Belt anomaly detection method and device and electronic equipment

Abstract

The invention provides a belt anomaly detection method and device and electronic equipment. The method comprises the steps that point cloud data of a conveying belt of a belt conveyor in a no-load state is obtained; belt cross section curves of the conveying belt at different moments are identified from the point cloud data; and extracting morphological characteristics of the belt cross section curve, and determining an abnormal result of the conveying belt according to the morphological characteristics. In the implementation process of the scheme, the belt cross-section curves of the conveying belt at different moments are identified from the point cloud data, and the abnormal result of the conveying belt is determined according to the morphological characteristics of the belt cross-section curves, so that the influence of various factors such as personal experience, vision and fatigue state on manual inspection is effectively reduced, and the inspection accuracy is improved. Therefore, the accuracy of detecting the abnormal result of the conveying belt is improved.

Description

Technical Field

[0001] The present application relates to the technical fields of industrial automation, computer vision and machine learning, and in particular to a belt anomaly detection method, device and electronic equipment. Background Art

[0002] At present, the inspection method of conveyor belts is usually to detect whether there are abnormalities through manual inspection. However, some conveyor belts are very long, and the inspectors need to run back and forth during the inspection, which makes it impossible to timely detect abnormalities such as tearing, bulging or denting of the conveyor belts. In addition, the human eye may not be able to see relatively small differences in the manual inspection method. Therefore, the accuracy of the results of detecting abnormalities of conveyor belts through manual inspection is low. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a belt abnormality detection method, device and electronic equipment, which are used to improve the problem of low accuracy in detecting abnormal results of a transport belt.

[0004] The embodiment of the present application provides a belt abnormality detection method, including: obtaining point cloud data of a conveyor belt of a belt conveyor in an unloaded state; identifying the belt cross-section curve of the conveyor belt at different times from the point cloud data; extracting the morphological features of the belt cross-section curve, and determining the abnormal results of the conveyor belt according to the morphological features. In the implementation process of the above scheme, by identifying the belt cross-section curve of the conveyor belt at different times from the point cloud data, and determining the abnormal results of the conveyor belt according to the morphological features of the belt cross-section curve, the influence of various factors such as personal experience, vision and fatigue status on manual inspection is effectively reduced, thereby improving the accuracy of detecting abnormal results of the conveyor belt.

[0005] Optionally, in an embodiment of the present application, the above-mentioned morphological features include: height difference; determining the abnormal result of the transport belt according to the morphological features includes: judging whether the height difference between the first point and the second point in the belt cross-sectional curve is greater than a first preset threshold, and the straight-line distance between the first point and the second point is less than the distance threshold; if so, determining the abnormal result of the transport belt as a tearing abnormality. In the implementation process of the above scheme, by calculating the height difference between two points in the belt cross-sectional curve, it is possible to accurately identify slight changes in the belt. The height difference is a key indicator for detecting tearing abnormalities, and can effectively capture sudden changes on the belt surface. Combining multiple features such as height difference and straight-line distance can more comprehensively describe the state of the belt and improve the accuracy and precision of detection.

[0006] Optionally, in an embodiment of the present application, the above-mentioned morphological features include: slope change value; determining the abnormal result of the transport belt according to the morphological features includes: calculating a first slope value between a first point and a second point in the belt cross-section curve, and a second slope value between the second point and a third point in the belt cross-section curve, the straight-line distance between the first point and the second point being equal to the straight-line distance between the second point and the third point; judging whether the difference between the first slope value and the second slope value is greater than a second preset threshold; if so, determining the abnormal result of the transport belt as a tearing abnormality. In the implementation process of the above scheme, by calculating the slope value between two points in the belt cross-section curve and comparing the changes in these slope values, small changes in the belt can be accurately identified. The slope change value is a key indicator for detecting tearing abnormalities, which can effectively capture mutations on the belt surface. Combining multiple features such as the slope change value and the straight-line distance can more comprehensively describe the state of the belt and improve the accuracy and precision of the detection.

[0007] Optionally, in an embodiment of the present application, the above-mentioned morphological features include: axial distance; determining the abnormal result of the transport belt according to the morphological features includes: judging whether the axial distances of the first point, the second point and the third point found in sequence in the belt cross-section curve meet preset conditions, the preset conditions include: the axial distance of the first point is less than the axial distance of the second point, and is equal to the axial distance of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point; if so, the abnormal result of the transport belt is determined as a convex abnormality. In the implementation process of the above scheme, by calculating the distance (axial distance) between each point in the belt cross-section curve and the assumed center of the circle, the slight changes of the belt can be accurately identified. The axial distance is a key indicator for detecting convex abnormalities, which can effectively capture the sudden changes on the belt surface. Combining multiple features such as axial distance and straight-line distance can more comprehensively describe the state of the belt and improve the accuracy and precision of detection.

[0008] Optionally, in an embodiment of the present application, after determining whether the axial distances of the first point, the second point, and the third point found in sequence in the belt cross-section curve meet the preset conditions, it also includes: if the axial distance of the first point is greater than or equal to the axial distance of the second point, and the axial distance of the first point is equal to the axial distance of the third point, then the abnormal result of the transport belt is determined as a concave abnormality. In the implementation process of the above scheme, by specifically analyzing the relationship between the axial distances of the first point, the second point, and the third point, the specific abnormal type of the belt can be more accurately identified. This subdivision makes the detection results more accurate, avoids misclassification of different types of abnormalities, effectively reduces false alarms, and ensures that only the belt state that truly meets the concave abnormality conditions will be marked as abnormal, which improves the accuracy of abnormal type identification.

[0009] Optionally, in an embodiment of the present application, the above-mentioned morphological features include: a height value; determining the abnormal result of the transport belt according to the morphological features includes: judging whether the height values ​​of the first point, the second point and the third point found in sequence in the belt cross-section curve meet preset conditions, the preset conditions include: the height value of the first point is less than the height value of the second point, and is equal to the height value of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point; if so, the abnormal result of the transport belt is determined as a concave abnormality. In the implementation process of the above scheme, the depression abnormality is defined by precise mathematical conditions. Due to the use of a specific mathematical model (that is, the height of the first point is less than that of the second point and equal to that of the third point, and the distance from the first point to the second point is equal to the distance from the second point to the third point), the true depression abnormality and other types of normal changes or slight deformations can be effectively distinguished, and false alarms caused by non-abnormal factors are reduced. The detection is not only based on the change in height value, but also considers the relative position and distance between points. Only when all conditions are met will it be judged as a depression abnormality. This reduces the possibility of misdiagnosing other types of abnormalities (such as bulges, tears, etc.) as depression abnormalities, and also reduces the risk of missing the diagnosis of depression abnormalities, effectively improving the accuracy of detecting depression abnormalities.

[0010] Optionally, in an embodiment of the present application, after determining whether the height values ​​of the first point, the second point, and the third point found in sequence in the belt cross-section curve meet the preset conditions, it also includes: if the height value of the first point is greater than or equal to the height value of the second point, and the height value of the first point is equal to the height value of the third point, then the abnormal result of the transport belt is determined to be a convex abnormality. In the implementation process of the above scheme, by introducing the judgment logic for different types of abnormalities, the detection system is more flexible and can adapt to more diverse application scenarios and working environments. In addition to being able to accurately detect the concave abnormality of the belt, it can now effectively identify the convex abnormality on the belt. This means that the system can monitor the status of the belt more comprehensively, ensuring that any problems that may cause equipment failure can be discovered in a timely manner, effectively improving the comprehensiveness of belt abnormality detection and the timeliness of maintenance.

[0011] An embodiment of the present application also provides a belt abnormality detection device, including: a point cloud data acquisition module, used to acquire point cloud data of the transport belt of the belt conveyor in an unloaded state; a cross-section curve recognition module, used to identify the belt cross-section curve of the transport belt at different times from the point cloud data; an abnormal result determination module, used to extract the morphological features of the belt cross-section curve, and determine the abnormal results of the transport belt based on the morphological features.

[0012] Optionally, in an embodiment of the present application, the morphological features include: a height difference; an abnormal result determination module includes: a curve two-point height judgment submodule, used to judge whether the height difference between the first point and the second point in the belt cross-section curve is greater than a first preset threshold, and the straight-line distance between the first point and the second point is less than the distance threshold; a first tearing abnormality determination submodule, used to determine the abnormal result of the transport belt as a tearing abnormality if the height difference between the first point and the second point in the belt cross-section curve is greater than the first preset threshold.

[0013] Optionally, in an embodiment of the present application, the morphological features include: a slope change value; an abnormal result determination module includes: a point slope value calculation submodule, used to calculate a first slope value between a first point and a second point in the belt cross-section curve, and a second slope value between the second point and a third point in the belt cross-section curve, the straight-line distance between the first point and the second point being equal to the straight-line distance between the second point and the third point; a slope difference judgment submodule, used to judge whether the difference between the first slope value and the second slope value is greater than a second preset threshold; a second tear abnormality determination submodule, used to determine the abnormal result of the transport belt as a tear abnormality if the difference between the first slope value and the second slope value is greater than the second preset threshold.

[0014] Optionally, in an embodiment of the present application, the morphological features include: axial distance; the abnormal result determination module includes: an axial distance condition judgment submodule, used to judge whether the axial distances of the first point, the second point and the third point found in sequence in the belt cross-section curve meet preset conditions, the preset conditions include: the axial distance of the first point is less than the axial distance of the second point, and is equal to the axial distance of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point; a first convex abnormality determination submodule, used to determine the abnormal result of the transport belt as a convex abnormality if the axial distances of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions.

[0015] Optionally, in an embodiment of the present application, the abnormal result determination module also includes: a first concave abnormality determination submodule, which is used to determine the abnormal result of the transport belt as a concave abnormality if the axial distance of the first point is greater than or equal to the axial distance of the second point, and the axial distance of the first point is equal to the axial distance of the third point.

[0016] Optionally, in an embodiment of the present application, the morphological features include: a height value; an abnormal result determination module includes: a curve point height value judgment submodule, used to judge whether the height values ​​of the first point, the second point and the third point found in sequence in the belt cross-section curve meet preset conditions, the preset conditions include: the height value of the first point is less than the height value of the second point, and is equal to the height value of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point; a second depression abnormality determination submodule, used to, if so, determine the abnormal result of the transport belt as a depression abnormality.

[0017] Optionally, in an embodiment of the present application, the abnormal result determination module also includes: a second bulge abnormality determination submodule, which is used to determine the abnormal result of the transport belt as a bulge abnormality if the height value of the first point is greater than or equal to the height value of the second point, and the height value of the first point is equal to the height value of the third point.

[0018] An embodiment of the present application further provides an electronic device, including: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions execute the method described above when executed by the processor.

[0019] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described above is executed.

[0020] The embodiment of the present application also provides a computer program product, including: a computer program or a computer instruction, and the computer program or the computer instruction executes the method described above when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A schematic diagram of a process flow of a belt abnormality detection method provided by an embodiment of the present application is shown;

[0023] Figure 2 A schematic cross-sectional view of a conveyor belt provided by an embodiment of the present application in a normal no-load state is shown;

[0024] Figure 3 A schematic diagram showing a transport belt provided by an embodiment of the present application having abnormal tearing;

[0025] Figure 4 A schematic diagram showing an abnormal bulge on a transport belt provided by an embodiment of the present application;

[0026] Figure 5 A schematic diagram showing an abnormal depression of a conveyor belt provided by an embodiment of the present application;

[0027] Figure 6 A schematic diagram of the structure of a belt abnormality detection device provided in an embodiment of the present application is shown;

[0028] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] To make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. It should be understood that the drawings in the embodiment of the present application only serve the purpose of explanation and description, and are not used to limit the protection scope of the embodiment of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in the embodiment of the present application shows the operation implemented according to some embodiments of the embodiment of the present application. It should be understood that the operation of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the embodiment of the present application, or remove one or more operations from the flowchart.

[0030] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all embodiments. The components of the embodiments of the present application described and shown in the drawings generally here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the embodiments of the present application claimed, but merely represents the selected embodiments of the embodiments of the present application.

[0031] It is understandable that the "first" and "second" in the embodiments of the present application are used to distinguish similar objects. Those skilled in the art will understand that the words "first" and "second" do not limit the quantity and execution order, and the words "first" and "second" do not necessarily limit the difference. In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that there may be three relationships, such as A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the related objects before and after are in an "or" relationship. The term "multiple" refers to more than two (including two), and similarly, "multiple groups" refers to more than two groups (including two groups).

[0032] It should be noted that the belt anomaly detection method provided in the embodiment of the present application can be executed by an electronic device, where the electronic device refers to a device terminal or server with the function of executing a computer program, such as a smart phone, a personal computer, a tablet computer, a personal digital assistant or a mobile Internet device. A server refers to a device that provides computing services through a network, such as an x86 server and a non-x86 server, and a non-x86 server includes a mainframe, a minicomputer and a UNIX server.

[0033] In the process of transporting materials by the belt of a large belt conveyor, the transport belt may gradually experience various surface wear or internal wear due to long-term operation, which may eventually lead to abnormalities such as tearing, bulging or depression. Among them, surface wear, such as when the belt contacts with rollers, drums, materials, etc., it will be affected by friction, resulting in gradual surface wear. Internal wear, such as the belt repeatedly undergoing cyclic stresses such as stretching, compression and bending during operation, leads to material fatigue. Long-term fatigue accumulation will reduce the strength of the belt and easily cause abnormal tearing.

[0034] In the related art, manual inspection is usually used to detect whether there is an abnormality. However, in various industrial fields such as mines, ports, power plants, cement plants, etc., the length of the conveyor belts in these fields is very long. During the inspection, the inspectors need to run back and forth, which makes it impossible to timely detect abnormalities such as tearing, bulging or denting of the conveyor belt. In the process of practice, it is found that manual inspections in most cases cannot achieve 24-hour seamless inspections, and the human eye may not be able to see relatively small differences in manual inspections, making it difficult to accurately detect whether the conveyor belt has an abnormality. Therefore, the accuracy of the results of detecting abnormalities of the conveyor belt through manual inspections is low.

[0035] To improve the above problems, see Figure 1 The flowchart of the belt anomaly detection method provided by the embodiment of the present application is shown; the main idea of ​​the belt anomaly detection method is to identify the belt cross-section curve of the transport belt at different times from the point cloud data, and determine the abnormal result of the transport belt according to the morphological characteristics of the belt cross-section curve, which effectively reduces the influence of various factors such as personal experience, vision and fatigue status on manual inspection, thereby improving the accuracy of detecting abnormal results of the transport belt. The implementation of the above-mentioned belt anomaly detection method may include:

[0036] Step S110: Acquire point cloud data of the conveyor belt of the belt conveyor in an unloaded state.

[0037] See also Figure 2The schematic diagram of the cross section of the conveyor belt provided by the embodiment of the present application in a normal no-load state is shown; as shown in the above figure, the conveyor belt of the belt conveyor is such a smooth curve in a normal no-load state. The conveyor belt is a curve with an arc. Even if the goods (such as flour, etc.) are put in, the arc will be deepened, but it is still a smooth curve with a deepening arc. The implementation method of the above step S110 is, for example: the conveyor belt in the no-load state is scanned in real time by a depth camera above the conveyor belt to obtain the point cloud data of the conveyor belt in the no-load state, and then the depth camera can directly send the point cloud data to the electronic device, and the electronic device can receive the above point cloud data of the conveyor belt in the no-load state. Among them, the point cloud data is composed of many points with three-dimensional coordinates, such as points with three axis coordinates of the x-axis, y-axis and z-axis. The above point cloud data may include: the cross section of the conveyor belt at different times, so in the following steps, the belt cross-section curve of the conveyor belt at different times can be identified from the point cloud data, and the belt cross-section curve here is the position curve of the conveyor belt on the cross section.

[0038] It is understandable that the camera of the above-mentioned depth camera can be set from top to bottom, and the depth camera can be a high-precision and high-resolution depth camera used in the field of industrial vision, so that the depth camera shoots the running process of the conveyor belt in an unloaded state downward. This camera setting method makes the depth camera less likely to accumulate dust and more integrated to obtain high-precision three-dimensional point cloud data. Optionally, the depth camera can also scan the running conveyor belt of the belt conveyor in real time at a high frame rate, so that the industrial vision system can ensure that abnormalities can be discovered in time through the obtained point cloud data to achieve rapid response and real-time monitoring. Compared with manual inspections, this method can achieve 24-hour continuous monitoring without missing any abnormalities in any time period. Furthermore, using a high-precision depth camera to obtain three-dimensional point cloud data of the belt can more comprehensively and accurately describe the geometric shape and surface features of the belt. Compared with traditional two-dimensional images, three-dimensional data provides more information and reduces false alarms and missed reports.

[0039] Step S120: Identify the belt cross-section curves of the transport belt at different times from the point cloud data.

[0040] For example, in the implementation of the above step S120, in the cross-sections of the conveyor belt at different times, these cross-sections are perpendicular to the conveying direction of the conveyor belt, and a fitting algorithm can be used to perform curve fitting on the belt cross-section curve in the cross-section of the point cloud data, so as to obtain the belt cross-section curve of the conveyor belt at different times. Among them, the above fitting algorithm can adopt the least squares method, Bezier curve fitting, spline curve fitting and other algorithms.

[0041] Step S130: extracting the morphological features of the belt cross-sectional curve, and determining the abnormal results of the transport belt according to the morphological features.

[0042] Morphological features refer to the geometric features that need to be processed in the industrial vision system reflected on the belt cross-sectional curve. There are many kinds of morphological features of the above-mentioned belt cross-sectional curve, including: height difference, slope change value, axis distance and / or height value and other geometric features. These features can reflect the state changes of the belt in more detail and improve the accuracy of detection.

[0043] It can be understood that since the abnormal results of the conveyor belt include: tearing abnormality, convex abnormality and concave abnormality, etc., there are many implementation methods for determining the abnormal results of the conveyor belt according to morphological characteristics. The implementation method for determining the abnormal results of the conveyor belt according to morphological characteristics will be described in detail below.

[0044] The implementation method of extracting the morphological features of the belt cross-section curve in the above step S130 is explained here by taking the tearing anomaly as an example. The method of extracting morphological features in the process of convex anomaly and concave anomaly is also similar, so it will not be repeated. Compared with the morphological features of the belt cross-section curve extracted using a single frame without longitudinal information, it may cause false alarms (such as tiny sand particles) in the case of transient noise. In order to reduce the probability of such false alarms, the morphological features of the belt cross-section curve can be determined by comparing the changes in morphological features between consecutive frames with longitudinal information, thereby ensuring that such morphological features are persistent and not caused by transient noise. This improves the reliability of belt anomaly detection, which is very important in industrial vision because industrial processes often require continuous and stable monitoring. The above-mentioned longitudinal information tearing anomaly in the single frame case is specifically manifested as occasional small holes, but the tearing anomaly in the multi-frame case will cause small holes to continue to appear in multiple frames. Specifically, if the morphological features between the point cloud data of a consecutive preset number of frames do not change, the morphological features between the point cloud data of a consecutive preset number of frames will be determined as the morphological features of the belt cross-sectional curve, ensuring that the detected abnormal results are persistent rather than instantaneous noise, thereby improving the reliability of belt abnormality detection.

[0045] In the process of implementing the above scheme, by identifying the belt cross-section curve of the conveyor belt at different times from the point cloud data, and determining the abnormal results of the conveyor belt according to the morphological characteristics of the belt cross-section curve, the influence of various factors such as personal experience, vision and fatigue status on manual inspection is effectively reduced, human errors are eliminated, and tiny differences that are difficult to detect with the naked eye can be captured, thereby improving the accuracy of detecting abnormal results of the conveyor belt.

[0046] As an optional implementation of the above step S130, the above morphological features may include: height difference; the above implementation of determining the abnormal result of the transport belt according to the morphological features may include:

[0047] Step S131a: Determine whether the height difference between the first point and the second point in the belt cross-section curve is greater than a first preset threshold, and whether the straight-line distance between the first point and the second point is less than the distance threshold.

[0048] See also Figure 3 The schematic diagram of the transport belt provided by the embodiment of the present application is shown; the dotted box in the figure is the situation where the belt is torn abnormally (also known as belt breakage), and the detailed tearing difference can be seen from the figure. It can be understood that if the difference between two points on the belt cross-section curve in the cross section on the y-axis coordinate (i.e., the height difference between the first point and the second point) is greater than a preset threshold, it can be considered that the transport belt has a tear gap.

[0049] Step S131b: If the height difference between the first point and the second point in the belt cross-section curve is greater than a first preset threshold, the abnormal result of the transport belt is determined as a tearing abnormality.

[0050] The implementation of the above steps S131a to S131b is, for example: ′ =|h1-h2| formula to determine whether the height difference between the first point and the second point in the belt cross-section curve is greater than the first preset threshold, and the straight-line distance between the first point and the second point is less than the distance threshold. If the height difference between the first point and the second point in the belt cross-section curve is greater than the first preset threshold, that is, if h ′ =|h1-h2|>τ1, the abnormal result of the conveyor belt is determined to be a tearing abnormality. ′ represents the height difference between the first point and the second point, h1 represents the height value of the first point, h2 represents the height value of the second point, and τ1 represents the first preset threshold.

[0051] As an optional implementation of the above step S130, the above morphological features may include: a slope change value; the above implementation of determining the abnormal result of the transport belt according to the morphological features may include:

[0052] Step S132a: Calculate the first slope value between the first point and the second point in the belt cross-sectional curve, and the second slope value between the second point and the third point in the belt cross-sectional curve, and the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point.

[0053] It can be understood that, taking the first slope value between the first point and the second point in the belt cross-section curve as an example, the above slope calculation process can be expressed using pseudo code as follows:

[0054] posEnd=points[min(index+defLen,len(points)-1)];

[0055] posStart = points[index];

[0056]

[0057] Wherein, points represents the point set of the belt cross-section curve, posStart represents the first point, posEnd represents the second point, index represents the index value of the first point in the point set of the belt cross-section curve, defLen represents the number of points between the first point and the second point (which can be set according to empirical values, for example, 10 or 15 points in the x-axis direction), len(points) represents the number of all points in the point set of the belt cross-section curve, posEnd[0] and posStart[0] represent the x-axis coordinate value of the first point and the x-axis coordinate value of the second point respectively, posEnd[1] and posStart[1] represent the y-axis coordinate value of the first point and the y-axis coordinate value of the second point respectively.

[0058] It can be understood that the above introduces the calculation process of the first slope value between the first point and the second point in the belt cross-sectional curve. Since the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point, that is, the number of points between the first point and the second point is equal to the number of points between the second point and the third point, the calculation process of the second slope value between the second point and the third point is also similar, and will not be repeated here.

[0059] Step S132b: Determine whether the difference between the first slope value and the second slope value is greater than a second preset threshold.

[0060] Step S132c: If the difference between the first slope value and the second slope value is greater than the second preset threshold, the abnormal result of the transport belt is determined as a tearing abnormality.

[0061] The implementation of the above steps S132b to S132c is, for example: by formula s ′=|s1-s2| to determine whether the difference between the first slope value and the second slope value is greater than the second preset threshold. In order to ensure that the detected anomaly is persistent rather than instantaneous noise, the slope value changes between consecutive frames can be compared. For example, if the difference between the first slope value and the second slope value in multiple consecutive frames is greater than the second preset threshold (expressed as s ′ =|s1-s2|>τ2,), that is, multiple consecutive frames show tearing anomalies, then it can be determined that the abnormal result of the conveyor belt is indeed a tearing anomaly. ′ represents the slope difference between the first slope value and the second slope value, s1 represents the first slope value, s2 represents the second slope value, and τ2 represents the first preset threshold value.

[0062] As an optional implementation of the above step S130, the above morphological features may include: axis distance; the above implementation of determining the abnormal result of the transport belt according to the morphological features may include:

[0063] Step S133a: Determine whether the axial distances of the first point, the second point, and the third point found in sequence in the belt cross-section curve meet preset conditions, wherein the preset conditions include: the axial distance of the first point is smaller than the axial distance of the second point, and is equal to the axial distance of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point.

[0064] See also Figure 4 A schematic diagram of a transport belt provided by an embodiment of the present application is shown in which there is an abnormal bulge in the transport belt; it can be understood that once the transport belt has an abnormal bulge, it means that the transport belt begins to show bulges or high protrusions, and the size and shape of the bulge can be seen in the belt cross-section curve in the point cloud data of continuous frames. The electronic device can identify abnormalities such as the size and position of the bulge through shape features such as the axial center distance. Specifically, the above-mentioned axial center distance is the distance between the current point and the center of the circle corresponding to the belt cross-section curve (or the focus of the hyperbola). It is assumed here that the belt cross-section curve is approximately a circle (it may also be a hyperbola). The center of the circle is used as an example for explanation. It is assumed that the two-dimensional coordinates of the center of the circle on the cross section are (x0, y0), and the two-dimensional coordinates of each point on the belt cross-section curve are (x i ,y i ), then the distance between each point on the belt cross-section curve and the center of the circle (i.e., the axis distance) is calculated as

[0065] Step S133b: If the axial center distances of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions, the abnormal result of the transport belt is determined as a convex abnormality.

[0066] For example, the implementation of the above step S133b is as follows: if the axis distances of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions, that is, the preset conditions met include: the axis distance of the first point is less than the axis distance of the second point, and is equal to the axis distance of the third point, and the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point. In order to ensure that the detected abnormality is persistent rather than instantaneous noise, the changes in the axis distances between consecutive frames can be compared, that is, if a point is displayed as a convex abnormality in multiple consecutive frames, the abnormal result of the transport belt can be determined as a convex abnormality.

[0067] As an optional implementation of the above step S130, after determining whether the axial center distances of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions, the following may also be included:

[0068] Step S133c: If the axial distance of the first point is greater than or equal to the axial distance of the second point, and the axial distance of the first point is equal to the axial distance of the third point, the abnormal result of the conveyor belt is determined as a concave abnormality.

[0069] See also Figure 5 A schematic diagram showing a depression abnormality in a conveyor belt provided in an embodiment of the present application is shown; an implementation example of the above step S133c is as follows: if the axial distance of the first point is greater than or equal to the axial distance of the second point, and the axial distance of the first point is equal to the axial distance of the third point, and the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point, in order to ensure that the detected abnormality is persistent rather than instantaneous noise, the change in the axial distance between consecutive frames can be compared, that is, if a certain point is displayed as a depression abnormality in multiple consecutive frames, then the abnormal result of the conveyor belt can be determined as a depression abnormality.

[0070] As an optional implementation of the above step S130, the above morphological features may include: a height value; the above implementation of determining the abnormal result of the transport belt according to the morphological features may include:

[0071] Step S134a: Determine whether the height values ​​of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions, the preset conditions including: the height value of the first point is less than the height value of the second point, and is equal to the height value of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point.

[0072] Step S134b: If the height values ​​of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions, the abnormal result of the transport belt is determined as a concave abnormality.

[0073] An implementation example of the above-mentioned steps S134a to S134b is: determine whether the height values ​​of the first point, the second point, and the third point found in sequence in the belt cross-section curve meet the preset conditions. If the height values ​​of the first point, the second point, and the third point found in sequence in the belt cross-section curve meet the preset conditions, that is, the preset conditions satisfied by the height values ​​of the first point, the second point, and the third point include: the height value of the first point is less than the height value of the second point, and the height value of the first point is equal to the height value of the third point, and the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point. In order to ensure that the detected abnormality is persistent rather than instantaneous noise, the height value changes between consecutive frames can be compared, that is, if a point is displayed as a concave abnormality in multiple consecutive frames, the abnormal result of the transport belt can be determined as a concave abnormality.

[0074] As an optional implementation of the above step S130, after determining whether the height values ​​of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions, the following may also be included:

[0075] Step S134c: If the height value of the first point is greater than or equal to the height value of the second point, and the height value of the first point is equal to the height value of the third point, the abnormal result of the transport belt is determined as a convex abnormality.

[0076] An implementation example of the above-mentioned step S134c is: if the height value of the first point is greater than or equal to the height value of the second point, and the height value of the first point is equal to the height value of the third point, and the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point, in order to ensure that the detected abnormality is persistent rather than instantaneous noise, the height value changes between consecutive frames can be compared, that is, if a certain point is displayed as a raised abnormality in multiple consecutive frames, then the abnormal result of the conveyor belt can be determined as a raised abnormality.

[0077] Optionally, after the industrial vision system upgraded or modified using the above-mentioned belt anomaly detection method detects the abnormal results of the transport belt, the transport belt can also be repaired in a targeted manner according to the abnormal results of the transport belt, thereby delaying the service life of the belt. Furthermore, the above-mentioned industrial vision system can also promptly detect minor abnormalities of the belt, and allow the industrial vision system to provide early warnings, perform repairs and replacements in advance, avoid production line shutdowns due to belt failures, discover potential problems in advance, and avoid greater losses. Furthermore, after the above-mentioned industrial vision system detects minor abnormalities of the belt, it can also generate maintenance suggestions based on the abnormal results of the transport belt, and send the maintenance suggestions to maintenance personnel. The maintenance suggestions are used to help maintenance personnel quickly find the problem. The industrial vision system can quickly locate the fault location and improve maintenance efficiency through precise feature extraction and anomaly detection.

[0078] See also Figure 6 The structure diagram of the belt abnormality detection device provided in the embodiment of the present application is shown; the embodiment of the present application provides a belt abnormality detection device 200, including:

[0079] The point cloud data acquisition module 210 is used to acquire point cloud data of the conveyor belt of the belt conveyor in an empty state.

[0080] The cross-section curve identification module 220 is used to identify the belt cross-section curve of the conveyor belt at different times from the point cloud data.

[0081] The abnormal result determination module 230 is used to extract the morphological features of the belt cross-sectional curve and determine the abnormal result of the transport belt according to the morphological features.

[0082] As an optional implementation of the above device, the morphological feature includes: a height difference value; and the abnormal result determination module includes:

[0083] The curve two-point height judgment submodule is used to judge whether the height difference between the first point and the second point in the belt cross-section curve is greater than a first preset threshold, and the straight-line distance between the first point and the second point is less than a distance threshold.

[0084] The first tearing abnormality determination submodule is used to determine the abnormal result of the transport belt as a tearing abnormality if the height difference between the first point and the second point in the belt cross-section curve is greater than a first preset threshold.

[0085] As an optional implementation of the above device, the morphological feature includes: a slope change value; and the abnormal result determination module includes:

[0086] The point slope value calculation submodule is used to calculate the first slope value between the first point and the second point in the belt cross-section curve, and the second slope value between the second point and the third point in the belt cross-section curve. The straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point.

[0087] The slope difference judgment submodule is used to judge whether the difference between the first slope value and the second slope value is greater than a second preset threshold.

[0088] The second tearing abnormality determination submodule is used to determine the abnormal result of the conveying belt as a tearing abnormality if the difference between the first slope value and the second slope value is greater than a second preset threshold.

[0089] As an optional implementation of the above device, the morphological characteristics include: axis distance; the abnormal result determination module includes:

[0090] The axial distance condition judgment submodule is used to judge whether the axial distances of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions. The preset conditions include: the axial distance of the first point is less than the axial distance of the second point, and is equal to the axial distance of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point.

[0091] The first bulge abnormality determination submodule is used to determine the abnormal result of the transport belt as a bulge abnormality if the axial center distances of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions.

[0092] As an optional implementation of the above device, the abnormal result determination module further includes:

[0093] The first depression abnormality determination submodule is used to determine the abnormal result of the conveyor belt as a depression abnormality if the axial center distance of the first point is greater than or equal to the axial center distance of the second point, and the axial center distance of the first point is equal to the axial center distance of the third point.

[0094] As an optional implementation of the above device, the morphological feature includes: a height value; and the abnormal result determination module includes:

[0095] The curve point height value judgment submodule is used to judge whether the height values ​​of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions, and the preset conditions include: the height value of the first point is less than the height value of the second point, and is equal to the height value of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point.

[0096] The second depression abnormality determining submodule is used to determine the abnormal result of the conveying belt as a depression abnormality if yes.

[0097] As an optional implementation of the above device, the abnormal result determination module further includes:

[0098] The second bulge abnormality determination submodule is used to determine the abnormal result of the conveyor belt as a bulge abnormality if the height value of the first point is greater than or equal to the height value of the second point, and the height value of the first point is equal to the height value of the third point.

[0099] It should be understood that the device corresponds to the above-mentioned belt abnormality detection method embodiment and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the device can be found in the above description, and the detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0100] See also Figure 7 The electronic device 300 provided in the embodiment of the present application includes: a processor 310 and a memory 320, wherein the memory 320 stores machine-readable instructions executable by the processor 310, and when the machine-readable instructions are executed by the processor 310, the above method is executed.

[0101] The embodiment of the present application also provides a computer-readable storage medium 330, on which a computer program is stored, and the computer program is executed by the processor 310 to execute the above method. The computer-readable storage medium 330 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0102] The embodiment of the present application also provides a computer program product, including: a computer program or a computer instruction, and the computer program or the computer instruction executes the method described above when executed by a processor.

[0103] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0104] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed device and method can also be implemented in other ways. The device embodiments described above are only schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible implementation architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a part of a module, a program segment or a code, and a part of a module, a program segment or a code includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also be different from the order of occurrence marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which is mainly determined by the functions involved.

[0105] In addition, each functional module of each embodiment in the embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. In addition, in the description of this specification, the description of reference terms "one embodiment", "some embodiments", "example", "specific example", "some examples", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present application. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples without contradiction.

[0106] The above description is only an optional implementation manner of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the embodiments of the present application, which should be covered within the protection scope of the embodiments of the present application.

Claims

1. A belt abnormality detection method, characterized in that: include: Obtain point cloud data of the conveyor belt of the belt conveyor in an empty state; Identifying the belt cross-section curves of the conveyor belt at different times from the point cloud data; The morphological features of the belt cross-section curve are extracted, and the abnormal results of the transport belt are determined according to the morphological features.

2. The method according to claim 1, characterized in that The morphological feature includes: a height difference value; the abnormal result of determining the transport belt according to the morphological feature includes: Determine whether the height difference between the first point and the second point in the belt cross-section curve is greater than a first preset threshold, and the straight-line distance between the first point and the second point is less than a distance threshold; If so, the abnormal result of the conveyor belt is determined as a tearing abnormality.

3. The method according to claim 1, characterized in that The morphological feature includes: a slope change value; the abnormal result of determining the transport belt according to the morphological feature includes: Calculate a first slope value between a first point and a second point in the belt cross-section curve, and a second slope value between the second point and a third point in the belt cross-section curve, wherein a straight-line distance between the first point and the second point is equal to a straight-line distance between the second point and the third point; Determining whether a difference between the first slope value and the second slope value is greater than a second preset threshold; If so, the abnormal result of the conveyor belt is determined as a tearing abnormality.

4. The method according to claim 1, characterized in that The morphological features include: axis distance; the abnormal result of determining the transport belt according to the morphological features includes: Determine whether the axial center distances of the first point, the second point, and the third point found in sequence in the belt cross-section curve meet a preset condition, wherein the preset condition includes: the axial center distance of the first point is less than the axial center distance of the second point, and is equal to the axial center distance of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point; If so, the abnormal result of the conveyor belt is determined as a convex abnormality.

5. The method according to claim 4, characterized in that After determining whether the axial center distances of the first point, the second point, and the third point found in sequence in the belt cross-section curve meet the preset conditions, the method further includes: If the axial center distance of the first point is greater than or equal to the axial center distance of the second point, and the axial center distance of the first point is equal to the axial center distance of the third point, the abnormal result of the conveyor belt is determined to be a concave abnormality.

6. The method according to claim 1, characterized in that The morphological feature comprises: a height value; and the abnormal result of determining the transport belt according to the morphological feature comprises: Determine whether the height values ​​of the first point, the second point, and the third point found in sequence in the belt cross-section curve meet a preset condition, wherein the preset condition includes: the height value of the first point is less than the height value of the second point and is equal to the height value of the third point, wherein the straight-line distance between the first point and the second point is equal to the straight-line distance between the second point and the third point; If so, the abnormal result of the conveyor belt is determined as a depression abnormality.

7. The method according to claim 6, characterized in that After determining whether the height values ​​of the first point, the second point and the third point found in sequence in the belt cross-section curve meet the preset conditions, the method further includes: If the height value of the first point is greater than or equal to the height value of the second point, and the height value of the first point is equal to the height value of the third point, the abnormal result of the transport belt is determined to be a convex abnormality.

8. A belt abnormality detection device, characterized in that: include: A point cloud data acquisition module is used to acquire point cloud data of the conveyor belt of the belt conveyor in an empty state; A cross-section curve recognition module, used to recognize the belt cross-section curve of the conveyor belt at different times from the point cloud data; The abnormal result determination module is used to extract the morphological features of the belt cross-section curve and determine the abnormal result of the transport belt according to the morphological features.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions are executed by the processor to perform any method according to claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is executed.

11. A computer program product, characterized in that include: A computer program or a computer instruction, wherein when the computer program or the computer instruction is executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images