Conveyor belt tearing detection method and system of material conveyor and storage medium

Abstract

The invention provides a conveyor belt tearing detection method and system of a material conveyor and a storage medium, and relates to the technical field of logistics conveying. The multi-dimensional operation state data comprises at least three of pressure data, surface contour data, image data, electromagnetic induction data, vibration frequency, vibration sound data and temperature data. Therefore, the collected data is richer and more complete. And inputting the multi-dimensional operation state data into a pre-trained tearing confidence coefficient determination model, and determining the confidence coefficient that the conveyor belt of the material conveyor is torn. The tearing confidence coefficient determination model is obtained by inputting the plurality of training samples into the to-be-trained network for training, and the collected data is richer and more complete, so that the reliability of determining the tearing confidence coefficient of the conveyor belt of the material conveyor can be high. And under the condition that the determined confidence coefficient is larger than the set confidence coefficient threshold value, it is determined that the conveying belt of the material conveyor is torn, and the accuracy is high.

Description

Technical Field

[0001] The present application relates to the technical field of logistics transmission, and in particular, to a method, a system, and a storage medium for detecting a tear in a conveyor belt of a material conveyor. Background Art

[0002] A material conveyor can be used for horizontal transportation or inclined transportation of bulk materials (such as sand and coal mines, etc.), and is widely used in various modern industrial enterprises, such as underground roadways in mines, mine surface transportation systems, open-pit mining sites, and concentrator plants. During the operation of the material conveyor, the conveyor belt of the material conveyor may be torn due to uneven stress, material jamming, or mechanical failures. As a result, significant economic losses may occur.

[0003] Currently, an induction module can be set below the tail of the material conveyor. When the conveyor belt is torn, when the torn part of the conveyor belt moves to the tail of the material conveyor, the material will fall from the torn part to below the tail of the material conveyor and be sensed by the induction module, so that it can be determined that the conveyor belt is torn.

[0004] However, the above method has low accuracy in determining that the conveyor belt is torn (for example, bulk materials falling from one side of the conveyor belt will also be sensed by the induction module), and has a long delay (it is necessary for the torn part to move to the tail of the material conveyor). Summary of the Invention

[0005] The present application provides a method, a system, and a storage medium for detecting a tear in a conveyor belt of a material conveyor, which are used to solve the problem of low accuracy in determining that the conveyor belt is torn in the prior art.

[0006] The present application provides a method for detecting a tear in a conveyor belt of a material conveyor, including:

[0007] Receiving multi-dimensional operating state data on the back of the conveyor belt of the material conveyor collected by a multi-dimensional data sensing unit, where the multi-dimensional operating state data includes at least three of pressure data, surface profile data, image data, electromagnetic induction data, vibration frequency, vibration sound data, and temperature data, and the multi-dimensional data sensing unit is located between the working surface and the non-working surface of the conveyor belt;

[0008] Inputting the multi-dimensional operating state data into a pre-trained tear confidence determination model to determine the confidence that the conveyor belt of the material conveyor is torn, where the tear confidence determination model is obtained by training multiple training samples input into a network to be trained, and each training sample includes historical multi-dimensional operating state data and the actual confidence that the conveyor belt of the material conveyor is torn;

[0009] When the determined confidence level is greater than the set confidence level threshold, it is determined that the conveyor belt of the material conveyor is torn.

[0010] In some embodiments, the number of multi-dimensional data sensing units is multiple, and the multiple multi-dimensional data sensing units are arranged at intervals between the working surface and the non-working surface of the conveyor belt. When the determined confidence level is greater than the set confidence level threshold, determining that the conveyor belt of the material conveyor is torn includes:

[0011] When the confidence level corresponding to the multi-dimensional operating state data collected by any one multi-dimensional data sensing unit is greater than the set confidence level threshold, it is determined that the conveyor belt of the material conveyor is torn.

[0012] In some embodiments, after determining that the conveyor belt of the material conveyor is torn, the method further includes:

[0013] Receiving the mapping position on the conveyor belt transmitted by the multi-dimensional data sensing unit associated with the multi-dimensional operating state data whose confidence level is greater than the set confidence level threshold;

[0014] According to the preset operating speed of the conveyor belt, the preset delay duration from collecting the multi-dimensional operating state data to determining that the conveyor belt of the material conveyor is torn, and the mapping position, determining the position where the tear occurs on the conveyor belt;

[0015] Outputting the position where the tear occurs to the terminal device for display.

[0016] In some embodiments, after determining that the conveyor belt of the material conveyor is torn, the method further includes:

[0017] Controlling the conveyor belt of the material conveyor to stop running;

[0018] And / or controlling the alarm module to give an alarm.

[0019] In a second aspect, the present application also provides a conveyor belt tear detection system for a material conveyor, including:

[0020] A multi-dimensional data sensing unit for collecting multi-dimensional operating state data on the back of the conveyor belt of the material conveyor, where the multi-dimensional operating state data includes at least three of pressure data, surface profile data, electromagnetic induction data, vibration frequency, vibration sound data, and temperature data, and the multi-dimensional data sensing unit is located between the working surface and the non-working surface of the conveyor belt;

[0021] A data acquisition unit for receiving the multi-dimensional operating state data and transmitting it to the central controller;

[0022] A central controller is configured to input multi-dimensional operating state data into a pre-trained tear confidence determination model to determine the confidence that the conveyor belt of the material conveyor is torn. The tear confidence determination model is obtained by training multiple training samples input into a network to be trained. Each training sample includes multi-dimensional historical operating state data and the actual confidence that the conveyor belt of the material conveyor is torn.

[0023] The central controller is further configured to determine that the conveyor belt of the material conveyor is torn when the determined confidence is greater than a set confidence threshold.

[0024] In some embodiments, the number of multi-dimensional data sensing units is multiple. The multiple multi-dimensional data sensing units are spaced between the working surface and the non-working surface of the conveyor belt. The central controller is specifically configured to determine that the conveyor belt of the material conveyor is torn when the confidence corresponding to the multi-dimensional operating state data collected by any one of the multi-dimensional data sensing units is greater than the set confidence threshold.

[0025] In some embodiments, the central controller is further configured to receive the mapping position on the conveyor belt transmitted by the multi-dimensional data sensing unit associated with the multi-dimensional operating state data whose confidence is greater than the set confidence threshold; determine the position where the tear occurs on the conveyor belt according to the preset operating speed of the conveyor belt, the preset delay duration from collecting the multi-dimensional operating state data to determining that the conveyor belt of the material conveyor is torn, and the mapping position; and output the position where the tear occurs to the terminal device for display.

[0026] In some embodiments, the multi-dimensional data sensing unit includes at least three of a pressure sensor, a laser point cloud scanner, an image sensor, an electromagnetic induction sensor, a vibration sensor, an acoustic emission sensor, and a temperature sensor. Among them,

[0027] The pressure sensor is used to collect the pressure exerted on the conveyor belt.

[0028] The laser point cloud scanner is used to collect the surface profile data of the back of the conveyor belt.

[0029] The image sensor is used to collect the surface profile data of the back of the conveyor belt.

[0030] The electromagnetic induction sensor is used to collect electromagnetic induction data.

[0031] The acoustic emission sensor is used to collect the vibration sound data of the conveyor belt.

[0032] The temperature sensor is used to collect the temperature data of the conveyor belt.

[0033] In some embodiments, the multi-dimensional data sensing unit is installed in an explosion-proof and waterproof housing, and the explosion-proof and waterproof housing is installed on a shock-proof bracket.

[0034] In a third aspect, an embodiment of the present application further provides a storage medium storing a computer program, which, when executed by a central controller, causes the computer to execute the method provided in the embodiment of the present application.

[0035] In a fourth aspect, an embodiment of the present application further provides a computer program product including a computer program, which, when run, causes the central controller to execute the method provided in the embodiment of the present application.

[0036] The present application provides a method, a system, and a storage medium for detecting a tear in a conveyor belt of a material conveyor. Since the multi-dimensional operating state data includes at least three of pressure data, surface profile data, image data, electromagnetic induction data, vibration frequency, vibration sound data, and temperature data. Thus, the collected data is more rich and complete. The multi-dimensional operating state data is input into a pre-trained tear confidence determination model to determine the confidence that the conveyor belt of the material conveyor is torn. Since the tear confidence determination model is obtained by training multiple training samples input into a network to be trained, each training sample includes historical multi-dimensional operating state data and the actual confidence that the conveyor belt of the corresponding material conveyor is torn; and because the collected data is more rich and complete, the reliability of determining the confidence that the conveyor belt of the material conveyor is torn can be made high. When the determined confidence is greater than a set confidence threshold, it is determined that the conveyor belt of the material conveyor is torn, with high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0038] Figure 1 It is a circuit module connection block diagram of the conveyor belt tear detection system of the material conveyor provided in the embodiment of the present application;

[0039] Figure 2 It is a flowchart of the conveyor belt tear detection method of the material conveyor provided in the embodiment of the present application;

[0040] Figure 3 It is a structural schematic diagram of the conveyor belt tear detection system of the material conveyor provided in the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0042] Various structural schematic diagrams according to embodiments of the present disclosure are shown in the accompanying drawings. These figures are not drawn to scale, where for the purpose of clear expression, some details are enlarged and some details may be omitted. The shapes of various regions and layers shown in the figures, as well as their relative sizes and positional relationships, are merely exemplary and may deviate in practice due to manufacturing tolerances or technical limitations. And those skilled in the art can design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0043] In the context of the present disclosure, when a layer / element is referred to as being "on" another layer / element, the layer / element can be directly on the other layer / element, or there can be an intermediate layer / element between them. Additionally, if a layer / element is "on" another layer / element in one orientation, then when the orientation is reversed, the layer / element can be "under" the other layer / element.

[0044] Hereinafter, the technical solution of the present application and how the technical solution of the present application solves the above technical problems will be described in detail with specific embodiments. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0045] An embodiment of the present application provides a method for detecting a tear in a conveyor belt of a material conveyor, which is applied to a central controller. As Figure 1 shown, the central controller belongs to the conveyor belt tear detection system of the material conveyor, and the conveyor belt tear detection system of the material conveyor further includes a multi-dimensional data sensing unit 102, a data acquisition unit, a terminal device, and an alarm module. Exemplarily, the multi-dimensional data sensing unit 102 includes at least three of a pressure sensor, a laser point cloud scanner, an image sensor, an electromagnetic induction sensor, a vibration sensor, an acoustic emission sensor, and a temperature sensor. Figure 1The multi-dimensional data sensing unit 102 includes a pressure sensor, a laser point cloud scanner, an image sensor (such as an infrared thermal imaging module or a camera), an electromagnetic induction sensor, a vibration sensor (such as a three-axis high-frequency vibration sensor with a frequency range of 0.5 kHz - 20 kHz), an acoustic emission sensor (such as a broadband acoustic emission sensor with a frequency range of 20 kHz - 400 kHz), and a temperature sensor. The central controller can be, but is not limited to, a programmable logic controller PLC (Programmable Logic Controller, PLC). The material conveyor 101 is used to convey bulk materials. For example, the bulk materials can be, but are not limited to, sand, coal, etc. The length of the working surface 103 of the conveyor belt of the material conveyor 101 can be, but is not limited to, 100 m, 500 m, 2000 m, 4000 m, etc., which is not limited herein. In the embodiment of the present application, the material conveyor 101 can be, but is not limited to, a belt conveyor. As Figure 2 shown, the method provided by the embodiment of the present application includes:

[0046] S201: Receive multi-dimensional operating state data of the back surface of the conveyor belt of the material conveyor 101 collected by the multi-dimensional data sensing unit 102.

[0047] For example, the central controller can receive the multi-dimensional operating state data from the multi-dimensional data sensing unit 102 through an industrial Ethernet or a 4G network.

[0048] The multi-dimensional operating state data includes at least three of pressure data, surface profile data, image data, electromagnetic induction data, vibration frequency, vibration sound data, and temperature data. As Figure 3 shown, the multi-dimensional data sensing unit 102 is located between the working surface 103 and the non-working surface 104 of the conveyor belt.

[0049] Among them, it is possible to receive the pressure data of the conveyor belt collected by the pressure sensor; the surface profile data of the back surface of the conveyor belt collected by the laser point cloud scanner; the image of the back surface of the conveyor belt collected by the image sensor; the electromagnetic induction data collected by the electromagnetic induction sensor; the vibration frequency of the conveyor belt collected by the vibration sensor, the vibration sound data of the conveyor belt collected by the acoustic emission sensor; the temperature data of the conveyor belt collected by the temperature sensor.

[0050] Understandably, when the pressure data indicates a sharp drop in the pressure on the conveyor belt, it may be due to a tear in the conveyor belt resulting in material leakage, triggering the sharp drop in pressure, or it may be caused by a decrease in the weight of the material itself or other reasons; when the surface profile data and image data on the back of the conveyor belt are abnormal, it may be due to a tear in the conveyor belt, or stains, wrinkles, or other reasons on the conveyor belt; understandably, when the conveyor belt is in a moving state, if there are metal objects such as steel bars and iron sheets on the conveyor belt, they may cut the conveyor belt, and the electromagnetic induction data can be used to indicate whether there are metal products on the conveyor belt. When the vibration frequency of the conveyor belt is abnormal, it may be due to a tear in the conveyor belt, or it may be caused by a malfunction of the material conveyor 101; when the vibration sound data of the conveyor belt is abnormal, it may be due to a tear in the conveyor belt, or it may be caused by a malfunction of the material conveyor 101; in addition, when the temperature data indicates an abnormal temperature of the conveyor belt, it may be due to a malfunction of the temperature sensor, or it may be caused by the heat generated by the friction between the metal product and the moving conveyor belt when the metal product is inserted into the conveyor belt.

[0051] Based on the above, it is necessary to comprehensively consider the data in each of the above dimensions to accurately determine whether the conveyor belt is torn.

[0052] S202: Input the multi-dimensional operating state data into the pre-trained tear confidence determination model to determine the confidence that the conveyor belt of the material conveyor 101 is torn.

[0053] Among them, the tear confidence determination model is obtained by training multiple training samples into the network to be trained. Each training sample includes historical multi-dimensional operating state data and the actual confidence that the conveyor belt of the material conveyor 101 is torn. In this way, the reliability of the determined confidence that the conveyor belt is torn can be high.

[0054] S203: When the determined confidence is greater than the set confidence threshold, determine that the conveyor belt of the material conveyor 101 is torn.

[0055] For example, when the confidence is greater than 80%, 85% or 90%, determine that the conveyor belt of the material conveyor 101 is torn.

[0056] An embodiment of the present application provides a method for detecting belt tearing of a material conveyor. Since the multi-dimensional operating state data includes at least three of pressure data, surface profile data, image data, electromagnetic induction data, vibration frequency, vibration sound data, and temperature data. Thus, the collected data is more rich and complete. The multi-dimensional operating state data is input into a pre-trained tearing confidence determination model to determine the confidence that the belt of the material conveyor 101 is torn. Since the tearing confidence determination model is obtained by training multiple training samples input into a network to be trained, each training sample includes historical multi-dimensional operating state data and the actual confidence that the belt of the material conveyor 101 is torn; and because the collected data is more rich and complete, the reliability of determining the confidence that the belt of the material conveyor 101 is torn can be high. When the determined confidence is greater than the set confidence threshold, it is determined that the belt of the material conveyor 101 is torn, with high accuracy.

[0057] Further, still as Figure 1 shown, the number of multi-dimensional data sensing units 102 can be multiple, and the multiple multi-dimensional data sensing units 102 are arranged at intervals between the working surface 103 and the non-working surface 104 of the conveyor belt. From Figure 1 it can be seen that the multi-dimensional data sensing units 102 are distributed between the working surface 103 and the non-working surface 104, so that whether the conveyor belt is torn can be detected simultaneously at multiple positions. For example, when the length of the working surface 103 and the non-working surface 104 is 2000 m, a multi-dimensional data sensing unit 102 can be arranged every 50 m. When the confidence corresponding to the multi-dimensional operating state data collected by any one multi-dimensional data sensing unit 102 is greater than the set confidence threshold, it is determined that the belt of the material conveyor 101 is torn. Thus, when the belt of the material conveyor 101 is torn, the conveyor belt can detect that the belt is torn after moving at most 50 m, reducing the delay in detecting the torn belt.

[0058] In addition, after S204, the method provided by the embodiment of the present application may further include:

[0059] Step 1: Receive the mapping position on the conveyor belt transmitted by the multi-dimensional data sensing unit 102 associated with the multi-dimensional operating state data whose confidence is greater than the set confidence threshold.

[0060] For example, the mapping position of the multi-dimensional data sensing unit 102 on the conveyor belt in the vertical direction can be determined.

[0061] Step 2: Determine the position where tearing occurs on the conveyor belt according to the preset operating speed of the conveyor belt, the preset delay duration from collecting the multi-dimensional operating state data to determining that the belt of the material conveyor 101 is torn, and the mapping position.

[0062] For example, according to the formula d = vT, the moving distance of the conveyor belt is determined. Further, based on the mapped position and the moving distance of the conveyor belt, the position where the conveyor belt is torn is determined. Herein, d is the moving distance of the conveyor belt, v is the running speed of the conveyor belt, and T is the delay time from collecting multi-dimensional operating state data to determining that the conveyor belt of the material conveyor 101 is torn.

[0063] Step 3: Output the torn position to the terminal device for display.

[0064] For example, a simulation model of the material conveyor 101 can be pre-configured, mark the position where the conveyor belt is torn in the simulation model of the material conveyor 101, and transmit the simulation model of the material conveyor 101 marked with the torn position to the terminal device (such as a computer) for display.

[0065] In addition, after determining that the conveyor belt of the material conveyor 101 is torn, the method provided by the embodiments of the present application further includes: controlling the conveyor belt of the material conveyor 101 to stop running to ensure the running safety of the material conveyor 101 and reduce economic losses; and / or controlling the alarm module to alarm (such as sound and light alarm, or sending an alarm prompt message to the terminal device).

[0066] In addition, still as Figure 1 shown, the embodiments of the present application further provide a conveyor belt tear detection system for a material conveyor, including a multi-dimensional data sensing unit 102, a data acquisition unit, and a central controller, wherein,

[0067] The multi-dimensional data sensing unit 102 is configured to collect multi-dimensional operating state data on the back of the conveyor belt of the material conveyor 101. The multi-dimensional operating state data includes at least three of pressure data, surface profile data, electromagnetic induction data, vibration frequency, vibration sound data, and temperature data. The multi-dimensional data sensing unit 102 is located between the working surface 103 and the non-working surface 104 of the conveyor belt.

[0068] The data acquisition unit is configured to receive the multi-dimensional operating state data and transmit it to the central controller.

[0069] The central controller is configured to input the multi-dimensional operating state data into a pre-trained tear confidence determination model to determine the confidence that the conveyor belt of the material conveyor 101 is torn. The tear confidence determination model is obtained by training multiple training samples input into a network to be trained. Each training sample includes multi-dimensional historical operating state data and the actual confidence that the conveyor belt of the material conveyor 101 is torn.

[0070] The central controller is further configured to determine that the conveyor belt of the material conveyor 101 is torn when the determined confidence level is greater than the set confidence threshold.

[0071] In some embodiments, the number of multi-dimensional data sensing units 102 is multiple, and the multiple multi-dimensional data sensing units 102 are arranged at intervals between the working surface 103 and the non-working surface 104 of the conveyor belt. The central controller is specifically configured to determine that the conveyor belt of the material conveyor 101 is torn when the confidence level corresponding to the multi-dimensional operating state data collected by any one of the multi-dimensional data sensing units 102 is greater than the set confidence threshold.

[0072] In some embodiments, the central controller is further configured to receive the mapping position on the conveyor belt transmitted by the multi-dimensional data sensing unit 102 associated with the multi-dimensional operating state data with a confidence level greater than the set confidence threshold; determine the position where the tear occurs on the conveyor belt according to the preset operating speed of the conveyor belt, the preset delay duration from collecting the multi-dimensional operating state data to determining that the conveyor belt of the material conveyor 101 is torn, and the mapping position; and output the position where the tear occurs to the terminal device for display.

[0073] In some embodiments, the multi-dimensional data sensing unit 102 includes at least three of a pressure sensor, a laser point cloud scanner, an electromagnetic induction sensor, a vibration sensor, an acoustic emission sensor, and a temperature sensor, wherein

[0074] The pressure sensor is used to collect the pressure exerted on the conveyor belt;

[0075] The laser point cloud scanner is used to collect the surface profile data of the back of the conveyor belt;

[0076] The electromagnetic induction sensor is used to collect electromagnetic induction data;

[0077] The acoustic emission sensor is used to collect the vibration sound data of the conveyor belt;

[0078] The temperature sensor is used to collect the temperature data of the conveyor belt.

[0079] In some embodiments, the multi-dimensional data sensing unit 102 is installed in an explosion-proof and waterproof housing, wherein the explosion-proof and waterproof housing is installed on a shock-proof bracket. The explosion-proof and waterproof housing can prevent the multi-dimensional data sensing unit 102 from being damaged by erosion from the external environment (such as dust, slag, or water vapor), and the shock-proof bracket can prevent the multi-dimensional data sensing unit 102 from being damaged due to long-term vibration. Optionally, the multi-dimensional data sensing unit 102 can be powered by a solar cell.

[0080] In addition, an embodiment of the present application further provides a storage medium storing a computer program, which, when executed by a central controller, causes the computer to execute the method provided by the embodiment of the present application.

[0081] In addition, an embodiment of the present application further provides a computer program product including a computer program, which, when run, causes the central controller to execute the method provided by the embodiment of the present application.

[0082] In the above description, no detailed description is made of technical details such as the composition of each layer. However, those skilled in the art should understand that various technical means can be used to form layers, regions, etc. of the required shapes. In addition, in order to form the same structure, those skilled in the art can also design methods that are not exactly the same as the methods described above. In addition, although the above embodiments are described separately, this does not mean that the measures in each embodiment cannot be used in combination advantageously.

[0083] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0084] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A method for detecting belt tearing of a material conveyor, characterized in that The method includes: Receiving multi-dimensional operating state data of the back surface of the conveyor belt of the material conveyor collected by a multi-dimensional data sensing unit, where the multi-dimensional operating state data includes at least three of pressure data, surface profile data, image data, electromagnetic induction data, vibration frequency, vibration sound data, and temperature data, and the multi-dimensional data sensing unit is located between the working surface and the non-working surface of the conveyor belt; Inputting the multi-dimensional operating state data into a pre-trained tearing confidence determination model to determine the confidence of the conveyor belt of the material conveyor being torn, where the tearing confidence determination model is obtained by training a plurality of training samples input into a network to be trained, and each training sample includes historical multi-dimensional operating state data and the actual confidence of the conveyor belt of the material conveyor being torn; When the determined confidence is greater than a set confidence threshold, determining that the conveyor belt of the material conveyor is torn.

2. The method according to claim 1, wherein The number of the multi-dimensional data sensing units is multiple, and the multiple multi-dimensional data sensing units are arranged at intervals between the working surface and the non-working surface of the conveyor belt. When the determined confidence is greater than a set confidence threshold, determining that the conveyor belt of the material conveyor is torn includes: When the confidence corresponding to the multi-dimensional operating state data collected by any one of the multi-dimensional data sensing units is greater than a set confidence threshold, determining that the conveyor belt of the material conveyor is torn.

3. The method according to claim 2, wherein After determining that the conveyor belt of the material conveyor is torn, the method further includes: Receiving the mapping position on the conveyor belt transmitted by the multi-dimensional data sensing unit associated with the multi-dimensional operating state data whose confidence is greater than a set confidence threshold; Determining the position where the tear occurs on the conveyor belt according to the preset operating speed of the conveyor belt, the preset delay duration from collecting the multi-dimensional operating state data to determining that the conveyor belt of the material conveyor is torn, and the mapping position; Outputting the position where the tear occurs to a terminal device for display.

4. The method according to claim 1, wherein After determining that the conveyor belt of the material conveyor is torn, the method further includes: Controlling the conveyor belt of the material conveyor to stop running; And / or controlling an alarm module to give an alarm.

5. A conveyor belt tearing detection system for a material conveyor, characterized in that, The system includes: A multi-dimensional data sensing unit for collecting multi-dimensional operating state data of the back surface of the conveyor belt of the material conveyor, where the multi-dimensional operating state data includes at least three of pressure data, surface profile data, electromagnetic induction data, vibration frequency, vibration sound data, and temperature data, and the multi-dimensional data sensing unit is located between the working surface and the non-working surface of the conveyor belt; A data acquisition unit for receiving the multi-dimensional operating state data and transmitting it to a central controller; The central controller is configured to input the multi-dimensional operating state data into a pre-trained tearing confidence determination model to determine the confidence that the conveyor belt of the material conveyor is torn. The tearing confidence determination model is obtained by training a plurality of training samples input into a network to be trained. Each training sample includes multi-dimensional historical operating state data and the actual confidence that the conveyor belt of the material conveyor is torn. The central controller is further configured to determine that the conveyor belt of the material conveyor is torn when the determined confidence is greater than a set confidence threshold.

6. The system according to claim 5, wherein The number of the multi-dimensional data sensing units is multiple, and the multiple multi-dimensional data sensing units are arranged at intervals between the working surface and the non-working surface of the conveyor belt. Specifically, the central controller is configured to determine that the conveyor belt of the material conveyor is torn when the confidence corresponding to the multi-dimensional operating state data collected by any one of the multi-dimensional data sensing units is greater than a set confidence threshold.

7. The system according to claim 6, characterized in that, The central controller is further configured to receive the mapping position on the conveyor belt transmitted by the multi-dimensional data sensing unit associated with the multi-dimensional operating state data whose confidence is greater than a set confidence threshold, and determine the position where the tear occurs on the conveyor belt according to the preset operating speed of the conveyor belt, the preset delay duration from collecting the multi-dimensional operating state data to determining that the conveyor belt of the material conveyor is torn, and the mapping position. Output the position where the tear occurs to the terminal device for display.

8. The system according to claim 5, wherein The multi-dimensional data sensing unit includes at least three of a pressure sensor, a laser point cloud scanner, an image sensor, an electromagnetic induction sensor, a vibration sensor, an acoustic emission sensor, and a temperature sensor. Among them, The pressure sensor is configured to collect the pressure received by the conveyor belt. The laser point cloud scanner is configured to collect the surface contour data of the back of the conveyor belt. The image sensor is configured to collect the image data of the back of the conveyor belt. The electromagnetic induction sensor is configured to collect electromagnetic induction data. The acoustic emission sensor is configured to collect the vibration sound data of the conveyor belt. The temperature sensor is configured to collect the temperature data of the conveyor belt.

9. The system according to claim 8, wherein The multi-dimensional data sensing unit is installed in an explosion-proof and waterproof housing, and the explosion-proof and waterproof housing is installed on a shock-proof bracket.

10. A storage medium, characterized in that, The storage medium stores a computer program, wherein when the computer program is executed by a processor, the computer is caused to execute the method according to any one of claims 1 to 4.

Images