A method and device for detecting longitudinal tearing of conveyor belts

Abstract

The present invention discloses an online detection method and device for longitudinal tearing of a conveyor belt, comprising: projecting a detection laser line on the surface of the conveyor belt, collecting a first image of the area projected by the detection laser line, extracting each pixel point on the detection laser line from the foreground image, and dividing it into two or more line segments; fitting each line segment into a straight line, marking the pixel point whose distance is greater than a preset threshold value as a suspicious point, and verifying whether the suspicious point is a tearing point in adjacent multi-frame images. The present invention automatically detects the longitudinal tearing of the conveyor belt by combining visual detection with the detection laser line, and can highlight the longitudinal tearing features on the conveyor belt by projecting the detection laser line, thereby improving the detection accuracy. Furthermore, suspicious points can be obtained by segmentation, straight line fitting and distance calculation, and finally the tearing point can be obtained by verification, thereby improving the precision and accuracy of conveyor belt tearing judgment and avoiding missed judgment or misjudgment.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence detection, and specifically to an online detection method and device for longitudinal tearing of a conveyor belt. Background Art

[0002] As a mechanical transmission device, conveyor belts are widely used in the transportation of various granular materials, such as coal, gravel, grain and other granular materials. In the process of conveying materials, the conveyor belt is easily damaged due to uneven force, foreign objects blocking and other reasons. Among them, the problem of longitudinal tearing of the belt is particularly serious, which may cause the conveyor belt to shut down at the least and safety accidents at the worst. With the large-scale conveying system and the remote automatic control of conveyor belts, the safety status monitoring of conveyor belts has become increasingly important. Traditional conveyor belts require manual inspections during operation. Manual inspections are carried out closely to monitor the operation of the conveyor belts and respond quickly to abnormal failures to avoid loss of life and property. However, the workload of manual inspections is large, and real-time performance cannot be guaranteed. Therefore, how to detect the quality of conveyor belts in a timely and efficient manner during use has become a technical problem that urgently needs to be solved in this field. Summary of the invention

[0003] In view of the above problems, the present application provides an online detection method for longitudinal tearing of a conveyor belt, which is used to solve the technical problems of large workload and low timeliness in manual inspection of the conveyor belt.

[0004] To achieve the above object, the inventor provides an online method for detecting longitudinal tearing of a conveyor belt, comprising the following steps:

[0005] Projecting a detection laser line on the surface of the conveyor belt, wherein the detection laser line is projected laterally along the surface of the conveyor belt;

[0006] Capturing, by a camera, a first image of the area projected by the detection laser line when the conveyor belt is in operation;

[0007] Converting the first image into a corresponding grayscale image, and using a binarization algorithm to segment the grayscale image into a foreground image and a background image, wherein the brightness value of the foreground image is greater than the brightness value of the background image;

[0008] Extracting each pixel point on the detection laser line from the foreground image;

[0009] Dividing the detection laser line into two or more line segments according to the coordinates of each pixel point;

[0010] Using the least square method to fit each of the line segments into a straight line, and calculating the distance from the pixel point in each of the line segments to the corresponding straight line, and marking the pixel point whose distance is greater than a preset threshold value as a suspicious point;

[0011] It is counted whether the probability of the pixel point at the position where the suspicious point is located being marked as a suspicious point in multiple frames of images adjacent to the first image is greater than a preset value, and if so, the suspicious point is marked as a tearing point.

[0012] Furthermore, the detection laser line is divided into two or more line segments in an overlapping segmentation manner, and the ends of two adjacent line segments overlap; and fitting each line segment into a straight line comprises the steps of:

[0013] Fit the pixel points of each line segment to form a straight line;

[0014] The 5% pixel points farthest from the straight line are eliminated, and the remaining pixel points are fitted into straight lines again. This is repeated three times or more to obtain the straight lines corresponding to the line segments.

[0015] Furthermore, the sum of the overlapping lengths of the ends is greater than or equal to 50% of the length of the detection laser line.

[0016] Furthermore, the binarization algorithm is an adaptive binarization algorithm.

[0017] Furthermore, the projection shape of the detection laser line on the surface of the conveyor belt is a straight line;

[0018] When extracting the pixel points on the detection laser line from the foreground image, a search is performed in a manner of extending from the center of the detection laser line to both ends to obtain all the pixel points located on the detection laser line.

[0019] Further, more than two alarm thresholds are preset, each of which corresponds to an alarm level, and the alarm thresholds include a frequency threshold and / or a continuity threshold generated by the tearing point;

[0020] The generation frequency and / or continuity of the tearing points is detected, and an alarm event of a corresponding alarm level is triggered when the alarm threshold is reached.

[0021] Furthermore, the detection laser line is projected from bottom to top onto the surface of the back of the conveyor belt, and when the camera captures the first image, the projection area of ​​the detection laser line is supplemented with light by a supplementary light.

[0022] In order to solve the above technical problems, the present invention also provides another technical solution:

[0023] An online detection device for longitudinal tearing of a conveyor belt, comprising: an image acquisition module and an analysis module; the image acquisition module comprises a camera and a laser emitter, the laser emitter is used to project a detection laser line on the surface of the conveyor belt, the detection laser line is projected horizontally along the surface of the conveyor belt;

[0024] The camera is used to collect a first image of the area projected by the detection laser line when the conveyor belt is in operation;

[0025] The analysis module is used to convert the first image into a corresponding grayscale image, and use a binarization algorithm to segment the grayscale image into a foreground image and a background image, wherein the brightness value of the foreground image is greater than the brightness value of the background image;

[0026] Extracting each pixel point on the detection laser line from the foreground image;

[0027] Dividing the detection laser line into two or more line segments according to the coordinates of each pixel point;

[0028] Using the least square method to fit each of the line segments into a straight line, and calculating the distance from the pixel point in each of the line segments to the corresponding straight line, and marking the pixel point whose distance is greater than a preset threshold value as a suspicious point;

[0029] It is counted whether the probability of the pixel point at the position where the suspicious point is located being marked as a suspicious point in multiple frames of images adjacent to the first image is greater than a preset value, and if so, the suspicious point is marked as a tearing point.

[0030] Furthermore, the camera is a high-definition industrial camera, the camera and the laser emitter are arranged below the conveyor belt, and the front ends of the camera and the laser emitter are provided with light-transmitting protective covers.

[0031] Furthermore, the protective cover includes a stainless steel protective cover and a lens. The lens is arranged at the front end of the stainless steel protective cover, and a scraper for cleaning the lens is arranged on the surface of the lens.

[0032] Different from the prior art, the above technical solution can automatically detect the longitudinal tear of the conveyor belt by combining camera visual detection with detection laser line. By projecting the detection laser line on the conveyor belt, the longitudinal tear feature on the conveyor belt can be highlighted, thereby improving the detection accuracy; and when detecting the tear point, the extracted detection laser line is segmented and fitted into multiple straight lines, and then the distance between the pixel point and the corresponding straight line is calculated pixel by pixel to obtain the suspicious point. Finally, the suspicious point is verified through multiple adjacent frame images to obtain the tear point, which can further improve the precision and accuracy of the conveyor belt tear judgment and avoid missed judgment or misjudgment.

[0033] In some embodiments, the above technical solution also counts the frequency and continuity of the tear points, and analyzes the damage of the current conveyor belt based on the statistical results to obtain information such as tear length and tear width. Different alarm thresholds are set based on information such as tear length or tear width, and different alarm signals are set for each alarm threshold to facilitate on-site processing by the owner.

[0034] The above-mentioned records related to the invention content are only an overview of the technical solution of the present application. In order to enable ordinary technicians in the field to more clearly understand the technical solution of the present application, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned purpose and other purposes, features and advantages of the present application easier to understand, the following is an explanation in combination with the specific implementation mode and drawings of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings are only used to illustrate the principles, implementation methods, applications, characteristics and effects of the specific embodiments of the present invention and other related contents, and shall not be considered as limiting the present application.

[0036] In the drawings of the specification:

[0037] Figure 1 It is a flowchart of the online detection method of longitudinal tear of conveyor belt described in the specific implementation method;

[0038] Figure 2 It is a structural schematic diagram of the online detection device for longitudinal tearing of conveyor belts according to a specific implementation method;

[0039] Figure 3 It is a specific flow chart of the online detection method for longitudinal tearing of conveyor belts described in the specific implementation method;

[0040] Figure 4 It is a module block diagram of the on-line detection device for longitudinal tearing of conveyor belts according to the specific implementation method.

[0041] The reference numerals in the above drawings are described as follows:

[0042] 1. Mounting plate; 2. Laser transmitter; 21. Adjustment bracket; 22. Protective cover; 23. Scraper strip; 3. Camera; 31. Adjustment bracket; 32. Protective cover; 33. Scraper strip; 4. Wiring harness; 5. Buckle; 40. Analysis module; 400. Online detection device for longitudinal tearing of conveyor belt; DETAILED DESCRIPTION

[0043] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0044] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0045] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0046] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0047] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0048] Without further limitations, in this application, the words "include", "comprises", "has" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0049] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0050] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0051] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms such as "install", "connect", "connect", "fix", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For technicians in the technical field to which the present application belongs, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0052] The present embodiment provides an online detection method for longitudinal tearing of a conveyor belt, and the longitudinal tearing on the conveyor belt can be automatically detected by the present detection method. The detection method can be applied to various conveyor belts used for material transportation. For example, the conveyor belt can be a blast furnace feed conveyor belt. The conveyor belt is arranged on a conveyor frame and driven by a motor to rotate on the conveyor frame, thereby realizing material transportation. In the present embodiment, the conveyor belt is different from a polyester conveyor belt, a nylon conveyor belt or a metal conveyor belt in terms of material. The conveyor belt is made of natural rubber or synthetic rubber. In some conveyor belts, in order to enhance its tensile strength, reinforcing materials such as nylon wire may be provided inside. Therefore, longitudinal tearing is prone to occur on the surface of the conveyor belt, and regular inspection and maintenance are required.

[0053] See also Figure 1The present embodiment provides an online method for detecting longitudinal tearing of a conveyor belt, comprising the following steps:

[0054] S101, projecting a detection laser line on the surface of the conveyor belt, wherein the detection laser line is projected laterally along the surface of the conveyor belt;

[0055] S102, capturing, by a camera, a first image of the area projected by the detection laser line when the conveyor belt is in operation;

[0056] S103, converting the first image into a corresponding grayscale image, and using a binarization algorithm to segment the grayscale image into a foreground image and a background image, wherein the brightness value of the foreground image is greater than the brightness value of the background image;

[0057] S104, extracting each pixel point on the detection laser line from the foreground image;

[0058] S105, dividing the detection laser line into two or more line segments according to the coordinates of each pixel point;

[0059] S106, using the least square method to fit each of the line segments into a straight line, and calculating the distance from the pixel point in each of the line segments to the corresponding straight line, and marking the pixel point whose distance is greater than a preset threshold value as a suspicious point;

[0060] S107 , counting whether the probability of the pixel point at the position where the suspicious point is located being marked as a suspicious point in multiple frames of images adjacent to the first image is greater than a preset value, and if so, marking the suspicious point as a tearing point.

[0061] The longitudinal tearing refers to tearing along the length direction of the conveyor belt, and the length direction is the moving direction of the conveyor belt when it is running. In step S101, the detection laser line is generated by a laser emitter and projected onto the surface of the conveyor belt. The transverse direction of the surface of the conveyor belt refers to the width direction of the conveyor belt, which is perpendicular to the moving direction of the conveyor belt when it is running. Therefore, the laser emitter can be fixed, and when the conveyor belt is running in a cycle, the detection laser line can cover the entire conveyor belt.

[0062] In step S102, the camera may preferably be a high-resolution industrial camera, i.e., a high-definition industrial camera, and by adjusting the configuration parameters of the industrial camera, the industrial camera can capture a clear image of the conveyor belt during high-speed operation, i.e., a first image. The first image captured by the camera includes the detection laser line and the area around the detection laser line.

[0063] In step S103, the range of the pixel grayscale value of the grayscale image is ∈[0,255], so in the binarization algorithm, by setting a suitable threshold, the foreground image with higher brightness and the background image with lower brightness can be distinguished, wherein the foreground image with higher brightness is the area where the detection laser line is located, and the background image with lower brightness is the area around the detection laser line. Therefore, in step S103, the bright area where the detection laser line is located can be distinguished from the dark background through the binarization algorithm processing, so as to facilitate the subsequent analysis and processing.

[0064] In step S104, pixel points on the detection laser line are extracted one by one to obtain a pixel point set of the detection laser line, and the target area where the detection laser line is located is further separated from the background image to reduce interference of the background image on subsequent detection laser line processing.

[0065] In step S106, in each of the line segments, the least square method is used to perform straight line fitting. During the fitting process, several pixel points at both ends of the straight line are removed, or several pixel points that are the farthest from the straight line are removed to eliminate the interference of abnormal points on the straight line fitting. For example, when fitting a straight line, 5% of the pixel points that are the farthest from the fitting straight line are removed each time, and then the remaining pixel points are fitted with a straight line. Through N iterations of the above fitting process, where N can be greater than or equal to 3, the straight line corresponding to each of the line segments can be obtained. After obtaining the straight line, the formula:

[0066] ;

[0067] Calculate the outliers in the pixels of each line segment. is the distance from each pixel point on the laser line to the fitting straight line within this segment. If the value is greater than the set threshold, it means that the position on the conveyor belt may have distortion problems such as tearing. In step S106, the suspicious points and positions where distortions such as tearing may occur in each line segment can be obtained.

[0068] In step S107, the above suspicious points are further verified to be tearing points through adjacent multiple frames of images. Considering that the tear on the conveyor belt has a certain length, it is not possible to simply determine that a tear has occurred based on a single suspicious point. In this step, it is also necessary to further determine the tearing situation based on the situation of the adjacent frames of images in the first image at the same position. For example, the first few frames of the current frame of the first image can be used to determine the tearing point. The final judgment condition is that in the current frame and the previous M frames of images, in the same position, if If the value is greater than the set threshold number (for example, M / 2), it is determined that tearing has indeed occurred at this position, that is, the point is a tearing point, and the coordinates of the corresponding tearing point and other information are output.

[0069] In this embodiment, visual detection is combined with detection laser lines to automatically detect longitudinal tears in the conveyor belt, wherein by projecting a detection laser line on the conveyor belt, the longitudinal tear features on the conveyor belt can be highlighted, thereby improving the detection accuracy; and when detecting the tear point, the extracted detection laser line is segmented and fitted into multiple straight lines, and then the distance between the pixel point and the corresponding straight line is calculated pixel by pixel to obtain the suspicious point, and finally the suspicious point is verified through multiple adjacent frame images to obtain the tear point, thereby further improving the precision and accuracy of conveyor belt tear judgment to avoid missed judgment or misjudgment.

[0070] Preferably, the detection laser line is projected from bottom to top onto the surface of the back of the conveyor belt, and when the camera captures the first image, the projection area of ​​the detection laser line is supplemented with light by a fill light, so that a clear first image can be obtained.

[0071] like Figure 2 As shown, the camera 3 is arranged on the mounting plate 1 through the angle adjustment bracket 31, and the laser emitter 2 is arranged on the mounting plate 1 through the angle adjustment bracket 21. The camera 3 and the laser emitter 2 are both arranged below the conveyor belt, and project and shoot from bottom to top. Since the conveyed material is placed on the upper surface of the conveyor belt, the camera 3 and the laser emitter 2 are projected and shot from bottom to top, which can better avoid the obstruction of the conveyed material, and a clear first image can be obtained, thereby improving the accuracy of tear point detection.

[0072] In one embodiment, in step S105, the detection laser line is divided into two or more line segments in an overlapping manner, and ends of two adjacent line segments overlap.

[0073] In the overlapping segmentation method, in every two adjacent line segments obtained by segmentation, the pixel points within a certain length of the head end of the current line segment are the same as the pixel points within a certain length of the tail end of the previous line segment, that is, the ends overlap. In step S106, several pixel points at both ends of the straight line are removed during the straight line fitting process, so the overlapping segmentation method can avoid missing pixels on the detection laser line, and facilitate the iteration in step S106 to obtain the straight line corresponding to the line segment.

[0074] Preferably, in one embodiment, the sum of the overlapping lengths of the ends is greater than or equal to 50% of the length of the detection laser line.

[0075] In one embodiment, the binarization algorithm is an adaptive binarization algorithm, and the decision formula for binarization in the adaptive binarization algorithm is:

[0076] ;

[0077] In the formula, e is the constant value after binarization; After binarization, it is located at The pixel of the position; is the original input image (i.e. the first image) The pixel of the position; The calculated location is The decision threshold of the location point, Calculated by the following formula:

[0078] ;

[0079] In the formula, W is The side length of the square area with the center point as For each point and point in the area The horizontal coordinate difference of , ]; For each point and point in the area The vertical coordinate difference of , ].

[0080] In the adaptive binarization algorithm, the threshold at the pixel position can be determined according to the pixel values ​​of the adjacent domain blocks of the current pixel, so that the image can be accurately segmented into two parts: the foreground image and the background image.

[0081] In one embodiment, the projection shape of the detection laser line on the surface of the conveyor belt is a straight line; that is, the detection laser line is a straight line laser line.

[0082] When extracting the pixel points on the detection laser line from the foreground image, a search is performed in a manner of extending from the center of the detection laser line to both ends to obtain all the pixel points located on the detection laser line.

[0083] In this embodiment, the use of a straight laser line can facilitate segmentation in step S105 and straight line fitting in step S106, so that suspicious points and tearing points can be calculated more accurately and quickly. In other embodiments, the detection laser line is not limited to a straight laser line, and it can be a detection laser line of a triangle, square or other shape.

[0084] In one embodiment, the detection method further comprises the steps of: presetting more than two alarm thresholds, each of the alarm thresholds corresponding to an alarm level, the alarm thresholds comprising a frequency threshold and / or a continuity threshold generated by the tearing point;

[0085] The generation frequency and / or continuity of the tearing points is detected, and an alarm event of a corresponding alarm level is triggered when the alarm threshold is reached.

[0086] Among them, the alarm levels may include primary, intermediate and advanced levels. Different alarm levels are provided with corresponding processing mechanisms. In the primary alarm, only sound and light alarm signals may be generated, while in the intermediate alarm or advanced alarm, not only sound and light alarm signals are generated, but also processing measures such as forcing the conveyor belt to stop running may be included.

[0087] In the above embodiment, the alarm event and the corresponding tear point position are stored in a database, so that when the conveyor belt is stopped for maintenance, the alarm event can be checked and the tear point position can be quickly located.

[0088] Based on the above introduction, Figure 3 As shown, it is a specific flow chart of the online detection method of longitudinal tearing of conveyor belt in one embodiment. At the beginning of the detection, a detection laser line is projected onto the conveyor belt by a laser transmitter, and the detection laser line is a straight laser line, and a first image including the detection laser line is acquired by an industrial camera; then the first image is subjected to adaptive binarization processing; after the adaptive binarization processing, the foreground image where the detection laser line is located in the first image can be distinguished from the surrounding background image, so as to obtain the image of the detection laser line later, that is, to obtain the foreground image where the detection laser line is located. After acquiring the foreground image, the pixel points on the detection laser line are extracted point by point, wherein the extraction can be performed from the middle of the straight laser line to both ends, pixel by pixel. By extracting the laser line pixel points, the detection laser line can be further distinguished from the surrounding background image. After the detection laser line is extracted, the detection laser line is segmented to obtain multiple line segments. Among them, multiple line segments can be obtained by overlapping segmentation. Then, each line segment is fitted with a straight line one by one, that is, a straight line where the central axis of the line segment is located is fitted according to the distribution position of each pixel point in the line segment; when fitting the straight line, several pixel points at both ends of the straight line can be removed, and multiple fittings are performed iteratively to obtain a more accurate straight line. After fitting each straight line, the abnormal value data of each pixel point is calculated, that is, the distance (i.e., vertical distance) from each pixel point to the straight line is calculated; then, based on the distance, it is determined whether it may be a suspicious point. When the distance is greater than the preset threshold value, it is considered that the pixel point may be a tearing point; after obtaining the suspicious point, multiple frames of images adjacent to the current suspicious point are obtained, and it is determined whether the probability of the pixel point at the same position in the multiple frames of images being a suspicious point is greater than the preset value. If so, the pixel point is determined to be a tearing point, and information such as the coordinates of the tearing point is output, and a corresponding alarm signal is generated.

[0089] When the conveyor belt is running, each position of the conveyor belt can be automatically detected through the above steps.

[0090] like Figure 4 As shown, in one embodiment, an online detection device 400 for longitudinal tearing of a conveyor belt is provided. The online detection device 400 for longitudinal tearing of a conveyor belt comprises: a laser emitter 2, a camera 3 and an analysis module 40.

[0091] The laser transmitter 2 is used to project a detection laser line on the surface of the conveyor belt, and the detection laser line is projected laterally along the surface of the conveyor belt;

[0092] The camera 3 is used to collect a first image of the area projected by the detection laser line when the conveyor belt is in the running state;

[0093] The analysis module 40 is used to convert the first image into a corresponding grayscale image, and use a binarization algorithm to segment the grayscale image into a foreground image and a background image, wherein the brightness value of the foreground image is greater than the brightness value of the background image;

[0094] Extracting each pixel point on the detection laser line from the foreground image;

[0095] Dividing the detection laser line into two or more line segments according to the coordinates of each pixel point;

[0096] Using the least square method to fit each of the line segments into a straight line, and calculating the distance from the pixel point in each of the line segments to the corresponding straight line, and marking the pixel point whose distance is greater than a preset threshold value as a suspicious point;

[0097] It is counted whether the probability of the pixel point at the position where the suspicious point is located being marked as a suspicious point in multiple frames of images adjacent to the first image is greater than a preset value, and if so, the suspicious point is marked as a tearing point.

[0098] The analysis module 40 can be a computer, server, industrial computer, etc., which can analyze and process image data. The analysis module 40 is connected to the camera 3 to receive the first image taken by the camera 3, and then analyzes the first image to obtain the tear point.

[0099] like Figure 2 As shown, the camera 3 is a high-definition industrial camera, and the camera 3 and the laser emitter 2 are arranged below the conveyor belt. In order to prevent the camera 3 and the laser emitter from being damaged by materials falling from the conveyor belt, the front ends of the camera 3 and the laser emitter 2 are provided with light-transmissive protective covers 32 and protective covers 22.

[0100] Specifically, the camera 3 is set on the mounting plate 1 through the angle adjustment bracket 31, and the laser emitter 2 is set on the mounting plate 1 through the angle adjustment bracket 21. The angles of the camera 3 and the laser emitter 2 in the vertical direction can be adjusted through the angle adjustment bracket 31 and the angle adjustment bracket 21.

[0101] like Figure 2 As shown, the protective cover includes a stainless steel protective cover and a lens. The lens is arranged at the front end of the stainless steel protective cover, and the surface of the lens is provided with a scraper 33 and a scraper 23 for cleaning the lens.

[0102] The scraper bar 33 and the scraper bar 23 are electric scrapers, and the ends of the scraper bar 33 and the scraper bar 23 are provided with a rotating shaft and connected to a driving motor. The driving motor rotates to drive the scraper bar to move back and forth on the lens, thereby scraping off the dust on the lens. The wiring harness 4 of the camera 3 and the laser transmitter 2 is fixed to the mounting plate 1 by a buckle 5. The camera 3 and the laser transmitter 2 are linked and controlled, and the scraper bar 33 and the scraper bar 23 can automatically and regularly scrape the camera 3 and the laser transmitter 2 without manual control.

[0103] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. An online method for detecting longitudinal tearing of a conveyor belt, characterized in that: The following steps are involved: Projecting a detection laser line on the surface of the conveyor belt, wherein the detection laser line is projected laterally along the surface of the conveyor belt; Capturing, by a camera, a first image of the area projected by the detection laser line when the conveyor belt is in operation; Converting the first image into a corresponding grayscale image, and using a binarization algorithm to segment the grayscale image into a foreground image and a background image, wherein the brightness value of the foreground image is greater than the brightness value of the background image; Extracting each pixel point on the detection laser line from the foreground image, wherein the detection laser line is a straight laser line. When extracting each pixel point on the detection laser line from the foreground image, a search is performed by extending from the center of the detection laser line to both ends to obtain all the pixel points on the detection laser line; Dividing the detection laser line into two or more line segments according to the coordinates of each pixel point; Using the least square method to fit each of the line segments into a straight line, and calculating the distance from the pixel point in each of the line segments to the corresponding straight line, and marking the pixel point whose distance is greater than a preset threshold value as a suspicious point; Counting whether the probability of the pixel point at the position where the suspicious point is located being marked as a suspicious point in multiple frames of images adjacent to the first image is greater than a preset value, and if so, marking the suspicious point as a tearing point; taking the first few frames of images before the current frame of the first image to perform tearing point judgment, the judgment condition is that in the image including the current frame and the previous M frames, in the same position, if E r If the value is greater than the set threshold, it is determined that tearing occurs at that position, and the coordinates of the corresponding tearing point are output; The E r =∑di, where di is the distance from each pixel on the laser line to the fitting straight line, E r A value greater than the set threshold indicates that tearing distortion may have occurred at that location on the conveyor belt; The detection laser line is divided into two or more line segments in an overlapping segmentation manner, and the ends of two adjacent line segments overlap; and fitting each line segment into a straight line comprises the steps of: Fit the pixel points of each line segment to form a straight line; The 5% pixel points farthest from the straight line are eliminated, and the remaining pixel points are fitted into straight lines again. This is repeated three times or more to obtain the straight lines corresponding to the line segments.

2. The method for detecting longitudinal tearing of a conveyor belt according to claim 1, characterized in that: The sum of the overlapping lengths of the ends of the line segments is greater than or equal to 50% of the length of the detection laser line.

3. The method for detecting longitudinal tearing of a conveyor belt according to claim 1, characterized in that: The binarization algorithm is an adaptive binarization algorithm.

4. The method for detecting longitudinal tearing of a conveyor belt according to claim 1, characterized in that: Preset more than two alarm thresholds, each of which corresponds to an alarm level, and the alarm thresholds include a frequency threshold and / or a continuity threshold generated by the tearing point; The generation frequency and / or continuity of the tearing points is detected, and an alarm event of a corresponding alarm level is triggered when the alarm threshold is reached.

5. The method for detecting longitudinal tearing of a conveyor belt according to claim 1, characterized in that: The detection laser line is projected from bottom to top onto the surface of the back of the conveyor belt. When the camera captures the first image, the projection area of ​​the detection laser line is supplemented with light by a supplementary light.

6. An online detection device for longitudinal tearing of a conveyor belt, characterized in that: include: A laser transmitter, used for projecting a detection laser line on the surface of the conveyor belt, wherein the detection laser line is projected laterally along the surface of the conveyor belt; A camera, used for collecting a first image of the area projected by the detection laser line when the conveyor belt is in a running state; An analysis module, used for converting the first image into a corresponding grayscale image, and using a binarization algorithm to segment the grayscale image into a foreground image and a background image, wherein the brightness value of the foreground image is greater than the brightness value of the background image; Extracting each pixel point on the detection laser line from the foreground image, wherein the detection laser line is a straight laser line. When extracting each pixel point on the detection laser line from the foreground image, a search is performed by extending from the center of the detection laser line to both ends to obtain all the pixel points on the detection laser line; Dividing the detection laser line into two or more line segments according to the coordinates of each pixel point; Using the least square method to fit each of the line segments into a straight line, and calculating the distance from the pixel point in each of the line segments to the corresponding straight line, and marking the pixel point whose distance is greater than a preset threshold value as a suspicious point; Counting whether the probability of the pixel point at the position where the suspicious point is located being marked as a suspicious point in multiple frames of images adjacent to the first image is greater than a preset value, and if so, marking the suspicious point as a tearing point; taking the first few frames of images before the current frame of the first image to perform tearing point judgment, the judgment condition is that in the image including the current frame and the previous M frames, in the same position, if E r If the value is greater than the set threshold, it is determined that tearing occurs at that position, and the coordinates of the corresponding tearing point are output; The E r =∑di, where di is the distance from each pixel on the laser line to the fitting straight line, E r A value greater than the set threshold indicates that tearing distortion may have occurred at that location on the conveyor belt; The detection laser line is divided into two or more line segments in an overlapping segmentation manner, and the ends of two adjacent line segments overlap; and fitting each line segment into a straight line comprises the steps of: Fit the pixel points of each line segment to form a straight line; The 5% pixel points farthest from the straight line are eliminated, and the remaining pixel points are fitted into straight lines again. This is repeated three times or more to obtain the straight lines corresponding to the line segments.

7. The conveyor belt longitudinal tearing online detection device according to claim 6 is characterized in that: The camera is a high-definition industrial camera. The camera and the laser emitter are arranged below the conveyor belt. The front ends of the camera and the laser emitter are provided with light-transmitting protective covers.

8. The conveyor belt longitudinal tearing online detection device according to claim 7, characterized in that: The protective cover comprises a stainless steel protective cover and a lens. The lens is arranged at the front end of the stainless steel protective cover, and a scraper strip for cleaning the lens is arranged on the surface of the lens.

Images