A method and system for monitoring the running status of rubber rollers of belt conveyor

Abstract

The present invention discloses a method and system for monitoring the running state of a rubber roller of a belt conveyor, the method comprising: constructing a two-dimensional coordinate system, importing each marked target end face image into the two-dimensional coordinate system, obtaining the coordinate information of the marked frame in each target end face image, sorting the coordinate information of the marked frame in each target end face image based on the sequence of the acquisition time of each end face image, and obtaining a coordinate information sequence; judging whether the first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than the first preset threshold, and whether the second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold; judging whether the third difference between the two coordinate information in the sliding window is greater than the second preset threshold at each sliding. The abnormal vibration of the rubber roller to be tested in different directions can be captured as much as possible, thereby improving the accuracy of monitoring the running state of the rubber roller to be tested.

Description

Technical Field

[0001] The invention belongs to the technical field of rubber roller running status monitoring, and in particular relates to a method and system for monitoring the running status of a rubber roller of a belt conveyor. Background Art

[0002] The rubber roller is one of the most important parts of the belt conveyor. The main function of the rubber roller is to transport materials. During the operation of the belt conveyor, the rubber roller may vibrate abnormally due to improper installation or defects on the surface of the rubber roller, further affecting the normal operation of the belt conveyor.

[0003] In the prior art, the image of the rubber roller to be tested is mainly analyzed when it is working, and the similarity between the real-time vibration image and the expected vibration image is used to distinguish whether the rubber roller to be tested is operating abnormally. However, in actual work, the rotation speed of the rubber roller to be tested may be variable, and the normal vibration amplitude of the rubber roller to be tested at different speeds is also different. Therefore, the method of analyzing the similarity between the real-time vibration image and the expected vibration image has limitations and cannot accurately determine whether the rubber roller to be tested is in an abnormal operating state. Summary of the invention

[0004] The present invention provides a method and system for monitoring the operating status of a rubber roller of a belt conveyor, which are used to solve the technical problem that the method of analyzing the similarity between a real-time vibration image and an expected vibration image has limitations and cannot accurately determine whether the rubber roller to be tested is in an abnormal operating state.

[0005] In a first aspect, the present invention provides a method for monitoring the running status of a rubber roller of a belt conveyor, comprising:

[0006] Acquire the end surface images of the rubber roller to be tested at different times within a preset time period, and amplify each end surface image according to a preset amplification strategy to obtain a target end surface image;

[0007] Annotate the rubber roller to be tested in each target end face image according to a preset annotation frame, and construct a two-dimensional coordinate system, import each annotated target end face image into the two-dimensional coordinate system, and obtain coordinate information of the annotation frame in each target end face image, wherein the coordinate information is the coordinate value of the center point of the annotation frame;

[0008] The coordinate information of the marked boxes in the target end face images is sorted based on the sequence of the acquisition moments of the end face images to obtain a coordinate information sequence, wherein the coordinate information sequence at least includes a first coordinate information longitudinal subsequence and a first coordinate information transverse subsequence corresponding to the first coordinate information longitudinal subsequence, the longitudinal coordinate values ​​of each coordinate information in the first coordinate information longitudinal subsequence are all within a first preset range, and the transverse coordinate values ​​of each coordinate information in the first coordinate information transverse subsequence are all within the first preset range;

[0009] Determine whether a first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than a first preset threshold, and whether a second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold;

[0010] If both the first difference and the second difference are not greater than a first preset threshold, aligning the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence, and sliding on the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence according to a preset sliding window, and determining whether a third difference between two coordinate information in the sliding window is greater than a second preset threshold each time the sliding occurs;

[0011] If the third difference is greater than the second preset threshold, it is determined that the current operating state of the rubber roller to be tested is abnormal.

[0012] In a second aspect, the present invention provides a belt conveyor rubber roller operation status monitoring system, comprising:

[0013] A processing module is configured to obtain end surface images of the rubber roller to be tested at different times within a preset time period, and to amplify each end surface image according to a preset amplification strategy to obtain a target end surface image;

[0014] An import module is configured to mark the rubber roller to be tested in each target end face image according to a preset marking frame, and construct a two-dimensional coordinate system, and import each marked target end face image into the two-dimensional coordinate system to obtain coordinate information of the marking frame in each target end face image, wherein the coordinate information is the coordinate value of the center point of the marking frame;

[0015] A sorting module is configured to sort the coordinate information of the marked boxes in each target end face image based on the order of the acquisition moments of each end face image to obtain a coordinate information sequence, wherein the coordinate information sequence at least includes a first coordinate information longitudinal subsequence and a first coordinate information transverse subsequence corresponding to the first coordinate information longitudinal subsequence, the longitudinal coordinate values ​​of each coordinate information in the first coordinate information longitudinal subsequence are all within a first preset range, and the transverse coordinate values ​​of each coordinate information in the first coordinate information transverse subsequence are all within the first preset range;

[0016] A first judgment module is configured to judge whether a first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than a first preset threshold, and whether a second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold;

[0017] a second judgment module configured to align the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence if both the first difference and the second difference are not greater than a first preset threshold, and slide on the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence according to a preset sliding window, and judge whether a third difference between two coordinate information in the sliding window is greater than a second preset threshold each time the sliding occurs;

[0018] The determination module is configured to determine that the current operating state of the rubber roller to be tested is abnormal if the third difference is greater than a second preset threshold.

[0019] According to a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the method for monitoring the operating status of the rubber roller of a belt feeder according to any embodiment of the present invention.

[0020] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the method for monitoring the operating status of the rubber roller of a belt feeder according to any embodiment of the present invention.

[0021] The method and system for monitoring the running status of the rubber roller of a belt conveyor of the present application amplifies each end face image according to a preset amplification strategy to obtain a target end face image, and can amplify the vibration state, so as to facilitate the subsequent acquisition of a larger coordinate difference as much as possible, and then annotates the rubber roller to be measured in each target end face image according to a preset annotation frame, and constructs a two-dimensional coordinate system, and imports each annotated target end face image into the two-dimensional coordinate system to obtain the coordinate information of the annotation frame in each target end face image, and sorts the coordinate information of the annotation frame in each target end face image based on the sequence of the acquisition time of each end face image to obtain a coordinate information sequence, which can perform abnormal analysis of the running status based on a variable speed scenario without stopping the belt conveyor, and It is determined whether the first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than a first preset threshold value, and whether the second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold value; if both the first difference and the second difference are not greater than the first preset threshold value, the vertical subsequence of the first coordinate information and the horizontal subsequence of the first coordinate information are aligned, and a preset sliding window is slid on the vertical subsequence of the first coordinate information and the horizontal subsequence of the first coordinate information according to the preset sliding window, and it is determined whether the third difference between the two coordinate information in the sliding window is greater than the second preset threshold value each time the sliding occurs, so that the abnormal vibration of the rubber roller to be tested in different directions can be captured as much as possible, thereby improving the accuracy of monitoring the operating status of the rubber roller to be tested. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flow chart of a method for monitoring the running status of a rubber roller of a belt feeder provided by an embodiment of the present invention;

[0024] Figure 2 A structural block diagram of a belt conveyor rubber roller operating status monitoring system provided by an embodiment of the present invention;

[0025] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] See also Figure 1 , which shows a flow chart of a method for monitoring the operating status of a rubber roller of a belt feeder according to the present application.

[0028] like Figure 1 As shown, the method for monitoring the running status of the rubber roller of the belt conveyor specifically includes the following steps:

[0029] Step S101, acquiring end surface images of the rubber roller to be tested at different times within a preset time period, and amplifying each end surface image according to a preset amplification strategy to obtain a target end surface image.

[0030] In this step, the static center point of the rubber roller to be tested in the static end face image is obtained, wherein the static end face image is an end face image of the rubber roller to be tested taken in a static state; the position of the static center point is marked in each end face image to obtain each marked point, and each marked point is used as the enlarged center point to enlarge each end face image to obtain the target end face image.

[0031] In a specific embodiment, each end face image is input into a preset image magnification model, and the input image is received according to the magnification unit in the image magnification model, the image is magnified, and an enlarged image is generated; the input image is received according to the front-end convolution path included in the neural network module in the image magnification model to perform a convolution operation and generate a front-end operation output result; the front-end operation output results are respectively received according to multiple convolution paths included in the neural network module to perform a convolution operation and generate multiple groups of output image residuals; the output image residuals are weighted and mixed according to the weight settings related to multiple image areas of the input image according to the mixing module included in the neural network module to generate a group of final output image residuals; and the enlarged image is enhanced according to the enhancement module of the image magnification model according to the group of final output image residuals to generate an output enlarged image, i.e., a target end face image.

[0032] The magnification module can achieve the purpose of magnification through various suitable operation mechanisms, such as but not limited to performing interpolation operations according to pixels included in the input image.

[0033] Step S102, annotate the rubber roller to be tested in each target end face image according to a preset annotation frame, construct a two-dimensional coordinate system, import each annotated target end face image into the two-dimensional coordinate system, and obtain the coordinate information of the annotation frame in each target end face image, wherein the coordinate information is the coordinate value of the center point of the annotation frame.

[0034] In this step, a target end face image is input into a preset image recognition model, and the image recognition model outputs a target area corresponding to the target end face image; it is determined whether the size of the target area is consistent with the fixed size of the annotation box; if they are consistent, the annotation box is marked at a target area position of the target end face image; if they are inconsistent, a first target end face image and a second target end face image adjacent to the target end face image are obtained, and the first target end face image and the second target end face image are respectively recognized based on the image recognition model to obtain a first target center point of the first target area corresponding to the first target end face image, and a second target center point of the second target area corresponding to the second target end face image; the center point of the annotation box is moved along the direction of the target line segment until the annotation box covers the largest area of ​​a target area in the target end face image, and then the annotation box is stopped from being moved, that is, the annotation box is marked at a target area position of the target end face image, wherein the target line segment is a line connecting the first target center point and the second target center point.

[0035] In a specific application scenario, when the edge of the rubber roller to be tested in a certain end face image is blurred, the target area in the end face image will be larger than the marking box. At this time, the center point of the target area cannot be determined, which affects the subsequent vibration analysis.

[0036] Since the vibration of the rubber roller to be tested is a continuous process in time, there is a certain correlation between the movement of the center point at the previous moment, the current moment and the next moment. For this reason, the first target end face image at the previous moment of a certain end face image and the first target end face image at the next moment of a certain end face image are obtained. By obtaining the first target end face image and the target center point in the first target end face image and connecting the two target center points, a certain center point in a certain end face image is most likely in the direction of the connection line, or near the direction of the connection line. Therefore, the center point of the annotation box is moved along the direction of the target line segment until the annotation box covers the largest area of ​​a certain target area in a certain target end face image. Then, the movement of the annotation box is stopped. At this time, the center point of the annotation box is defined as a certain target center point of a certain end face image, thereby improving the accuracy of determining the target center point as much as possible.

[0037] It should be noted that the image recognition model can be obtained through convolutional neural network training.

[0038] Specifically, a target end face image is input into a two-dimensional coordinate system, and the target vertices of the target end face image are aligned with the coordinate origin to obtain the first coordinate information of each vertex of the marked box in the target end face image; the coordinates of the center point of the marked box in the target end face image are calculated according to the first coordinate information of each vertex; another target end face image is input into the two-dimensional coordinate system, and the target vertices of the other target end face image are aligned with the coordinate origin to obtain the second coordinate information of each vertex of the marked box in the other target end face image; the coordinates of the center point of the marked box in the other target end face image are calculated according to the second coordinate information of each vertex.

[0039] Step S103, sorting the coordinate information of the marked boxes in each target end face image based on the sequence of the acquisition moments of each end face image to obtain a coordinate information sequence, wherein the coordinate information sequence at least includes a first coordinate information vertical subsequence and a first coordinate information horizontal subsequence corresponding to the first coordinate information vertical subsequence, the vertical coordinate values ​​of each coordinate information in the first coordinate information vertical subsequence are all within a first preset range, and the horizontal coordinate values ​​of each coordinate information in the first coordinate information horizontal subsequence are all within the first preset range.

[0040] In this step, the coordinate information sequence also includes a second coordinate information vertical subsequence and a second coordinate information horizontal subsequence corresponding to the second coordinate information vertical subsequence.

[0041] Specifically, the coordinate information of the marked boxes in each target end face image is sorted based on the sequence of the acquisition time of each end face image, and the obtained coordinate information sequence includes:

[0042] Obtain the center point coordinates of the marked boxes in each target end face image; cluster the center points whose vertical coordinate values ​​are within a first preset range to obtain a first clustering result, and sort the first clustering result based on the chronological order of the end face image acquisition moments to obtain a first coordinate information vertical subsequence; cluster the center points whose vertical coordinate values ​​are within a second preset range to obtain a second clustering result, and sort the second clustering result based on the chronological order of the end face image acquisition moments to obtain a second coordinate information vertical subsequence; cluster the center points whose horizontal coordinate values ​​are within the first preset range to obtain a third clustering result, and sort the third clustering result based on the chronological order of the end face image acquisition moments to obtain a first coordinate information horizontal subsequence; cluster the center points whose horizontal coordinate values ​​are within the second preset range to obtain a fourth clustering result, and sort the fourth clustering result based on the chronological order of the end face image acquisition moments to obtain a second coordinate information horizontal subsequence.

[0043] In this embodiment, by using the first preset range and the second preset range or other preset ranges, the center point coordinates of the marked boxes in each acquired target end face image can be classified, so as to facilitate the subsequent determination of whether the rubber roller to be tested is normal vibration or abnormal. For example, when the tape feeder is working, the speed of its tape feed may vary within a whole working cycle, so the normal vibration of the rubber roller to be tested may change with the change of speed. If this situation cannot be distinguished, even if the subsequent steps S104-S106 perform the judgment of the coordinate difference, the abnormal vibration situation may be covered by the change of the normal vibration.

[0044] Step S104, determining whether a first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than a first preset threshold, and whether a second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold.

[0045] In a specific embodiment, after determining whether the first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than the first preset threshold, and whether the second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold, if the first difference is greater than the first preset threshold, or the second difference is greater than the first preset threshold, it is determined that the current operating state of the rubber roller to be tested is abnormal.

[0046] Step S105: If the first difference and the second difference are not greater than the first preset threshold, align the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence, and slide on the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence according to a preset sliding window to determine whether the third difference between the two coordinate information in the sliding window is greater than the second preset threshold each time.

[0047] In this step, it is determined whether the third difference between the two coordinate information in the sliding window is greater than the second preset threshold each time the sliding occurs, so as to screen abnormal vibrations in different directions as much as possible, wherein the second preset threshold is set smaller than the first preset threshold.

[0048] In a specific embodiment, after determining whether the third difference between the two coordinate information in the sliding window is greater than the second preset threshold value each time sliding, if the third difference is not greater than the second preset threshold value, it is determined that the current operating state of the rubber roller to be tested is normal.

[0049] Step S106: If the third difference is greater than the second preset threshold, it is determined that the current operating state of the rubber roller to be tested is abnormal.

[0050] In summary, the method of the present application amplifies each end face image according to a preset amplification strategy to obtain a target end face image, which can amplify the vibration state, so as to facilitate the subsequent acquisition of a larger coordinate difference as much as possible, and then annotates the rubber roller to be tested in each target end face image according to a preset annotation frame, and constructs a two-dimensional coordinate system, imports each annotated target end face image into the two-dimensional coordinate system to obtain the coordinate information of the annotation frame in each target end face image, and sorts the coordinate information of the annotation frame in each target end face image based on the sequence of the acquisition time of each end face image to obtain a coordinate information sequence, which can perform an abnormal operation status analysis based on a variable speed scenario without stopping the belt conveyor, and judge the first Whether the first difference between any two coordinate information in a vertical subsequence of a coordinate information is greater than a first preset threshold, and whether the second difference between any two coordinate information in a horizontal subsequence of the first coordinate information is greater than the first preset threshold; if the first difference and the second difference are not greater than the first preset threshold, aligning the first vertical subsequence of the coordinate information and the first horizontal subsequence of the coordinate information, and sliding on the first vertical subsequence of the coordinate information and the first horizontal subsequence of the coordinate information according to a preset sliding window, judging whether the third difference between the two coordinate information in the sliding window is greater than the second preset threshold each time sliding, can capture as much abnormal vibration of the rubber roller to be tested in different directions as possible, thereby improving the accuracy of monitoring the running status of the rubber roller to be tested.

[0051] See also Figure 2 , which shows a structural block diagram of a belt feeder rubber roller operating status monitoring system of the present application.

[0052] like Figure 2 As shown, the belt conveyor rubber roller operation status monitoring system 200 includes a processing module 210 , an importing module 220 , a sorting module 230 , a first judging module 240 , a second judging module 250 and a determining module 260 .

[0053] Wherein, the processing module 210 is configured to obtain the end face images of the rubber roller to be tested at different times within a preset time period, and to amplify each end face image according to a preset amplification strategy to obtain a target end face image; the importing module 220 is configured to annotate the rubber roller to be tested in each target end face image according to a preset annotation frame, and to construct a two-dimensional coordinate system, and to import each annotated target end face image into the two-dimensional coordinate system to obtain the coordinate information of the annotation frame in each target end face image, wherein the coordinate information is the coordinate value of the center point of the annotation frame; the sorting module 230 is configured to sort the coordinate information of the annotation frame in each target end face image based on the sequence of the acquisition time of each end face image, and to obtain a coordinate information sequence, wherein the coordinate information sequence at least includes a first coordinate information vertical subsequence and a first coordinate information horizontal subsequence corresponding to the first coordinate information vertical subsequence, and the vertical coordinates of each coordinate information in the first coordinate information vertical subsequence are The values ​​are all within the first preset range, and the horizontal coordinate values ​​of each coordinate information in the horizontal subsequence of the first coordinate information are all within the first preset range; the first judgment module 240 is configured to judge whether the first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than the first preset threshold, and whether the second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold; the second judgment module 250 is configured to align the vertical subsequence of the first coordinate information and the horizontal subsequence of the first coordinate information if the first difference and the second difference are not greater than the first preset threshold, and slide on the vertical subsequence of the first coordinate information and the horizontal subsequence of the first coordinate information according to a preset sliding window, and judge whether the third difference between the two coordinate information in the sliding window is greater than the second preset threshold each time sliding; the determination module 260 is configured to determine that the current operating state of the rubber roller to be tested is abnormal if the third difference is greater than the second preset threshold.

[0054] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 2 The modules in it will not be described in detail here.

[0055] In some other embodiments, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the program instructions are executed by a processor, the processor executes the method for monitoring the running state of the rubber roller of the belt feeder in any of the above method embodiments;

[0056] As an implementation mode, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows:

[0057] Acquire the end surface images of the rubber roller to be tested at different times within a preset time period, and amplify each end surface image according to a preset amplification strategy to obtain a target end surface image;

[0058] Annotate the rubber roller to be tested in each target end face image according to a preset annotation frame, and construct a two-dimensional coordinate system, import each annotated target end face image into the two-dimensional coordinate system, and obtain coordinate information of the annotation frame in each target end face image, wherein the coordinate information is the coordinate value of the center point of the annotation frame;

[0059] The coordinate information of the marked boxes in the target end face images is sorted based on the sequence of the acquisition moments of the end face images to obtain a coordinate information sequence, wherein the coordinate information sequence at least includes a first coordinate information longitudinal subsequence and a first coordinate information transverse subsequence corresponding to the first coordinate information longitudinal subsequence, the longitudinal coordinate values ​​of each coordinate information in the first coordinate information longitudinal subsequence are all within a first preset range, and the transverse coordinate values ​​of each coordinate information in the first coordinate information transverse subsequence are all within the first preset range;

[0060] Determine whether a first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than a first preset threshold, and whether a second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold;

[0061] If both the first difference and the second difference are not greater than a first preset threshold, aligning the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence, and sliding on the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence according to a preset sliding window, and determining whether a third difference between two coordinate information in the sliding window is greater than a second preset threshold each time the sliding occurs;

[0062] If the third difference is greater than the second preset threshold, it is determined that the current operating state of the rubber roller to be tested is abnormal.

[0063] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the belt feeder rubber roller operation status monitoring system, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the belt feeder rubber roller operation status monitoring system via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0064] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3 In the example, the connection through the bus is taken as an example. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the method for monitoring the running status of the rubber roller of the belt feeder in the above-mentioned method embodiment is realized. The input device 330 can receive input digital or character information, and generate key signal input related to the user setting and function control of the running status monitoring system of the rubber roller of the belt feeder. The output device 340 may include a display device such as a display screen.

[0065] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0066] As an implementation mode, the electronic device is applied to a belt conveyor rubber roller operation status monitoring system, and is used for a client, and includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can:

[0067] Acquire the end surface images of the rubber roller to be tested at different times within a preset time period, and amplify each end surface image according to a preset amplification strategy to obtain a target end surface image;

[0068] Annotate the rubber roller to be tested in each target end face image according to a preset annotation frame, and construct a two-dimensional coordinate system, import each annotated target end face image into the two-dimensional coordinate system, and obtain coordinate information of the annotation frame in each target end face image, wherein the coordinate information is the coordinate value of the center point of the annotation frame;

[0069] The coordinate information of the marked boxes in the target end face images is sorted based on the sequence of the acquisition moments of the end face images to obtain a coordinate information sequence, wherein the coordinate information sequence at least includes a first coordinate information longitudinal subsequence and a first coordinate information transverse subsequence corresponding to the first coordinate information longitudinal subsequence, the longitudinal coordinate values ​​of each coordinate information in the first coordinate information longitudinal subsequence are all within a first preset range, and the transverse coordinate values ​​of each coordinate information in the first coordinate information transverse subsequence are all within the first preset range;

[0070] Determine whether a first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than a first preset threshold, and whether a second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold;

[0071] If both the first difference and the second difference are not greater than a first preset threshold, aligning the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence, and sliding on the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence according to a preset sliding window, and determining whether a third difference between two coordinate information in the sliding window is greater than a second preset threshold each time the sliding occurs;

[0072] If the third difference is greater than the second preset threshold, it is determined that the current operating state of the rubber roller to be tested is abnormal.

[0073] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the running status of a rubber roller of a belt conveyor, characterized in that: include: Acquire the end surface images of the rubber roller to be tested at different times within a preset time period, and amplify each end surface image according to a preset amplification strategy to obtain a target end surface image; Annotate the rubber roller to be tested in each target end face image according to a preset annotation frame, and construct a two-dimensional coordinate system, import each annotated target end face image into the two-dimensional coordinate system, and obtain coordinate information of the annotation frame in each target end face image, wherein the coordinate information is the coordinate value of the center point of the annotation frame; The coordinate information of the marked boxes in the target end face images is sorted based on the sequence of the acquisition moments of the end face images to obtain a coordinate information sequence, wherein the coordinate information sequence at least includes a first coordinate information longitudinal subsequence and a first coordinate information transverse subsequence corresponding to the first coordinate information longitudinal subsequence, the longitudinal coordinate values ​​of each coordinate information in the first coordinate information longitudinal subsequence are all within a first preset range, and the transverse coordinate values ​​of each coordinate information in the first coordinate information transverse subsequence are all within the first preset range; Determine whether a first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than a first preset threshold, and whether a second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold; If both the first difference and the second difference are not greater than a first preset threshold, aligning the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence, and sliding on the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence according to a preset sliding window, and determining whether a third difference between two coordinate information in the sliding window is greater than a second preset threshold each time the sliding occurs; If the third difference is greater than the second preset threshold, it is determined that the current operating state of the rubber roller to be tested is abnormal.

2. A method for monitoring the running status of a rubber roller of a belt conveyor according to claim 1, characterized in that: The step of enlarging each end face image according to a preset enlarging strategy to obtain a target end face image comprises: Acquire the static center point of the rubber roller to be tested in the static end surface image, wherein the static end surface image is an end surface image of the rubber roller to be tested taken in a static state; The position of the static center point is marked in each end face image to obtain each marked point, and each marked point is used as an enlarged center point to enlarge each end face image to obtain a target end face image.

3. The method for monitoring the running status of the rubber roller of a belt conveyor according to claim 1, characterized in that: The step of marking the rubber roller to be tested in each target end face image according to a preset marking frame includes: Inputting a target end face image into a preset image recognition model, the image recognition model outputting a target area corresponding to the target end face image; Determining whether the size of the target area is consistent with the fixed size of the annotation box; If they are consistent, marking the annotation frame at a target area position of the target end face image; If they are inconsistent, obtaining a first target end surface image and a second target end surface image adjacent to the certain target end surface image, and respectively identifying the first target end surface image and the second target end surface image based on the image recognition model to obtain a first target center point of a first target area corresponding to the first target end surface image, and a second target center point of a second target area corresponding to the second target end surface image; Move the center point of the annotation box along the direction of the target line segment until the annotation box covers the largest area of ​​a target region in the target end face image, then stop moving the annotation box, i.e. mark the annotation box at a target region position in the target end face image, wherein the target line segment is a line connecting the center point of the first target and the center point of the second target.

4. A method for monitoring the running status of a rubber roller of a belt conveyor according to claim 1, characterized in that: The step of constructing a two-dimensional coordinate system and importing each annotated target end face image into the two-dimensional coordinate system to obtain coordinate information of annotated boxes in each target end face image includes: Inputting a target end face image into the two-dimensional coordinate system, and aligning the target vertices of the target end face image with the coordinate origin, to obtain first coordinate information of each vertex of the marked box in the target end face image; Calculate the coordinates of the center point of the marked box in the target end face image according to the first coordinate information of each vertex; Inputting another target end surface image into the two-dimensional coordinate system, and aligning the target vertices of the other target end surface image with the coordinate origin, to obtain second coordinate information of each vertex of the marked box in the other target end surface image; The coordinates of the center point of the marked box in the end face image of the other target are calculated according to the second coordinate information of each vertex.

5. The method for monitoring the running status of the rubber roller of a belt conveyor according to claim 1, characterized in that: The coordinate information sequence also includes a second coordinate information vertical subsequence and a second coordinate information horizontal subsequence corresponding to the second coordinate information vertical subsequence; The coordinate information of the marked boxes in each target end face image is sorted based on the sequence of the acquisition time of each end face image to obtain a coordinate information sequence, which includes: Obtain the center point coordinates of the marked boxes in each target end face image; Clustering each center point whose ordinate value is within a first preset range to obtain a first clustering result, and sorting the first clustering result based on the sequence of the acquisition moments of each end face image to obtain a first coordinate information ordinate subsequence; Clustering each center point whose ordinate value is within a second preset range to obtain a second clustering result, and sorting the second clustering result based on the sequence of the end face image acquisition moments to obtain a second coordinate information ordinate subsequence; Clustering each center point whose horizontal coordinate value is within the first preset range to obtain a third clustering result, and sorting the third clustering result based on the sequence of the end face image acquisition moments to obtain a horizontal subsequence of the first coordinate information; Clustering each center point whose horizontal coordinate value is within the second preset range to obtain a fourth clustering result, and sorting the fourth clustering result based on the sequence of the end face image acquisition moments to obtain a second coordinate information horizontal subsequence.

6. A method for monitoring the running status of a rubber roller of a belt conveyor according to claim 1, characterized in that: After determining whether a first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than a first preset threshold, and whether a second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold, the method further includes: If the first difference is greater than a first preset threshold, or the second difference is greater than a first preset threshold, it is determined that the current operating state of the rubber roller to be tested is abnormal.

7. A method for monitoring the running status of a rubber roller of a belt conveyor according to claim 1, characterized in that: After determining whether the third difference between the two coordinate information in the sliding window is greater than the second preset threshold value each time the sliding occurs, the method further includes: If the third difference is not greater than the second preset threshold, it is determined that the current operating state of the rubber roller to be tested is normal.

8. A belt conveyor rubber roller operation status monitoring system, characterized in that: include: A processing module is configured to obtain end surface images of the rubber roller to be tested at different times within a preset time period, and to amplify each end surface image according to a preset amplification strategy to obtain a target end surface image; An import module is configured to mark the rubber roller to be tested in each target end face image according to a preset marking frame, and construct a two-dimensional coordinate system, and import each marked target end face image into the two-dimensional coordinate system to obtain coordinate information of the marking frame in each target end face image, wherein the coordinate information is the coordinate value of the center point of the marking frame; A sorting module is configured to sort the coordinate information of the marked boxes in each target end face image based on the order of the acquisition moments of each end face image to obtain a coordinate information sequence, wherein the coordinate information sequence at least includes a first coordinate information longitudinal subsequence and a first coordinate information transverse subsequence corresponding to the first coordinate information longitudinal subsequence, the longitudinal coordinate values ​​of each coordinate information in the first coordinate information longitudinal subsequence are all within a first preset range, and the transverse coordinate values ​​of each coordinate information in the first coordinate information transverse subsequence are all within the first preset range; A first judgment module is configured to judge whether a first difference between any two coordinate information in the vertical subsequence of the first coordinate information is greater than a first preset threshold, and whether a second difference between any two coordinate information in the horizontal subsequence of the first coordinate information is greater than the first preset threshold; a second judgment module configured to align the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence if both the first difference and the second difference are not greater than a first preset threshold, and slide on the first coordinate information vertical subsequence and the first coordinate information horizontal subsequence according to a preset sliding window, and judge whether a third difference between two coordinate information in the sliding window is greater than a second preset threshold each time the sliding occurs; The determination module is configured to determine that the current operating state of the rubber roller to be tested is abnormal if the third difference is greater than a second preset threshold.

9. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images