Conveyor belt operation safety detection method and device, electronic equipment and medium

Abstract

The invention provides a conveyor belt operation safety detection method and device, electronic equipment and a medium, and the method comprises the steps: determining whether a to-be-detected conveyor belt is in a load operation state or not according to a temperature value of a carrier roller of the to-be-detected conveyor belt; under the condition that the to-be-detected conveying belt is in the load running state, the state of the to-be-detected conveying belt is determined according to the proportion of the to-be-detected conveying belt in the first detection area; under the condition that the to-be-detected conveying belt is in the off-tracking state, a deviation correction signal is sent to a controller corresponding to the to-be-detected conveying belt, so that the controller controls the to-be-detected conveying belt to be in a non-off-tracking state; under the condition that the to-be-detected conveying belt is in the non-deviation state, whether the surface of the to-be-detected conveying belt is torn or not is determined according to the surface image in the second detection area; when the surface of the conveying belt to be detected is torn, an alarm signal is sent out, so that when the conveying belt is in a running state, automatic detection is carried out, and corresponding operation is carried out in time when an abnormal running condition occurs.

Description

Background Art

[0002] Belt conveyors are important equipment widely used in many industries such as metallurgy, mining, chemical industry, petroleum, power plants, ports, and building materials. Especially under the requirements of long-distance, high-power, large-volume, and high-speed transportation, belt conveyors have become the main trend of belt conveyor development. As an important component of the conveyor, the conveyor belt mainly connects the drive device and transports materials. Its cost accounts for about 40%-60% of the total conveyor cost. In the actual production process, the conveyor belt may be pierced by sharp objects or deviate. If the inspectors cannot find it in time, the conveyor belt will be torn over a large area, resulting in the dumping of goods, paralyzing the entire conveyor. In severe cases, it will cause casualties among inspectors and cause huge economic losses. Summary of the invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is:

[0004] According to one aspect of the present application, a conveyor belt operation safety detection method is provided, comprising:

[0005] According to the temperature value of the roller of the conveyor belt to be detected, it is determined whether the conveyor belt to be detected is in a load-carrying operation state;

[0006] When the conveyor belt to be detected is in a loaded running state, the state of the conveyor belt to be detected is determined according to the proportion of the conveyor belt to be detected in the corresponding first detection area; the state of the conveyor belt to be detected includes a deviation state and a non-deviation state;

[0007] When the conveyor belt to be detected is in a deviated state, a deviation correction signal is sent to a controller corresponding to the conveyor belt to be detected, so that the controller controls the conveyor belt to be detected to be in a non-deviated state;

[0008] When the conveyor belt to be detected is in a non-deviation state, determining whether the surface of the conveyor belt to be detected is torn according to the surface image of the conveyor belt to be detected in the corresponding second detection area;

[0009] When a tear occurs on the surface of the conveyor belt to be inspected, an alarm signal is issued.

[0010] In an exemplary embodiment of the present application, determining whether the conveyor belt to be detected is in a load-carrying operation state according to the temperature value of the roller of the conveyor belt to be detected includes:

[0011] Real-time acquisition of the temperature value of the roller to be detected when the conveyor belt to be detected is in a running state; the roller to be detected is any roller among the plurality of rollers corresponding to the conveyor belt to be detected and / or the roller with the largest area among the plurality of rollers;

[0012] If the temperature of the roller to be tested in this detection is greater than the temperature of the roller to be tested in the previous detection, and the temperature difference is greater than the preset first temperature difference threshold, and the temperature of the roller to be tested in this detection is less than the temperature of the roller to be tested in the next detection, and the temperature difference is less than or equal to the preset second temperature difference threshold, it is determined that the conveyor belt to be tested is in a load-carrying operation state; the first temperature difference threshold is greater than or equal to the second temperature difference threshold.

[0013] In an exemplary embodiment of the present application, when the conveyor belt to be detected is in a loaded running state, determining the state of the conveyor belt to be detected according to the proportion of the conveyor belt to be detected in the corresponding first detection area includes:

[0014] When the conveyor belt to be detected is in a loaded running state, a first detection image of a first detection area captured by a first image acquisition device corresponding to the conveyor belt to be detected is acquired in real time; the first detection area is the area captured by the first image acquisition device; the first image acquisition device is arranged below the conveyor belt to be detected, and the shooting angle of the first image acquisition device is toward the edge of the conveyor belt to be detected;

[0015] Performing semantic segmentation processing on the first detection image to obtain a conveyor belt image area corresponding to the conveyor belt to be detected included in the first detection image;

[0016] When the ratio of the area of ​​the conveyor belt image region to the area of ​​the first detection image is greater than a preset area ratio threshold, it is determined that the conveyor belt to be detected is in a deviation state;

[0017] When the ratio of the area of ​​the conveyor belt image region to the area of ​​the first detection image is less than or equal to a preset area ratio threshold, it is determined that the conveyor belt to be detected is in a non-deviated state.

[0018] In an exemplary embodiment of the present application, the execution method of the controller corresponding to the conveyor belt to be detected includes:

[0019] In response to receiving the correction signal, the conveyor belt to be detected is controlled to offset the correction angle to the initial position corresponding to the conveyor belt to be detected; the correction angle is (T1-T2)×T0; wherein T1 is the ratio of the area of ​​the conveyor belt image area in the first detection image at the current moment to the area of ​​the first detection image; T2 is the preset area ratio threshold; T0 is the preset correction initial angle.

[0020] In an exemplary embodiment of the present application, when the conveyor belt to be detected is in a non-deviation state, determining whether the surface of the conveyor belt to be detected is torn according to the surface image of the conveyor belt to be detected in the corresponding second detection area includes:

[0021] When the conveyor belt to be detected is in a non-deviation state, a second detection image of a second detection area photographed by a second image acquisition device corresponding to the conveyor belt to be detected is acquired in real time; the second detection area is an area photographed by the second image acquisition device; the second image acquisition device is arranged on the roller of the conveyor belt to be detected, and the shooting angle of the second image acquisition device is toward the surface of the conveyor belt to be detected;

[0022] graying the second detection image to obtain a third detection image;

[0023] Performing Laplace transform on the third detection image to obtain a convolution kernel variance corresponding to the third detection image;

[0024] When the convolution kernel variance is greater than a preset variance threshold, image recognition is performed on the second detection image to obtain a surface image area corresponding to the conveyor belt to be detected included in the second detection image;

[0025] Performing feature recognition on a number of pixel points in the surface image area, and determining pixel points that meet preset tearing feature rules as tearing pixel points;

[0026] Determine the area composed of torn pixels as the torn area;

[0027] When the length of the torn area is greater than a preset length threshold, it is determined that a tear occurs on the surface of the conveyor belt to be detected.

[0028] In an exemplary embodiment of the present application, performing Laplace transform on the third detection image to obtain the convolution kernel variance corresponding to the third detection image also includes:

[0029] When the convolution kernel variance is less than or equal to a preset variance threshold, a cleaning signal is sent to the controller corresponding to the conveyor belt to be detected, so that the controller controls the cleaning device to clean the shooting lens of the second image acquisition device.

[0030] In an exemplary embodiment of the present application, the conveyor belt operation safety detection method further includes:

[0031] Storing the running status data of the conveyor belt to be tested;

[0032] The running status data of the conveyor belt to be detected includes any one or more combinations of the following:

[0033] The temperature value of the roller of the conveyor belt to be detected, the proportion of the conveyor belt to be detected in the corresponding first detection area when it is in a deviation state, and the surface image of the conveyor belt to be detected when the surface is torn.

[0034] According to one aspect of the present application, a conveyor belt operation safety detection device is provided, comprising:

[0035] A load judgment module, used to determine whether the conveyor belt to be detected is in a loaded operation state according to the temperature value of the roller of the conveyor belt to be detected;

[0036] A deviation judgment module is used to determine the state of the conveyor belt to be detected according to the proportion of the conveyor belt to be detected in the corresponding first detection area when the conveyor belt to be detected is in a loaded running state; the state of the conveyor belt to be detected includes a deviation state and a non-deviation state;

[0037] A deviation correction control module is used to send a deviation correction signal to a controller corresponding to the conveyor belt to be detected when the conveyor belt to be detected is in a deviation state, so that the controller controls the conveyor belt to be detected to be in a non-deviation state;

[0038] A tearing judgment module is used to determine whether a tear occurs on the surface of the conveyor belt to be detected according to a surface image of the conveyor belt to be detected in the corresponding second detection area when the conveyor belt to be detected is in a non-deviation state;

[0039] The tear alarm module is used to send out an alarm signal when a tear occurs on the surface of the conveyor belt to be detected.

[0040] According to one aspect of the present application, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the aforementioned conveyor belt operation safety detection method.

[0041] According to one aspect of the present application, an electronic device is provided, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0042] The present invention has at least the following beneficial effects:

[0043] The conveyor belt operation safety detection method of the present invention first determines whether the conveyor belt to be detected is in a load-bearing operation state according to the temperature value of the roller of the conveyor belt to be detected. If the conveyor belt to be detected is in a load-bearing operation state, then according to the proportion of the conveyor belt to be detected in the corresponding first detection area, it is determined whether the conveyor belt to be detected is in a deviation state. If the conveyor belt to be detected is in a deviation state, a correction signal is sent to a controller corresponding to the conveyor belt to be detected, so that the controller controls the conveyor belt to be detected to be in a non-deviation state. If the conveyor belt to be detected is in a non-deviation state, then according to the surface image of the conveyor belt to be detected in the corresponding second detection area, it is determined whether the surface of the conveyor belt to be detected is torn. If the surface of the conveyor belt to be detected is torn, an alarm signal is sent to perform automatic detection when the conveyor belt is in an operation state and take corresponding operations in time when an abnormal operation condition occurs, so as to avoid economic losses caused by abnormal operation of the conveyor belt. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A flow chart of a conveyor belt operation safety detection method provided by an embodiment of the present invention;

[0046] Figure 2 A block diagram of a conveyor belt operation safety detection device provided by an embodiment of the present invention;

[0047] Figure 3 The infrared image of the temperature of the roller of the conveyor belt to be inspected provided by the embodiment of the present invention;

[0048] Figure 4-Figure 6 A schematic diagram of a process of performing semantic segmentation on a first detection image provided by an embodiment of the present invention;

[0049] Figure 7 A schematic diagram of a tear area on a second detection image of a conveyor belt to be detected provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0051] In view of the current problem of abnormal operation of conveyor belts, it is necessary to conduct safety inspections on the conveyor belts in operation to promptly discover abnormal operation of the conveyor belts. Existing conveyor belt safety inspection products (such as the longitudinal tear identification system for mining conveyor belts) all include functions such as conveyor belt tearing and scratch identification, and on-site sound and light alarms, and their algorithm basis is CNN convolutional neural network (Convolutional Neural Networks) and target detection algorithm. Most of the existing conveyor belt detection technologies only perform visual inspections of tearing and scratches in the image, and then perform sound and light alarms to prompt the staff to take the next step. They only serve as reminders and cannot prevent the possible paralysis of the conveying system. In severe cases, they will also cause casualties to patrol personnel. In view of the fact that there is no comprehensive algorithm system that can truly realize unmanned autonomous detection of the operating status of the conveyor belt, and autonomously warn and control the operation of the conveyor belt before an accident occurs, the conveyor belt operation safety detection method described in the present invention is proposed.

[0052] like Figure 1 As shown, the conveyor belt operation safety detection method described in the present application includes:

[0053] Step S100, determining whether the conveyor belt to be detected is in a load-carrying operation state according to the temperature value of the roller of the conveyor belt to be detected;

[0054] When the conveyor belt is in a no-load running state, since there is no load on the conveyor belt, even if the conveyor belt has an operating abnormality at this time, such as deviation or tearing, it will not cause a safety accident in the conveying system. Therefore, in order to reduce the amount of data processing, when the conveyor belt is in a no-load running state, the conveyor belt operation safety detection method described in the present application is not executed, but the temperature value of the roller of the conveyor belt to be detected is obtained in real time, and according to the temperature value of the roller of the conveyor belt to be detected, it is determined whether the conveyor belt to be detected is in a loaded running state; if the conveyor belt to be detected is in a loaded running state, that is, there is an object on the conveyor belt to be detected, the conveyor belt operation safety detection method described in the present application is executed to detect whether the conveyor belt to be detected is deviated / torn.

[0055] Further, in step S100, determining whether the conveyor belt to be detected is in a load-carrying state according to the temperature value of the roller of the conveyor belt to be detected, that is, the method for determining the load-carrying state of the conveyor belt to be detected, includes steps S110 to S120:

[0056] Step S110, obtaining in real time the temperature value of the roller to be tested when the conveyor belt to be tested is in a running state;

[0057] The roller to be detected is any roller among the plurality of rollers corresponding to the conveyor belt to be detected and / or the roller with the largest area among the plurality of rollers.

[0058] Step S120: If the temperature of the roller to be detected in this detection is greater than the temperature of the roller to be detected in the previous detection, and the temperature difference is greater than the preset first temperature difference threshold, and the temperature of the roller to be detected in this detection is less than the temperature of the roller to be detected in the next detection, and the temperature difference is less than or equal to the preset second temperature difference threshold, it is determined that the conveyor belt to be detected is in a loaded operation state;

[0059] The first temperature difference threshold is greater than or equal to the second temperature difference threshold.

[0060] like Figure 3 As shown, it is the temperature infrared image of the roller of the conveyor belt to be detected. The roller can be identified from the image by the target detection algorithm. When the conveyor belt to be detected is unloaded, there is no contact between the conveyor belt to be detected and the roller. Therefore, the temperature value on the roller is low. When the conveyor belt to be detected is loaded with objects, the weight on the conveyor belt to be detected contacts the roller, and the conveyor belt to be detected is in operation. Therefore, the conveyor belt to be detected rubs against the roller, and the temperature value on the roller increases, indicating that the conveyor belt to be detected is in a loaded operation state.

[0061] Step S200, when the conveyor belt to be detected is in a loaded running state, determining the state of the conveyor belt to be detected according to the proportion of the conveyor belt to be detected in the corresponding first detection area; the state of the conveyor belt to be detected includes a deviation state and a non-deviation state;

[0062] Further, in step S200, when the conveyor belt to be detected is in a loaded running state, the state of the conveyor belt to be detected is determined according to the proportion of the conveyor belt to be detected in the corresponding first detection area, that is, the method for determining the deviation state of the conveyor belt to be detected, including steps S210-step S240:

[0063] Step S210: when the conveyor belt to be detected is in a loaded running state, obtaining in real time a first detection image of a first detection area captured by a first image acquisition device corresponding to the conveyor belt to be detected;

[0064] The first detection area is the area photographed by the first image acquisition device.

[0065] The first image acquisition device is arranged below the conveyor belt to be detected, and the shooting angle of the first image acquisition device is toward the edge of the conveyor belt to be detected. The first image acquisition device can be set to multiple. For example, when the conveyor belt to be detected is wider, a first image acquisition device can be arranged below each of the two edges of the conveyor belt to be detected. The first image acquisition device can be a visible light camera.

[0066] Step S220, performing semantic segmentation processing on the first detection image to obtain a conveyor belt image area corresponding to the conveyor belt to be detected included in the first detection image;

[0067] like Figure 4-Figure 6 As shown, Figure 4 is the original image of the first detection image, Figure 5 are two image regions obtained after semantic segmentation processing is performed on the first detection image, Figure 6 It is an image after binarization of two image areas. The white area is the conveyor belt image area corresponding to the conveyor belt to be detected, and the black area is the background image area of ​​the conveyor belt not to be detected included in the first detection image, which is used to more clearly show the conveyor belt image corresponding to the conveyor belt to be detected.

[0068] Semantic segmentation processing can be achieved through FCN fully convolutional neural networks (FCN). By using the FCN fully convolutional neural network semantic segmentation in deep learning to estimate the proportion of the conveyor belt deviation area, the correction device parameters can be adjusted in time to reduce conveyor belt wear, material spillage and other problems. The FCN-based algorithm can cope with more complex situations such as occlusion, lighting changes, etc., so the algorithm is more universal and robust.

[0069] Step S230: when the ratio of the area of ​​the conveyor belt image region to the area of ​​the first detection image is greater than a preset area ratio threshold, it is determined that the conveyor belt to be detected is in a deviation state;

[0070] Step S240: When the ratio of the area of ​​the conveyor belt image region to the area of ​​the first detection image is less than or equal to a preset area ratio threshold, it is determined that the conveyor belt to be detected is in a non-deviation state.

[0071] If the ratio of the area of ​​the conveyor belt image region to the area of ​​the first detection image is greater than a preset area ratio threshold, it indicates that the conveyor belt to be detected has deviated from the initial position, and it is determined that the conveyor belt to be detected is in a deviation state.

[0072] Step S300: When the conveyor belt to be detected is in a deviation state, a deviation correction signal is sent to a controller corresponding to the conveyor belt to be detected, so that the controller controls the conveyor belt to be detected to be in a non-deviation state;

[0073] Further, the execution method of the controller corresponding to the conveyor belt to be detected includes step S310:

[0074] Step S310, in response to receiving the deviation correction signal, controlling the conveyor belt to be detected to deviate by a deviation correction angle to the initial position corresponding to the conveyor belt to be detected;

[0075] The correction angle is (T1-T2)×T0; wherein T1 is the ratio of the area of ​​the conveyor belt image region in the first detection image at the current moment to the area of ​​the first detection image; T2 is the preset area ratio threshold; and T0 is the preset initial correction angle.

[0076] After receiving the correction signal, the controller sends instructions to the conveyor belt analog correction device, instructing the conveyor belt analog correction device to control the conveyor belt to be detected for correction. The conveyor belt analog correction device is a device that controls the movement of the servo motor of the conveyor belt to be detected through an analog input signal. It generally controls the torque, speed or position of the motor to achieve the purpose of adjusting the direction of the conveyor belt.

[0077] Step S400: when the conveyor belt to be detected is in a non-deviation state, determining whether the surface of the conveyor belt to be detected is torn according to the surface image of the conveyor belt to be detected in the corresponding second detection area;

[0078] The premise for detecting whether the surface of the conveyor belt to be detected is that the conveyor belt to be detected is in a non-deviation state. If the conveyor belt to be detected is in a deviation state, the conveyor belt to be detected is first corrected, and then it is determined whether the conveyor belt to be detected is torn.

[0079] Further, in step S400, when the conveyor belt to be detected is in a non-deviation state, determining whether the surface of the conveyor belt to be detected is torn according to the surface image of the conveyor belt to be detected in the corresponding second detection area, that is, the method for determining whether the conveyor belt to be detected is torn, includes steps S410-step S470:

[0080] Step S410: When the conveyor belt to be detected is in a non-deviation state, a second detection image of a second detection area captured by a second image acquisition device corresponding to the conveyor belt to be detected is acquired in real time;

[0081] The second detection area is the area photographed by the second image acquisition device;

[0082] The second image acquisition device is arranged on the roller of the conveyor belt to be inspected. The shooting angle of the second image acquisition device is toward the surface of the conveyor belt to be inspected. The number of the second image acquisition devices can also be set to multiple. Its main function is to shoot the surface of the conveyor belt to be inspected. The second image acquisition device can be an infrared camera.

[0083] Step S420, graying the second detection image to obtain a third detection image;

[0084] Grayscale processing is beneficial to the subsequent feature recognition of the image.

[0085] Step S430, performing Laplace transform on the third detection image to obtain a convolution kernel variance corresponding to the third detection image;

[0086] Laplace transform is used to detect edge and texture features in the third detection image, and the image clarity of the third detection image is determined by convolution kernel variance.

[0087] The Laplace operator in the Laplace transform is used to measure the second-order derivative of the third detection image. The Laplace transform highlights image areas that contain rapid intensity changes, which is very similar to the Sobel operator and the Scharr operator. And, like these operators, the Laplace is often used for edge detection, by calculating the sum of the second-order partial derivatives of the image on the horizontal and vertical axes to determine the edge and texture features in the image. If the image contains high variance, there is a wide range of responses, including edge classes and non-edge classes, representing a normal focus image. However, if the variance is very low, the distribution of the response is small, indicating that the edges in the image are very small. Therefore, the blurrier the image, the fewer edges there are, and the lower the variance of its convolution kernel.

[0088] Step S431: When the variance of the convolution kernel is less than or equal to a preset variance threshold, a cleaning signal is sent to a controller corresponding to the conveyor belt to be detected, so that the controller controls the cleaning device to clean the shooting lens of the second image acquisition device;

[0089] If the convolution kernel variance is less than or equal to the preset variance threshold, it means that the clarity of the second detection image of the second detection area taken by the second image acquisition device is low. Since the working environment of the conveyor belt is often an outdoor scene, it can be considered that there is dust or other obstructions on the shooting lens of the second image acquisition device. The controller then sends a cleaning instruction to the cleaning device to enable the cleaning device to clean the shooting lens or light source device of the second image acquisition device.

[0090] Step S440: when the convolution kernel variance is greater than a preset variance threshold, image recognition is performed on the second detection image to obtain a surface image area corresponding to the conveyor belt to be detected included in the second detection image;

[0091] Step S450, performing feature recognition on a number of pixel points in the surface image area, and determining pixel points that meet a preset tear feature rule as tear pixel points;

[0092] Step S460, determining the area composed of torn pixels as a torn area;

[0093] Step S470: When the length of the torn area is greater than a preset length threshold, it is determined that a tear has occurred on the surface of the conveyor belt to be detected.

[0094] like Figure 7As shown, it is an image of the torn area on the second detection image of the conveyor belt to be detected. By comparing the length of the torn area, it is determined whether the surface of the conveyor belt to be detected is torn or scratched.

[0095] Step S500: When a tear occurs on the surface of the conveyor belt to be detected, an alarm signal is issued.

[0096] In addition, when the conveyor belt to be tested is in a load-carrying state, the operating status data of the conveyor belt to be tested is stored, and the stored operating status data of the conveyor belt to be tested is visualized and displayed to the user in real time, so that the user or staff can check the operating status of the conveyor belt at any time. The operating status data of the conveyor belt to be tested can be stored in a local database, or in an algorithm data middle platform or a data sharing center. The user can interact with the roller temperature detection algorithm, the conveyor belt deviation detection algorithm, the conveyor belt analog deviation correction device, the conveyor belt tear / scratch detection algorithm and the conveyor belt motor operating status signal control through the algorithm data middle platform.

[0097] Among them, the operating status data of the conveyor belt to be detected includes any one or more combinations of the following: the temperature value of the roller of the conveyor belt to be detected, the proportion of the conveyor belt to be detected in the corresponding first detection area when it is in a deviation state, and the surface image of the conveyor belt to be detected when the surface is torn.

[0098] In addition, the present invention also provides a conveyor belt operation safety detection device 100, such as Figure 2 As shown, including:

[0099] The load determination module 110 is used to determine whether the conveyor belt to be detected is in a loaded operation state according to the temperature value of the roller of the conveyor belt to be detected;

[0100] The deviation judging module 120 is used to determine the state of the conveyor belt to be detected according to the proportion of the conveyor belt to be detected in the corresponding first detection area when the conveyor belt to be detected is in a loaded running state; the state of the conveyor belt to be detected includes a deviation state and a non-deviation state;

[0101] The deviation correction control module 130 is used to send a deviation correction signal to a controller corresponding to the conveyor belt to be detected when the conveyor belt to be detected is in a deviation state, so that the controller controls the conveyor belt to be detected to be in a non-deviation state;

[0102] A tearing judgment module 140 is used to determine whether a tear occurs on the surface of the conveyor belt to be detected according to a surface image of the conveyor belt to be detected in the corresponding second detection area when the conveyor belt to be detected is in a non-deviation state;

[0103] The tear alarm module 150 is used to send out an alarm signal when a tear occurs on the surface of the conveyor belt to be detected.

[0104] The conveyor belt operation safety detection method of the present invention first determines whether the conveyor belt to be detected is in a load-bearing operation state according to the temperature value of the roller of the conveyor belt to be detected. If the conveyor belt to be detected is in a load-bearing operation state, then according to the proportion of the conveyor belt to be detected in the corresponding first detection area, it is determined whether the conveyor belt to be detected is in a deviation state. If the conveyor belt to be detected is in a deviation state, a deviation correction signal is sent to a controller corresponding to the conveyor belt to be detected, so that the controller controls the conveyor belt to be detected to be in a non-deviation state. If the conveyor belt to be detected is in a non-deviation state, then according to the surface image of the conveyor belt to be detected in the corresponding second detection area, it is determined whether the surface of the conveyor belt to be detected is torn. If the surface of the conveyor belt to be detected is torn, an alarm signal is sent to perform automatic detection when the conveyor belt is in an operating state and to correct the abnormality in the event of an abnormality. The system integrates the deviation detection algorithm and the tear detection algorithm into one system to realize unmanned automatic detection of conveyor belt operation, tearing, scratches and alarms. By introducing a lightweight network architecture algorithm and combining the fast forward deployment framework on the sensor side, a complete control system algorithm is implemented to detect conveyor belt movement, longitudinal tearing of conveyor belts, and deviation correction of scratched conveyor belts in real time on the edge computing side. By identifying the running status of the conveyor belt, the clarity of the shooting lens of the second image acquisition device is detected, and the lens is automatically wiped when the shooting lens of the second image acquisition device is blurred, the deviation status of the conveyor belt is identified and the correction is controlled, the tearing / scratching of the conveyor belt is identified, and an emergency shutdown and other actions are performed before a safety accident may occur, so as to make up for the economic losses caused by the paralysis of the entire conveyor belt in time.

[0105] An embodiment of the present invention further provides a computer program product, which includes program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present invention described above in this specification.

[0106] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0107] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0108] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0109] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0110] The electronic device according to this embodiment of the present invention is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0111] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0112] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0113] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0114] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0115] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0116] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter.

[0117] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0118] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0119] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0120] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0121] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0122] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0123] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0124] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0125] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A conveyor belt operation safety detection method, characterized in that: The method comprises: Determine whether the conveyor belt to be detected is in a load-carrying state according to the temperature value of the roller of the conveyor belt to be detected; When the conveyor belt to be detected is in a loaded running state, the state of the conveyor belt to be detected is determined according to the proportion of the conveyor belt to be detected in the corresponding first detection area; the state of the conveyor belt to be detected includes a deviation state and a non-deviation state; When the conveyor belt to be detected is in a deviated state, a deviation correction signal is sent to a controller corresponding to the conveyor belt to be detected, so that the controller controls the conveyor belt to be detected to be in a non-deviated state; When the conveyor belt to be detected is in a non-deviation state, determining whether the surface of the conveyor belt to be detected is torn according to the surface image of the conveyor belt to be detected in the corresponding second detection area; When a tear occurs on the surface of the conveyor belt to be detected, an alarm signal is issued.

2. The method according to claim 1, characterized in that The step of determining whether the conveyor belt to be detected is in a load-carrying state according to the temperature value of the roller of the conveyor belt to be detected comprises: Acquire in real time the temperature value of the roller to be detected when the conveyor belt to be detected is in a running state; the roller to be detected is any roller among the plurality of rollers corresponding to the conveyor belt to be detected and / or the roller with the largest area among the plurality of rollers; If the temperature of the roller to be tested in this detection is greater than the temperature of the roller to be tested in the previous detection, and the temperature difference is greater than the preset first temperature difference threshold, and the temperature of the roller to be tested in this detection is lower than the temperature of the roller to be tested in the next detection, and the temperature difference is less than or equal to the preset second temperature difference threshold, it is determined that the conveyor belt to be tested is in a load-bearing running state; the first temperature difference threshold is greater than or equal to the second temperature difference threshold.

3. The method according to claim 1, characterized in that When the conveyor belt to be detected is in a load-carrying state, determining the state of the conveyor belt to be detected according to the proportion of the conveyor belt to be detected in the corresponding first detection area includes: When the conveyor belt to be detected is in a loaded running state, a first detection image of a first detection area photographed by a first image acquisition device corresponding to the conveyor belt to be detected is acquired in real time; the first detection area is an area photographed by the first image acquisition device; the first image acquisition device is arranged below the conveyor belt to be detected, and the shooting angle of the first image acquisition device is toward the edge of the conveyor belt to be detected; Performing semantic segmentation processing on the first detection image to obtain a conveyor belt image area corresponding to the conveyor belt to be detected included in the first detection image; When the ratio of the area of ​​the conveyor belt image region to the area of ​​the first detection image is greater than a preset area ratio threshold, it is determined that the conveyor belt to be detected is in a deviation state; When the ratio of the area of ​​the conveyor belt image region to the area of ​​the first detection image is less than or equal to a preset area ratio threshold, it is determined that the conveyor belt to be detected is in a non-deviated state.

4. The method according to claim 3, characterized in that The execution method of the controller corresponding to the conveyor belt to be detected includes: In response to receiving a correction signal, the conveyor belt to be detected is controlled to offset a correction angle to the initial position corresponding to the conveyor belt to be detected; the correction angle is (T1-T2)×T0; wherein T1 is the ratio of the area of ​​the conveyor belt image area in the first detection image at the current moment to the area of ​​the first detection image; T2 is a preset area ratio threshold; and T0 is a preset correction initial angle.

5. The method according to claim 1, characterized in that When the conveyor belt to be detected is in a non-deviation state, determining whether the surface of the conveyor belt to be detected is torn according to the surface image of the conveyor belt to be detected in the corresponding second detection area includes: When the conveyor belt to be detected is in a non-deviation state, a second detection image of a second detection area photographed by a second image acquisition device corresponding to the conveyor belt to be detected is acquired in real time; the second detection area is an area photographed by the second image acquisition device; the second image acquisition device is arranged on the roller of the conveyor belt to be detected, and the shooting angle of the second image acquisition device is toward the surface of the conveyor belt to be detected; grayscale the second detection image to obtain a third detection image; Performing Laplace transform on the third detection image to obtain a convolution kernel variance corresponding to the third detection image; When the variance of the convolution kernel is greater than a preset variance threshold, performing image recognition on the second detection image to obtain a surface image area corresponding to the conveyor belt to be detected included in the second detection image; Performing feature recognition on a plurality of pixel points in the surface image area, and determining pixel points that meet a preset tearing feature rule as tearing pixel points; Determine the area composed of torn pixels as the torn area; When the length of the torn area is greater than a preset length threshold, it is determined that a tear occurs on the surface of the conveyor belt to be detected.

6. The method according to claim 5, characterized in that The performing Laplace transform on the third detection image to obtain the convolution kernel variance corresponding to the third detection image further includes: When the variance of the convolution kernel is less than or equal to a preset variance threshold, a cleaning signal is sent to the controller corresponding to the conveyor belt to be detected, so that the controller controls the cleaning device to clean the shooting lens of the second image acquisition device.

7. The method according to claim 1, characterized in that The method further comprises: Storing the running status data of the conveyor belt to be detected; The running status data of the conveyor belt to be detected includes any one or more combinations of the following: The temperature value of the roller of the conveyor belt to be detected, the proportion of the conveyor belt to be detected in the corresponding first detection area when it is in a deviation state, and the surface image of the conveyor belt to be detected when the surface is torn.

8. A conveyor belt operation safety detection device, characterized in that: include: A load judgment module, used to determine whether the conveyor belt to be detected is in a loaded running state according to the temperature value of the roller of the conveyor belt to be detected; A deviation judgment module, used for determining the state of the conveyor belt to be detected according to the proportion of the conveyor belt to be detected in the corresponding first detection area when the conveyor belt to be detected is in a loaded running state; the state of the conveyor belt to be detected includes a deviation state and a non-deviation state; A deviation correction control module, used for sending a deviation correction signal to a controller corresponding to the conveyor belt to be detected when the conveyor belt to be detected is in a deviation state, so that the controller controls the conveyor belt to be detected to be in a non-deviation state; A tearing judgment module, used for determining whether a tear occurs on the surface of the conveyor belt to be detected according to a surface image of the conveyor belt to be detected in a corresponding second detection area when the conveyor belt to be detected is in a non-deviation state; The tearing alarm module is used to send out an alarm signal when a tear occurs on the surface of the conveyor belt to be detected.

9. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the conveyor belt operation safety detection method as described in any one of claims 1-7.

10. An electronic device, characterized in that: The invention comprises a processor and the non-transitory computer-readable storage medium as claimed in claim 9.

Images