billet is located from the scene three-dimensional point cloud data after the origin is calibrated.

Step 142: and carrying out point cloud segmentation processing on the three-dimensional point cloud data of the region to obtain a plurality of point cloud sets.

Step 143: and selecting a point cloud set with the total number of point coordinates larger than a point number threshold value from the point cloud sets, and determining the point cloud set with the total number of the point coordinates larger than the point number threshold value as target three-dimensional point cloud data corresponding to the square billet.

Specifically, taking a raw material billet with a square billet as a rod wire as an example, because the laser radar scanning range is relatively large, points outside the region where the raw material billet is located are removed firstly, and the region where the raw material billet appears is selected according to the value range of X, Y coordinates, namely x1 is reserved<x<x2，y1<y<And y2, wherein the selection of x1, x2, y1 and y2 is obtained according to field measurement. Because the position of the raw blank has higher height (namely, the Z-axis coordinate value is larger) than other objects, the point cloud is screened again through the range of the Z coordinates, and the range of the Z coordinates is reserved to be within (h) ₁ ,h ₂ ) Data points of the interval to obtain a point cloud P _z ，h ₁ And h ₂ The value range of (2) satisfies h ₁ <h _r +h _s <h ₂ Wherein h is _r Is the height of the roller way, h _s The specific value of the section height of the raw material blank is determined according to the actual condition of the site.

Point-to-point cloud P _z Performing point cloud segmentation operation, namely dividing 2 points with a distance smaller than a certain threshold value (1 cm can be taken) into the same set by operators in a point cloud analysis library such as PCL, halcon and the like to realize segmentation of different objects in the point cloud, wherein a plurality of small point cloud sets P can be formed after segmentation _s . Again to P _s Screening and traversing P _s If the number of the points in the small point cloud is larger than a certain threshold (1000 can be taken), the point cloud is regarded as the surface P of the raw material blank _t (this is because the surface of the raw blank has the most points), and other screened point clouds are noise points.

As can be seen from the above description, according to the method for detecting the bending of the square billet provided by the embodiment of the application, by extracting the regional three-dimensional point cloud data and selecting the point cloud set with the total number of the point coordinates larger than the point number threshold value after the point cloud segmentation processing is performed on the regional three-dimensional point cloud data, the accuracy and the reliability of extracting the target three-dimensional point cloud data corresponding to the square billet from the scene three-dimensional point cloud data can be effectively improved, the efficiency and the automation degree of obtaining the target three-dimensional point cloud data can be effectively improved, an accurate and effective data basis is provided for the follow-up bending detection of the square billet, and further the bending detection precision and the accuracy of the bending detection result of the square billet can be further improved, and the bending detection efficiency of the square billet is improved.

In order to improve accuracy and reliability of determining whether an abnormal point exists at each edge point on a long side of the square billet in the target point set, in an embodiment of the square billet bending detection method provided in the present application, referring to fig. 10, step 300 in the square billet bending detection method specifically includes the following steps:

step 310: and carrying out alignment and de-duplication processing on each point coordinate in the target point set.

Step 320: and selecting each edge point on one long side of the square billet from the target point set subjected to alignment and de-duplication treatment to form an edge point set.

Step 330: and selecting an X-axis maximum value and an X-axis minimum value from the edge point set.

Step 340: and acquiring a linear equation of the X-axis maximum value and the X-axis minimum value.

Step 350: and sequentially calculating the distances between each edge point of the edge point set and the linear equation, wherein the distances between each edge point of the edge point set are respectively equal to the distance between each edge point of the edge point set and the linear equation.

Step 360: and judging whether abnormal points with the distance between the abnormal points and the linear equation being greater than a distance threshold exist in all edge points except the edge point corresponding to the maximum value of the X axis and the edge point corresponding to the minimum value of the X axis in the edge point set, and if so, executing step 370.

Step 370: determining that the square billet is bent on the horizontal plane.

Step 380: and outputting alarm information for indicating that the square billet bends on the horizontal plane, and/or controlling transportation equipment where the square billet is positioned to stop running.

Specifically P _project In effect, a set of coordinate points (x, y) is a series of points, requiring a first pair of points P _project The coordinate alignment and the de-duplication are carried out, the method is that the x and y coordinates are rounded according to the precision requirement, the precision can be 1cm (can be determined according to the actual field situation), a large number of repeated points exist after rounding, the point cloud can be traversed for de-duplication, and a new coordinate point set P is obtained _new 。

After alignment and de-duplication, the edge point of the long side of the raw material blank along the X-axis direction can be obtained, and the process is as follows:

first, a set P is obtained _new Maximum X in X-axis coordinates _max And a minimum value X _min Then from X _min Starting point and traversing P _new Obtaining P _new Wherein the X coordinate is equal to X _min If the set is empty, then slide right with d as step size (d may take 1 cm), continue traversing P _new The method comprises the steps of carrying out a first treatment on the surface of the Such asIf the set of fruits is not empty, taking the point (x, Y) with the minimum value of the Y coordinate, adding the set P of the lower edge points of the raw blank _edge . Then continue to slide right along X-axis direction with d as step length, and continue to traverse the set P _new Until the collection P of all points of the lower edge of the raw material blank is obtained _edge . It should be noted that, since the green stock may have a certain inclination on the roller table, a point not belonging to the lower edge is obtained at the head or tail of the green stock according to the above method. The solution is to ignore the length sigma of the head and tail (sigma is selected according to the actual situation in the field, 10cm is optional), namely only the set P between the X coordinates from B to C is processed _new Since the length of the raw material blank is more than 10m, the detection result is not affected by omitting 10cm at two ends.

Acquiring a set P of raw material blank edge points _edge And then, detecting whether the raw material blank is bent or not. At set P _edge Finding out 2 points with the maximum and minimum X coordinates, and obtaining a linear equation L of the two points; then calculate the set P _edge If the distance between the other points in the line L is greater than a certain threshold delta (delta is selected according to the actual situation in the field, and is 10cm, the bending of the raw material blank can be judged, and if the distance between all the points and the line L is smaller than delta, the raw material blank is judged not to be bent.

As can be seen from the foregoing description, in the method for detecting bending of a square billet according to the embodiment of the present application, by sequentially calculating the distances between each of the edge points of the edge point set, except for the edge point corresponding to the maximum value of the X axis and the edge point corresponding to the minimum value of the X axis, and the straight line equation, the accuracy and reliability for determining whether an abnormal point exists at each edge point on one long side of the square billet in the target point set can be effectively improved, and the efficiency and the degree of automation for determining whether an abnormal point exists at each edge point on one long side of the square billet in the target point set can be effectively improved.

In order to solve the problems of long time consumption, high working strength of personnel, low accuracy, low production efficiency and the like of the conventional square billet bending detection mode by manually checking whether the square billet is bent or not by an operator at the side of a production line in a software aspect, the application provides an embodiment of a square billet bending detection device for executing all or part of the contents in the square billet bending detection method, and referring to fig. 11, the square billet bending detection device specifically comprises the following contents:

the three-dimensional acquisition module 10 is used for acquiring target three-dimensional point cloud data corresponding to a square billet from above the square billet placed horizontally.

The data projection module 20 is configured to project each point coordinate in the target three-dimensional point cloud data onto a horizontal plane to obtain a corresponding target point set.

And the edge detection module 30 is configured to determine whether an abnormal point exists at each edge point on a long side of the square billet in the target point set, and if yes, determine that the square billet is bent on the horizontal plane.

The embodiment of the billet bending detection device provided in the present application may be specifically used to execute the processing flow of the embodiment of the billet bending detection method in the above embodiment, and the functions thereof are not described herein in detail, and reference may be made to the detailed description of the above method embodiment.

As can be seen from the foregoing description, the square billet bending detection device provided in the embodiment of the present application, by applying the target three-dimensional point cloud data corresponding to the square billet, and projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane, and then determining whether each edge point on one long side of the square billet in the target point set has an abnormal point, the automatic bending detection of the square billet can be implemented, the bending detection precision of the square billet and the accuracy of the bending detection result can be effectively improved, further the labor cost and the time cost can be effectively saved, the bending detection efficiency of the square billet can be improved, the automatic closed-loop control of the square billet in the production line can be effectively implemented, the production efficiency of the square billet in the production line can be effectively improved, and the user experience of the production personnel can be improved.

Based on the above-mentioned square billet bending detection method and/or square billet bending detection device's embodiment, in order to solve current square billet bending detection mode and mostly carry out manual visual inspection by the operative employee near the production line, whether observe square billet bending by the manual work for current square billet bending detection mode exists long, personnel working strength is high, the accuracy is low and production efficiency scheduling problem, this application embodiment still provides a bar wire stock blank bending detection system, this bar wire stock blank bending detection system specifically includes:

The device comprises a square billet bending detection device and a laser radar fixedly arranged above a conveying roller way in a production line;

the square billet bending detection device is used for executing all or part of the content in the square billet bending detection method according to the previous embodiment of the application, and is in communication connection with the laser radar and used for receiving the three-dimensional point cloud data acquired by the laser radar.

It can be understood that the billet bending detection device can be also in communication connection with the controller of the transport roller way, and is used for sending a pause operation instruction to the controller when the bar and wire raw material billets are determined to bend on the horizontal plane, so that the controller can control transport equipment where the billets are located to pause operation according to the pause operation instruction.

In addition, the billet bending detection device may be communicatively connected to a client device held by a producer or the like, and configured to send, when it is determined that the billet is bent on the horizontal plane, warning information indicating that the billet is bent on the horizontal plane to the client device.

And the square billet bending detection device can be also in communication connection with alarm equipment such as audible and visual alarm equipment corresponding to the production line, so as to control the alarm equipment to carry out alarm prompt when the situation that the raw bar and wire rod billet is bent on the horizontal plane is determined.

The embodiment of the rod and wire stock billet bending detection system provided in the application may be specifically used to execute the square billet bending detection method and/or the processing flow of the embodiment of the square billet bending detection device in the above embodiment, and the functions thereof are not described herein in detail, and may refer to the detailed description of the embodiments of the method and/or the device.

As can be seen from the foregoing description, in the rod-wire raw material blank bending detection system provided in the embodiments of the present application, by applying the target three-dimensional point cloud data corresponding to the raw material blank of the rod wire, and projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane, and then determining whether an abnormal point exists at each edge point on one long side of the raw material blank of the rod wire in the target point set, automatic bending detection of the raw material blank of the rod wire can be implemented, bending detection precision of the raw material blank of the rod wire and accuracy of a bending detection result can be effectively improved, further labor cost and time cost can be effectively saved, bending detection efficiency of the raw material blank of the rod wire can be improved, automatic closed-loop control of the raw material blank of the rod wire in a production line can be effectively implemented, production efficiency of the raw material blank of the rod wire in the production line can be effectively improved, and user experience of production personnel can be improved.

In order to further explain the scheme, taking a raw material billet of a rod wire in a square billet as an example, the application example of the application provides a method for detecting the bending of the raw material billet of the rod wire, a three-dimensional point cloud analysis technology is adopted, a laser scanning radar is placed near a furnace front conveying roller way, three-dimensional point cloud information of the raw material billet is collected, whether the raw material billet is bent or not is automatically identified, and a detection result is fed back to an automatic control system to reject the bent raw material billet. The method for detecting the bending of the raw bar and wire rod material blank is specifically described as follows:

(1) Device arrangement

Referring to the field device arrangement shown in fig. 12, a laser radar is arranged above the side of the conveying roller way, and before blanks enter the furnace, the blanks need to stay on the conveying roller way temporarily, and at the moment, three-dimensional point clouds are collected by the laser radar, so that bending detection is completed. The point cloud data scanned by the laser radar is a set of a series of (x, y, z) coordinates, the coordinate precision of the point cloud can be accurate to millimeter according to the scanning precision of actual equipment, and an example of three-dimensional point cloud data obtained by scanning is shown in fig. 13, wherein the frame is the point cloud data of a raw blank.

(2) Bending detection algorithm

Because the laser radar is difficult to be installed to be completely horizontal, a certain inclination angle can be formed on the ground, and in order to facilitate the analysis of the point cloud, the coordinate system of the point cloud is firstly subjected to rotation correction, so that the corrected coordinate of the point cloud on the ground is ensured to be parallel to the xy plane of the xyz coordinate system.

And after the laser radar mounting position is fixed, scanning by using the laser radar to obtain three-dimensional point cloud data of the background. Referring to fig. 14, the horizontal plane correction mainly uses point cloud data of the ground.

1) Horizontal plane rotation correction

Referring to fig. 15, the basic procedure of the horizontal plane rotation correction is to detect a plane P (corresponding to the ground in fig. 14) existing in the point cloud by a plane detection algorithm, and to obtain a plane equation ax+by+cz+d=0 of P. Where (a, b, c) is the normal vector of plane P and the vertical vector in the radar coordinate system should be (0, 1), it is therefore necessary to calculate the rotation matrix R rotated from the normal vector of plane (a, b, c) to the vertical vector (0, 1).

After the installation position of the laser radar is determined, the initial correction operation is only required to be executed once, and the obtained matrix R is the correction parameter. In the subsequent application, only the original point cloud data P measured by the laser radar is needed _ori Multiplying the rotation matrix R to obtain rotation corrected point cloud data P _adjust ：

P _a djust＝P _ori ·R

2) Bending detection

a) Origin calibration

Since the point cloud data acquired by the laser radar usually uses the position of the point cloud data as the origin of the coordinate system, the origin of the coordinate system needs to be transformed, and the vertical projection point of the laser radar on the ground is used as the 0 coordinate point of the Z axis (see fig. 14), so that the data processing can be more conveniently performed.

b) Point cloud extraction of upper surface of raw material blank

Referring to fig. 17, since the laser radar scan range is relatively large, points outside the region where the raw material blank is located are first removed, and the region where the raw material blank appears is selected according to the range of X, Y coordinates, that is, x1 is reserved<x<x2，y1<y<And y2, wherein the selection of x1, x2, y1 and y2 is obtained according to field measurement. Because the position of the raw blank has higher height (namely, the Z-axis coordinate value is larger) than other objects, the point cloud is screened again through the range of the Z coordinates, and the range of the Z coordinates is reserved to be within (h) ₁ ,h ₂ ) Data points of the interval to obtain a point cloud P _z ，h ₁ And h ₂ The value range of (2) satisfies h ₁ <h _r +h _s <h ₂ Wherein h is _r Is the height of the roller way, h _s For the self section height of the raw blank, the specific value is determined according to the actual condition of the site, wherein the screening point cloud according to the height can be seen in fig. 16.

c) Bend determination

Referring to FIG. 22, a point cloud P is formed on the upper surface of the obtained green stock _t Based on the above, a bending determination is performed. First, the point cloud P _t Projection onto the XY plane, i.e. point cloud P _t All points (X, Y)Z), only the X-axis, Y-axis coordinates are retained, i.e. (X, Y, Z) =>(X, Y) acquiring a set P of projected points _project . See fig. 18 for a schematic projection.

After the operation, only P needs to be judged _project Whether the long side of (2) is bent.

P _project In effect, a set of coordinate points (x, y) is a series of points, requiring a first pair of points P _project The coordinate alignment and the de-duplication are carried out, the method is to round the x and y coordinates according to the precision requirement, the precision can be 1cm (can be determined according to the actual field situation), a large number of repeated points exist after the rounding, the point cloud can be traversed for de-duplication, and a new coordinate point set Pnew is obtained. Point-cloud collection before performing aligned deduplication see fig. 19, and point-cloud collection effect before performing aligned deduplication see fig. 20.

After alignment and de-duplication, the edge point of the long side of the raw material blank along the X-axis direction can be obtained, and the process is as follows: first, a set P is obtained _new Maximum X in X-axis coordinates _max And a minimum value X _min Then from X _min Starting point and traversing P _new Obtaining P _new Wherein the X coordinate is equal to X _min If the set is empty, then slide right with d as step size (d may take 1 cm), continue traversing P _new The method comprises the steps of carrying out a first treatment on the surface of the If the set is not empty, taking the point (x, Y) with the minimum value of the Y coordinate, adding the set P of the lower edge points of the raw blank _edge . Then continue to slide right along X-axis direction with d as step length, and continue to traverse the set P _new Until the collection P of all points of the lower edge of the raw material blank is obtained _edge . It should be noted that, since the green stock may have a certain inclination on the roller table, a point not belonging to the lower edge is obtained at the head or tail of the green stock according to the above method, see point a in fig. 21. The solution is to ignore the length sigma of the head and tail (sigma is selected according to the actual situation in the field, 10cm is optional), namely only the set P between the X coordinates from B to C is processed _new Since the length of the raw material blank is more than 10m, the detection result is not affected by omitting 10cm at two ends.

Obtaining edge points of the raw material blank Set P _edge And then, detecting whether the raw material blank is bent or not. At set P _edge Finding out 2 points with the maximum and minimum X coordinates, and obtaining a linear equation L of the two points; then calculate the set P _edge If the distance between the other points in the line L is greater than a certain threshold delta (delta is selected according to the actual situation in the field, and is 10cm, the bending of the raw material blank can be judged, and if the distance between all the points and the line L is smaller than delta, the raw material blank is judged not to be bent.

Based on the above, the method for detecting the bending of the raw bar and wire rod material blank provided by the application example of the application can replace manual detection, can be combined with an automatic control system, and realizes unmanned production; higher detection precision and detection efficiency exist, and the personnel reduction and synergy can be realized.

For solving the problems of long time consumption, high working strength of personnel, low accuracy, low production efficiency and the like of the traditional square billet bending detection mode by manually observing whether the square billet is bent or not by an operator at the side of a production line in order to solve the problems of the traditional square billet bending detection mode, the application provides an embodiment of electronic equipment for realizing all or part of contents in the square billet bending detection method, and the electronic equipment specifically comprises the following contents:

Fig. 23 is a schematic block diagram of a system configuration of an electronic device 9600 of an embodiment of the present application. As shown in fig. 23, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 23 is exemplary; other types of structures may also be used in addition to or in place of the structures to implement telecommunications functions or other functions.

In one embodiment, the billet bending detection function may be integrated into the central processor. Wherein the central processor may be configured to control:

As can be seen from the above description, in the electronic device provided in this embodiment of the present application, by applying the target three-dimensional point cloud data corresponding to the square billet, and projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane, and then determining whether each edge point on one long side of the square billet in the target point set has an abnormal point, automatic bending detection on the square billet can be implemented, bending detection precision and accuracy of a bending detection result of the square billet can be effectively improved, further labor cost and time cost can be effectively saved, bending detection efficiency of the square billet can be improved, automatic closed-loop control of the square billet in a production line can be effectively implemented, production efficiency of the square billet in the production line can be effectively improved, and user experience of production personnel can be improved.

In another embodiment, the billet bending detection device may be configured separately from the central processor 9100, for example, the billet bending detection device may be configured as a chip connected to the central processor 9100, and the billet bending detection function may be realized by the control of the central processor.

As shown in fig. 23, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 need not include all of the components shown in fig. 23; in addition, the electronic device 9600 may further include components not shown in fig. 23, and reference may be made to the related art.

As shown in fig. 23, the central processor 9100, sometimes also referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, which central processor 9100 receives inputs and controls the operation of the various components of the electronic device 9600.

The memory 9140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information about failure may be stored, and a program for executing the information may be stored. And the central processor 9100 can execute the program stored in the memory 9140 to realize information storage or processing, and the like.

The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.

The memory 9140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, etc. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 storing application programs and function programs or a flow for executing operations of the electronic device 9600 by the central processor 9100.

The memory 9140 may also include a data store 9143, the data store 9143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, address book applications, etc.).

The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. A communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, as in the case of conventional mobile communication terminals.

Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, etc., may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and to receive audio input from the microphone 9132 to implement usual telecommunications functions. The audio processor 9130 can include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100 so that sound can be recorded locally through the microphone 9132 and sound stored locally can be played through the speaker 9131.

The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the billet bending detection method in the above embodiments, the computer-readable storage medium storing thereon a computer program which, when executed by a processor, implements all the steps in the billet bending detection method in which the execution subject in the above embodiments is a server or a client, for example, the processor implements the following steps when executing the computer program:

Taking a square billet as a raw material billet of a rod wire as an example, and spot-bonding the upper surface of the obtained raw material billet Cloud P _t Based on the above, a bending determination is performed. First, the point cloud P _t Projection onto the XY plane, i.e. point cloud P _t Only the X-axis, Y-axis coordinates, i.e., (X, Y, Z) =are retained>(X, Y) acquiring a set P of projected points _project 。

As can be seen from the foregoing description, the computer readable storage medium provided in the embodiments of the present application, by applying the target three-dimensional point cloud data corresponding to the square billet, and projecting each point coordinate in the target three-dimensional point cloud data onto a horizontal plane, and then determining whether each edge point on one long side of the square billet in the target point set has an abnormal point, it is able to implement automatic bending detection on the square billet, effectively improve the bending detection precision of the square billet and the accuracy of the bending detection result, further effectively save labor cost and time cost, improve the bending detection efficiency of the square billet, further effectively implement automatic closed-loop control of the square billet in the production line, and effectively improve the production efficiency of the square billet in the production line, and improve the user experience of the producer.

It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The principles and embodiments of the present invention have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. A method for detecting bending of a square billet, comprising:

judging whether each edge point on one long side of the square billet in the target point set has an abnormal point, if so, determining that the square billet is bent on the horizontal plane;

wherein the determining whether an abnormal point exists at each edge point on a long side of the square billet in the target point set, if yes, determining that the square billet is bent on the horizontal plane includes:

2. The method for detecting bending of a billet according to claim 1, wherein the step of collecting the target three-dimensional point cloud data corresponding to the horizontally placed billet from above the billet comprises:

3. The method for detecting the bending of the square billet according to claim 2, wherein the rotating correction processing is performed on the three-dimensional point cloud data of the scene to obtain the three-dimensional point cloud data of the scene after the rotating correction, and the method comprises the steps of:

4. The method for detecting the bending of the square billet according to claim 2, wherein the performing origin calibration processing on the rotation-corrected three-dimensional point cloud data of the scene to obtain origin-calibrated three-dimensional point cloud data of the scene comprises:

5. The method for detecting the bending of the square billet according to claim 2, wherein extracting the target three-dimensional point cloud data corresponding to the square billet from the scene three-dimensional point cloud data after the origin calibration comprises:

6. A billet bending detection apparatus for performing the billet bending detection method according to any one of claims 1 to 5, comprising:

7. A rod and wire stock bend detection system, comprising: the device comprises a square billet bending detection device and a laser radar fixedly arranged above a conveying roller way in a production line;

the square billet bending detection device is used for executing the square billet bending detection method according to any one of claims 1 to 5, and is in communication connection with the laser radar and used for receiving the three-dimensional point cloud data acquired by the laser radar.

8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor implements the billet bending detection method of any of claims 1 to 5.

9. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the billet bending detection method according to any of claims 1 to 5.