Method and device for detecting deviation and load of a conveyor belt

Abstract

The application provides a transportation belt deviation and load weight detection method and device, a computer readable medium and an electronic device. The transportation belt deviation and load weight detection method comprises: using a camera to collect images in real time during the operation of a transportation belt; preprocessing the collected images to generate preprocessed images; using a deep learning neural network model to identify a target area in the preprocessed images to obtain an identification result; calculating a deviation ratio of the transportation belt through the identification result; and determining whether the transportation belt is deviated based on the deviation ratio of the transportation belt. The technical solution of the application uses a deep learning-based visual intelligent judgment method to obtain the pixel area of left and right rollers in the image through an artificial intelligence algorithm, accurately monitors the belt deviation and load weight, and improves the monitoring accuracy, real-time performance and intelligent level of the transportation belt.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a method, apparatus, computer-readable medium, and electronic device for detecting conveyor belt misalignment and load capacity. Background Technology

[0002] Conveyor belts play a vital role in industrial production, especially in industries like coal mining, where their stable operation is crucial for production efficiency. Belt misalignment and load are key factors affecting the safe and efficient operation of transportation systems. Traditional technologies typically use mechanical sensors to monitor belt operation. While there have been some attempts to incorporate image processing techniques into belt monitoring, most remain at the level of simple image segmentation and object detection, failing to fully leverage the advantages of technologies like deep learning. However, these methods have limitations, struggling to adapt to complex and changing working conditions, resulting in low efficiency and inaccurate detection of conveyor belt misalignment and load. Summary of the Invention

[0003] The embodiments of this application provide a method, apparatus, computer-readable medium, and electronic device for detecting conveyor belt misalignment and load capacity, which can at least partially solve the problems of low efficiency and insufficient accuracy in detecting conveyor belt misalignment and load capacity.

[0004] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0005] According to one aspect of this application, a method for detecting conveyor belt misalignment and load capacity is provided, comprising: acquiring images of the conveyor belt in operation in real time using a camera; preprocessing the acquired images to generate a preprocessed image; identifying target regions in the preprocessed image using a deep learning neural network model to obtain an identification result; calculating the misalignment ratio of the conveyor belt based on the identification result; and determining whether the conveyor belt is misaligned based on the misalignment ratio.

[0006] In this application, based on the aforementioned scheme, the method further includes: calculating the load ratio of the transport belt using the identification results.

[0007] In this application, based on the aforementioned scheme, the step of preprocessing the acquired image to generate a preprocessed image includes: denoising the acquired image to generate a denoised image; converting the denoised image to grayscale to generate a grayscale image; and performing image enhancement processing on the grayscale image to generate the preprocessed image.

[0008] In this application, based on the aforementioned scheme, before using a deep learning neural network model to identify the target region in the preprocessed image and obtain the identification result, the method further includes: acquiring image samples and labeling the image samples to generate corresponding labeling information; performing data augmentation on the image samples to generate derived samples; and training the deep learning neural network model based on the image samples, their labeling information, and the derived samples.

[0009] In this application, based on the aforementioned scheme, after the real-time acquisition of images of the conveyor belt during operation using a camera, the method further includes: uploading the images to a server via a preset communication protocol; wherein the communication protocol includes Message Queuing Telemetry Transport (MQTT) or CoAP (Coordinated Application Protocol).

[0010] In this application, based on the aforementioned scheme, the step of calculating the deviation ratio of the transport belt through the recognition result includes: at any time, obtaining the area of ​​a set of rollers on the left and right sides of the transport belt in the image, which are a first area and a second area; and calculating the deviation ratio based on the maximum and minimum values ​​of the first area and the second area.

[0011] In this application, based on the aforementioned scheme, the step of calculating the load ratio of the transport belt using the recognition result includes: when the transport belt is unloaded, obtaining the areas of a set of rollers on the left and right sides of the transport belt in the image, which are the third area and the fourth area; when the transport belt is fully loaded, obtaining the areas of a set of rollers on the left and right sides of the transport belt in the image, which are the fifth area and the sixth area; and performing normalization calculation based on the sum of the first area and the second area, the sum of the third area and the fourth area, and the sum of the fifth area and the sixth area to obtain the load ratio of the transport belt.

[0012] According to one aspect of this application, a conveyor belt misalignment and load detection device is provided, comprising:

[0013] The image acquisition module uses a camera to acquire images of the conveyor belt in real time during its operation.

[0014] The image preprocessing module preprocesses the acquired images to generate a preprocessed image;

[0015] The target recognition module uses a deep learning neural network model to identify target regions in the preprocessed image and obtain recognition results.

[0016] The status judgment module calculates the deviation ratio of the conveyor belt based on the recognition results;

[0017] The result output module determines whether the conveyor belt is misaligned based on the belt misalignment ratio.

[0018] In this application, based on the aforementioned scheme, the method further includes: calculating the load ratio of the transport belt using the identification results.

[0019] In this application, based on the aforementioned scheme, the step of preprocessing the acquired image to generate a preprocessed image includes: denoising the acquired image to generate a denoised image; converting the denoised image to grayscale to generate a grayscale image; and performing image enhancement processing on the grayscale image to generate the preprocessed image.

[0020] In this application, based on the aforementioned scheme, before using a deep learning neural network model to identify the target region in the preprocessed image and obtain the identification result, the method further includes: acquiring image samples and labeling the image samples to generate corresponding labeling information; performing data augmentation on the image samples to generate derived samples; and training the deep learning neural network model based on the image samples, their labeling information, and the derived samples.

[0021] In this application, based on the aforementioned scheme, after the real-time acquisition of images of the conveyor belt during operation using a camera, the method further includes: uploading the images to a server via a preset communication protocol; wherein the communication protocol includes Message Queuing Telemetry Transport (MQTT) or CoAP (Coordinated Application Protocol).

[0022] In this application, based on the aforementioned scheme, the step of calculating the deviation ratio of the transport belt through the recognition result includes: at any time, obtaining the area of ​​a set of rollers on the left and right sides of the transport belt in the image, which are a first area and a second area; and calculating the deviation ratio based on the maximum and minimum values ​​of the first area and the second area.

[0023] In this application, based on the aforementioned scheme, the step of calculating the load ratio of the transport belt using the recognition result includes: when the transport belt is unloaded, obtaining the areas of a set of rollers on the left and right sides of the transport belt in the image, which are the third area and the fourth area; when the transport belt is fully loaded, obtaining the areas of a set of rollers on the left and right sides of the transport belt in the image, which are the fifth area and the sixth area; and performing normalization calculation based on the sum of the first area and the second area, the sum of the third area and the fourth area, and the sum of the fifth area and the sixth area to obtain the load ratio of the transport belt.

[0024] According to one aspect of this application, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the conveyor belt misalignment and load detection method as described in the above embodiments.

[0025] According to one aspect of this application, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement the conveyor belt misalignment and load detection method as described in the above embodiments.

[0026] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the conveyor belt misalignment and load detection method provided in the various optional implementations described above.

[0027] In the technical solution of this application, a camera is used to acquire images of the conveyor belt in real time during operation; the acquired images are preprocessed to generate preprocessed images; a deep learning neural network model is used to identify target areas in the preprocessed images to obtain identification results; the belt misalignment ratio is calculated based on the identification results; and the belt misalignment ratio is used to determine whether the conveyor belt is misaligned. This technical solution, based on a deep learning-based visual intelligent judgment method, uses artificial intelligence algorithms to obtain the pixel area of ​​the left and right rollers in the image, achieving accurate monitoring of belt misalignment and load capacity, and improving the monitoring accuracy, real-time performance, and intelligence level of the conveyor belt.

[0028] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0029] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0030] Figure 1 The flowchart illustrating a method for detecting conveyor belt misalignment and load capacity in one embodiment of this application is shown schematically.

[0031] Figure 2 The illustration shows a schematic diagram of conveyor belt misalignment detection in one embodiment of this application.

[0032] Figure 3 The schematic diagram illustrates a conveyor belt misalignment and load detection device in one embodiment of this application.

[0033] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0034] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0035] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0036] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0037] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0038] Conveyor belts play a vital role in industrial production, especially in industries like coal mining, where their stable operation is crucial for production efficiency. Belt misalignment and load are key factors affecting the safe and efficient operation of transport systems. Traditional technologies typically use mechanical sensors to monitor belt operation, but these methods have limitations and are ill-suited to complex and changing operating conditions. In recent years, with the development of computer vision and deep learning technologies, visual intelligent monitoring technology has been increasingly applied to belt conveyor systems, providing a more flexible and intelligent solution.

[0039] The existing implementation scheme most similar to the embodiments of this application is as follows:

[0040] 1. Traditional mechanical sensor monitoring solutions:

[0041] Traditional belt monitoring solutions typically employ mechanical sensors, such as displacement and force sensors, to determine the belt's condition by measuring physical parameters like displacement and tension. While this method is simple and intuitive, it has the following drawbacks:

[0042] 1) A large number of sensors are needed to cover the entire belt, which increases the system cost and complexity.

[0043] 2) Difficult to adapt to complex environments and easily affected by external interference.

[0044] 3) The real-time monitoring effect on deviation and load is limited.

[0045] 2. Image processing-based monitoring scheme:

[0046] In recent years, some image processing-based monitoring solutions have begun to be applied to belt conveyor systems. These solutions utilize cameras to capture images of the belt in operation and then use image processing and computer vision technologies to monitor the belt's condition. Specific steps include image segmentation and target detection.

[0047] 1) Image segmentation: Image segmentation techniques are used to separate targets such as belts and rollers from images for subsequent processing.

[0048] 2) Target detection: Use target detection algorithms to identify the rollers on the belt and obtain their position information.

[0049] These solutions have the advantage of enabling non-contact monitoring of belt operation status, but the following problems still exist:

[0050] 1. It has high requirements for image processing and is easily affected by factors such as lighting and occlusion.

[0051] 2. The accuracy of some solutions in identifying rollers needs to be improved.

[0052] 3. Lacks comprehensive intelligent judgment, usually requires further integration with rules to determine the state.

[0053] In summary, although there have been some attempts to use image processing technology in belt monitoring, most of them remain at the stage of simple image segmentation and target detection, failing to fully leverage the advantages of technologies such as deep learning. Therefore, the visual intelligent judgment method proposed in this application introduces a deep learning neural network model on the basis of image processing to achieve intelligent recognition of exposed rollers, providing a more efficient and accurate solution for monitoring belt misalignment and load.

[0054] Conveyor belts are widely used in industrial production, but belt misalignment and load monitoring have always been significant issues affecting system safety and efficiency. Traditional methods, such as mechanical sensors and simple image processing techniques, are insufficient to meet the high-precision requirements for monitoring belt operation. This application provides a deep learning-based visual intelligent judgment method capable of accurately monitoring belt misalignment and load.

[0055] The implementation details of the technical solution of this application are described below:

[0056] Figure 1 A flowchart illustrating a method for detecting conveyor belt misalignment and load capacity according to an embodiment of this application is shown. (Refer to...) Figure 1 As shown, the method for detecting conveyor belt misalignment and load capacity includes at least steps S110 to S150, which are described in detail below:

[0057] In step S110, a camera is used to collect images of the conveyor belt in real time during its operation.

[0058] In one embodiment of this application, a camera is used to collect images of the conveyor belt in real time during its operation, enabling non-contact, intelligent monitoring of the belt's operating status.

[0059] In one embodiment of this application, after real-time acquisition of images of the conveyor belt during its operation using a camera, the method further includes:

[0060] The image is uploaded to the server using a preset communication protocol, wherein the communication protocol includes Message Queuing Telemetry Transport (MQTT) or CoAP (Co-Restricted Application Protocol).

[0061] Optionally, in this embodiment, the image acquisition device may be an industrial-grade camera, and it is connected to the monitoring system through an efficient image transmission protocol.

[0062] Optionally, in this embodiment, the real-time transmission of monitoring results can be achieved using communication protocols such as Message Queuing Telemetry Transmission (MQTT), CoAP (Co-Restricted Application Protocol), or HTTP (Hypertext Transfer Protocol), with the appropriate communication protocol selected based on the specific application scenario and requirements.

[0063] This embodiment achieves an efficient combination of real-time monitoring and remote transmission through the integrated design of real-time monitoring and remote transmission. It adopts an efficient communication protocol to ensure that the monitoring results can be transmitted to the remote monitoring system in real time and stably, thereby improving the practicality and reliability of the monitoring system.

[0064] In step S120, the acquired image is preprocessed to generate a preprocessed image.

[0065] In one embodiment of this application, the acquired image is preprocessed to generate a preprocessed image, which improves the accuracy of identifying targets such as rollers on both sides of the conveyor belt.

[0066] In one embodiment of this application, the acquired image is preprocessed to generate a preprocessed image, including:

[0067] The acquired images are denoised to generate denoised images;

[0068] The denoised image is converted to grayscale to generate a grayscale image;

[0069] The grayscale image is subjected to image enhancement processing to generate the preprocessed image.

[0070] The embodiments of this application preprocess the acquired images, and the key is the use of an optimization algorithm, including steps such as noise reduction and grayscale conversion, to improve image quality and provide more reliable input for subsequent target recognition.

[0071] In addition, other image enhancement techniques, such as histogram equalization and filtering, can be considered to further improve image quality.

[0072] In step S130, a deep learning neural network model is used to identify the target region in the preprocessed image to obtain the identification result.

[0073] In one embodiment of this application, a deep learning neural network model is used to identify the target region in the preprocessed image to obtain the identification result.

[0074] The embodiments of this application can employ deep learning frameworks such as TensorFlow or PyTorch for model training. Through deep learning, the system possesses a certain degree of self-learning capability and greater adaptability. While the embodiments of this application utilize a self-learning method to achieve the system's adaptive capability, other machine learning methods, such as reinforcement learning and genetic algorithms, can be considered to achieve a higher level of intelligence.

[0075] In one embodiment of this application, before obtaining the recognition result by using a deep learning neural network model to identify the target region in the preprocessed image, the method further includes:

[0076] Acquire image samples, annotate the image samples, and generate corresponding annotation information;

[0077] The image samples are augmented to generate derived samples;

[0078] The deep learning neural network model is trained based on the image samples and their annotation information, as well as the derived samples.

[0079] This application uses a deep learning neural network model to identify the belt running status. The key lies in the training method of the model, including sample acquisition, annotation, data augmentation, etc., to improve the accuracy and robustness when identifying targets such as rollers.

[0080] Alternatively, in addition to deep learning neural network models, traditional computer vision algorithms, such as Haar cascade classifiers and HOG+SVM, can also be considered in artificial intelligence algorithms. Choosing different object detection algorithms may affect the system's real-time performance and accuracy.

[0081] This application embodiment utilizes deep learning, enabling the system to possess a certain degree of self-learning capability and adapt to the belt running state under different working conditions, thereby improving the system's intelligence level. This application embodiment improves the accuracy of belt running state recognition by optimizing the deep learning model training method. Compared to existing technologies, it can more accurately identify targets such as rollers in images, demonstrating greater adaptability and intelligence.

[0082] In step S140, the deviation ratio of the transport belt is calculated based on the identification results.

[0083] In one embodiment of this application, the identification result is used to determine whether the belt is misaligned and to calculate the load ratio.

[0084] The recognition results include information obtained from preprocessed image recognition, such as the area of ​​the conveyor belt, the area of ​​the rollers on the left and right sides of the conveyor belt, etc.

[0085] like Figure 2As shown, in one embodiment of this application, calculating the belt misalignment ratio includes:

[0086] At any given time, the area of ​​a set of rollers on the left and right sides of the conveyor belt in the image is obtained, which is the first area and the second area.

[0087] The deviation ratio is calculated based on the maximum and minimum values ​​of the first area and the second area.

[0088] Specifically, for the amount of coal loaded on the conveyor belt at any given time, the areas of the left and right rollers are the first area (Sl) and the second area (Sr), and the sum of their left and right areas is: S = Sl + Sr.

[0089] For the belt misalignment ratio, the value is defined as 0 in the middle, meaning the exposed areas of the left and right rollers are equal. The maximum deviation to the left is -1, and the maximum deviation to the right is 1, meaning the value range is [-1, 1]. The misalignment ratio y is calculated as follows:

[0090] y=(2*(Sl-min(Sl, Sr)) / (max(Sl, Sr)-min(Sl, Sr)))-1

[0091] In one embodiment of this application, the method further includes: calculating the load ratio of the transport belt based on the identification result. Specifically, this includes:

[0092] When the conveyor belt is unloaded, the area of ​​a set of rollers on the left and right sides of the conveyor belt in the image is obtained, which are the third area and the fourth area;

[0093] When the conveyor belt is fully loaded, the area of ​​a set of rollers on the left and right sides of the conveyor belt in the image is obtained, which are the fifth area and the sixth area;

[0094] Based on the sum of the first area and the second area, the sum of the third area and the fourth area, and the sum of the fifth area and the sixth area, a normalized calculation is performed to obtain the load ratio of the transport belt.

[0095] Specifically, for the calculation of the load ratio, we define it as 0 when unloaded and 1 when fully loaded, i.e., the value range is [0, 1]. We can obtain the area of ​​the roller in the image through the roller recognition model.

[0096] When the belt is unloaded, record the areas of the first two rollers on the image, which we assume to be the third area (Sl_empty) and the fourth area (Sr_empty). Then, the sum of the left and right areas of the rollers when the belt is unloaded (S_empty) is:

[0097] S_empty = Sl_empty + Sr_empty

[0098] When the belt is fully loaded, the areas of the left and right rollers are the fifth area (Sl full) and the sixth area (Sr full). Therefore, the sum of the left and right roller areas (S full) when the belt is fully loaded is:

[0099] S_full = S_l_full + S_r_full

[0100] Normalizing S, we obtain the load ratio x at any given time as:

[0101] x = (SS empty) / (S full - S empty)

[0102] Therefore, by combining the two parameters x ~ [0, 1] and y ~ [-1, 1], we can determine the current coal load of the conveyor belt and the belt deviation rate.

[0103] In step S150, it is determined whether the conveyor belt is misaligned based on the belt misalignment ratio.

[0104] After calculating the belt misalignment ratio and load ratio, and combining the two parameters x ~ [0, 1] and y ~ [-1, 1], the current coal load and belt misalignment rate of the conveyor belt can be determined. For example, if the above parameters are detected to be outside the corresponding range, it is determined that the conveyor belt is misaligned, and an alarm or notification is issued.

[0105] Taking a coal mine conveyor belt as an example, cameras are installed above the belt system to capture real-time images of the belt's operation. After preprocessing, the images are input into a deep learning neural network. Once trained, the model can accurately identify targets such as the belt and rollers in the images. The identification results are used to determine if the belt is misaligned and to calculate the load ratio. The monitoring results are transmitted to a monitoring system via the network, enabling remote monitoring of the belt's condition.

[0106] For example, in a coal mining and transportation application scenario, the following steps are included, and the resulting detection results are shown in the table below:

[0107] Table 1: Load Ratio and Offset Ratio Chart

[0108] Load ratio Deviation ratio 0.1 -0.05 0.3 0.15 0.5 0.28 0.7 0.40 0.9 0.60

[0109] 1. Image Acquisition: Obtain real-time image data from the camera.

[0110] 2. Target detection: Using a trained roller recognition model, identify the positions of the left and right rollers in the image.

[0111] 3. Image preprocessing: Perform preprocessing operations such as noise reduction and grayscale conversion on the acquired images to improve recognition accuracy.

[0112] 4. Roller Recognition: Using artificial intelligence algorithms, the left and right rollers in the image are identified and their areas are calculated.

[0113] 5. Coal load ratio calculation: Calculate the current coal load ratio of the conveyor belt based on the roller area.

[0114] 6. Calculation of belt misalignment rate: The current belt misalignment rate is calculated using the difference in exposed roller area.

[0115] 7. Output Results: Output the calculated information to a display or other monitoring equipment.

[0116] In this application's technical solution, a camera is used to acquire images of the conveyor belt in real time during operation; the acquired images are preprocessed to generate preprocessed images; a deep learning neural network model is used to identify target areas in the preprocessed images to obtain identification results; the conveyor belt deviation ratio is calculated based on the identification results; and based on the conveyor belt deviation ratio, it is determined whether the conveyor belt is misaligned. This application's technical solution, based on a deep learning-based visual intelligent judgment method, uses artificial intelligence algorithms to obtain the pixel area of ​​the left and right rollers in the image, achieving accurate monitoring of belt deviation and load capacity, and improving the monitoring accuracy, real-time performance, and intelligence level of the conveyor belt.

[0117] The following describes an embodiment of the apparatus described in this application, which can be used to execute the conveyor belt misalignment and load detection method in the above embodiments of this application. It is understood that the apparatus can be a computer program (including program code) running on a computer device, for example, the apparatus is application software; the apparatus can be used to execute the corresponding steps in the method provided in the embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the conveyor belt misalignment and load detection method described above in this application.

[0118] Figure 3 A block diagram of a conveyor belt misalignment and load detection device according to an embodiment of this application is shown.

[0119] Reference Figure 3 As shown, a conveyor belt misalignment and load detection device according to an embodiment of this application includes:

[0120] The image acquisition module 310 uses a camera to acquire images of the conveyor belt in real time during its operation.

[0121] The image preprocessing module 320 preprocesses the acquired image to generate a preprocessed image;

[0122] The target recognition module 330 uses a deep learning neural network model to identify the target region in the preprocessed image and obtain the recognition result.

[0123] The status judgment module 340 calculates the deviation ratio of the transport belt based on the recognition result;

[0124] The result output module 350 determines whether the transport belt is misaligned based on the belt misalignment ratio.

[0125] In this application, based on the aforementioned scheme, the method further includes: calculating the load ratio of the transport belt using the identification results.

[0126] In this application, based on the aforementioned scheme, the step of preprocessing the acquired image to generate a preprocessed image includes: denoising the acquired image to generate a denoised image; converting the denoised image to grayscale to generate a grayscale image; and performing image enhancement processing on the grayscale image to generate the preprocessed image.

[0127] In this application, based on the aforementioned scheme, before using a deep learning neural network model to identify the target region in the preprocessed image and obtain the identification result, the method further includes: acquiring image samples and labeling the image samples to generate corresponding labeling information; performing data augmentation on the image samples to generate derived samples; and training the deep learning neural network model based on the image samples, their labeling information, and the derived samples.

[0128] In this application, based on the aforementioned scheme, after the real-time acquisition of images of the conveyor belt during operation using a camera, the method further includes: uploading the images to a server via a preset communication protocol; wherein the communication protocol includes Message Queuing Telemetry Transport (MQTT) or CoAP (Coordinated Application Protocol).

[0129] In this application, based on the aforementioned scheme, the step of calculating the deviation ratio of the transport belt through the recognition result includes: at any time, obtaining the area of ​​a set of rollers on the left and right sides of the transport belt in the image, which are a first area and a second area; and calculating the deviation ratio based on the maximum and minimum values ​​of the first area and the second area.

[0130] In this application, based on the aforementioned scheme, the step of calculating the load ratio of the transport belt using the recognition result includes: when the transport belt is unloaded, obtaining the areas of a set of rollers on the left and right sides of the transport belt in the image, which are the third area and the fourth area; when the transport belt is fully loaded, obtaining the areas of a set of rollers on the left and right sides of the transport belt in the image, which are the fifth area and the sixth area; and performing normalization calculation based on the sum of the first area and the second area, the sum of the third area and the fourth area, and the sum of the fifth area and the sixth area to obtain the load ratio of the transport belt.

[0131] This application utilizes a camera to capture images of the conveyor belt in operation in real time; preprocesses the captured images to generate preprocessed images; identifies target areas in the preprocessed images using a deep learning neural network model to obtain identification results; calculates the belt misalignment ratio based on the identification results; and determines whether the conveyor belt is misaligned based on the belt misalignment ratio. The technical solution of this application, based on a deep learning-based visual intelligent judgment method, uses artificial intelligence algorithms to obtain the pixel area of ​​the left and right rollers in the image, achieving accurate monitoring of belt misalignment and load capacity, and improving the monitoring accuracy, real-time performance, and intelligence level of the conveyor belt.

[0132] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0133] It should be noted that the computer system 400 of the electronic device shown in the figure is only an example and should not impose any limitations on the function and scope of use of the embodiments of this application.

[0134] The computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 402 or programs loaded from Storage Unit 408 into Random Access Memory (RAM) 403, such as performing the methods described in the above embodiments. The RAM 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0135] The following components are connected to I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to I / O interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 410 as needed so that computer programs read from it can be installed into storage section 408 as needed.

[0136] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs various functions defined in the system of this application.

[0137] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-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 a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0138] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0139] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0140] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.

[0141] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

[0142] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0143] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0144] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0145] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for detecting conveyor belt misalignment and load capacity, characterized in that, include: The system uses cameras to capture images of the conveyor belt in real time during its operation. The acquired images are preprocessed to generate preprocessed images; The target region in the preprocessed image is identified using a deep learning neural network model to obtain the identification result; Based on the identification results, the deviation ratio of the transport belt is calculated; The calculation of the belt misalignment ratio includes: At any given time, the area of ​​a set of rollers on the left and right sides of the conveyor belt in the image is obtained, which is the first area and the second area. The deviation ratio is calculated based on the maximum and minimum values ​​of the first area and the second area; The areas of the left and right rollers are the first area (Sl) and the second area (Sr), and the sum of their left and right areas is: S = Sl + Sr; For the belt misalignment ratio, the value is defined as 0 in the middle, meaning the exposed areas of the left and right rollers are equal. The maximum deviation to the left is -1, and the maximum deviation to the right is 1, meaning the value range is [-1, 1]. The method for calculating the misalignment ratio y is as follows: y=(2×(Sl-min(Sl, Sr)) / (max(Sl, Sr)-min(Sl, Sr)))-1; Based on the identification results, the load ratio of the transport belt is calculated, including: When the conveyor belt is unloaded, the area of ​​a set of rollers on the left and right sides of the conveyor belt in the image is obtained, which are the third area and the fourth area; When the conveyor belt is fully loaded, the area of ​​a set of rollers on the left and right sides of the conveyor belt in the image is obtained, which are the fifth area and the sixth area; Based on the sum of the third and fourth areas, and the sum of the fifth and sixth areas, a normalized calculation is performed to obtain the load ratio of the transport belt; This includes recording the areas of the first two rollers (left and right) on the image when the belt is unloaded, the third area (Sl_empty), and the fourth area (Sr_empty). The sum of the left and right areas of the rollers when the belt is unloaded (S_empty) is: S_empty = Sl_empty + Sr_empty When the belt is fully loaded, the areas of the left and right rollers are the fifth area (Sl full) and the sixth area (Sr full). The sum of the areas of the left and right rollers when the belt is fully loaded (S full) is: S_full = S_l_full + S_r_full Normalizing S, we obtain the load ratio x at any given time as: x = (SS empty) / (S full - S empty) The standard ranges for x and y are: x ~ [0, 1], y ~ [-1, 1]. When the detected parameters are not within the corresponding ranges, it is determined that the conveyor belt is off-track, and an alarm or notification is issued.

2. The method according to claim 1, characterized in that, The acquired images are preprocessed to generate preprocessed images, including: The acquired images are denoised to generate denoised images; The denoised image is converted to grayscale to generate a grayscale image; The grayscale image is subjected to image enhancement processing to generate the preprocessed image.

3. The method according to claim 1, characterized in that, Before obtaining the recognition result, the following steps are also included: Using a deep learning neural network model to identify the target region in the preprocessed image. Acquire image samples, annotate the image samples, and generate corresponding annotation information; The image samples are augmented to generate derived samples; The deep learning neural network model is trained based on the image samples and their annotation information, as well as the derived samples.

4. The method according to claim 1, characterized in that, After using cameras to collect images of the conveyor belt in real time during operation, the process also includes: The image is uploaded to the server using a preset communication protocol, wherein the communication protocol includes Message Queuing Telemetry Transport (MQTT) or CoAP (Co-Restricted Application Protocol).

5. A device for detecting conveyor belt misalignment and load capacity, characterized in that, include: The image acquisition module uses a camera to acquire images of the conveyor belt in real time during its operation. The image preprocessing module preprocesses the acquired images to generate a preprocessed image; The target recognition module uses a deep learning neural network model to identify target regions in the preprocessed image and obtain recognition results. The status judgment module calculates the deviation ratio of the conveyor belt based on the recognition results; The calculation of the belt misalignment ratio includes: At any given time, the area of ​​a set of rollers on the left and right sides of the conveyor belt in the image is obtained, which is the first area and the second area. The deviation ratio is calculated based on the maximum and minimum values ​​of the first area and the second area; The areas of the left and right rollers are the first area (Sl) and the second area (Sr), and the sum of their left and right areas is: S = Sl + Sr; For the belt misalignment ratio, the value is defined as 0 in the middle, meaning the exposed areas of the left and right rollers are equal. The maximum deviation to the left is -1, and the maximum deviation to the right is 1, meaning the value range is [-1, 1]. The method for calculating the misalignment ratio y is as follows: y=(2×(Sl-min(Sl, Sr)) / (max(Sl, Sr)-min(Sl, Sr)))-1; Based on the identification results, the load ratio of the transport belt is calculated, including: When the conveyor belt is unloaded, the area of ​​a set of rollers on the left and right sides of the conveyor belt in the image is obtained, which are the third area and the fourth area; When the conveyor belt is fully loaded, the area of ​​a set of rollers on the left and right sides of the conveyor belt in the image is obtained, which are the fifth area and the sixth area; Based on the sum of the third and fourth areas, and the sum of the fifth and sixth areas, a normalized calculation is performed to obtain the load ratio of the transport belt; This includes recording the areas of the first two rollers (left and right) on the image when the belt is unloaded, the third area (Sl_empty), and the fourth area (Sr_empty). The sum of the left and right areas of the rollers when the belt is unloaded (S_empty) is: S_empty = Sl_empty + Sr_empty When the belt is fully loaded, the areas of the left and right rollers are the fifth area (Sl full) and the sixth area (Sr full). The sum of the areas of the left and right rollers when the belt is fully loaded (S full) is: S_full = S_l_full + S_r_full Normalizing S, we obtain the load ratio x at any given time as: x = (SS empty) / (S full - S empty) The output module specifies the standard ranges for x and y as follows: x ~ [0, 1], y ~ [-1, 1]. When the detected parameters are not within the corresponding range, it is determined that the conveyor belt is off-track, and an alarm or notification is issued.

6. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the conveyor belt misalignment and load detection method as described in any one of claims 1 to 4.

7. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the conveyor belt misalignment and load detection method as described in any one of claims 1 to 4.

Images