Method and device for monitoring steel charging process of heating furnace, storage medium and processor

Abstract

The embodiment of the invention provides a method and device for monitoring the steel charging process of a heating furnace, a storage medium and a processor, and belongs to the technical field of steel billet machining. The method comprises the steps that after a to-be-heated steel billet meeting the machining requirement is conveyed to a preset position in front of a heating furnace, three-dimensional scanning equipment is controlled to be started; receiving point cloud data acquired by the three-dimensional scanning equipment, and preprocessing the point cloud data; according to a random sample consistency algorithm, fitting a heating furnace wall plane in the point cloud data, and distinguishing steel billet point cloud data in the point cloud data; according to a random sample consistency algorithm, fitting a steel billet end face close to the heating furnace wall in the steel billet point cloud data; according to the position relation between the steel billet end face and the heating furnace wall plane, whether the roller way continues to convey the to-be-heated steel billet or not is controlled till the to-be-heated steel billet is located at the designated position in the heating furnace. The method can monitor whether the state and the position of the to-be-heated steel billet meet the steel loading requirement or not, and the automation level of steel billet production is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of steel billet processing, and in particular to a method, a device, a storage medium and a processor for monitoring a steel charging process of a heating furnace. Background Art

[0002] In the production process of the steel industry, heating of steel billets is a key link. The step of feeding steel billets into the heating furnace is called "charging steel". During the charging process, after confirming that the steel billets to be heated meet the processing requirements, the furnace door is opened and the steel billets to be heated are fed into the heating furnace through the furnace roller.

[0003] In the prior art, operators usually precisely control the rollers to ensure that the state and position of the billet to be heated meet the requirements. After the operator confirms that the billet is in place, the furnace door is closed to complete the steel loading process. During the steel loading process, it is necessary to manually observe the state of the billet and control the conveying rollers to ensure that the billet remains level on the rollers, and strictly monitor whether the billet accurately reaches the designated position in the heating furnace, otherwise it may cause production accidents.

[0004] However, on the one hand, the production environment of the heating furnace is bad, which affects the health of the on-site operators; on the other hand, manual measurement has large errors and is prone to mistakes, making it impossible to achieve the effect of automated production control. The inventors of this application found in the process of realizing the present invention that the above technical defects have not been effectively solved. Summary of the invention

[0005] The purpose of the embodiment of the present invention is to provide a method for monitoring the steel charging process of a heating furnace, which can monitor whether the state and position of the steel billet to be heated meet the steel charging requirements and improve the automation level of steel billet production.

[0006] In order to achieve the above object, an embodiment of the present invention provides a method for monitoring a heating furnace steel charging process, comprising:

[0007] After the steel billet to be heated that meets the processing requirements is transported to the preset position in front of the heating furnace, the 3D scanning device is controlled to start;

[0008] Receive point cloud data acquired by a 3D scanning device and pre-process the point cloud data;

[0009] According to the random sample consistency algorithm, the heating furnace wall plane in the point cloud data is fitted, and the billet point cloud data in the point cloud data is distinguished;

[0010] Fitting the end face of the billet close to the heating furnace wall in the billet point cloud data according to the random sample consistency algorithm; and

[0011] According to the positional relationship between the end face of the steel billet and the plane of the furnace wall of the heating furnace, the roller is controlled to continue conveying the steel billet to be heated until the steel billet to be heated is at a specified position in the heating furnace.

[0012] Optionally, the method for monitoring the steel charging process of a heating furnace further includes:

[0013] While controlling the start-up of the 3D scanning device, notify or control the furnace entrance to open; and / or

[0014] After confirming that the steel billet to be heated is completely in the heating furnace, the furnace inlet is notified or controlled to be closed.

[0015] Optionally, pre-process the point cloud data, including:

[0016] Filter out points below the horizontal plane of the roller from the point cloud data;

[0017] Points above the horizontal plane where the upper edge of the heating furnace inlet is located are filtered out from the remaining point cloud data.

[0018] Optionally, according to a random sample consistency algorithm, a heating furnace wall plane in the point cloud data is fitted, and the billet point cloud data in the point cloud data is distinguished, including:

[0019] Fitting the point cloud data according to a random sample consistency algorithm to calculate a first plane of the heating furnace wall plane; and

[0020] The steel billet point cloud data is the point cloud data obtained by deleting the points that conform to the first plane from the preprocessed point cloud data.

[0021] Furthermore, according to the random sample consistency algorithm, the end face of the steel billet close to the heating furnace wall in the steel billet point cloud data is fitted, including:

[0022] Fitting multiple surfaces of the steel billet to be heated from the steel billet point cloud data according to a random sample consistency algorithm; and

[0023] Identify whether each of the multiple fitted surfaces is a positive surface,

[0024] The multiple surfaces include: a front surface, an upper surface and a side surface, and the front surface is the end surface of the steel billet close to the furnace wall of the heating furnace.

[0025] Further, identifying whether each of the plurality of fitted surfaces is a positive surface includes:

[0026] Determine whether the currently fitted surface is a vertical plane according to the angle θ between the normal vector of the currently fitted surface and the horizontal plane;

[0027] If so, the currently fitted surface is a candidate surface;

[0028] If not, all points on the currently fitted surface are deleted from the billet point cloud data, and a new surface is fitted from the remaining billet point cloud data;

[0029] Until each surface in the billet point cloud data is fitted and all candidate surfaces are determined;

[0030] For each candidate surface, according to the angle between the current candidate surface and the plane of the heating furnace wall Determine whether the current candidate surface is parallel to the plane of the heating furnace wall; and

[0031] The candidate surface parallel to the plane of the heating furnace wall is determined to be the end surface of the billet.

[0032] Furthermore, θ is calculated according to the following formula,

[0033] Where (nx,ny,nz) is the plane normal vector of the currently fitted surface,

[0034] Calculate according to the following formula

[0035] Where (A, B, C) is the normal vector of the plane equation of the first plane.

[0036] Further, the roller is controlled whether to continue to transport the billet to be heated according to the positional relationship between the end surface of the billet and the plane of the wall of the heating furnace, including:

[0037] Calculate the center point P of the end face of the steel billet and the reference point Q of P on the plane of the heating furnace wall;

[0038] Calculate the normal vector and vector of the heating furnace wall plane The dot product of

[0039] If the dot product is ≤0, it is determined that the end surface of the billet is outside the plane of the heating furnace wall, and the roller conveyor is controlled to continue to transport the billet to be heated;

[0040] If the dot product > 0, the position relationship is determined to be that the end face of the steel billet is on the inner side of the plane of the heating furnace wall, and the roller is controlled to transport the steel billet to be heated to a specified position in the heating furnace, wherein the specified position is a position that makes the distance between the plane of the heating furnace wall and the end face of the steel billet meet a preset distance.

[0041] On the other hand, an embodiment of the present invention provides a device for monitoring the steel charging process of a heating furnace, comprising: a three-dimensional scanning device, a roller table and a controller,

[0042] Among them, the roller table is used to transport the steel billet to be heated to the designated position in the heating furnace;

[0043] A three-dimensional scanning device is arranged outside the furnace entrance of the heating furnace and faces the furnace entrance, and is used to scan the target area inside and outside the furnace entrance and obtain point cloud data of the target area;

[0044] The controller is configured as:

[0045] After the steel billet to be heated that meets the processing requirements is transported to the preset position in front of the heating furnace, the 3D scanning device is controlled to start;

[0046] Receive point cloud data acquired by a 3D scanning device and pre-process the point cloud data;

[0047] According to the random sample consistency algorithm, the heating furnace wall plane in the point cloud data is fitted, and the billet point cloud data in the point cloud data is distinguished;

[0048] According to the random sample consistency algorithm, the end face of the billet close to the heating furnace wall in the billet point cloud data is fitted;

[0049] According to the positional relationship between the end face of the steel billet and the plane of the furnace wall of the heating furnace, the roller is controlled to continue conveying the steel billet to be heated until the steel billet to be heated is at a specified position in the heating furnace.

[0050] Optionally, the three-dimensional scanning device is a lidar.

[0051] Optionally, the controller is further configured to:

[0052] While controlling the start-up of the 3D scanning device, notify or control the furnace entrance to open; and / or

[0053] After confirming that the steel billet to be heated is completely in the heating furnace, the furnace inlet is notified or controlled to be closed.

[0054] Furthermore, in the controller, the point cloud data is pre-processed, including:

[0055] Filter out points below the horizontal plane of the roller from the point cloud data;

[0056] Points above the horizontal plane where the upper edge of the heating furnace inlet is located are filtered out from the remaining point cloud data.

[0057] Furthermore, in the controller, according to the random sample consistency algorithm, the heating furnace wall plane in the point cloud data is fitted, and the billet point cloud data in the point cloud data is distinguished, including:

[0058] Fitting the point cloud data according to a random sample consistency algorithm to calculate a first plane of the heating furnace wall plane; and

[0059] The steel billet point cloud data is the point cloud data obtained by deleting the points that conform to the first plane from the preprocessed point cloud data.

[0060] Furthermore, in the controller, according to the random sample consistency algorithm, the end face of the steel billet close to the furnace wall of the heating furnace in the steel billet point cloud data is fitted, including:

[0061] According to the random sample consistency algorithm, multiple surfaces of the steel billet to be heated are fitted from the steel billet point cloud data;

[0062] According to the following steps, it is identified whether each fitted surface is a positive surface, wherein the positive surface is the end surface of the steel billet close to the furnace wall of the heating furnace:

[0063] Determine whether the currently fitted surface is a vertical plane according to the angle θ between the normal vector of the currently fitted surface and the horizontal plane;

[0064] If so, the currently fitted surface is a candidate surface;

[0065] If not, all points on the currently fitted surface are deleted from the billet point cloud data, and a new surface is fitted from the remaining billet point cloud data;

[0066] Until each surface in the billet point cloud data is fitted and all candidate surfaces are determined;

[0067] For each candidate surface, according to the angle between the current candidate surface and the plane of the heating furnace wall Determine whether the current candidate surface is parallel to the plane of the heating furnace wall; and

[0068] The candidate surface parallel to the plane of the heating furnace wall is determined to be the end surface of the billet.

[0069] Furthermore, in the controller, θ is calculated according to the following formula,

[0070] Where (nx,ny,nz) is the plane normal vector of the currently fitted surface,

[0071] Calculate according to the following formula

[0072] Where (A, B, C) is the normal vector of the plane equation of the first plane.

[0073] Furthermore, in the controller, the roller is controlled to continue to transport the billet to be heated according to the positional relationship between the end surface of the billet and the plane of the wall of the heating furnace, including:

[0074] Calculate the center point P of the end face of the steel billet and the reference point Q of P on the plane of the heating furnace wall;

[0075] Calculate the normal vector and vector of the heating furnace wall plane The dot product of

[0076] If the dot product is ≤0, it is determined that the end surface of the billet is outside the plane of the heating furnace wall, and the roller conveyor is controlled to continue to transport the billet to be heated;

[0077] If the dot product > 0, the position relationship is determined to be that the end face of the steel billet is on the inner side of the plane of the heating furnace wall, and the roller is controlled to transport the steel billet to be heated to a specified position in the heating furnace, wherein the specified position is a position that makes the distance between the plane of the heating furnace wall and the end face of the steel billet meet a preset distance.

[0078] On the other hand, an embodiment of the present invention provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute: the method of monitoring the steel charging process of a heating furnace of the present application.

[0079] On the other hand, an embodiment of the present invention provides a processor for running a program, wherein the program, when being run, is used to execute: the method for monitoring the steel charging process of a heating furnace of the present application.

[0080] On the other hand, an embodiment of the present invention provides a heating furnace for heating steel billets, comprising: a device for monitoring the steel charging process of the heating furnace of the present application, and monitoring the steel charging process of the steel billets to be heated by the device for monitoring the steel charging process of the heating furnace.

[0081] Through the above technical scheme, after the steel billet to be heated that meets the processing requirements is conveyed to the preset position in front of the heating furnace, the three-dimensional scanning equipment is started to scan the target area inside and outside the furnace entrance of the heating furnace from outside and toward the furnace entrance of the heating furnace, and the point cloud data of the target area is obtained; for the pre-processed point cloud data, the heating furnace wall plane and the steel billet end face close to the heating furnace wall are successively fitted according to the random sample consistency algorithm, and finally, according to the relative position relationship between the heating furnace wall plane and the steel billet end face, it is judged whether the steel billet to be heated is completely conveyed to the inside of the heating furnace, and it can automatically monitor whether the state and position of the steel billet to be heated meet the steel loading requirements, eliminating the work of manual observation and manual control of the roller table, and improving the automation level of steel billet production.

[0082] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0084] Figure 1 is a flow chart of an embodiment of a method for monitoring a heating furnace steel charging process of the present invention;

[0085] Figure 2 It is a schematic diagram of the layout of an embodiment of a device for monitoring the steel charging process of a heating furnace according to the present invention. DETAILED DESCRIPTION

[0086] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0087] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0088] The embodiment of the present invention provides a method for monitoring the steel charging process of a heating furnace, such as Figure 1 As shown, the process steps include:

[0089] Step 1: After the steel billet to be heated that meets the processing requirements is transported to the preset position in front of the heating furnace, the 3D scanning device is controlled to start;

[0090] Step 2: Receive the point cloud data acquired by the 3D scanning device and pre-process the point cloud data;

[0091] Step 3: According to the random sample consistency algorithm, fit the heating furnace wall plane in the point cloud data, and distinguish the billet point cloud data in the point cloud data;

[0092] Step 4: fitting the end face of the billet close to the heating furnace wall in the billet point cloud data according to the random sample consistency algorithm; and

[0093] Step 5: Control the roller to continue conveying the billet to be heated according to the positional relationship between the end face of the billet and the plane of the furnace wall of the heating furnace, until the billet to be heated is at a specified position in the heating furnace.

[0094] In this embodiment, the steel billet to be heated that meets the processing requirements refers to the steel billet that meets the length, bending and inclination angle before entering the furnace after measurement, and the preset position in front of the heating furnace refers to the position where one end of the steel billet to be heated near the heating furnace reaches Figure 2 The furnace delivery line position on the left side of the furnace entrance. Once it reaches this position, the 3D scanning device is controlled to start, and the furnace entrance is notified or controlled to open. If necessary, the roller table should be controlled to stop first, confirm that the furnace entrance is open, and then the 3D scanning device should be controlled to start and scan the target area inside and outside the furnace entrance.

[0095] In this embodiment, the three-dimensional scanning device is a laser radar, and the heating furnace is a walking beam heating furnace, but the present invention is not limited thereto. After the laser radar is started, the cloud data scanning in the target area is immediately performed, focusing on the distance between the end of the billet and the furnace entrance. The scanning results are transmitted to the control system in real time to provide an accurate basis for the final furnace entry decision. When the position of the billet meets the furnace entry completion conditions, the system automatically closes the furnace door, completes the single steel loading process, and prepares to wait for the next billet.

[0096] In this embodiment, the target area mainly includes the heating furnace wall, the steel billet (including the visible area outside and inside the furnace), and the roller. With the plane where the roller is located as the XOY plane and the vertical upward as the Z axis, draw the XYZ three-dimensional coordinate system. Filter the points where the Z axis is greater than 0 or the z axis is greater than h, and only the points of the heating furnace wall and the steel billet are retained. For the remaining points, process them in the order of steps 3-5.

[0097] Specifically, in step 3, the following sub-steps may also be included:

[0098] Step 301: fitting point cloud data according to a random sample consistency algorithm to calculate a first plane of a heating furnace wall plane; and

[0099] Step 302: The steel billet point cloud data is the point cloud data after the preprocessed point cloud data has been deleting the points that conform to the first plane.

[0100] In step 4, the following sub-steps may also be included:

[0101] Step 401: fitting multiple surfaces of the steel billet to be heated from the steel billet point cloud data according to a random sample consistency algorithm; and

[0102] Step 402: Identify whether each of the multiple fitted surfaces is a front surface, wherein the multiple surfaces include: a front surface, an upper surface and a side surface, and the front surface is the end surface of the steel billet close to the furnace wall of the heating furnace.

[0103] In some implementations, step 402 further includes the following sub-steps:

[0104] Step 4011: determine whether each currently fitted surface is a vertical plane according to the angle θ between the normal vector of the currently fitted surface and the horizontal plane. If so, record the currently fitted surface as a candidate surface. Otherwise, jump to step 4011.

[0105] Step 4012: Delete all points on the currently fitted surface from the billet point cloud data. If a new surface is fitted from the remaining billet point cloud data, jump to step 4011; otherwise, jump to step 4013.

[0106] Step 4013: For each candidate surface, according to the angle between the current candidate surface and the plane of the heating furnace wall Determine whether the current candidate surface is parallel to the plane of the heating furnace wall;

[0107] Step 4014: Determine the candidate surface parallel to the plane of the heating furnace wall as the end face of the billet.

[0108] In step 4011, according to the formula Calculate θ, where (nx, ny, nz) is the plane normal vector of the currently fitted surface.

[0109] In step 4013, according to the formula calculate Where (A, B, C) is the normal vector of the plane equation of the first plane.

[0110] In step 5, the following sub-steps may also be included:

[0111] Step 501: Calculate the center point P of the end face of the steel billet and the reference point Q of P on the plane of the heating furnace wall.

[0112] Step 502: Calculate the normal vector and vector of the heating furnace wall plane If the dot product is ≤0, execute step 503; if the dot product is >0, execute step 504.

[0113] Step 503: determining that the positional relationship is that the end surface of the steel billet is outside the plane of the furnace wall of the heating furnace, and controlling the roller to continue conveying the steel billet to be heated;

[0114] Step 504: Determine the positional relationship such that the end face of the steel billet is on the inner side of the plane of the heating furnace wall, and control the roller conveyor to transport the steel billet to be heated to a specified position in the heating furnace, wherein the specified position is a position where a preset distance is maintained between the plane of the heating furnace wall and the end face of the steel billet.

[0115] Compared with the prior art, the technical advantages of this embodiment are:

[0116] 1. The 3D point cloud data of the steel loading site is tracked and acquired in real time by 3D scanning equipment, and the 3D point cloud data is analyzed and processed to determine the positional relationship between the steel billet and the heating furnace, and the furnace entry operation is automatically and accurately controlled accordingly, which not only improves the steel loading efficiency, but also significantly improves the production quality and safety of the heating furnace.

[0117] 2. By reasonably setting the position of the 3D scanning equipment and the designated position for loading steel, it can adapt to steel billets of different lengths and has good flexibility and scalability.

[0118] The embodiment of the present invention provides a device for monitoring the steel charging process of a heating furnace, comprising: a three-dimensional scanning device, a roller table and a controller, which are arranged as follows: Figure 2 As shown, the roller is used to transport the steel billet to be heated to the specified position in the heating furnace; the three-dimensional scanning equipment is arranged outside the furnace entrance of the heating furnace and faces the furnace entrance, and is used to scan the target area inside and outside the furnace entrance and obtain the point cloud data of the target area; the controller is used to monitor whether the state and position of the steel billet to be heated meet the steel loading requirements.

[0119] Specifically, the controller is configured to: control the start of the three-dimensional scanning device after the steel billet to be heated that meets the processing requirements is transported to a preset position in front of the heating furnace; receive the point cloud data acquired by the three-dimensional scanning device, and pre-process the point cloud data; fit the heating furnace wall plane in the point cloud data according to the random sample consistency algorithm, and distinguish the steel billet point cloud data in the point cloud data; fit the steel billet end face close to the heating furnace wall in the steel billet point cloud data according to the random sample consistency algorithm; control whether the roller continues to transport the steel billet to be heated according to the positional relationship between the steel billet end face and the heating furnace wall plane until the steel billet to be heated is completely in the heating furnace.

[0120] It should be noted that Figure 2 The three-dimensional scanning device shown in the figure is a laser radar, and the heating furnace is a walking heating furnace, but the present invention is not limited to this.

[0121] It should also be noted that Figure 2 The target area inside and outside the furnace inlet is scanned by the three-dimensional scanning device, but the target area is not limited to Figure 2 The area shown is not limited to a fixed area, but is obtained by moving the three-dimensional scanning device (i.e. Figure 2 The technicians can move the scanning area of ​​the 3D scanning device according to the position change of the roller conveying the heated billet.

[0122] In this embodiment, the steel billet to be heated that meets the processing requirements refers to the steel billet that meets the length, bending and inclination angle before entering the furnace after measurement, and the preset position in front of the heating furnace refers to the position where one end of the steel billet to be heated near the heating furnace reaches Figure 2 The furnace delivery line position on the left side of the furnace entrance. Once it reaches this position, the 3D scanning device is controlled to start, and the furnace entrance is notified or controlled to open. If necessary, the roller table should be controlled to stop first, confirm that the furnace entrance is open, and then the 3D scanning device should be controlled to start and scan the target area inside and outside the furnace entrance.

[0123] In some embodiments, the controller is further configured to: notify or control the furnace entrance to open while controlling the start-up of the three-dimensional scanning device; and / or notify or control the furnace entrance to close after determining that the steel billet to be heated is completely in the heating furnace.

[0124] In some embodiments, the controller pre-processes the point cloud data, including the following steps:

[0125] Filter out points below the horizontal plane of the roller from the point cloud data;

[0126] Points above the horizontal plane where the upper edge of the heating furnace inlet is located are filtered out from the remaining point cloud data.

[0127] It should be noted that Figure 2 A well-established plane rectangular coordinate system is shown in Figure 2 The coordinate system shown should delete the points in the point cloud data that are below the XOY plane and above the horizontal plane that is parallel to the XOY plane at the furnace entrance height, but the present invention is not limited to this. The technicians can actually set the coordinate system to first filter out the points below the horizontal plane where the roller is located from the point cloud data, and then filter out the points above the horizontal plane where the upper edge of the furnace entrance is located from the remaining point cloud data.

[0128] In some embodiments, the controller fits the heating furnace wall plane in the point cloud data according to the random sample consistency algorithm, and distinguishes the steel billet point cloud data in the point cloud data, including the following steps:

[0129] Fitting the point cloud data according to a random sample consistency algorithm to calculate a first plane of the heating furnace wall plane; and

[0130] The steel billet point cloud data is the point cloud data obtained by deleting the points that conform to the first plane from the preprocessed point cloud data.

[0131] Specifically, the point cloud data (Cloud_Fur, not shown) is fitted using the Random Sample Consensus (RANSAC) algorithm to accurately calculate the furnace wall plane (Plane_Fur, see Figure 2 ) is Ax+By+Cz+D=0, using n given =(A, B, C) represents the normal vector of the plane. By deleting all points near the plane Plane_Fur, the billet point cloud data (Cloud_Bil, not shown) can be obtained.

[0132] In some embodiments, the controller fits the end face of the steel billet close to the furnace wall of the heating furnace in the steel billet point cloud data according to the random sample consistency algorithm, including the following steps:

[0133] According to the random sample consistency algorithm, multiple surfaces of the steel billet to be heated are fitted from the steel billet point cloud data;

[0134] According to the following steps, it is identified whether each fitted surface is a positive surface, wherein the positive surface is the end surface of the steel billet close to the furnace wall of the heating furnace:

[0135] 1. Determine whether the currently fitted surface is a vertical plane based on the angle θ between the normal vector of the currently fitted surface and the horizontal plane;

[0136] 2. If yes, the currently fitted surface is the candidate surface;

[0137] 3. If not, all points on the currently fitted surface are deleted from the billet point cloud data, and a new surface is fitted from the remaining billet point cloud data;

[0138] 4. Until each surface in the billet point cloud data is fitted and all candidate surfaces are determined;

[0139] 5. For each candidate surface, according to the angle between the current candidate surface and the plane of the heating furnace wall Determine whether the current candidate surface is parallel to the plane of the heating furnace wall;

[0140] 6. Determine the candidate surface parallel to the plane of the heating furnace wall as the end face of the billet.

[0141] In some embodiments, the controller calculates θ according to the following formula, Where (nx,ny,nz) is the plane normal vector of the currently fitted surface.

[0142] In some embodiments, the controller calculates according to the following formula Where (A, B, C) is the normal vector of the plane equation of the first plane.

[0143] Specifically, since the lower surface, the rear surface and part of the side surface are blocked when the laser radar scans the billet, the billet point cloud data Cloud_Bil has three rectangular surfaces: the front surface, the upper surface, and the left or right side surface. The RANSAC algorithm is used to perform initial plane fitting on the billet point cloud data Cloud_Bil. For each fitted plane, immediately evaluate whether it is a front surface, that is, the end face of the billet close to the furnace wall of the heating furnace. The evaluation method is as follows: calculate the angle θ between the current fitted plane normal vector and the XOY plane; if |θ-90°|>α (α is the preset threshold, α<10°), the plane is considered not to be a vertical plane. If the fitted plane is not a vertical plane, immediately delete the points near the plane from the point cloud. For candidate planes identified as vertical planes, further determine whether they are parallel to the given vertical plane. Calculate the candidate plane normal vector n candidate =(nx,ny,nz) and the given plane normal vector n given Angle: if or (β is the preset threshold, β<10°), the candidate plane is considered to be parallel to the given vertical plane. If the fitted plane is not parallel to the plane Plane_Fur, the points near the plane are deleted from the point cloud. Continue to perform RANSAC fitting on the remaining point clouds until the end face of the billet close to the heating furnace wall is found (Plane_Bil, see Figure 2 ).

[0144] In some embodiments, the controller controls whether the roller conveyor continues to convey the billet to be heated according to the positional relationship between the billet end surface and the wall plane of the heating furnace, including the following steps:

[0145] Calculate the center point P of the end face of the steel billet and the reference point Q of P on the plane of the heating furnace wall;

[0146] Calculate the normal vector and vector of the heating furnace wall plane The dot product of

[0147] If the dot product > 0, it is determined that the positional relationship is that the end surface of the steel billet is on the inner side of the plane of the heating furnace wall, and the roller conveyor is controlled to stop conveying the steel billet to be heated;

[0148] If the dot product is ≤0, the positional relationship is that the end face of the billet is outside the plane of the heating furnace wall, and the roller is controlled to continue to transport the billet to be heated.

[0149] Specifically, after finding the billet end surface Plane_Bil, it is necessary to calculate the distance between Plane_Bil and Plane_Fur, and determine whether Plane_Bil is on the left or right side of Plane_Fur, so as to calculate the position coordinates of the billet in the heating furnace.

[0150] More specifically, take a point (x, y, z) on Plane_Bil, and the distance from the point to the plane Plane_Fur can be calculated according to the point-to-plane distance formula. For a more accurate result, the average distance d from all points on Plane_Bil to a given plane can be calculated. The following is a method for simply calculating whether the billet is located on the left or right side of the heating furnace wall in this application. Take the center point P of Plane_Bil and the reference point Q of Plane_Fur, and use the Plane_Fur normal vector n given and vector The dot product dot_product determines the relative position of Plane_Bil and Plane_Fur: dot_product = (Px-Qx)*A+(Py-Qy)*B+(Pz-Qz)*C.

[0151] If dot_product>0, it means that the billet is in the heating furnace. The controller can determine whether the conditions for entering the furnace are met based on the distance d. If so, entering the furnace is completed. If dot_product≤0, the end face of the billet is outside the furnace or just at the entrance of the heating furnace, and has not yet completely entered the furnace. Continue monitoring and calculation until entering the furnace is completed.

[0152] An embodiment of the present invention provides a device for monitoring the steel charging process of a heating furnace, including a processor and a memory. The controller is stored in the memory as a program unit, and the processor executes the program unit stored in the memory to implement corresponding functions.

[0153] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the state and position of the billet to be heated can be monitored by adjusting the kernel parameters to see if they meet the requirements for loading steel, thereby improving the automation level of billet production.

[0154] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0155] An embodiment of the present invention provides a storage medium on which a program is stored. When the program is executed by a processor, the method for monitoring the steel charging process of a heating furnace of the present application is implemented.

[0156] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program, when running, executes the method of monitoring the steel charging process of a heating furnace of the present application.

[0157] The embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the method steps of monitoring the steel charging process of a heating furnace of the present application when executing the program. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0158] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps for monitoring the steel charging process of a heating furnace of the present application.

[0159] The present application also provides a heating furnace for heating steel billets, comprising: a device for monitoring the steel charging process of the heating furnace of the present application, and monitoring the steel charging process of the steel billets to be heated by the device.

[0160] 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.

[0161] 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.

[0162] 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 including 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.

[0163] 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 The steps for the functions specified in one or more boxes.

[0164] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0165] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0166] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0167] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0168] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for monitoring a heating furnace steel charging process, comprising: After the steel billet to be heated that meets the processing requirements is transported to a preset position in front of the heating furnace, the three-dimensional scanning device is controlled to start; Receiving point cloud data acquired by the three-dimensional scanning device, and preprocessing the point cloud data; According to a random sample consistency algorithm, fitting the heating furnace wall plane in the point cloud data, and distinguishing the steel billet point cloud data in the point cloud data; Fitting the end face of the steel billet close to the heating furnace wall in the steel billet point cloud data according to a random sample consistency algorithm; and The roller is controlled to continue conveying the steel billet to be heated according to the positional relationship between the end surface of the steel billet and the plane of the furnace wall of the heating furnace, until the steel billet to be heated is at a specified position in the heating furnace.

2. The method for monitoring the steel charging process of a heating furnace according to claim 1, characterized in that: Also includes: While controlling the three-dimensional scanning device to start, notifying or controlling the furnace entrance to open; and / or After determining that the steel billet to be heated is completely in the heating furnace, the furnace inlet is notified or controlled to be closed.

3. The device for monitoring the steel charging process of a heating furnace according to claim 1, characterized in that: The preprocessing of the point cloud data comprises: Screening out points below the horizontal plane where the roller is located from the point cloud data; Points above the horizontal plane where the upper edge of the furnace inlet of the heating furnace is located are filtered out from the remaining point cloud data.

4. The method for monitoring the steel charging process of a heating furnace according to any one of claims 1 to 3, characterized in that: The method of fitting the heating furnace wall plane in the point cloud data according to the random sample consistency algorithm and distinguishing the steel billet point cloud data in the point cloud data includes: Fitting the point cloud data according to a random sample consistency algorithm to calculate a first plane of the heating furnace wall plane; and The steel billet point cloud data is the point cloud data obtained by deleting points conforming to the first plane from the preprocessed point cloud data.

5. The method for monitoring the steel charging process of a heating furnace according to claim 4, characterized in that: The step of fitting the end face of the steel billet close to the furnace wall of the heating furnace in the steel billet point cloud data according to the random sample consistency algorithm comprises: fitting a plurality of surfaces of the steel billet to be heated from the steel billet point cloud data according to a random sample consistency algorithm; and Identify whether each of the multiple fitted surfaces is a positive surface, The multiple surfaces include: a front surface, an upper surface and a side surface, and the front surface is the end surface of the steel billet close to the furnace wall of the heating furnace.

6. The method for monitoring the steel charging process of a heating furnace according to claim 5, characterized in that: The step of identifying whether each of the plurality of fitted surfaces is a positive surface comprises: Determine whether the currently fitted surface is a vertical plane according to the angle θ between the normal vector of the currently fitted surface and the horizontal plane; If so, the currently fitted surface is a candidate surface; If not, all points on the currently fitted surface are deleted from the steel billet point cloud data, and a new surface is fitted from the remaining steel billet point cloud data; until each surface in the steel billet point cloud data is fitted and all candidate surfaces are determined; For each candidate surface, according to the angle between the current candidate surface and the plane of the heating furnace wall, Determine whether the current candidate surface is parallel to the plane of the heating furnace wall; and A candidate surface parallel to the plane of the heating furnace wall is determined as the end surface of the steel billet.

7. The method for monitoring the steel charging process of a heating furnace according to claim 6, characterized in that: The θ is calculated according to the following formula, Where (nx,ny,nz) is the plane normal vector of the currently fitted surface, The calculation is based on the following formula Wherein, (A, B, C) is the normal vector of the plane equation of the first plane.

8. The method for monitoring the steel charging process of a heating furnace according to claim 5, characterized in that: The step of controlling whether the roller conveyor continues to convey the steel billet to be heated according to the positional relationship between the end surface of the steel billet and the plane of the furnace wall of the heating furnace comprises: Calculate the center point P of the end face of the steel billet and the reference point Q of P on the plane of the furnace wall of the heating furnace; Calculate the normal vector and vector of the heating furnace wall plane The dot product of If the dot product is ≤0, determining that the positional relationship is that the end surface of the steel billet is outside the plane of the furnace wall of the heating furnace, and controlling the roller to continue conveying the steel billet to be heated; and If the dot product > 0, the positional relationship is determined to be that the end face of the steel billet is on the inner side of the plane of the heating furnace wall, and the roller conveyor is controlled to transport the steel billet to be heated to a specified position in the heating furnace, wherein the specified position is a position that makes the distance between the plane of the heating furnace wall and the end face of the steel billet meet a preset distance.

9. A device for monitoring the steel charging process of a heating furnace, characterized in that: include: 3D scanning equipment, roller table and controller, Wherein, the roller is used to transport the steel billet to be heated to a designated position in the heating furnace; The three-dimensional scanning device is arranged outside the furnace entrance of the heating furnace and faces the furnace entrance, and is used to scan the target area inside and outside the furnace entrance and obtain point cloud data of the target area; The controller is configured to: After the steel billet to be heated that meets the processing requirements is transported to a preset position in front of the heating furnace, controlling the three-dimensional scanning device to start; Receiving point cloud data acquired by the three-dimensional scanning device, and preprocessing the point cloud data; According to a random sample consistency algorithm, fitting the heating furnace wall plane in the point cloud data, and distinguishing the steel billet point cloud data in the point cloud data; According to a random sample consistency algorithm, fitting the end face of the steel billet close to the furnace wall of the heating furnace in the steel billet point cloud data; The roller is controlled to continue conveying the steel billet to be heated according to the positional relationship between the end surface of the steel billet and the plane of the furnace wall of the heating furnace, until the steel billet to be heated is at a specified position in the heating furnace.

10. The device for monitoring the steel charging process of a heating furnace according to claim 9, characterized in that: The three-dimensional scanning device is a laser radar.

11. The device for monitoring the steel charging process of a heating furnace according to claim 9, characterized in that: The controller is also configured to: While controlling the start-up of the three-dimensional scanning device, notifying or controlling the furnace entrance to open; and / or After determining that the steel billet to be heated is completely in the heating furnace, the furnace inlet is notified or controlled to be closed.

12. The device for monitoring the steel charging process of a heating furnace according to any one of claims 9 to 11, characterized in that: The controller pre-processes the point cloud data, including: Screening out points below the horizontal plane where the roller is located from the point cloud data; Points above the horizontal plane where the upper edge of the furnace inlet of the heating furnace is located are filtered out from the remaining point cloud data.

13. The device for monitoring the steel charging process of a heating furnace according to claim 12, characterized in that: The controller, according to a random sample consistency algorithm, fits the heating furnace wall plane in the point cloud data and distinguishes the steel billet point cloud data in the point cloud data, including: Fitting the point cloud data according to a random sample consistency algorithm to calculate a first plane of the heating furnace wall plane; and The steel billet point cloud data is the point cloud data obtained by deleting points conforming to the first plane from the preprocessed point cloud data.

14. The device for monitoring the steel charging process of a heating furnace according to claim 13, characterized in that: The controller, according to a random sample consistency algorithm, fits the end face of the steel billet close to the furnace wall of the heating furnace in the steel billet point cloud data, including: Fitting multiple surfaces of the steel billet to be heated from the steel billet point cloud data according to a random sample consistency algorithm; According to the following steps, it is identified whether each fitted surface is a positive surface, wherein the positive surface is the end surface of the steel billet close to the furnace wall of the heating furnace: Determine whether the currently fitted surface is a vertical plane according to the angle θ between the normal vector of the currently fitted surface and the horizontal plane; If so, the currently fitted surface is a candidate surface; If not, all points on the currently fitted surface are deleted from the steel billet point cloud data, and a new surface is fitted from the remaining steel billet point cloud data; until each surface in the steel billet point cloud data is fitted and all candidate surfaces are determined; For each candidate surface, according to the angle between the current candidate surface and the plane of the heating furnace wall, Determine whether the current candidate surface is parallel to the plane of the heating furnace wall; and A candidate surface parallel to the plane of the heating furnace wall is determined as the end surface of the steel billet.

15. The device for monitoring the steel charging process of a heating furnace according to claim 14, characterized in that: In the controller, The θ is calculated according to the following formula, Where (nx,ny,nz) is the plane normal vector of the currently fitted surface, The calculation is based on the following formula Wherein, (A, B, C) is the normal vector of the plane equation of the first plane.

16. The device for monitoring the steel charging process of a heating furnace according to claim 14, characterized in that: The controller controls whether the roller continues to transport the steel billet to be heated according to the positional relationship between the end surface of the steel billet and the plane of the furnace wall of the heating furnace, including: Calculate the center point P of the end face of the steel billet and the reference point Q of P on the plane of the furnace wall of the heating furnace; Calculate the normal vector and vector of the heating furnace wall plane The dot product of If the dot product is ≤0, determining that the positional relationship is that the end surface of the steel billet is outside the plane of the furnace wall of the heating furnace, and controlling the roller to continue conveying the steel billet to be heated; and If the dot product > 0, the positional relationship is determined to be that the end face of the steel billet is on the inner side of the plane of the heating furnace wall, and the roller conveyor is controlled to transport the steel billet to be heated to a specified position in the heating furnace, wherein the specified position is a position that makes the distance between the plane of the heating furnace wall and the end face of the steel billet meet a preset distance.

17. A machine-readable storage medium having instructions stored thereon, characterized in that: The instruction is used to make the machine execute: the method for monitoring the steel charging process of a heating furnace according to any one of claims 1 to 8.

18. A processor, characterized in that: Used to run a program, wherein the program, when run, is used to execute: the method for monitoring the steel charging process of a heating furnace according to any one of claims 1 to 8.

19. A heating furnace for heating a steel billet, characterized in that: include: The device for monitoring the steel charging process of a heating furnace according to any one of claims 9 to 16, and the steel charging process of the steel billet to be heated is monitored by the device for monitoring the steel charging process of a heating furnace.

Images