Method, device, system, equipment and medium for detecting deviation of conveyor belt

Abstract

This specification discloses a belt deviation detection method for a belt conveyor, including: obtaining a preselected area containing a belt edge in an image to be detected; performing edge detection on the preselected area using probabilistic Hough transform to obtain multiple candidate edges on each side of the belt; determining a unique edge on each side of the belt from the multiple candidate edges; respectively calculating the stable distance between the unique edge on each side of the belt and a reference line, the reference line being the center line of the belt when the belt is not deviated; and determining the belt deviation result based on the stable distance on each side of the belt. The present invention adopts machine vision technology, and through video images, uses simple algorithm transformation and judgment ratio to determine the belt deviation result, thereby avoiding the influence of contact detection on detection accuracy. Compared with traditional contact detection, the method of the present invention has the advantages of simple deployment, high real-time performance, high detection accuracy, and comprehensive detection performance.

Description

Technical Field

[0001] The present invention relates to the field of equipment detection technology, and in particular to a method, device, system, electronic equipment and storage medium for detecting deviation of a conveyor belt. Background Art

[0002] Belt conveyors play an important role in industrial and mining production and are essential for material transportation in industries such as coal mining and metallurgy. During use, factors such as uneven distribution of transported materials can cause belt deviation, which in turn increases belt wear and causes belt tearing and other malignant failures. Therefore, monitoring whether the belt is deviating is crucial to ensure the continuity and reliability of production.

[0003] Currently, the main means of monitoring belt deviation is to install devices such as laser rangefinders or photoelectric sensors on the belt, and determine whether the belt deviates from the normal track through contact detection.

[0004] However, the sensor is easily damaged in long-term contact with the belt, which will affect the accuracy of belt deviation detection. Therefore, achieving stable and efficient deviation detection for conveyor belts is an urgent problem to be solved. Summary of the invention

[0005] The present invention provides a method and device for detecting deviation of a conveyor belt, which monitors the operation of the belt by a computer vision method, and is used to solve the problem that the sensor in the contact detection method is easily damaged, resulting in reduced detection accuracy and stability.

[0006] To solve the above technical problems, the present invention is achieved as follows:

[0007] In one aspect, the present invention provides a method for detecting belt deviation of a belt conveyor, the method comprising:

[0008] Acquire a preselected area containing the belt edge in the image to be inspected;

[0009] Performing edge detection on the preselected area using probabilistic Hough transform to obtain a plurality of candidate edges on each side of the belt;

[0010] determining a unique edge on each side of the belt from a plurality of the candidate edges;

[0011] Calculating the stable distance between the only edge on each side of the belt and a reference line, respectively, wherein the reference line is the center line of the belt when the belt is not deviated;

[0012] The deviation result of the belt is determined based on the stable distance on each side of the belt.

[0013] In another aspect, the present invention provides a belt deviation detection device for a belt conveyor, comprising:

[0014] An image pre-selection module is configured to obtain a pre-selected area containing the edge of each side of the belt in the image to be inspected;

[0015] an edge detection module configured to perform edge detection on the preselected area using a probabilistic Hough transform to obtain a plurality of candidate edges on each side of the belt;

[0016] an edge determination module configured to determine a unique edge on each side of the belt from a plurality of the candidate edges;

[0017] A distance calculation module is configured to respectively calculate a stable distance between a unique edge on each side of the belt and a reference line, wherein the reference line is a center line of the belt when the belt is not deviated;

[0018] The deviation determination module is configured to determine the deviation result of the belt according to the stable distance on each side of the belt.

[0019] On the other hand, the present invention further provides an electronic device for detecting belt deviation of a belt conveyor, the electronic device comprising at least one processor; and

[0020] a memory communicatively coupled to the at least one processor;

[0021] in,

[0022] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform any of the methods described above.

[0023] On the other hand, the present invention also provides a system for detecting belt deviation of a belt conveyor, the system comprising an electronic device for detecting belt deviation of a belt conveyor as described above, and an image acquisition device arranged along the conveyor belt; the electronic device processes the belt image captured by the image acquisition device to determine the degree of deviation of the belt.

[0024] On the other hand, the present invention further provides a computer-readable storage medium, which stores executable instructions. When the instructions are executed by a processor, the processor implements the method described in the present invention.

[0025] The embodiments of the present invention adopt at least one of the above technical solutions to achieve the following beneficial effects: using machine vision technology and non-contact detection, the wear and damage caused by the sensor directly contacting the belt is avoided, and the impact on the detection accuracy is reduced. The method of the present invention can process the collected image information online in real time, and through algorithm optimization, it can achieve comprehensive monitoring of the belt status. Compared with traditional contact detection, the method of the present invention has the advantages of simple deployment, high real-time performance, high detection accuracy, and comprehensive detection performance.

[0026] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0028] Figure 1 A schematic diagram of an application scenario of the belt deviation detection method in an embodiment of the present invention;

[0029] Figure 2 A flowchart of an embodiment of a belt deviation detection method for implementing the present invention;

[0030] Figure 3 is an example of an image to be inspected in an embodiment of the present invention;

[0031] Figure 4 Schematic diagram of the conversion between Cartesian coordinates and polar coordinates;

[0032] Figure 5 is a flowchart of the algorithm execution in the embodiment of the present invention;

[0033] Figure 6 It is a structural block diagram of a belt deviation detection device according to an embodiment of the present invention;

[0034] Figure 7 The structure block diagram of the belt deviation detection system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0036] Belt conveyor, also known as belt conveyor, is a friction-driven machine that transports materials in a continuous manner. It is mainly composed of a frame, conveyor belt, rollers, drums, tensioning devices, transmission devices, etc. It can transport materials from the initial feeding point to the final unloading point, forming a material transportation process. Conveyor belts, often called belts, move according to the principle of friction transmission. They are suitable for conveying powdered, granular, small-block, low-abrasive materials and bagged materials that are easy to take out, such as coal, gravel, sand, cement, fertilizer, grain, etc. In mining production, belt conveyors are efficient and continuous transportation equipment with the advantages of long transportation distance, large transportation volume, continuous transportation, etc., and reliable operation, easy to realize automation and centralized control, which is crucial for material transportation in coal mining, metallurgy and other industries.

[0037] During the operation of the belt conveyor, factors such as the uneven distribution of the transported materials may cause the belt to deviate, increase belt wear, and even cause serious failures such as belt tearing. Therefore, timely and accurate monitoring of whether the belt is deviating is crucial to ensure the continuity and reliability of production. Currently, the belt status is mainly monitored by installing equipment such as laser rangefinders or photoelectric sensors on the belt to monitor whether the belt deviates from the normal track. In the existing method, the sensor is easily damaged due to long-term contact with the belt, which affects the detection accuracy.

[0038] The inventor of the present invention has conducted extensive research on the operation data of belt conveyor belts and found that the shape and size of the belts of large belt conveyors remain basically unchanged during movement or after being subjected to force, and have the performance of a nearly rigid body. Based on this discovery, the present invention proposes to determine the degree of belt deviation by analyzing the image of the belt. Specifically, the method is: obtaining a preselected area containing the belt edge in the image to be inspected; using probabilistic Hough transform to perform edge detection on the preselected area to obtain multiple candidate edges on each side of the belt; determining the unique edge on each side of the belt from the multiple candidate edges; respectively calculating the stable distance between the unique edge on each side of the belt and the reference line, which is the center line of the belt when the belt is not deviated; and determining the deviation result of the belt according to the stable distance on each side of the belt. The method utilizes the characteristic that the belt has a small deformation of an almost rigid body, uses probabilistic Hough transform to detect the edge, and determines whether the belt is deviated according to the ratio of the distance between the left and right edges of the belt and the reference center line. If the belt is not deviated, the ratio is 1. If deviation occurs, the degree of deviation can be analyzed by the size of the ratio.

[0039] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Without loss of generality, this specification will be described by taking a belt conveyor in a coal mine as an example.

[0040] Figure 1 The following is a schematic diagram showing an application scenario of the belt deviation detection method according to an embodiment of the present invention. It should be noted that: Figure 1 What is shown is only an example of an application scenario of an embodiment of the present invention, to help those skilled in the art understand the technical content of the present invention, but it does not mean that the belt deviation detection method of the embodiment of the present invention cannot be applied to other scenarios.

[0041] like Figure 1 As shown, the scene includes a camera 110, a detection server 120, a display screen 130, and a belt 140 to be detected.

[0042] In this scenario, the camera 110 is set along the conveying line of the belt 140 to be inspected, and the collected video data of the belt is uploaded to the detection server 120. The detection server 120 completes the detection of the degree of belt deviation based on the video data, and outputs the detection results to the display screen 120 for the convenience of management personnel to view.

[0043] Combine the following Figure 2 An embodiment of the belt deviation detection method of the present invention is described.

[0044] Figure 2 The flowchart of the belt deviation detection method according to an embodiment of the present invention is schematically shown.

[0045] like Figure 2 As shown, the method includes operations S210 to S250.

[0046] In operation S210, a preselected area including a belt edge in the image to be inspected is obtained;

[0047] In operation S220, edge detection is performed on the preselected area using a probabilistic Hough transform to obtain a plurality of candidate edges on each side of the belt;

[0048] In operation S230, a unique edge on each side of the belt is determined from the plurality of candidate edges;

[0049] In operation S240, a stable distance between a unique edge on each side of the belt and a reference line is calculated respectively, wherein the reference line is a center line of the belt when the belt is not deviated;

[0050] In operation S250, a deviation result of the belt is determined according to a stable distance on each side of the belt.

[0051] According to an embodiment of the present invention, an industrial smart camera can be pre-installed on the material transportation production line, placed at the station to be inspected, and the running image of the conveyor belt can be collected and uploaded to the ground inspection server through the wireless network and the industrial ring network. During the inspection, the approximate range of the belt in the image can be determined according to the shooting field of view of the current camera, and the centerline position of the belt when the belt is not deviated can be pre-extracted as a reference line. In the image to be inspected, the pre-selected area containing the edges on both sides of the belt is marked, and then the above method is executed for the image to be inspected to be processed. The pre-selected area includes the pre-selected area on the left edge of the belt and the pre-selected area on the right edge of the belt. Figure 3 Given an image to be inspected, such as Figure 3 As shown in the figure, the boxes are pre-selected areas on both sides of the belt edge. At this time, the belt is not deviated and the belt centerline is the reference line. The pre-selected area and the belt centerline can be obtained by manual marking.

[0052] According to an embodiment of the present invention, in operation S220, the image of the preselected area is processed by the probabilistic Hough transform method, and the edge segments in the preselected area can be extracted in real time. Due to the characteristics of the Hough transform algorithm itself and factors such as the line texture on the belt, a large number of similar line segments will be extracted in this operation, and these line segments serve as candidate edges on each side of the belt.

[0053] The basic principle of Hough transform is as follows:

[0054] For a straight line y=mx+b expressed in the Cartesian coordinate system, where m is the slope of the line, b is the intercept, and x and y are the coordinates of the point in the Cartesian coordinate system; convert the line to the Hough space and express it as b=-xm+y, where x and y are the slope and intercept in the Hough space, and b and m are the coordinates of the point in the Hough space. It can be seen that a straight line in the Cartesian coordinate system corresponds to a point in the Hough space; a straight line in the Hough space corresponds to a point in the Cartesian coordinate system, that is, if multiple points in the Cartesian coordinate system are collinear, then multiple straight lines in the Hough space will intersect at the same point.

[0055] Considering that it is inconvenient to express the straight line in Cartesian coordinates when the slope is infinite, the Cartesian coordinates are converted to polar coordinates. The straight line is represented as r = x cos (φ) + y sin (φ). In the polar coordinate system, the polar coordinate points still correspond to the straight line in the Hough space, but in the Hough space, they are no longer represented by the parameters of b and m, but by the parameters of r and φ. The conversion between Cartesian coordinates and polar coordinates is shown below: Figure 4 shown.

[0056] The basic process of probabilistic Hough transform is as follows:

[0057] a. For each point on the edge (x i ,y i ), randomly select a possible line parameter set (m,b) or (φ,r).

[0058] b. Calculate the projection of the straight line in the parameter space under the selected parameter group.

[0059] c. For each projection point, check whether there are other projection points nearby to form a weighted one.

[0060] d. Statistically obtain the parameter group with sufficient weight as the potential straight line.

[0061] That is to say, points with the same coordinates in the Hough space, when transformed to the Cartesian coordinate system, are points on the same straight line in actual detection, and candidate edges are detected based on this principle.

[0062] The results detected using the probabilistic Hough transform (or Hough transform) often contain many similar line segments or a large number of discontinuous line segments. Although most of them are credible, the edge on each side of the belt is unique. Therefore, in operation S230, the unique edge on each side of the belt must be determined from multiple candidate edges.

[0063] The algorithm for determining the unique edge on each side of the belt can select the only most reliable line segment as the unique edge on each side of the belt by voting according to the principle of minority obeys majority. That is, based on the angle between multiple candidate edges, the unique edge on each side of the belt is determined by voting. Specifically, a threshold τ can be preset, and for each side of the belt, voting is performed based on the comparison result of the angle between multiple candidate edges and the preset threshold, and the candidate edge with the highest number of votes is determined as the unique edge on this side. In implementation, for each side of the belt, the angle between all candidate edge segments is calculated. If the angle is less than the given threshold τ, the two candidate edges are considered to be the same line segment, which is recorded as voting for each other once. τ can be given as needed. The larger the τ, the looser the condition, the smaller the possibility of missed detection and the higher the possibility of false detection; otherwise, the opposite is true. Since most edges are credible, false detection can be ignored in most cases. All pairs of candidate edges are traversed for voting, and the straight line with the highest number of votes is finally determined as the unique stable straight line.

[0064] The unique edge of each side of the belt can also be determined by edge connection method. After edge detection, the detected multiple edges are connected into a continuous contour or boundary using a method based on watershed transformation. Or it can be obtained by contour analysis method. For the detected edge contour, the contour is screened and merged according to the shape, size, direction and other characteristics of the contour to obtain a unique edge. Or it can be obtained by skeletonization algorithm. By skeletonizing the image, the edge in the image can be converted into a skeleton line, and then further analysis and processing are performed based on the skeleton line to obtain a unique edge. And, it can be obtained by curvature-based method. According to the curvature characteristics of the edge, multiple detected edges are screened and merged to obtain a unique edge.

[0065] In operation S240, according to the unique edge on each side of the belt determined in the previous operation, the stable distance of each side is calculated respectively, that is, for the unique edge on each side of the belt, the first distance and the second distance between two non-adjacent points on the unique edge of the side and the reference line, and the third distance and the fourth distance between two non-adjacent points on the reference line and the unique edge of the side are calculated respectively, and then, the minimum value among the first distance, the second distance, the third distance and the fourth distance is taken as the stable distance of the corresponding side of the belt. The reference line can be the center line of the belt, which is obtained by manually marking or calibrating the image of the belt in a non-deviation state. In some embodiments, since the candidate edge detected by the probabilistic Hough transform in S220 is a line segment, at this time, the two endpoints of the unique edge on each side of the belt can be taken to calculate its distance from the reference line. Similarly, the reference line is also a line segment, and its two endpoints are taken to calculate its distance from the unique edge on each side.

[0066] In S250, the ratio R between the stable distances on both sides of the belt can be calculated; the degree of the belt deviation can be determined according to the size of the ratio R. When the belt is not deviated, the stable distances of the left and right edges of the belt should be equal, and the ratio at this time is 1. If the belt is deviated, the ratio is not 1. Therefore, the degree of belt deviation can be determined by the size of |R-1|, and different deviation ranges are pre-set to correspond to different fault levels, thereby determining the fault level of the belt deviation.

[0067] The algorithm execution flow to achieve the above operation is as follows Figure 5 As shown. The algorithms for both sides of the belt can be run in parallel. After obtaining the only edge on the left and right sides, calculate the distance from the two ends of the left edge to the center line, and calculate the distance from the two ends of the center line to the left edge. Take the minimum value of all distances as the stable distance distanceLeft of the left edge. Similarly, calculate the stable distance distanceRight of the right edge. The ratio R can be R = distanceLeft / distanceRight. Determine whether the belt is deviating and the degree of deviation based on the size of the ratio, and finally output the deviation detection result.

[0068] The method of the embodiment of the present invention adopts machine vision technology, and determines the belt deviation result through video images by using simple algorithm transformation and judgment ratio, thereby avoiding the influence of contact detection on detection accuracy, and can perform online real-time processing of the collected image information. Compared with traditional contact detection, the method of the embodiment of the present invention has the advantages of simple deployment, high real-time performance, high detection accuracy and comprehensive detection performance.

[0069] Based on the same inventive concept, this specification also provides a belt deviation detection device 600 for a belt conveyor. Figure 6 The belt deviation detection device 600 will be described.

[0070] Figure 6 The block diagram of the belt deviation detection device 600 according to the embodiment of the present invention is schematically shown. The detection device 600 can be implemented as part or all of the electronic device through software, hardware or a combination of both.

[0071] like Figure 6 As shown, the detection device 600 includes an image pre-selection module 610, an edge detection module 620, an edge determination module 630, a distance calculation module 640, and a deviation determination module 650. The detection device 600 can execute the various methods described above.

[0072] The image pre-selection module 610 is configured to obtain a pre-selected area in the image to be inspected that includes the edge of each side of the belt.

[0073] The edge detection module 620 is configured to perform edge detection on the pre-selected area using probabilistic Hough transform to obtain a plurality of candidate edges on each side of the belt.

[0074] The edge determination module 630 is configured to determine a unique edge on each side of the belt from the plurality of candidate edges.

[0075] The distance calculation module 640 is configured to respectively calculate the stable distance between the unique edge on each side of the belt and a reference line, wherein the reference line is the center line of the belt when the belt is not deviated.

[0076] The deviation determination module 650 is configured to determine the deviation result of the belt according to the stable distance on each side of the belt.

[0077] According to the belt deviation detection device of the embodiment of the present invention, the collected image information is processed online in real time, and the distance between the two side edges of the belt and the center line is compared through algorithm optimization, thereby detecting the degree of belt deviation, which has the beneficial effects of simple deployment, high real-time performance and high detection accuracy.

[0078] This specification also provides an electronic device 710 for detecting belt deviation of a belt conveyor, the electronic device 710 comprising at least one processor; and

[0079] a memory communicatively coupled to the at least one processor;

[0080] in,

[0081] The memory stores instructions that can be executed 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 any belt deviation detection method as described above.

[0082] Based on the same inventive concept, this specification also provides a belt deviation detection system 700, which can be applied to a belt conveyor. Figure 7 A block diagram of a detection system 700 for implementing an embodiment of the present invention is schematically shown.

[0083] like Figure 7 As shown, the detection system 700 includes the electronic device 710 for detecting belt deviation of the belt conveyor as described above, and an image acquisition device 720 arranged along the conveyor belt. The electronic device 710 processes the belt image acquired by the image acquisition device 720 to determine the degree of belt deviation.

[0084] This specification also provides a computer-readable storage medium, which can be a computer-readable storage medium included in the electronic device or computer system in the above embodiment; or a computer-readable storage medium that exists independently and is not assembled into the device. The computer-readable storage medium stores executable instructions, which, when executed by a processor, enable the processor to implement the belt deviation detection method described in this specification.

[0085] The above describes specific embodiments of the present invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0086] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, electronic device, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0087] The apparatus, electronic device, non-volatile computer storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the apparatus, electronic device and non-volatile computer storage medium also have beneficial technical effects similar to those of the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, electronic device and non-volatile computer storage medium will not be repeated here.

[0088] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0089] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0090] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0091] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0092] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0093] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data optimization device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data optimization device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0094] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data optimization device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0095] These computer program instructions may also be loaded onto a computer or other programmable data optimization device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0096] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0097] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0098] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0100] The specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0101] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0102] The above is only an embodiment of this specification and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A belt deviation detection method for a belt conveyor, characterized in that: The method comprises: Acquire a preselected area containing the belt edge in the image to be inspected; Performing edge detection on the preselected area using probabilistic Hough transform to obtain a plurality of candidate edges on each side of the belt; Determining the unique edge on each side of the belt from the plurality of candidate edges, comprising: for each side of the belt, voting based on a comparison result of the angles between the plurality of candidate edges and a preset threshold, and determining the candidate edge with the highest number of votes as the unique edge on the side; Calculating the stable distance between the only edge on each side of the belt and a reference line, respectively, wherein the reference line is the center line of the belt when the belt is not deviated; The deviation result of the belt is determined based on the stable distance on each side of the belt.

2. The method according to claim 1, characterized in that The step of respectively calculating the stable distance between the unique edge on each side of the belt and the reference line comprises: For the only edge on each side of the belt, respectively calculate a first distance and a second distance between two non-adjacent points on the only edge and a reference line, and a third distance and a fourth distance between two non-adjacent points on the reference line and the only edge; The minimum value among the first distance, the second distance, the third distance and the fourth distance is taken as the stable distance of the corresponding side of the belt.

3. The method according to claim 1, characterized in that The step of determining the belt deviation result according to the stable distance on each side of the belt comprises: Calculating the ratio R between the stable distances on both sides of the belt; The degree of belt deviation is determined according to the size of the ratio R.

4. The method according to claim 3, characterized in that The method further comprises: The belt fault level is output according to the degree of belt deviation.

5. A belt deviation detection device for a belt conveyor, characterized in that: include: An image pre-selection module is configured to obtain a pre-selected area containing the edge of each side of the belt in the image to be inspected; an edge detection module configured to perform edge detection on the preselected area using a probabilistic Hough transform to obtain a plurality of candidate edges on each side of the belt; The edge determination module is configured to determine the only edge on each side of the belt from the plurality of candidate edges, including: for each side of the belt, voting is performed based on the comparison result of the angle between two of the plurality of candidate edges and a preset threshold, and the candidate edge with the highest number of votes is determined as the only edge on the side; A distance calculation module is configured to respectively calculate a stable distance between a unique edge on each side of the belt and a reference line, wherein the reference line is a center line of the belt when the belt is not deviated; The deviation determination module is configured to determine the deviation result of the belt according to the stable distance on each side of the belt.

6. An electronic device for detecting belt deviation of a belt conveyor, comprising: at least one processor; as well as, a memory communicatively coupled to the at least one processor; in, The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

7. A system for detecting belt deviation of a belt conveyor, characterized in that: The system comprises the electronic device as claimed in claim 6, and an image acquisition device arranged along the conveyor belt; the electronic device processes the belt image acquired by the image acquisition device to determine the degree of deviation of the belt.

8. A computer-readable storage medium storing executable instructions, wherein when the instructions are executed by a processor, the processor implements the method according to any one of claims 1 to 4.

Images