A method, control device, medium, and system for detecting conveyor belt misalignment.

Abstract

This invention relates to the field of conveyor belt transportation monitoring, specifically disclosing a method, control device, medium, and system for detecting conveyor belt misalignment. The method for detecting conveyor belt misalignment includes: receiving monitoring images of idlers on both sides of the conveyor belt; obtaining the position and number of the idlers based on visual target detection and the images; and determining whether the conveyor belt is misaligned based on the position and number of the idlers. This invention achieves accurate and stable conveyor belt misalignment detection.

Description

Technical Field

[0001] This invention relates to the field of conveyor belt transportation monitoring, and specifically to a method, control device, medium, and system for detecting conveyor belt deviation. Background Technology

[0002] One common problem in the mining industry is conveyor belt (commonly known as belt) misalignment. This is caused by the uneven distribution of materials such as coal, leading to an imbalance in the conveyor belt during operation. This uneven load results in uneven tension on both sides of the conveyor belt, ultimately causing misalignment. Misalignment not only causes system failures and downtime, directly impacting production efficiency, but also poses potential safety risks. Furthermore, misalignment can lead to material accumulation and leakage, causing environmental pollution. Therefore, it is necessary to monitor conveyor belt misalignment in real time and issue timely alarms so that relevant management personnel can take swift action.

[0003] There are generally two methods to determine if a conveyor belt is misaligned. One method uses preset left and right reference lines to detect the edges of the conveyor belt on both sides, checking if they intersect with the reference lines or if the angle of intersection is large, thus determining the conveyor belt's misalignment. The other method compares the number of idlers on the left and right sides of the conveyor belt with a preset number of idlers to determine the misalignment in real time. However, both methods have some problems. First, each video feed requires manual setting and adjustment of the reference target, increasing the workload. Second, the usual shooting angle is from the opposite direction of the conveyor belt, which leads to a significant perspective effect (objects appear larger when closer and smaller when farther away), making it difficult to accurately identify and detect distant conveyor belts or idlers, easily causing missed detections and false alarms, further exacerbating the problem of false alarms about conveyor belt misalignment. Summary of the Invention

[0004] To overcome the above-mentioned defects, this invention proposes a method, control device, medium, and system for detecting conveyor belt misalignment, thereby achieving accurate and stable detection of conveyor belt misalignment.

[0005] In a first aspect, the present invention provides a method for detecting conveyor belt misalignment, comprising:

[0006] Receive monitoring images of the idlers on both sides of the conveyor belt;

[0007] Based on visual target detection, the position and number of the idlers are obtained from the image;

[0008] Based on the position and number of the idlers, determine whether the conveyor belt is off-track.

[0009] In one technical solution of the above method, obtaining the position of the idler roller based on the image includes:

[0010] Based on the image, the position of each idler roller relative to the conveyor belt is obtained;

[0011] Based on the positions, all idlers are divided into a first group and a second group, wherein the idlers of the first group and the second group are located on both sides of the conveyor belt, respectively.

[0012] The step of determining the number of idlers based on the image includes:

[0013] The number of rollers in the first group and the second group are obtained from the image.

[0014] In one technical solution of the above method, determining whether the conveyor belt is misaligned based on the position and number of the idlers includes:

[0015] Determine the reference quantity of idlers;

[0016] Calculate the difference between the number of idlers obtained from the image and the reference number of idlers;

[0017] Based on the difference, determine whether the conveyor belt is off-center.

[0018] In one technical solution of the above method, determining the reference number of idlers includes:

[0019] Calculate the first difference between the number of idlers in the first group and the second group;

[0020] Determine whether the first difference is less than a first preset threshold;

[0021] If the number is less than the number of rollers in the first group, a first reference number is determined based on the number of rollers in the first group, and a second reference number is determined based on the number of rollers in the second group.

[0022] In one technical solution of the above method, the calculation of the difference between the number of idlers obtained from the image and the reference number of idlers includes:

[0023] Calculate the second difference between the number of the first group of idlers obtained from the image and the first reference number;

[0024] Calculate the third difference between the number of the second group of idlers obtained from the image and the second reference number;

[0025] The step of determining whether the conveyor belt is off-track based on the difference includes:

[0026] Determine whether the second difference is greater than the second preset threshold. If it is, the conveyor belt is misaligned.

[0027] Determine whether the third difference is greater than a third preset threshold. If it is, the conveyor belt is misaligned.

[0028] In one technical solution of the above method, the receiving monitoring images of the idlers on both sides of the conveyor belt includes:

[0029] Receive images of the idlers on both sides of the conveyor belt acquired by the image acquisition device;

[0030] The step of obtaining the position and number of the idlers based on the image also includes:

[0031] In the image, the idlers are sorted in order from near to far from the image acquisition device, and the first k idlers are selected, where k is a preset value;

[0032] Based on the image, the positions and number of the first k idlers are obtained;

[0033] The step of determining whether the conveyor belt is off-track based on the position and number of the idlers further includes:

[0034] Based on the selected positions and numbers of the first k idlers, determine whether the conveyor belt is off-track.

[0035] In one technical solution of the above method, the visual target detection includes:

[0036] Based on the YOLO object detection model.

[0037] In a second aspect, the present invention provides a control device including a processor and a storage device, the storage device being adapted to store a plurality of program codes, characterized in that the program codes are adapted to be loaded by the processor and run in accordance with the method for detecting conveyor belt deviation as described in any of the first aspects.

[0038] In a third aspect, the present invention provides a computer-readable storage medium storing a plurality of program codes adapted to be loaded and executed by a processor for the method of detecting conveyor belt deviation as described in any of the first aspects.

[0039] In a fourth aspect, the present invention provides a system for detecting conveyor belt misalignment, comprising:

[0040] Image acquisition device, used to acquire monitoring images of the idlers on both sides of the conveyor belt; and

[0041] The aforementioned control device.

[0042] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0043] This invention utilizes visual target detection technology to monitor conveyor belt misalignment, achieving real-time monitoring of conveyor belt misalignment and improving the accuracy and efficiency of monitoring.

[0044] This invention sets a reference number for the idler rollers, eliminating the need for manually setting reference targets, reducing manual workload, and improving the level of intelligence;

[0045] This invention employs a front-line screening mechanism to determine whether the conveyor belt is misaligned based on the position and number of the first k selected idlers. This eliminates idlers that are far from the image acquisition device, effectively mitigating the impact of the perspective effect on long-distance conveyor belt misalignment monitoring, reducing the false alarm rate, and improving the reliability, accuracy, and stability of monitoring. Attached Figure Description

[0046] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Furthermore, similar numbers in the drawings are used to denote similar components, wherein:

[0047] Figure 1 This is a schematic flowchart of the main steps of a method for detecting conveyor belt misalignment according to an embodiment of the present invention;

[0048] Figure 2 This is a schematic diagram of a drive belt not being covered by idlers when it is not deviating according to an embodiment of the present invention;

[0049] Figure 3 This is a schematic flowchart of the main steps of a method for determining the position and quantity of idlers according to an embodiment of the present invention;

[0050] Figure 4 This is a schematic flowchart illustrating the main steps of determining whether the conveyor belt is misaligned based on the position and number of the idlers, according to an embodiment of the present invention.

[0051] Figure 5 This is a schematic diagram showing the partial coverage of the idler roller when the transmission belt does not deviate according to an embodiment of the present invention;

[0052] Figure 6 This is a schematic diagram of the covered portion of the idler roller when the transmission belt deviates according to an embodiment of the present invention;

[0053] Figure 7 This is a schematic diagram of the main structure of a system for detecting conveyor belt misalignment according to an embodiment of the present invention.

[0054] List of reference numerals :

[0055] 1: Drive belt; 2: Idler roller; 3: Image acquisition device. Detailed Implementation

[0056] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0057] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module may include hardware circuitry, various suitable sensors, communication ports, and memory, and may also include software components, such as program code, or a combination of software and hardware. A processor may be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor may be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media include any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc.

[0058] This invention provides a method for detecting conveyor belt misalignment, referring to... Figure 1 ,include:

[0059] S1, Receive monitoring images of the idlers on both sides of the conveyor belt;

[0060] S2, Based on visual target detection, the position and number of the idlers are obtained from the image;

[0061] S3. Determine whether the conveyor belt is off-center based on the position and number of the idlers.

[0062] The monitoring images in S1 of this invention can be frame-by-frame images processed from video, or images captured by a camera at high frequency.

[0063] During the movement of the conveyor belt, video input is obtained by an image acquisition device 3, such as a camera, and the video image shows the operation of the conveyor belt.

[0064] Reference Figure 2 The image acquisition device 3 is located in front of the transmission belt in the direction of travel (as indicated by the arrow on the transmission belt). The image acquisition device 3 is aimed at the transmission belt and its idlers to capture images. Several idlers 2 are arranged under the transmission belt, and the outer periphery of the idlers 2 is exposed on both sides of the transmission belt 1. Thus, in the monitoring image of S1, the distribution information (position and number) of the idlers 2 can be obtained, and it can be seen whether the idlers 2 are obstructed. Idler refers to a mechanical element used to support and guide the movement of a belt or conveyor belt. In the mining and industrial fields, idlers are usually composed of cylindrical rollers or drums, which are installed at the bottom or side of the conveyor belt, in contact with the conveyor belt, and support and guide the movement of the conveyor belt.

[0065] This invention utilizes visual object detection, such as deep learning-based idler roller detection, to process video frames using deep learning technology to detect the position and number of idler roller targets. For example, this step, aided by a trained visual object detection model, can accurately identify idler rollers on a conveyor belt. Deep learning-based idler roller detection technology is an image processing technique based on deep learning algorithms used to detect idler roller targets in video frames. By learning from a large number of samples, the deep learning model can automatically identify and locate idler rollers in images and output their position information.

[0066] By accurately identifying the idlers on the conveyor belt, it can be determined whether the conveyor belt abnormally covers the idlers, thereby determining whether the conveyor belt is running off-track.

[0067] In one application scenario, the vision-based target detection includes:

[0068] Based on the YOLO object detection model.

[0069] Preferably, the YOLOv8m target detection model is used, which can achieve a good balance between accuracy and speed in practical applications.

[0070] Step S2 provides the location and quantity of the idler rollers. First, the location is described, referring to... Figure 3 In one embodiment, obtaining the position of the idler roller based on the image in S2 includes:

[0071] S21, Based on the image, obtain the position of each idler roller relative to the conveyor belt;

[0072] To determine which side of the conveyor belt each idler roller is located on, refer to... Figure 2 For example, determining whether it is located on the left or right side of the conveyor belt.

[0073] S22, based on the positions, all idlers are divided into a first group and a second group, wherein the idlers of the first group and the second group are located on both sides of the conveyor belt, respectively.

[0074] This embodiment demonstrates the position of the idlers. Each idler is assigned to either a first or second group, grouped based on which side of the conveyor belt it is located on; idlers on the same side are grouped together. The idlers in each group are arranged along the direction of the conveyor belt's travel.

[0075] Let's explain the above grouping from another perspective:

[0076] Perpendicular to the direction of travel of the conveyor belt, the conveyor belt includes a first side and a second side;

[0077] Based on the aforementioned position, the idlers located on the first side of the conveyor belt are configured as the first group;

[0078] The idlers located on the second side of the conveyor belt are set as the second group.

[0079] Still refer to Figure 2 The first group is roller 2 located on the left side of the diagram, and the second group is located on the right side of the diagram. Figure 2 The right-side idler roller 2 can also be divided into two groups according to needs and habits. For example, if the transmission belt is in the direction of travel, the left side of the direction of travel is designated as the first group, and the right side of the direction of travel is designated as the second group. Regardless of the classification, the idler rollers of the two groups are divided into two groups with the transmission belt 1 as the center.

[0080] In one embodiment, the quantity is further described, still referring to Figure 3 The step of obtaining the number of idlers based on the image in S2 includes:

[0081] S23, the number of idlers in the first group and the second group are obtained according to the image.

[0082] Still refer to Figure 2 During normal operation, the left side of the diagram (assuming it is the first group) has 4 idlers, and the right side of the diagram (assuming it is the second group) has 4 idlers.

[0083] The position and number of idlers on both sides of the conveyor belt can be obtained through real-time monitoring images, that is, the number of idlers on the left and right sides. This is the basis for judging deviation in this invention and is used to judge whether the conveyor belt is deviating.

[0084] In one embodiment, reference is made to Figure 4 S3, determining whether the conveyor belt is misaligned based on the position and number of the idlers includes:

[0085] S31, Determine the reference quantity of idlers;

[0086] S32, calculate the difference between the number of idlers obtained from the image and the reference number of idlers;

[0087] S33, Based on the difference, determine whether the conveyor belt is off-center.

[0088] To determine whether the vehicle has deviated from its course, a baseline needs to be set, i.e., the case where it is not deviating.

[0089] By comparing the real-time monitoring data with the baseline, the severity of the difference can be determined, thereby identifying whether the system has deviated from its intended path.

[0090] In one embodiment, the process of establishing the reference number, S31, includes determining the reference number of idlers:

[0091] S311, Calculate the first difference between the number of idlers in the first group and the second group;

[0092] S312, determine whether the first difference is less than a first preset threshold;

[0093] S313, if it is less than, then determine the first reference quantity based on the number of idlers in the first group and determine the second reference quantity based on the number of idlers in the second group.

[0094] This invention is based on visual target detection. First, based on the X-axis coordinate of the idler rollers, the idler rollers are divided into left and right groups. If the absolute error in the number of idler rollers in the left and right groups is within a threshold, then the currently detected number of idler rollers in the left and right groups will be set as the reference target number, i.e., the idler roller reference number in S31.

[0095] To address the issue of requiring manual settings, this invention employs an automatic reference target configuration mechanism. Initially, the idlers are divided into left and right groups based on the target coordinate X-axis. If the absolute error in the number of idlers in the left and right groups is within a threshold, the currently detected number of idlers in the left and right groups can be set as the reference target number, i.e., the idler reference number in S31. This is used in conjunction with the subsequently detected number of idlers in real time to determine whether the idler is misaligned. For example, if the currently detected number of idlers on the left (assuming it is the first group) is 5 and the number of idlers on the right (assuming it is the second group) is 5, with a difference of zero, which is less than the first preset threshold (empirical value) of 1, then this is the idler reference number. The first reference number is set to 5 based on the number of idlers in the first group, and the second reference number is set to 5 based on the number of idlers in the second group.

[0096] If the current detected number of idlers on the left (assuming it is the first group) is 5 and the number of idlers on the right (assuming it is the second group) is 3, the difference is 2, which is greater than the first preset threshold (empirical value) of 1, indicating that it cannot be used to set the reference target number.

[0097] The reference number of idlers can be determined before the conveyor belt starts or during operation. Only when the difference between the number of idlers in the first group and the second group is less than the preset threshold, it indicates that the conveyor belt is in a stable operating state and there is no deviation. At this time, the number of idlers in the first group and the second group can be used as the reference value.

[0098] Although in the example above, when the number of left and right side rollers is 5, the first reference number and the second reference number are determined, it does not mean that the reference can only be set when the number of rollers in the first group and the second group are equal. Due to the installation position of the image acquisition device and the real-time viewing angle, the number of rollers in the first group and the second group may not be equal, but as long as the difference is less than the first preset threshold, the first and second reference numbers can be determined.

[0099] This embodiment provides an automatic reference target configuration mechanism, which is an automated mechanism used to determine the number of reference targets, i.e., the number of idler rollers, in conveyor belt misalignment monitoring. This mechanism automatically sets the reference targets based on the coordinate information of the idler rollers, without requiring manual intervention. The introduction of this automatic reference target configuration mechanism eliminates the tedious process of manually setting reference targets, thereby improving the convenience and efficiency of operation.

[0100] Determining the number of idler rollers as a reference target provides a method for identifying the standard used in conveyor belt misalignment monitoring. The system monitors the conveyor belt's condition by automatically configuring or setting the number of idler rollers as a reference.

[0101] In one embodiment, step S32, calculating the difference between the number of idlers obtained from the image and the reference number of idlers, includes:

[0102] S321, calculate the second difference between the number of the first group of idlers obtained from the image and the first reference number;

[0103] S322, calculate the third difference between the number of the second group of idlers obtained from the image and the second reference number;

[0104] S33, determining whether the conveyor belt is off-track based on the difference includes:

[0105] S331, determine whether the second difference is greater than the second preset threshold; if it is, the conveyor belt will deviate.

[0106] S332, determine whether the third difference is greater than the third preset threshold. If it is greater, the conveyor belt will deviate.

[0107] It should be noted that if any difference in S331 and S332 exceeds the corresponding preset threshold, the deviation is determined.

[0108] This invention continuously monitors the idler targets on the conveyor belt in real time. The number of detected idlers is compared with the previously set reference target number, i.e., the idler reference number, to determine whether the conveyor belt is deviating from its designated path.

[0109] This invention, based on the determination of the number of idlers, can accurately identify whether the drive belt is misaligned. Figure 2 5 and 6, from Figure 2 and Figure 5 As can be seen from the idler rollers marked with the same cross-sectional line (the idler roller at the bottom left of the figure), this idler roller exposed to the drive belt... Figure 2 There is no cover in the middle. Figure 5 Partially covered, Figure 6 Completely covered.

[0110] When it doesn't deviate, it is Figure 2 There are 4 idlers on each side, and the difference is less than the first preset threshold. Therefore, the reference number of idlers is determined to be 4 on the left and 4 on the right. The conveyor belt tilts slightly during its transmission. Figure 5 Even though the idlers covered by the tilted conveyor belt are still identifiable in the image, they are still counted. At this point, the image still shows four idlers on each side, and misalignment is not assessed. (Refer to...) Figure 6 When the drive belt deviates to a certain extent and completely covers part of the idler roller, Figure 6 In the image, roller 3 is on the left and roller 4 is on the right. Since the conveyor belt completely covers one of the idlers on the left, this idler cannot be identified from the image and is not counted. Therefore, the difference between the real-time monitored roller 3 on the left and the determined reference number of idlers 4 on the left is 1 (the second difference). If this difference is greater than the second preset threshold of 0.5, it is determined that the conveyor belt is misaligned, and an alarm is triggered. Thus, the method of this invention can avoid false alarms for normal fluctuations in the conveyor belt during operation and can accurately detect the actual misalignment of the conveyor belt.

[0111] In one embodiment, S1, the monitoring images of the idlers on both sides of the conveyor belt include:

[0112] S11, Receive images of the idlers on both sides of the conveyor belt acquired by the image acquisition device;

[0113] The step S2, which involves obtaining the position and number of the idlers from the image, further includes:

[0114] S24, in the image, the idlers are sorted in order from near to far from the image acquisition device, and the first k idlers are selected, where k is a preset value;

[0115] S25, based on the image, obtain the position and number of the selected first k idlers.

[0116] In order to alleviate the false alarms caused by the severe perspective effect of the transmission belt running off track, this embodiment uses a front-row screening mechanism. The left and right grouped idlers are sorted according to the Y-axis of the detection frame coordinates. Based on the Top-k principle, the first k idlers are selected to filter out idlers that are too far away, thereby improving the accuracy and stability of effective idler detection. Furthermore, an effective observation area is constructed based on the grouped reference idlers selected by Top-k. Only idlers that are detected in real time and are within the effective observation area are considered as effective idler targets.

[0117] Perspective effect refers to the phenomenon where objects appear to be at different distances in an image due to the relative positional relationship between the observation point and the object. In surveillance, perspective effect can affect the identification and localization of distant objects.

[0118] The Top-k principle is a selection rule that chooses the top k elements or objects based on certain criteria. Here, the Top-k principle is used to select the top k idlers as effective targets to mitigate the effects of perspective distortion.

[0119] The first k rollers are the k rollers closest to the image acquisition device. For example, the first group and the second group each have 7 rollers, for a total of 14 rollers. k is 4, and the 4 rollers closest to the image acquisition device are selected.

[0120] k can be 3-5.

[0121] The step of determining whether the conveyor belt is off-track based on the position and number of the idlers further includes:

[0122] Based on the selected positions and numbers of the first k idlers, determine whether the conveyor belt is off-track.

[0123] If k is 4, the four idlers closest to the image acquisition device are selected. Based on the position and number of these four selected idlers, it is determined whether the conveyor belt is misaligned. Correspondingly, the reference number of idlers is also determined based on the k (4 in the aforementioned example) idlers closest to the image acquisition device.

[0124] This embodiment employs a front-row screening mechanism, selecting the top k idlers as valid targets and excluding idlers located further away. This effectively mitigates the impact of the perspective effect on conveyor belt misalignment monitoring at long distances, reduces the false alarm rate, and improves the reliability, accuracy, and stability of the monitoring.

[0125] When the first k idlers are selected as valid targets, the reference number of idlers and the position and number of idlers obtained from the real-time monitored images are determined. The determination of whether the conveyor belt is off-track is also calculated and judged using these k idlers. For example, if the first group of idlers has 7 rollers and the second group has 6 rollers, and k is 5, then during monitoring, for any idlers appearing in the image, only the 5 rollers closest to the image acquisition device are considered valid targets for calculation and judgment. Other idlers in the image are ignored. For instance, when determining the reference number of idlers, the target for calculating the first difference between the number of idlers in the first and second groups is the selected 5 closest idlers. When judging whether the conveyor belt is off-track, the difference between the number of idlers obtained from the image and the reference number is calculated using the selected 5 closest idlers.

[0126] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0127] The present invention also provides a control device. In one embodiment of the control device according to the present invention, the control device includes a processor and a storage device. The storage device can be configured to store a program for detecting conveyor belt deviation that executes the above-described method embodiments. The processor can be configured to execute the program in the storage device, which includes, but is not limited to, the program for detecting conveyor belt deviation that executes the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of the present invention are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The control device can be a control device device comprising various electronic devices.

[0128] Reference Figure 7 The present invention also provides a system for detecting conveyor belt misalignment, comprising:

[0129] Image acquisition device, used to acquire monitoring images of the idlers on both sides of the conveyor belt; and

[0130] The aforementioned control device.

[0131] The image acquisition device can be a camera.

[0132] The image acquisition device can be installed above the transmission belt, capturing images of all idlers on the transmission belt from a top-down angle. (See reference) Figure 2 The image acquisition device is installed in front of the transmission belt in the direction of travel, preferably in the middle of the transmission belt, so that the idlers on both sides of the transmission belt are symmetrically displayed on the acquired monitoring image. If a value k is set, then at least the first k selected idlers on both sides of the transmission belt are displayed on the acquired monitoring image.

[0133] In one application scenario, the image acquisition device receives video data from the operation of a mine conveyor belt as input and periodically acquires continuous image frames to capture the instantaneous state of the conveyor belt during its operation.

[0134] The control device mainly includes the following modules:

[0135] 1. Idler roller target detection module.

[0136] The idler roller target detection module includes a target detection model, such as the YOLOv8m target detection model, which receives monitoring images of the idlers on both sides of the conveyor belt and then detects the xy coordinates of the idler roller position. Its task is to accurately identify and locate the idlers on the conveyor belt using deep learning technology after receiving continuous video frames, thereby obtaining the position and number of idlers. The accuracy of this module enables it to accurately extract the position and quantity information of the idlers and pass it to subsequent processing.

[0137] 2. Real-time monitoring module;

[0138] The real-time monitoring module undertakes the task of continuous monitoring, constantly tracking the number and position of idlers in actual operation, ensuring that these idlers are always within the effective observation area, so as to accurately reflect the state of the transmission belt at any time, and compare the number of idlers on both sides of the actual transmission belt with the configured reference target (idler reference number). Once the deviation judgment module detects an abnormality in the transmission belt, it will issue an alarm in time.

[0139] 3. Automatic reference target configuration module;

[0140] The automatic reference target configuration module uses an automatic reference target configuration mechanism to determine the reference quantity of the idler rollers.

[0141] The automatic reference target configuration module fully utilizes the idler position and quantity information provided by the idler target detection module to intelligently group the detected idlers into a first group and a second group, determining the reference number of idlers for subsequent deviation monitoring. This mechanism ensures a relatively uniform number of idlers in the first and second groups without manual intervention, thereby improving monitoring accuracy.

[0142] 4. Top-ranking screening module;

[0143] The front-row filtering module utilizes a front-row filtering mechanism designed to address perspective effects caused by the camera's viewing angle. The rollers are arranged in an orderly fashion according to their vertical position (Y-axis coordinate) within the video frame. Then, based on the Top-k principle, it selects the first k rollers while filtering out rollers further away, aiming to construct an effective observation area for more accurate and stable detection.

[0144] Comparative Example

[0145] A transmission belt segmentation model is used for belt misalignment monitoring. This model segments the transmission belt image to detect its position and shape, thereby determining whether the belt is misaligned.

[0146] The proportional method requires manually drawing reference lines to achieve accurate segmentation, which is time-consuming and labor-intensive. In addition, the processing speed of the segmentation model (including post-processing) is relatively slow, making it difficult to meet the needs of real-time monitoring.

[0147] Compared with the comparative example, the method of the present invention greatly reduces manual intervention and improves the degree of automation of monitoring; in addition, it can also reduce the influence of the perspective effect on the detection results. The present invention has good real-time performance, accuracy and stability of idler roller detection.

[0148] It should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, a part of its hardware, or a combination of software and hardware. Therefore, the number of modules shown in the figures is merely illustrative.

[0149] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0150] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0151] Furthermore, the present invention also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to the present invention, the computer-readable storage medium can be configured to store a program for executing the method of detecting conveyor belt deviation described in the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described method for detecting conveyor belt deviation. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium can be a storage device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0152] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for detecting conveyor belt misalignment, characterized in that, include: Receive monitoring images of the idlers on both sides of the conveyor belt; Based on visual target detection, the position and number of the idlers are obtained from the image; Based on the position and number of the idlers, determine whether the conveyor belt is off-track; The step of determining the position of the idler roller based on the image includes: Based on the image, the position of each idler roller relative to the conveyor belt is obtained; Based on the positions, all idlers are divided into a first group and a second group, wherein the idlers of the first group and the second group are located on both sides of the conveyor belt, respectively. The step of determining the number of idlers based on the image includes: The number of idlers in the first group and the second group are obtained from the images respectively; The step of determining whether the conveyor belt is off-track based on the position and number of the idlers includes: Determine the reference quantity of idlers; Calculate the difference between the number of idlers obtained from the image and the reference number of idlers; Based on the difference, determine whether the conveyor belt is off-center; The determination of the reference number of idler rollers includes: Calculate the first difference between the number of idlers in the first group and the second group; Determine whether the first difference is less than a first preset threshold; If it is less than the number of rollers in the first group, then a first reference number is determined based on the number of rollers in the first group and a second reference number is determined based on the number of rollers in the second group. The difference between the number of idlers calculated from the image and the reference number of idlers includes: Calculate the second difference between the number of the first group of idlers obtained from the image and the first reference number; Calculate the third difference between the number of the second group of idlers obtained from the image and the second reference number; The step of determining whether the conveyor belt is off-track based on the difference includes: Determine whether the second difference is greater than the second preset threshold. If it is, the conveyor belt is misaligned. Determine whether the third difference is greater than a third preset threshold. If it is, the conveyor belt is misaligned.

2. The method according to claim 1, characterized in that, The monitoring images of the idlers on both sides of the receiving conveyor belt include: Receive images of the idlers on both sides of the conveyor belt acquired by the image acquisition device; The step of obtaining the position and number of the idlers based on the image also includes: In the image, the idlers are sorted in order from near to far from the image acquisition device, and the first k idlers are selected, where k is a preset value; Based on the image, the positions and number of the first k idlers are obtained; The step of determining whether the conveyor belt is off-track based on the position and number of the idlers further includes: Based on the selected positions and numbers of the first k idlers, determine whether the conveyor belt is off-track.

3. The method according to claim 1, characterized in that, The visual target detection includes: Based on the YOLO object detection model.

4. A control device, comprising a processor and a storage device, said storage device being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the method for detecting conveyor belt deviation as described in any one of claims 1 to 3.

5. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the method for detecting conveyor belt deviation as described in any one of claims 1 to 3.

6. A system for detecting conveyor belt misalignment, characterized in that, include: Image acquisition device, used to acquire monitoring images of the idlers on both sides of the conveyor belt; as well as The control device according to claim 4.

Images