A method and system for detecting a sintering machine trolley operation time apron fault

Abstract

The application relates to the field of sintering machine trolley fault detection, and provides a sintering machine trolley operation fence failure detection method and system. A line structure light device is arranged at the waist line of the fence, and is connected with a computer to control the line laser generator to emit a laser line to form a light stripe on the fence. The camera is controlled to collect the data of the light stripe, the data of the light stripe is transmitted to the computer to generate fence scanning data. A world coordinate system is established with the vertical and horizontal ground direction as the X axis, the vertical fence direction as the Y axis, and the movement direction of the trolley as the Z axis to generate a point cloud model of the fence outer side contour. Whether the fence has an angle defect, inclination or a gap between adjacent fences is judged according to the point cloud model of the fence outer side contour. The fence angle defect, inclination or gap between adjacent fences can be detected, the detection result is not interfered by the fence outer side reinforcing rib, and the detection result is accurate and timely.

Description

Technical Field

[0001] This application relates to the field of sintering machine trolley fault detection, and in particular to a method and system for detecting side plate faults during sintering machine trolley operation. Background Technology

[0002] The sintering machine is the main equipment in the sintering production process, and its normal operation directly affects the stability of the entire production process. The sintering machine trolley, as a core component of the sintering machine, plays a crucial role in the machine's operating rate. The sintering machine trolley consists of seven parts: the body, side rails, wheels, grate bars, heat insulation components, sealing sliders, and grate pins. Due to the large number of trolleys on the sintering machine, their complex component structure, and the harsh operating conditions, downtime caused by sintering machine trolley malfunctions accounts for a significant proportion of abnormal downtime in sintering.

[0003] During the sintering process, the trolley side panels may tilt or break due to the harsh environment of alternating hot and cold temperatures, material gravity, and the overturning of the trolley's head and tail tracks. This can affect normal material loading, hinder the normal operation of the sintering machine, and in severe cases, lead to production accidents. In particular, tilting of the side panels increases the gap between adjacent panels, allowing external airflow to easily enter the negative pressure system at the bottom of the trolley, resulting in increased ineffective air leakage and additional power consumption of the main exhaust fan. Therefore, fault detection of the sintering machine trolley side panels is of paramount importance.

[0004] Figure 1 This is a schematic diagram of a prior art side panel fault detection device. The trolley mainly includes a frame, grate bars, side panels, and rollers. The rotation of the rollers drives the grate bars to move, which are used to transport the mixture. The side panels on the frame are used to block the mixture, acting as a seal to prevent overflow. To detect faults in the sintering machine trolley side panels, an image acquisition device is added to one side of the side panels. The image acquisition device captures images of the side panels and analyzes them to determine whether there are faults such as breaks or gaps in the side panels.

[0005] However, see Figure 2 The diagram shows an existing balustrade structure. The balustrade is divided into an upper balustrade and a lower balustrade, which are fixed together by bolts. To ensure sufficient strength, the outer side of the balustrade is usually equipped with ribs. These ribs can interfere with image acquisition and analysis. In addition, the existing balustrade fault detection devices cannot detect whether the balustrade is tilted inward or outward, or whether there are gaps between the balustrades. Summary of the Invention

[0006] In order to detect whether the guardrail has missing corners, is tilted, or has gaps with adjacent guardrails, this application provides a method and system for detecting guardrail faults during the operation of a sintering machine trolley.

[0007] In a first aspect, this application provides a method for detecting side panel faults during the operation of a sintering machine trolley. The method is applied to a side panel fault detection system, which includes a line structured light imaging device and a computer. The line structured light imaging device is located at the waistline of the side panel. The line structured light imaging device includes a line laser generator and a camera. The line laser generator and the camera are located on the same horizontal plane. The line laser generator is perpendicular to the outer side of the side panel. The line laser generator is used to emit line lasers, and the laser lines are projected onto the side panel to form light stripes. The camera is used to capture the light stripes on the side panel. The line laser generator and the camera are connected. The computer is connected to both the line laser generator and the camera.

[0008] The method includes:

[0009] The control line laser generator emits laser lines, forming light stripes on the panel.

[0010] The camera is controlled to collect data of light stripes, and the data of light stripes is transmitted to the computer to generate slab scanning data.

[0011] The computer establishes a world coordinate system based on the scanned data of the railing, with the vertical direction to the horizontal ground as the X-axis, the direction from the railing to the inside of the railing as the Y-axis, and the movement direction of the trolley as the Z-axis, and generates a point cloud model of the outer contour of the railing.

[0012] Based on the point cloud model of the outer contour of the balustrade, determine whether the balustrade has missing corners, is tilted, or has gaps with adjacent balustrades.

[0013] Optionally, the point cloud model of the outer contour of the parapet is specifically:

[0014] Point p in the two-dimensional coordinate system of the outer contour of the parapet. i Transformed to the world coordinate system, it is represented as point P. i P i Given a three-dimensional coordinate system, with each row representing the X, Y, and Z coordinates from top to bottom, then point P... i for:

[0015]

[0016] Let Pc(k) be the cross-sectional data from the k-th detection.

[0017]

[0018] After the k-th test, all the data is denoted as Pa(k):

[0019] Pa(1)=Pc(1)

[0020]

[0021] v represents the speed of the trolley, and t represents the time interval between two data collections.

[0022] Optionally, before determining whether the railing has missing corners, is tilted, or has gaps between each railing panel based on the point cloud model of the outer contour of the railing panel, the method further includes railing panel segmentation on the trolley, wherein the railing panel segmentation includes:

[0023] Wheels with the same number corresponding to the side panels are marked as single side panels.

[0024] The length of a single panel is:

[0025] L3 = L1 + L2

[0026] L1 is the distance between wheels with the same number, L2 is the distance between adjacent wheels on two adjacent side panels, and L3 is the length of a single side panel.

[0027] Optional steps to determine if there is a missing corner include:

[0028] Set a square frame with a side length of dL.

[0029] The square frame slides from left to right and from bottom to top within the upper panel area, with a sliding interval of dL / 2.

[0030] When the square frame slides to the area to be measured, with the coordinates of its lower left corner being (xt, yt), determine all points P within the square frame that belong to this area. t P t Represented as:

[0031] P t ={p|px∈[xt,xt+dL]&&p.y∈[yt,yt+dL]}

[0032] Statistical P t If the number of points within the test area is greater than the threshold number M, the data of the fence in the test area is normal; if it is less than the threshold M, the fence in the test area is damaged, and the position (xt, yt) at this time is recorded.

[0033] Count all missing data within the upper panel. If the value is greater than 1, it indicates that there is a missing corner.

[0034] The determination of whether the railing is tilted includes: eliminating interference points, wherein the elimination of interference points includes:

[0035] Multiple vertical sampling lines were collected at equal intervals on the panel, avoiding the vertical bracing.

[0036] The jump data for the filtered tension section on each sampling line is as follows:

[0037] Sort the points on each line according to the X direction, calculate the gradient of each point on the sampling line, and find the gradient t of the i-th point. i for:

[0038] t i =(p i+1 .yp i-1 .y) / 2

[0039] Find the first point on the sampling line where the gradient is greater than the threshold N along the X-axis.

[0040] Find the first point where the gradient is less than -N, and you will find the points where the gradient is less than the threshold -N.

[0041] The two points Tk and -Tk form the interference interval [-N, N].

[0042] The interference interval [-N, N] is a complex interval; delete all interference intervals.

[0043] Optionally, the steps to determine whether the guardrail is tilted include:

[0044] Project the sampling lines onto the XY plane.

[0045] The sampling line was fitted using the least squares method:

[0046] y = g*x + h

[0047] Where g is the slope of the line and h is the offset coefficient.

[0048] Calculate the angle θ between the sampling line and the X-axis:

[0049] θ=tan -1 (g)

[0050] Obtain all tilt angles of all sampled lines on a single panel, and obtain the average tilt angle. The average tilt angle Represented as:

[0051]

[0052] The average tilt angle is the tilt angle of the railing. If the absolute value of the tilt angle is greater than the set tilt threshold P, the railing is determined to be tilted. If the absolute value of the tilt angle is less than or equal to the set tilt threshold P, the railing is determined to be normal.

[0053] Alternatively, fit a plane equation based on all sampled lines:

[0054] a*X+b*Y+c*Z=F

[0055] Where a, b, c, and F are coefficients.

[0056] The plane normal vector n(a, b, c) is obtained.

[0057] The angle is obtained by considering the angle between the plane normal vector and the y-axis (0, 1, 0). included angle Represented as:

[0058]

[0059] If the included angle If the absolute value is greater than the set threshold Q, it is determined that the railing is tilted; if the included angle is greater than the set threshold Q, it is determined that the railing is tilted. If the absolute value is less than or equal to the set threshold Q, the panel is considered normal.

[0060] Optionally, determining whether there is a gap between a balustrade panel and an adjacent balustrade panel includes:

[0061] If the absolute value of the difference between the inclination angle of a balustrade and the inclination angle of an adjacent balustrade is greater than a set threshold I, then it is determined that there is a gap between the balustrade and the adjacent balustrade.

[0062] Secondly, this application also provides a computer, which is a computer in a panel fault detection system, the computer comprising:

[0063] The laser generating module is used to control the line laser generator to emit laser lines, forming light stripes on the panel.

[0064] The light stripe acquisition module is used to control the camera to acquire light stripe data and transmit the light stripe data to the computer to generate panel scanning data.

[0065] The outer contour point cloud model creation module is used to establish a world coordinate system with the vertical direction of the horizontal ground as the X-axis, the direction from the vertical side panel to the inside of the side panel as the Y-axis, and the movement direction of the trolley as the Z-axis, and generate the point cloud model of the outer contour of the side panel.

[0066] The determination module is used to determine whether the railing has missing corners, is tilted, or has gaps with adjacent railings based on the point cloud model of the outer contour of the railing.

[0067] Thirdly, this application also provides a detection system for side panel faults during the operation of a sintering machine trolley, a line structured light imaging device, and a computer. The line structured light imaging device is located at the waistline of the side panel. The line structured light imaging device includes a line laser generator and a camera. The line laser generator and the camera are located on the same horizontal plane. The line laser generator is perpendicular to the outer side of the side panel. The line laser generator is used to emit line lasers, and the laser lines are projected onto the side panel to form light stripes. The camera is used to capture the light stripes on the side panel. The line laser generator and the camera are connected. The computer is connected to both the line laser generator and the camera.

[0068] The computer is configured to:

[0069] The laser generator is controlled to emit laser lines, forming light stripes on the panel.

[0070] The camera is controlled to collect data of light stripes, and the data of light stripes is transmitted to the computer to generate slab scanning data.

[0071] Based on the scanning data of the railing, a world coordinate system is established with the direction perpendicular to the horizontal ground as the X-axis, the direction perpendicular to the railing and inward as the Y-axis, and the movement direction of the trolley as the Z-axis, to generate a point cloud model of the outer contour of the railing.

[0072] Based on the point cloud model of the outer contour of the balustrade, determine whether the balustrade has missing corners, is tilted, or has gaps with adjacent balustrades.

[0073] As can be seen from the above technical solutions, this application provides a method and system for detecting side panel faults during the operation of a sintering machine trolley. A line structured light device is installed at the waistline of the side panel and connected to a computer. A line laser generator is controlled to emit laser lines, forming light stripes on the side panel. A camera is controlled to collect the data of the light stripes, which is then transmitted to the computer to generate side panel scanning data. Based on the side panel scanning data, a world coordinate system is established with the vertical direction to the horizontal ground as the X-axis, the direction perpendicular to the side panel and inward as the Y-axis, and the movement direction of the trolley as the Z-axis, generating a point cloud model of the outer contour of the side panel. Based on the point cloud model of the outer contour of the side panel, it is determined whether the side panel has missing corners, is tilted, or has gaps with adjacent side panels. The method and system for detecting side panel faults during the operation of a sintering machine trolley provided by this application can detect faults such as missing corners, tilting, or gaps with adjacent side panels, avoiding interference from the outer bracing of the side panel on the detection results, and providing accurate and timely detection results. Attached Figure Description

[0074] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0075] Figure 1 This is a schematic diagram of an existing parapet fault detection device;

[0076] Figure 2 A schematic diagram of the existing balustrade structure;

[0077] Figure 3 A schematic diagram of the world coordinate system established for the outer side of the balustrade;

[0078] Figure 4A scene diagram of a detection system for side panel failure during sintering machine trolley operation provided in an embodiment of this application;

[0079] Figure 5 This is a partial schematic diagram of the sampling line;

[0080] Figure 6 This is a schematic diagram of the balustrade segmentation;

[0081] Figure 7 A flowchart illustrating a method for detecting side plate failures during sintering machine trolley operation, as provided in this application embodiment;

[0082] Figure 8 This is a schematic diagram of the internal structure of a computer. Detailed Implementation

[0083] The embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described below do not represent all embodiments consistent with this application. They are merely examples of systems and methods consistent with some aspects of this application as detailed in the claims.

[0084] See Figure 4 This is a scene diagram of a sintering machine trolley side panel fault detection system provided in an embodiment of this application. See also... Figure 7 This is a flowchart of a method for detecting side panel faults during the operation of a sintering machine trolley, provided in an embodiment of this application.

[0085] In a first aspect, embodiments of this application provide a method for detecting side panel faults during the operation of a sintering machine trolley. The method is applied to a side panel fault detection system, which includes a line structured light imaging device and a computer. The line structured light imaging device is located at the waistline of the side panel. The line structured light imaging device includes a line laser generator and a camera. The line laser generator and the camera are located on the same horizontal plane. The line laser generator is perpendicular to the outer side of the side panel. The line laser generator is used to emit line lasers, and the laser lines are projected onto the side panel to form light stripes. The camera is used to capture the light stripes on the side panel. The line laser generator and the camera are connected. The computer is connected to both the line laser generator and the camera.

[0086] The line structured light imaging device is positioned 0.8m-2m from the outer edge of the railing, with a field of view covering the longitudinal area of ​​the railing. The specific installation location needs to be determined based on the site environment and sintering process requirements. The line structured light equipment consists of a line laser generator and a camera, connected together by a bracket. After special calibration, 3D scanning is performed. Typically, the line laser generator is perpendicular to the railing, with the line plane vertical. The camera is on the same horizontal plane as the line laser generator, forming an angle of approximately 30-70°, preferably 40°.

[0087] The method includes:

[0088] S101, the control line laser generator emits a laser line, forming light stripes on the panel.

[0089] S102 controls the camera to collect light stripe data, transmits the light stripe data to the computer, and generates panel scanning data.

[0090] S103, the computer establishes a world coordinate system based on the scanned data of the railing, with the vertical direction to the horizontal ground as the X-axis, the direction from the railing to the inside of the railing as the Y-axis, and the movement direction of the trolley as the Z-axis, and generates a point cloud model of the outer contour of the railing.

[0091] See Figure 3 This is a schematic diagram of the world coordinate system established on the outer side of the balustrade.

[0092] The line structured light device measures the contour data of a cross-section containing a laser line in a single measurement, measuring n points at a time, denoted as p1, p2, p3, ... p. i ...p n The result is a two-dimensional data in the laser plane.

[0093] Specifically, the point cloud model of the outer contour of the parapet is as follows:

[0094] Point p in the two-dimensional coordinate system of the outer contour of the parapet. i Transformed to the world coordinate system, it is represented as point P. i P i Given a three-dimensional coordinate system, with each row representing the X, Y, and Z coordinates from top to bottom, then point P... i for:

[0095]

[0096] Let Pc(k) be the cross-sectional data from the k-th detection.

[0097]

[0098] After the k-th test, all the data is denoted as Pa(k):

[0099] Pa(1)=Pc(1)

[0100]

[0101] v represents the speed of the trolley, and t represents the time interval between two data collections.

[0102] Through the above transformation, the outer cross-sectional data of the trolley side panels can be unified into the world coordinate system. As the trolley moves continuously, a complete dataset of the trolley side profile can be constructed. Based on the overall data model, the status of each wheel and side panel on the side of the sintering machine trolley can be intuitively reflected.

[0103] See Figure 6 This is a schematic diagram of the guardrail segmentation. Below the guardrail are the wheels, located on the outer side of the guardrail. Segmentation is performed based on positional limits in the X and Y directions to determine the wheel positions. The guardrail can be segmented based on the wheel positioning and wheel numbering signals, and its numbering information is recorded. Before the step of determining whether the guardrail has missing corners, tilting, or gaps between each guardrail segment based on the point cloud model of the outer contour of the guardrail, the process also includes trolley guardrail segmentation, which includes:

[0104] Wheels with the same number corresponding to the side panels are marked as single side panels.

[0105] The length of a single panel is:

[0106] L3 = L1 + L2

[0107] L1 is the distance between wheels with the same number, L2 is the distance between adjacent wheels on two adjacent side panels, and L3 is the length of a single side panel.

[0108] The division of the workshop is consistent with the boundary line of the trolley divided by the wheels, according to Figure 6 The dimensions are segmented. Based on the positioning information of the trolley, the trolley number can be matched one-to-one with the segmented trolley, which facilitates the subsequent analysis of the sideboard status. After identifying a sideboard fault, the corresponding sideboard can be accurately located.

[0109] S104, based on the point cloud model of the outer contour of the balustrade, determine whether the balustrade has missing corners, is tilted, or has gaps with adjacent balustrades.

[0110] The steps for determining whether there is a missing corner include:

[0111] Set a square frame with a side length of dL.

[0112] The square frame slides from left to right and from bottom to top within the upper panel area, with a sliding interval of dL / 2.

[0113] When the square frame slides to the area to be measured, with the coordinates of its lower left corner being (xt, yt), determine all points P within the square frame that belong to this area. t P t Represented as:

[0114] P t ={p|px∈[xt,xt+dL]&&p.y∈[yt,yt+dL]}

[0115] Statistical P t If the number of points within the test area is greater than the threshold M, the data of the panel in the test area is normal; if it is less than the threshold M, the panel in the test area is damaged, and the position (xt, yt) is recorded. The threshold M is set according to the number of points on the side of the square frame. For example, for a 10*10 square frame, the threshold M is 10.

[0116] Count all missing data within the upper panel. If the value is greater than 1, it indicates that there is a missing corner.

[0117] See Figure 5 This is a partial schematic diagram of the sampling line. The protruding part in the diagram is the tensioning part, which represents the data where the gradient in the Y direction suddenly increases and then suddenly decreases.

[0118] The determination of whether the railing is tilted includes: eliminating interference points, wherein the elimination of interference points includes:

[0119] Multiple vertical sampling lines were collected at equal intervals on the panel, avoiding the vertical bracing.

[0120] The jump data for the filtered tension section on each sampling line is as follows:

[0121] Sort the points on each line according to the X direction, calculate the gradient of each point on the sampling line, and find the gradient t of the i-th point. i for:

[0122] t i =(p i+1 .yp i-1 .y) / 2

[0123] The first point whose gradient is greater than the threshold N is found along the X-axis on the sampling line. The threshold N is set according to the height of the tie rod. The height of the non-tiest part is 0, and the tie rod part is a protruding part with a certain height. In this embodiment, it is set to 2.

[0124] Find the first point where the gradient is less than -N, and you will find the points where the gradient is less than the threshold -N.

[0125] The two points Tk and -Tk form the interference interval [-N, N].

[0126] The interference interval [-N, N] is a complex interval; delete all interference intervals.

[0127] The steps for determining whether a balustrade is tilted include:

[0128] Project the sampling lines onto the XY plane.

[0129] The sampling line was fitted using the least squares method:

[0130] y = g*x + h

[0131] Where g is the slope of the line and h is the offset coefficient.

[0132] Calculate the angle θ between the sampling line and the X-axis:

[0133] θ=tan -1 (g)

[0134] Obtain all tilt angles of all sampled lines on a single panel, and obtain the average tilt angle. The average tilt angle Represented as:

[0135]

[0136] The average tilt angle is the tilt angle of the guardrail. If the absolute value of the tilt angle is greater than the set tilt threshold P, the guardrail is determined to be tilted; if the absolute value of the tilt angle is less than or equal to the set tilt threshold P, the guardrail is determined to be normal. The tilt threshold P is the maximum allowable tilt angle of the guardrail based on actual production needs; in this embodiment, the tilt threshold is 3°.

[0137] Alternatively, fit a plane equation based on all sampled lines:

[0138] a*X+b*Y+c*Z=F

[0139] Where a, b, c, and F are coefficients.

[0140] The plane normal vector n(a, b, c) is obtained.

[0141] The angle is obtained by considering the angle between the plane normal vector and the y-axis (0, 1, 0). included angle Represented as:

[0142]

[0143] If the included angle If the absolute value is greater than the set threshold Q, it is determined that the railing is tilted; if the included angle is greater than the set threshold Q, it is determined that the railing is tilted. If the absolute value of the angle is less than or equal to the set threshold Q, the railing is determined to be normal. The threshold Q is the maximum allowable tilt angle based on actual production needs, which is essentially the angle between the normal vector of the railing plane and the Y-axis. In this embodiment, it is set to 3°.

[0144] The determination of whether there is a gap between a balustrade and an adjacent balustrade includes:

[0145] If the absolute value of the difference between the inclination angle of one balustrade and that of an adjacent balustrade is greater than a predetermined threshold I, then it is determined that a gap exists between the balustrade and the adjacent balustrade. The threshold I is set according to actual production needs, and it is the maximum allowable absolute value of the difference between the inclination angles of two adjacent balustrades. In this embodiment, the threshold I is set to 3°. If it exceeds 3°, it is determined that a gap exists.

[0146] See Figure 8 This is a schematic diagram of the internal structure of a computer. Secondly, this application also provides a computer, which is a computer in a panel fault detection system, the computer comprising:

[0147] S1, laser generation module, is used to control the line laser generator to emit laser lines, forming light stripes on the panel.

[0148] S2, the light stripe acquisition module, is used to control the camera to acquire light stripe data and transmit the light stripe data to the computer to generate panel scanning data.

[0149] S3, the point cloud model creation module for the outer contour, is used to establish a world coordinate system with the vertical direction of the horizontal ground as the X-axis, the direction from the vertical sideboard to the inside of the sideboard as the Y-axis, and the movement direction of the trolley as the Z-axis, and generate the point cloud model of the outer contour of the sideboard.

[0150] S4, the determination module, is used to determine whether the railing has missing corners, is tilted, or has gaps with adjacent railings based on the point cloud model of the outer contour of the railing.

[0151] Thirdly, this application also provides a detection system for side panel faults during the operation of a sintering machine trolley, a line structured light imaging device, and a computer. The line structured light imaging device is located at the waistline of the side panel. The line structured light imaging device includes a line laser generator and a camera. The line laser generator and the camera are located on the same horizontal plane. The line laser generator is perpendicular to the outer side of the side panel. The line laser generator is used to emit line lasers, and the laser lines are projected onto the side panel to form light stripes. The camera is used to capture the light stripes on the side panel. The line laser generator and the camera are connected. The computer is connected to both the line laser generator and the camera.

[0152] The computer is configured to:

[0153] The control line laser generator emits laser lines, forming light stripes on the panel.

[0154] The camera is controlled to collect data of light stripes, and the data of light stripes is transmitted to the computer to generate slab scanning data.

[0155] Based on the scanning data of the railing, a world coordinate system is established with the direction perpendicular to the horizontal ground as the X-axis, the direction perpendicular to the railing and inward as the Y-axis, and the movement direction of the trolley as the Z-axis, to generate a point cloud model of the outer contour of the railing.

[0156] Based on the point cloud model of the outer contour of the balustrade, determine whether the balustrade has missing corners, is tilted, or has gaps with adjacent balustrades.

[0157] As can be seen from the above technical solutions, this application provides a method and system for detecting side panel faults during the operation of a sintering machine trolley. A line structured light device is installed at the waistline of the side panel and connected to a computer. A line laser generator is controlled to emit laser lines, forming light stripes on the side panel. A camera is controlled to collect the data of the light stripes, which is then transmitted to the computer to generate side panel scanning data. Based on the side panel scanning data, a world coordinate system is established with the vertical direction to the horizontal ground as the X-axis, the direction perpendicular to the side panel and inward as the Y-axis, and the movement direction of the trolley as the Z-axis, generating a point cloud model of the outer contour of the side panel. Based on the point cloud model of the outer contour of the side panel, it is determined whether the side panel has missing corners, is tilted, or has gaps with adjacent side panels. The method and system for detecting side panel faults during the operation of a sintering machine trolley provided in this application can detect faults such as missing corners, tilting, or gaps with adjacent side panels, avoiding interference from the outer bracing of the side panel on the detection results, and providing accurate and timely detection results.

[0158] This embodiment of the application uses a line structured light device to acquire the contour data of the trolley side panels in real time, analyze the health status of the side panels, including abnormalities such as missing corners, tilting, and gaps between panels. When a problem is detected in the side panels, combined with the trolley's positioning information, an alarm is promptly triggered to report the fault type and the corresponding trolley number, reducing the time the trolley operates with faults, reducing the workload of manual inspections, and ensuring the normal operation of the sintering machine. This equipment is relatively simple to install, has low maintenance costs, requires few supporting devices, and is stable and reliable.

[0159] Similar parts between the embodiments provided in this application can be referred to mutually. The specific implementation methods provided above are only a few examples under the overall concept of this application and do not constitute a limitation on the scope of protection of this application. For those skilled in the art, any other implementation methods extended from the solution of this application without creative effort shall fall within the scope of protection of this application.

Claims

1. A method for detecting side panel failures during sintering machine trolley operation, characterized in that, The method is applied to a balustrade fault detection system. The system includes a line structured light imaging device and a computer. The line structured light imaging device is located at the waistline of the balustrade. The line structured light imaging device includes a line laser generator and a camera. The line laser generator and the camera are located on the same horizontal plane. The line laser generator is perpendicular to the outer side of the balustrade. The line laser generator is used to emit a line laser, which is projected onto the balustrade to form light stripes. The camera is used to capture the light stripes on the balustrade. The line laser generator and the camera are connected. The computer is connected to both the line laser generator and the camera. The method includes: The control line laser generator emits laser lines, forming light stripes on the panel; Control the camera to collect light stripe data, transmit the light stripe data to the computer, and generate panel scanning data; The computer establishes a world coordinate system based on the scanning data of the railing, with the vertical direction to the horizontal ground as the X-axis, the direction from the railing to the inside of the railing as the Y-axis, and the movement direction of the trolley as the Z-axis, and generates a point cloud model of the outer contour of the railing. Based on the point cloud model of the outer contour of the balustrade, determine whether the balustrade has missing corners, is tilted, or has gaps with adjacent balustrades. The determination of whether the railing is tilted includes: eliminating interference points, wherein the elimination of interference points includes: Multiple vertical sampling lines were collected at equal intervals on the panel, with the sampling lines avoiding the vertical tension ribs; The jump data for the filtered tension section on each sampling line is as follows: Points in the two-dimensional coordinate system of the outer contour of the parapet. Transformed to a point in the world coordinate system , It is a three-column data set containing three-dimensional coordinates. From top to bottom, each row represents the X, Y, and Z coordinate values, respectively. for: ； Sort the points on each line according to the X direction, calculate the gradient of each point on the sampling line, and calculate the gradient of the i-th point. for: ； Find the first point on the sampling line where the gradient is greater than the threshold N along the X-axis, and obtain the point where the gradient is greater than the threshold N. Find the first point where the gradient is less than -N, and you will find the points where the gradient is less than the threshold -N. The two points Tk and -Tk form the interference interval [-N, N]; The interference interval [-N, N] is a rigid interval; delete all interference intervals. Determining whether there are gaps between adjacent balustrades includes: If the absolute value of the difference between the inclination angle of a balustrade and the inclination angle of an adjacent balustrade is greater than a set threshold I, then it is determined that there is a gap between the balustrade and the adjacent balustrade.

2. The method for detecting side panel failures during sintering machine trolley operation according to claim 1, characterized in that, The point cloud model of the outer contour of the parapet is as follows: Let Pc(k) be the cross-sectional data from the k-th detection. ； After the k-th test, all the data is denoted as Pa(k): ； ； v represents the speed of the trolley, and t represents the time interval between two data collections.

3. The method for detecting side panel failures during sintering machine trolley operation according to claim 1, characterized in that, Before determining whether the railing has missing corners, is tilted, or has gaps between each railing based on the point cloud model of the outer contour of the railing, the process also includes railing segmentation on the trolley, which includes: Wheels with the same number corresponding to the side panels are marked as single side panels. The length of a single panel is: ； The distance between wheels with the same number. This refers to the distance between two adjacent guardrail panels and the distance between adjacent wheels. This refers to the length of a single panel.

4. The method for detecting side panel failures during sintering machine trolley operation according to claim 2, characterized in that, The steps to determine if there is a missing corner include: Set a square frame with a side length of dL; The square frame slides from left to right and from bottom to top within the upper panel area, with a sliding interval of dL / 2. When the square frame slides to the area to be measured, with the coordinates of its lower left corner being (xt, yt), determine all points within the square frame that belong to that area. , Represented as: ； statistics If the number of points within the test area is greater than the threshold number M, the data of the fence in the test area is normal; if it is less than the threshold M, the fence in the test area is damaged, and the position (xt, yt) at this time is recorded. Count all missing data within the upper panel. If the value is greater than 1, it indicates that there is a missing corner.

5. The method for detecting side panel failures during sintering machine trolley operation according to claim 1, characterized in that, The steps to determine if a balustrade is tilted include: Project the sampling lines onto the XY plane; The sampling line was fitted using the least squares method: ； in is the slope of the line, and h is the offset coefficient; Calculate the angle between the sampling line and the X-axis. : ； Obtain all tilt angles of all sampled lines on a single panel, and obtain the average tilt angle. The average tilt angle Represented as: ； The average tilt angle is the tilt angle of the railing. If the absolute value of the tilt angle is greater than the set tilt threshold P, the railing is determined to be tilted. If the absolute value of the tilt angle is less than or equal to the set tilt threshold P, the railing is determined to be normal. Alternatively, fit a plane equation based on all sampled lines: ； Where a, b, c, and F are coefficients; Obtain the plane normal vector n(a, b, c); The angle is obtained by considering the angle between the plane normal vector and the y-axis (0, 1, 0). included angle Represented as: ； If the included angle If the absolute value is greater than the set threshold Q, it is determined that the railing is tilted; if the included angle is greater than the set threshold Q, it is determined that the railing is tilted. If the absolute value is less than or equal to the set threshold Q, the panel is considered normal.

6. A computer, characterized in that, The computer is a computer in a panel fault detection system, and the computer includes: The laser generating module is used to control the line laser generator to emit laser lines, forming light stripes on the panel; The light stripe acquisition module is used to control the camera to acquire light stripe data and transmit the light stripe data to the computer to generate panel scanning data. The outer contour point cloud model creation module is used to establish a world coordinate system with the vertical direction of the horizontal ground as the X-axis, the direction from the vertical side panel to the inside of the side panel as the Y-axis, and the movement direction of the trolley as the Z-axis, and generate the point cloud model of the outer contour of the side panel. The determination module is used to determine whether the railing has missing corners, is tilted, or has gaps with adjacent railings based on the point cloud model of the outer contour of the railing. The determination module is also used to collect multiple vertical sampling lines at equal intervals on the railing, with the sampling lines avoiding the vertical tension bars. The jump data for the filtered tension section on each sampling line is as follows: Points in the two-dimensional coordinate system of the outer contour of the parapet. Transformed to a point in the world coordinate system , It is a three-column data set containing three-dimensional coordinates. From top to bottom, each row represents the X, Y, and Z coordinate values, respectively. for: ； Sort the points on each line according to the X direction, calculate the gradient of each point on the sampling line, and calculate the gradient of the i-th point. for: ； Find the first point on the sampling line where the gradient is greater than the threshold N along the X-axis, and obtain the point where the gradient is greater than the threshold N. Find the first point where the gradient is less than -N, and you will find the points where the gradient is less than the threshold -N. The two points Tk and -Tk form the interference interval [-N, N]; The interference interval [-N, N] is a rigid interval; delete all interference intervals. Furthermore, it is also used to determine that there is a gap between a balustrade and an adjacent balustrade if the absolute value of the difference between the inclination angle of the balustrade and the inclination angle of the adjacent balustrade is greater than a set threshold I.

7. A detection system for side panel faults during sintering machine trolley operation, characterized in that, include: A line structured light imaging device and the computer of claim 6, wherein the line structured light imaging device is located at the waistline of a railing, the line structured light imaging device includes a line laser generator and a camera, the line laser generator and the camera are located on the same horizontal plane, the line laser generator is perpendicular to the outer side of the railing, the line laser generator is used to emit a line laser, the laser line is projected onto the railing to form light stripes, the camera is used to photograph the light stripes on the railing, the line laser generator and the camera are connected, and the computer is connected to the line laser generator and the camera respectively; The computer is configured to: The control line laser generator emits laser lines, forming light stripes on the panel; Control the camera to collect light stripe data, transmit the light stripe data to the computer, and generate panel scanning data; Based on the scanning data of the railing, a world coordinate system is established with the direction perpendicular to the horizontal ground as the X-axis, the direction perpendicular to the railing and inward as the Y-axis, and the movement direction of the trolley as the Z-axis, to generate a point cloud model of the outer contour of the railing. Based on the point cloud model of the outer contour of the balustrade, determine whether the balustrade has missing corners, is tilted, or has gaps with adjacent balustrades. The determination of whether the railing is tilted includes: eliminating interference points, wherein the elimination of interference points includes: Multiple vertical sampling lines were collected at equal intervals on the panel, with the sampling lines avoiding the vertical tension ribs; The jump data for the filtered tension section on each sampling line is as follows: Points in the two-dimensional coordinate system of the outer contour of the parapet. Transformed to a point in the world coordinate system , It is a three-column data set containing three-dimensional coordinates. From top to bottom, each row represents the X, Y, and Z coordinate values, respectively. for: ； Sort the points on each line according to the X direction, calculate the gradient of each point on the sampling line, and calculate the gradient of the i-th point. for: ； Find the first point on the sampling line where the gradient is greater than the threshold N along the X-axis, and obtain the point where the gradient is greater than the threshold N. Find the first point where the gradient is less than -N, and you will find the points where the gradient is less than the threshold -N. The two points Tk and -Tk form the interference interval [-N, N]; The interference interval [-N, N] is a rigid interval; delete all interference intervals. Determining whether there are gaps between adjacent balustrades includes: If the absolute value of the difference between the inclination angle of a balustrade and the inclination angle of an adjacent balustrade is greater than a set threshold I, then it is determined that there is a gap between the balustrade and the adjacent balustrade.

Images