Method, system and equipment for identifying tearing of conveying belt based on double lasers and medium

Abstract

The invention discloses a method, a system and equipment for identifying tearing of a conveyor belt based on double lasers and a medium. The method comprises the following steps: acquiring a conveyor belt surface image projected with two laser rays through an industrial camera; wherein the two laser lines are generated by two line laser emitters which are arranged front and back in the running direction of the conveying belt, the laser irradiation direction is perpendicular to the longitudinal direction of the conveying belt, and the two laser lines are formed on the lower surface of the conveying belt, extend in the transverse direction and are arranged at intervals in the longitudinal direction; two laser lines are extracted from the image; according to the position information of each laser line, laser line breaking points are detected; judging whether the two laser lines have breaking points at close transverse image positions or not: if yes, calculating a pixel distance delta u of the two breaking points in the transverse axis direction of the image, and if delta u is smaller than or equal to a preset transverse alignment threshold value D, judging that the conveyor belt is torn; if not, or delta u is larger than D, it is judged that tearing does not occur. The method can quickly and accurately identify tearing.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and in particular to a method, system, device and medium for identifying conveyor belt tears based on dual lasers. Background Technology

[0002] Coal conveyor belts are the main transportation tool in the coal mining industry. Coal conveyor belt tearing is a very serious and urgent equipment failure caused by various reasons during the operation of the conveyor belt, resulting in horizontal or longitudinal cracks, breaks, or large-area damage.

[0003] Coal conveyor belt tears are usually not caused by a single reason, but are the result of a combination of factors. These factors typically include foreign object jamming, equipment mechanical failure, conveyor belt joint problems, unreasonable chute design or blockage, improper maintenance and operation, etc.

[0004] In existing technologies, traditional conveyor belt tear detection mainly employs the following three technical approaches:

[0005] 1. Mechanical detection: A metal wire is embedded in the conveyor belt, triggering an alarm when it breaks.

[0006] 2. Photoelectric detection: Detecting surface anomalies of the conveyor belt using laser scanning.

[0007] 3. Acoustic wave detection: Analyzing changes in the acoustic signature of the conveyor belt during operation.

[0008] With the development of AI technology, AI visual inspection systems have emerged that use high-speed cameras and deep learning algorithms to identify minute cracks as small as 0.1mm. However, in this type of technology, there is currently very little training material available for coal conveyor belt tearing, making it difficult to cover the types of tears in the training materials.

[0009] Therefore, conveyor belt tear detection using traditional technologies still has its value, while also having room for improvement. Regarding the photoelectric detection approach, the corresponding tear detection device mainly consists of an industrial camera, a laser, a supplementary light, and several other accessories. The entire device is installed at a height of approximately 40-50 cm from the bottom of the conveyor belt. The laser shines vertically upwards onto the bottom of the conveyor belt, the optical fiber is perpendicular to the direction of conveyor belt movement, and the industrial camera is tilted at a certain angle so that the laser beam falls at a suitable position on the camera's view. The supplementary light can be turned on / off and its brightness adjusted according to the ambient light level. During detection, this tear detection device projects a bright, thin, straight linear laser beam onto the surface of the moving conveyor belt, and the industrial camera simultaneously captures the image of the laser line on the conveyor belt surface. When the conveyor belt is intact, the laser line should appear as a continuous, smooth line in the image; when the conveyor belt experiences a longitudinal tear, the conveyor belt at the tear will deform, misalign, or open, causing the laser line projected onto it to show obvious local breakage, bending, or jumps. By analyzing the shape of the laser line in real time using image processing algorithms, it is possible to determine whether a tear has occurred. However, the aforementioned tear detection devices often have a high false alarm rate due to adhering substances, and there are also false alarms caused by the laser line appearing broken at the edge of the image due to conveyor belt deviation. Therefore, existing tear detection devices cannot accurately identify conveyor belt tears. Summary of the Invention

[0010] This application provides a method, system, device, and medium for identifying conveyor belt tears based on dual lasers, which solves the technical problem of poor accuracy in existing photoelectric detection technologies for identifying conveyor belt tears.

[0011] The first aspect of this application provides a method for identifying conveyor belt tears based on dual lasers, comprising:

[0012] An industrial camera captures an image of the conveyor belt surface projected with two laser lines. These two laser lines are generated by two line laser emitters arranged sequentially along the conveyor belt's running direction, with the laser irradiation direction perpendicular to the longitudinal direction of the conveyor belt. The two laser lines extend laterally and are spaced apart longitudinally on the lower surface of the conveyor belt. Two laser lines are extracted from the image. Based on the positional information of each laser line, break points are detected. It is determined whether both laser lines have break points at similar lateral image positions. If so, the pixel distance Δu between the two break points along the horizontal axis of the image is calculated. If Δu is less than or equal to a preset lateral alignment threshold D, the conveyor belt is considered to be torn. If not, or if Δu is greater than D, no tear has occurred.

[0013] Preferably, the determination of whether both laser lines have broken points detected at similar transverse image positions includes: when a broken point is detected only on one laser line, while the other laser line is continuous and intact in the corresponding transverse region, it is determined to be material adhesion or local interference.

[0014] Preferably, the lateral alignment threshold D is obtained according to the following formula: D=P base +β×V;

[0015] in:

[0016] P base Assuming an inherent baseline pixel spacing, multiple frames of images are acquired by controlling the conveyor belt to operate at at least one calibrated speed under tear-free conditions. The pixel spacing between corresponding point pairs of two laser lines along the horizontal axis of the image is calculated, and the statistical upper limit value of the pixel spacing is taken as P. base ;

[0017] β is the speed compensation coefficient, which is controlled by setting a physical mark on the surface of the conveyor belt to simulate tearing characteristics, thereby controlling the conveyor belt to move at at least two different speeds V. j Run the test and measure the pixel distance increment Δu of the image position caused by the physical marker on the two laser lines in the horizontal direction. j By fitting Δu j With V j The linear relationship is given, with the slope of the linear relationship being β;

[0018] V represents the real-time operating speed of the conveyor belt.

[0019] Preferably, extracting two laser lines from the image includes:

[0020] The image is converted from RGB space to HSV space. Thresholds for hue (H) and saturation (S) are set according to the specific wavelength of the laser, and binarization segmentation is performed to obtain the laser spot area. Morphological opening operations are performed on the binarized image in sequence for optimization. A laser line with a single pixel width is extracted from the optimized binarized image.

[0021] Preferably, the laser line with a single pixel width is obtained using the grayscale centroid method.

[0022] Preferably, the laser line for extracting a single pixel width is the laser center line.

[0023] Preferably, the step of acquiring the image of the conveyor belt surface projected with two laser lines using an industrial camera includes: setting the region of interest of the image based on the fixed projection area of ​​the two laser lines in the image, and acquiring the image within the region of interest for subsequent processing.

[0024] A second aspect of this application provides a system for identifying conveyor belt tears based on dual lasers, used to implement the method described in the first aspect of this application, comprising: an image acquisition module including an industrial camera; a dual laser projection module including two line laser emitters arranged back-to-back along the conveyor belt running direction, used to generate two laser lines extending laterally and spaced apart by a preset distance D on the surface of the conveyor belt; an image processing and analysis module configured to extract the two laser lines from the image, detect the break point of the laser line based on the position information of each laser line, and determine whether both laser lines have break points at similar lateral image positions and thus determine whether a tear has occurred; and an alarm output module used to output an alarm signal when a tear is determined to have occurred.

[0025] Preferably, the two line laser emitters project the same laser wavelength.

[0026] Preferably, a narrow-bandpass filter matching the laser wavelength is installed in front of the industrial camera lens.

[0027] A third aspect of this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it causes the electronic device to perform the method as described in the first aspect of this application.

[0028] A fourth aspect of this application provides a computer-readable storage medium for storing a computer program that, when run on a computer, causes the computer to perform the method described in the first aspect of this application.

[0029] Beneficial effects

[0030] This invention provides a method for identifying conveyor belt tears based on dual lasers. The method uses dual laser devices, an industrial camera, and a matching judgment algorithm to achieve tear recognition. Specifically, it uses two parallel laser lines with a preset fixed spacing as structural light sources, providing redundant and mutually verifiable visual information sources for tear detection. By comparing the positions of the break points on the two laser lines, it can distinguish between true tears and interference, achieving a recognition accuracy of 100%.

[0031] This method is an improvement on traditional laser recognition. Compared with existing single-laser recognition, dual-laser recognition has more accurate tear features and avoids false alarms. Compared with existing large-model recognition, it does not rely on training materials and avoids the situation where the accuracy of recognition is reduced due to the lack of materials in large-model recognition. Attached Figure Description

[0032] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0033] Figure 1 This is a schematic diagram of the layout of a conveyor belt tear detection system based on dual-laser recognition, according to an embodiment of this application.

[0034] Figure 2 This is a flowchart illustrating a method for identifying conveyor belt tears based on dual lasers, according to an embodiment of this application.

[0035] Figure 3 This is a schematic diagram of a laser line obtained according to the method of an embodiment of this application.

[0036] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of this application.

[0037] The meanings of the various reference numerals in the figure are as follows:

[0038] 1. Conveyor belt; 2. First-line laser emitter; 3. Second-line laser emitter; 4. Industrial camera; 5. First laser line; 6. Second laser line; 7. Computer. Detailed Implementation

[0039] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0040] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0041] like Figure 1 The diagram shown is a schematic representation of a dual-laser detection system for identifying tears in a conveyor belt 1, arranged around the conveyor belt 1 according to an embodiment of the present invention. Figure 1 It can be seen that the conveyor belt 1 is in Figure 1 Operating in a horizontal direction, the monitoring system includes at least the following components:

[0042] The dual-laser projection module includes two line laser emitters arranged front and rear along the running direction of the conveyor belt 1, namely a first line laser emitter 2 and a second line laser emitter 3. Preferably, the two line laser emitters project the same laser wavelength, and the laser irradiation direction is perpendicular to the longitudinal direction of the conveyor belt 1. The first line laser emitter 2 forms a first laser line 5 on the surface of the conveyor belt 1, and the second line laser emitter 3 forms a second laser line 6 on the surface of the conveyor belt 1. The two laser lines extend laterally (i.e., the width direction of the conveyor belt 1) and are spaced apart longitudinally (i.e., the running direction of the conveyor belt 1) on the lower surface of the conveyor belt 1. The image acquisition module includes an industrial camera 4, preferably an area array CMOS or CCD camera, which is arranged below the conveyor belt 1. The industrial camera 4 is positioned in front of or behind the two line laser emitters in the running direction of the conveyor belt 1 and performs image acquisition towards the laser lines formed on the conveyor belt 1, so that both laser lines are acquired simultaneously in the same frame image. In order to obtain high-quality laser lines, it is preferable to install a narrow-band pass filter that matches the laser wavelength in front of the lens of the industrial camera 4 to suppress interference from ambient light (such as miner's lamps) and diffuse reflection from materials (such as coal), and ensure that the laser lines are clear and conspicuous in the image.

[0043] Image processing and analysis module, built into Figure 1 In the computer 7 shown, the computer 7 is an industrial control computer or an embedded processor that runs image processing and judgment algorithms.

[0044] This module is configured to extract two laser lines from the image, detect the break point of each laser line based on its position information, and determine whether both laser lines have break points in similar horizontal image positions, thereby determining whether tearing has occurred. Figure 3 The diagram shows two laser lines obtained after processing. Because the conveyor belt 1 carries a heavy load, the resulting laser lines exhibit a cross-sectional shape that is high at both ends and concave in the middle. Furthermore, due to the characteristic that the conveyor belt 1 deforms less at both ends and more in the middle in the transverse direction, the distance between the two laser lines in the image obtained by the industrial camera 4 is larger in the middle region of the conveyor belt 1 and smaller at both ends. An alarm output module is used to output an alarm signal when a tear is detected.

[0045] In the above embodiments, the following models and parameters of devices can be selected:

[0046] A Basler ace 2 series industrial camera with a resolution of 2448×2048 and a frame rate of 75fps is used, equipped with a 16mm fixed-focus lens. A narrow bandpass filter with a center wavelength of 532nm and a bandwidth of 10nm is mounted in front of the camera lens to minimize ambient light. The camera is mounted perpendicular to the conveyor belt plane, 2.5 meters directly below the belt.

[0047] Two linear laser emitters, wavelength 532nm, green, output power 50mW.

[0048] An embedded industrial computer with an Intel i7 processor and 16GB of RAM.

[0049] The detection system described in the above embodiment has a simple structure and is easy to deploy. Compared with the traditional single-laser identification method, it mainly adds a laser source. In addition, the supporting analysis and judgment methods have been adjusted. Therefore, the modification cost of implementing the method of the present invention is low and the speed is fast.

[0050] The core of the aforementioned detection system is the analysis module, which determines the difference between actual tearing and adhesion interference, which will ultimately manifest differently on the two laser lines in the image. Specifically, this is divided into two aspects: along the longitudinal and transverse directions of conveyor belt 1.

[0051] Firstly, in the longitudinal direction, if it is a true tear, since a tear usually extends a certain distance longitudinally, the industrial camera 4 will inevitably capture at least one frame of an image on the conveyor belt in operation, showing break points at similar transverse positions on both laser lines. However, if it is an adherent substance, it is usually scattered lumps, clearly different from a tear. Based on the size of the adherent substances and the size of the tears that have historically appeared on conveyor belt 1, the distance between the two laser lines in the longitudinal direction of conveyor belt 1 is configured so that a tear can be characterized on both laser lines simultaneously, while coal slime, water droplets, etc., can only be characterized on one laser line. In the embodiment of the present invention, which is used to transport coal slime, common coal slime adherent substances, water droplets, and other interferences have a size of less than 40 mm on conveyor belt 1, and tears are usually greater than 40 mm. Therefore, in this embodiment, the distance between the two laser lines in the longitudinal direction of conveyor belt 1 is set to 4 cm, so that the laser line breakage caused by interference exists only on one laser line.

[0052] Secondly, in the horizontal direction, the tear is narrow and elongated, which means that the range of the break points on the laser line in the horizontal direction is usually limited and significantly smaller than the range formed by other interferences. Therefore, for break points in the image that exceed a certain threshold range in the horizontal direction, it can be ruled out that they are caused by the tear.

[0053] It should be noted that although the system modules are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules, for example, the image processing and analysis module can be split into an image processing module and an analysis module.

[0054] The above-mentioned judgment approach is clearly reliable and relies on relatively little computing power when implemented, such as... Figure 2 As shown, this is a method for identifying tearing of conveyor belt 1 based on dual lasers, implemented using the aforementioned system. Figure 2 It can be seen that the method includes the following steps:

[0055] Step S101: Acquire an image of the surface of the conveyor belt 1 projected with two laser lines using an industrial camera 4. Step S102: Extract the two laser lines from the image. Step S103: Detect the break points of the laser lines based on their position information. Step S104: Determine whether both laser lines have break points at similar horizontal image positions. If so, calculate the pixel distance Δu between the two break points along the horizontal axis of the image. If Δu is less than or equal to a preset horizontal alignment threshold D, the conveyor belt 1 is determined to be torn; otherwise, or if Δu is greater than D, it is determined that no tear has occurred.

[0056] Preferably, in step S104 above, when a break point is detected only on one laser line, while the other laser line remains continuous and intact in the corresponding transverse region, it is determined to be material adhesion or local interference.

[0057] In the above method, step S104 is the specific implementation of the above judgment idea. The lateral alignment threshold D is a key parameter used to determine whether it is a crack based on the characteristics of the lateral direction. If Δu is greater than D, it indicates that the judgment object is too wide, and tearing can be ruled out. Tearing is judged only if there are fracture points on both longitudinal laser lines and Δu is within a controllable range. The above method creatively proposes lateral alignment of double-line fracture as the core criterion for tearing, and uses single-line fracture with double-line misalignment as a logical rule to exclude local interference such as adhering substances.

[0058] The lateral distance between two possible break points on the actual conveyor belt 1 is obtained in the image formed by the industrial camera 4, corresponding to the aforementioned Δu, and can therefore be further compared with the aforementioned key parameter, the lateral alignment threshold D.

[0059] Different transported objects, environments, conveyor belt speeds, camera heights, angles, etc., may all affect the setting of the above-mentioned lateral alignment threshold D. In order to adapt to different scenarios, the above-mentioned lateral alignment threshold D parameter is adjustable in the embodiments of the present invention. This makes the method of the embodiments of the present invention have clear physical interpretation and strong on-site adaptability, avoiding the difficulties of debugging black box models.

[0060] In some preferred embodiments, step S101 involves acquiring an image of the surface of the conveyor belt 1 with two laser lines projected onto it using an industrial camera 4. This includes setting regions of interest (ROIs) for the image based on the fixed projection areas of the two laser lines in the image. Each ROI can precisely frame the image area where one of the laser lines appears, and subsequent processing is performed within these two ROIs.

[0061] In some preferred embodiments, in order to achieve stable and low-power extraction of laser lines in complex industrial environments, step S102, which involves extracting two laser lines from the image, includes:

[0062] Step S1021: Convert the image from RGB space to HSV space, set the thresholds for hue H and saturation S according to the specific wavelength of the laser, perform binarization segmentation, and obtain the laser spot area.

[0063] Specifically, for the 532nm green laser, the following threshold range is set for binarization segmentation:

[0064] Hue H[75, 105], Saturation S[150, 255], Brightness V[50, 255].

[0065] Pixels that meet the above conditions are set to green (or other colors that can be clearly distinguished from black, such as white), and the rest are set to black, thus obtaining an initial binary image. Step S1022: Morphological opening operations are sequentially performed on the binarized image to optimize it, thereby eliminating jagged noise at the edges of light spots, small holes, and minor breaks caused by water stains on the belt surface in the initial binary image.

[0066] The morphological opening operation specifically includes the following two steps:

[0067] First, a 3×3 pixel rectangular structuring element is used to erode the initial binary image, eliminating edge burrs and isolated noise points, thus thinning the laser line.

[0068] Next, the same 3×3 structuring element is used for dilation to restore the laser line to approximately its original width, connecting broken areas with lateral gaps not exceeding 2 pixels. After morphological opening operations, an optimized binary image is obtained, in which the laser spot is smoother and more continuous. Step S1023: Extract a single-pixel-width laser line from the optimized binary image. Specifically, in the optimized binary image, the contour of each connected component is extracted. For each elongated connected component formed by the laser line, a gray-scale centroid method or skeletonization algorithm is used to obtain a continuous laser line with a single-pixel width. In this step, the extracted single-pixel-width laser line is preferably the laser center line, and its precise coordinates in the image are recorded.

[0069] Specifically, in the above steps, a two-dimensional array is created for each laser line to represent the horizontal coordinate x and the vertical coordinate y. Specifically, in the i-th column of pixels, the coordinates of one laser center line are stored as (x1, y1). i The coordinates of the other laser centerline are stored as (x2, y2). i .

[0070] In some preferred embodiments, in step S103, the break point of the laser line is detected based on the position information of each laser line. Specifically, two laser lines are scanned according to the color coordinates corresponding to the laser lines. A break window threshold is predefined, which represents the lower limit of the tear width, for example, W=10 pixels (corresponding to an actual belt width of approximately 20mm). If, near a certain column coordinate x, no valid y-value can be calculated for more than W consecutive columns (i.e., there is no laser point in that column), then a potential break point is determined to have been found on that laser line, and its image horizontal coordinate x is recorded.

[0071] Because the tear occurs during high-speed belt movement (e.g., 4 m / s), and because tearing is a dynamic process that often starts from a single point and rapidly expands under belt tension, the entire expansion process takes time from initiation to completion, while the camera captures a snapshot of the instantaneous moment. Due to the belt's forward movement, the fracture points seen on the two laser lines exhibit both lateral misalignment caused by the laser line spacing and longitudinal misalignment caused by the belt's movement in the image.

[0072] Assume that at time t0, the tear starts from the edge of the first laser line on the belt, with the break point being B1, and then rapidly extends towards the second laser line. At time t0 + Δt, the tear point extends to the second laser line, with the break point being B2.

[0073] Where Δt = D_physical / V_rip.

[0074] D_physical is the physical distance between the two laser lines on conveyor belt 1;

[0075] V_rip is the tear propagation speed, which may be related to belt tension and material, but is usually much smaller than the belt forward speed V.

[0076] During the time interval Δt, conveyor belt 1 itself also moves the following distance: S = V * Δt = V * (D_physical / V_rip)

[0077] Therefore, in the same frame captured by industrial camera 4, the break points B1 and B2 are not formed by the same physical crack on the belt simultaneously cutting two lines in a static state. B1 is generated at a certain belt position P at time t0. After a time interval Δt, the belt moves forward a distance S, at which point the tear extends to line L2. Therefore, B2 is generated at time t0+Δt at belt position P + S.

[0078] Therefore, in the image, the lateral pixel distance between B1 and B2 reflects not only the fixed spacing D_physical between the two laser lines, but also the projection of the longitudinal offset caused by the forward movement distance S of the belt during the tear propagation time Δt onto the image.

[0079] Based on the above analysis, it can be seen that in order to determine whether B1 and B2 are caused by the same tear according to the horizontal alignment threshold D, the horizontal alignment threshold needs to be set reasonably. Therefore, in some preferred embodiments, when determining whether the two laser lines have break points at similar horizontal image positions in step S104, the horizontal alignment threshold D is not a fixed value. The system provides a configuration interface that allows users to automatically calculate and set the threshold according to the actual situation on site by using a calibration program or inputting known parameters.

[0080] In some specific embodiments, a dynamically adaptive threshold determination method is provided, wherein the lateral alignment threshold D is obtained according to the following formula: D=P base +β×V;

[0081] Where V is the real-time operating speed of conveyor belt 1.

[0082] The meanings and methods for obtaining the other two parameters that need to be calibrated on-site, Pbase and β, are as follows:

[0083] P base The inherent reference pixel spacing represents the inherent deviation caused by the perspective projection of the industrial camera 4, which is usually related to the camera position and angle. During calibration, the conveyor belt 1 is run at a typical speed in a safe and intact state to acquire multiple frames of images. The system automatically analyzes the images, calculates the pixel spacing distribution of the two laser lines on the horizontal axis of the image, and selects its statistical upper limit or 95th percentile as P. base To cover normal vibrations and noise.

[0084] β is the speed compensation coefficient, which characterizes the effect of the dynamic tearing process. During calibration, a narrow, vertical obstruction (such as a thin rod) is used to simulate the tear edge. The conveyor belt 1 is controlled to run at a speed V1, and the difference Δu1 between the two breakpoints on the horizontal coordinate of the image is recorded when the obstruction cuts the first laser line 5 and the second laser line 6. The belt speed is changed to V2, and the above process is repeated to obtain another set of differences Δu2. Since Δu ≈ P base + β × V, therefore the coefficient β can be calculated using β = (Δu2 -Δu1) / (V2 - V1). To improve accuracy, measurements can be taken at more velocity points and linear fitting can be performed.

[0085] After calibration, the system only needs to read the real-time speed V during runtime to calculate the accurate and adaptive threshold D using the above formula.

[0086] In some alternative embodiments, the lateral alignment threshold D is determined through a two-level adaptive approach:

[0087] The first level determines the speed range [V_m, V_n] and the preset horizontal alignment threshold value D for that range based on the real-time running speed V. base With the interval compensation coefficient β1;

[0088] The second stage involves determining the final lateral alignment threshold D based on the position of the real-time operating speed V within the current speed range through interpolation calculation: D = D base + β1 × (V - V_m).

[0089] For example, in this embodiment, the full speed range of conveyor belt 1 is first divided into several continuous intervals (e.g., 0-2m / s is the low-speed zone, 2-4m / s is the rated zone, and 4-6m / s is the high-speed zone). For each interval, a basic value D for the lateral alignment threshold is obtained using a dynamic adaptive threshold determination method provided in the above embodiment. base For example, take the threshold corresponding to the lower limit speed of the interval and an interval compensation coefficient β1.

[0090] During online operation, the system first determines the interval to which the current velocity V belongs. Then, it performs linear interpolation within the interval. For example, if the current velocity V = 3 m / s, belonging to the rated range [2, 4], and the interval D is known... base To correspond to the threshold of 2 m / s and β1, the final lateral alignment threshold D = D base + β1× (3 - 2).

[0091] Based on the same inventive concept as the above method embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the method in the above embodiments.

[0092] In one embodiment, the electronic device may be a server, and in this embodiment, the structure of the electronic device may be as follows: Figure 4 As shown, it includes a memory 2001, a communication module 2003, and one or more processors 2002.

[0093] The memory 2001 is used to store computer programs executed by the processor 2002. The memory 2001 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and programs required to run instant messaging functions, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0094] Memory 2001 may be volatile memory, such as random-access memory (RAM); memory 2001 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 2001 may be any other medium capable of carrying or storing a desired computer program having the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 2001 may be a combination of the above-mentioned memories.

[0095] Processor 2002 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 2002 is used to implement the above-mentioned audio data processing method when calling computer programs stored in memory 2001.

[0096] The communication module 2003 is used to communicate with terminal devices and other servers.

[0097] This application embodiment does not limit the specific connection medium between the memory 2001, communication module 2003, and processor 2002. This application embodiment... Figure 4 The memory 2001 and the processor 2002 are connected via a bus 2004, which is in... Figure 4The connections between other components are illustrated with arrows and are for illustrative purposes only, not as limiting information. The Bus 2004 can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 4 The text uses only one arrow to describe it, but does not indicate that there is only one bus or one type of bus.

[0098] Based on the same inventive concept as the above-described method embodiments, embodiments of the present invention also provide a computer-readable storage medium for storing a computer program. When the computer program is run on a computer, it enables the electronic device to implement the control method described in the above embodiments. The computer-readable storage medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0099] Based on the same inventive concept as the above-described method embodiments, embodiments of the present invention also provide a computer program product, which includes a computer program that, when run on an electronic device, causes the electronic device to perform the steps of the control methods described above according to various exemplary embodiments of this application. The program product may take the form of any combination of one or more readable media. These computer program commands can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the commands executed by the processor of the computer or other programmable data processing device generate a process for implementing... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

Claims

1. A method for identifying tear of a conveyor belt based on dual laser, characterized in that, a surface image of a conveyor belt with two laser lines projected thereon is captured by an industrial camera; wherein the two laser lines are generated by two line laser emitters arranged in front of and behind the running direction of the conveyor belt, and the laser irradiation direction is perpendicular to the longitudinal direction of the conveyor belt, and the two laser lines are formed on the lower surface of the conveyor belt and extend in the transverse direction and are arranged in the longitudinal direction with intervals; the two laser lines are extracted from the image; a laser line break point is detected according to the position information of each laser line; it is determined whether the two laser lines both have a break point in a similar transverse image position: if yes, the pixel distance Δu of the two break points in the transverse direction of the image is calculated, and if Δu is less than or equal to a preset transverse alignment threshold D, it is determined that the conveyor belt is torn; if no, or Δu is greater than D, it is determined that no tear occurs.

2. The method of claim 1, wherein, The determination of whether the two laser lines both have a break point in a similar transverse image position includes: when a break point is detected only on one of the two laser lines, and the other laser line is continuous and complete in the corresponding transverse region, it is determined that the material is adhered or locally interfered.

3. The method of claim 1, wherein, The lateral alignment threshold D is obtained according to the following formula: D = P base + β x V; Wherein: P base P is the inherent reference pixel pitch, by controlling the conveyor belt to run at at least one calibration speed, a plurality of images are collected in a non-tearing state, the pixel pitch of the corresponding point pairs of the two laser lines in the horizontal axis direction of the image is calculated, and the statistical upper limit value of the pixel pitch is taken as P base ; β is a speed compensation factor, by setting a physical mark simulating a tearing feature on the surface of the conveyor belt, controlling the conveyor belt to run at at least two different speeds V j , measuring the pixel distance increment Δu of the image position of the physical mark on the two laser lines in the horizontal axis direction j , by fitting the linear relationship of Δu j and V j , taking the slope of the linear relationship as β; V is the real-time running speed of the conveyor belt.

4. The method of claim 1, wherein, The extraction of the two laser lines from the image includes: converting the image from RGB space to HSV space, setting the hue H and saturation S threshold according to the specific wavelength of the laser, performing binaryzation segmentation to obtain the laser spot area; the binaryzation image is sequentially optimized by morphological opening operation; a single-pixel-width laser line is extracted from the optimized binaryzation image.

5. The method of claim 4, wherein, The single-pixel-width laser line is obtained by using the gray center of gravity method; Preferably, the single-pixel-width laser line is a laser center line.

6. The method of claim 1, wherein, The surface image of the conveyor belt with two laser lines projected thereon is captured by an industrial camera, including: According to the fixed projection area of the two laser lines in the image, the region of interest of the image is set, and the image in the region of interest is obtained for subsequent processing.

7. A system for identifying a tear in a conveyor belt based on dual laser light for implementing the method of any one of claims 1-6, characterized in that, Including: an image acquisition module including an industrial camera; a dual laser projection module including two line laser emitters arranged in front of and behind the running direction of the conveyor belt, for generating two laser lines on the surface of the conveyor belt, which extend in the transverse direction and are arranged in the longitudinal direction with intervals on the lower surface of the conveyor belt; an image processing and analysis module configured to perform the extraction of the two laser lines from the image, the detection of the laser line break point according to the position information of each laser line, and the determination of whether the two laser lines both have a break point in a similar transverse image position and further determine whether a tear occurs; an alarm output module for outputting an alarm signal when a tear is determined to occur.

8. The system of claim 7, wherein, The two line laser emitters project laser beams of the same wavelength; Preferably, a narrow-band filter matching the wavelength of the laser is installed in front of the lens of the industrial camera.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to enable the electronic device to implement the method of any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium is used to store the computer program, which enables the computer to execute the method of any one of claims 1 to 6 when the computer program runs on the computer.

Images