Wear detection method and device for screw conveyer

Abstract

The invention discloses an abrasion detection method and device for a spiral conveyor. The method comprises the steps that in response to the fact that the working state of the spiral conveyor is a starting state, the rotating state of blades in the spiral conveyor is controlled to be a constant-speed rotating state; in the constant-speed rotating state, a visual detection module in the spiral conveyor is used for obtaining a first collection video of one side of the blade and a second collection video of the other side, corresponding to the one side, of the blade; forming a target acquisition video of the blade by using the first acquisition video and the second acquisition video; based on the target acquisition video, controlling the rotation state of the blade to be a rotation stopping state; and in the state of stopping rotation, the target acquisition video is analyzed, the abrasion result and the abrasion position of the blade are obtained, and the abrasion result is used for representing the abrasion degree of the blade. The technical problems that the abrasion detection efficiency of the spiral conveyor is low, and the cost of detection equipment is high are solved.

Description

Technical Field

[0001] The invention relates to the technical field of detecting screw conveyors, and in particular to a wear detection method and device for screw conveyors. Background Art

[0002] When the screw conveyor pushes the material to move, the interaction between the material and the blades may cause the blades in the screw conveyor to fail due to excessive wear. Therefore, it is necessary to promptly detect the wear of the blades in the screw conveyor.

[0003] At present, the methods for detecting the blades of screw conveyors can be divided into disassembly detection methods and non-disassembly detection methods. Among them, the disassembly detection method is to open the outer casing or observation window of the screw conveyor, and the technicians visually judge the degree of wear inside the screw conveyor, but this method takes a long time to detect; the non-disassembly detection method is to obtain the internal wear of the screw conveyor through built-in sensors, but this method requires the design of a complex structure on the blades and blade shafts where sensors and signal lines can be installed, resulting in excessively high equipment costs. From the above, it can be seen that the commonly used detection methods for screw conveyor blades are prone to technical problems such as low wear detection efficiency of screw conveyors and high detection equipment costs.

[0004] Currently, no effective solution has been proposed to the technical problems of low wear detection efficiency and high cost of detection equipment for the above-mentioned screw conveyor. Summary of the invention

[0005] The embodiments of the present invention provide a wear detection method and device for a screw conveyor to solve the technical problems of low wear detection efficiency of the screw conveyor and high cost of detection equipment.

[0006] According to one aspect of the embodiment of the invention, a wear detection method for a screw conveyor is provided. The method may include: in response to the working state of the screw conveyor being the start state, controlling the rotation state of the blade in the screw conveyor to be a constant speed rotation state, wherein the constant speed rotation state is used to characterize that the blade rotates at a target speed; in the constant speed rotation state, using the visual detection module in the screw conveyor, obtaining a first acquisition video of one side of the blade, and a second acquisition video of the other side corresponding to one side of the blade; the first acquisition video and the second acquisition video are combined to form a target acquisition video of the blade; based on the target acquisition video, controlling the rotation state of the blade to be a stop rotation state; in the stop rotation state, analyzing the target acquisition video to obtain the wear result and wear position of the blade, wherein the wear result is used to characterize the degree of wear of the blade.

[0007] Optionally, in a stopped rotating state, the target acquisition video is analyzed to obtain the wear result of the blade, including: in a stopped rotating state, performing a carbon powder detection on the target acquisition video to obtain a first detection result, wherein the first detection result is used to characterize whether carbon powder adheres to the blade; based on the first detection result, determining the wear result of the blade.

[0008] Optionally, based on the first detection result, determining the wear result of the blade includes: in response to the first detection result being that carbon powder is adhered to the blade, obtaining an initial adhesion image of carbon powder adhered to the blade from a target acquisition video; performing grayscale processing on the initial adhesion image to obtain a target adhesion image; based on the adhesion area of ​​the carbon powder on the blade, segmenting the target adhesion image to obtain a carbon powder area where the carbon powder is adhered to the blade; and determining the wear result based on the carbon powder area.

[0009] Optionally, based on the first detection result, the wear result of the blade is determined, including: in response to the first detection result that carbon powder is not adhered to the blade, the target acquisition video is input into the wear detection model of the screw conveyor for analysis to obtain the wear result, wherein the wear detection model is established through multiple acquisition images in the historical target acquisition video of the blade.

[0010] Optionally, in a stopped rotation state, the target acquisition video is analyzed to obtain the wear position of the blade, including: in a stopped rotation state, acquiring a target image in the target acquisition video and a target time corresponding to the acquired target image; determining the target position of the blade based on the target rotation speed, target time and the pitch of the blade; in response to the target position being greater than or equal to the length of the screw conveyor, determining the position at a first length away from the detection point in the target image as the wear position; in response to the target position being less than the length of the screw conveyor, determining the position at a second length away from the detection point in the target image as the wear position.

[0011] Optionally, the method also includes: the visual inspection module is installed in the guide groove of the screw conveyor, the guide groove is on the outer shell of the screw conveyor, and the structure of the guide groove is a T-shaped groove, and the structure of the visual inspection module is a T-shaped structure corresponding to the T-shaped groove.

[0012] Optionally, the visual inspection module includes: a protective shell, a camera, a lighting lamp and a roller, wherein the protective shell contains two cavities, in which the camera and the lighting lamp are installed respectively.

[0013] Optionally, the method also includes: obtaining the angle between the axis of the camera and the axis of the lighting lamp; adjusting the angle to a target angle, wherein the target angle is determined by the axis of the camera, the pitch of the blade, the distance from the center of the roller to the axis of the camera, the helix angle of the blade, and the radius of the roller.

[0014] Optionally, in a constant speed rotation state, a visual detection module in the screw conveyor is used to obtain a first captured video of one side of the blade and a second captured video of the other side corresponding to the one side of the blade, including: in a constant speed rotation state, in response to a target speed being less than a speed threshold corresponding to the target speed, the visual detection module is used to obtain the first captured video and the second captured video, wherein the speed threshold is determined by the field of view angle of the camera lens in the visual detection module and the helix angle of the blade.

[0015] According to one aspect of an embodiment of the present invention, a wear detection device for a screw conveyor is provided. The device may include: a first control unit, which is used to control the rotation state of the blade in the screw conveyor to be a constant speed rotation state in response to the working state of the screw conveyor being a start state, wherein the constant speed rotation state is used to characterize that the blade rotates at a target speed; a first acquisition unit, which is used to acquire a first acquisition video of one side of the blade and a second acquisition video of the other side corresponding to one side of the blade using a visual detection module in the screw conveyor in the constant speed rotation state; a composition unit, which is used to combine the first acquisition video and the second acquisition video to form a target acquisition video of the blade; a second control unit, which is used to control the rotation state of the blade to be a stop rotation state based on the target acquisition video; an analysis unit, which is used to analyze the target acquisition video in the stop rotation state to obtain the wear result and wear position of the blade, wherein the wear result is used to characterize the wear degree of the blade.

[0016] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0017] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0018] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0019] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0020] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0021] In an embodiment of the present invention, in response to the working state of the screw conveyor being the start state, the rotation state of the blade in the screw conveyor is controlled to be a constant speed rotation state, wherein the constant speed rotation state is used to characterize that the blade rotates at a target speed; in the constant speed rotation state, the visual detection module in the screw conveyor is used to obtain a first acquisition video of one side of the blade and a second acquisition video of the other side corresponding to one side of the blade; the first acquisition video and the second acquisition video are used to form a target acquisition video of the blade; based on the target acquisition video, the rotation state of the blade is controlled to be a stop rotation state; in the stop rotation state, the target acquisition video is analyzed to obtain the wear result and wear position of the blade, wherein the wear result is used to characterize the wear degree of the blade. That is to say, considering that when the blade is in a constant speed rotation state, the visual detection module is used to obtain the first acquisition video and the second acquisition video of the blade, and then the first acquisition video and the second acquisition video are used to form a target acquisition video, at this time, the blade is controlled to be in a stop rotation state, so as to analyze the target acquisition video, so as to achieve the purpose of determining the wear result and wear position of the blade, so as to solve the technical problems of low wear detection efficiency of the screw conveyor and high cost of detection equipment, and achieve the technical effect of improving the wear detection efficiency of the screw conveyor and controlling the low cost of detection equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0023] Figure 1 is a flow chart of a wear detection method for a screw conveyor according to an embodiment of the present invention;

[0024] Figure 2 is a flow chart of a wear detection method for a screw conveyor based on visual activated carbon according to an embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of a wear detection system for a screw conveyor based on visual activated carbon according to an embodiment of the present invention;

[0026] Figure 4 is a schematic diagram of a visual detection module in a wear detection system for a screw conveyor according to an embodiment of the present invention;

[0027] Figure 5 is a schematic diagram of determining the maximum detection speed of a screw conveyor blade according to an embodiment of the present invention;

[0028] Figure 6 is a schematic diagram of determining an angle between an illumination axis and a camera axis according to an embodiment of the present invention;

[0029] Figure 7 Schematic diagram of a wear detection device for a screw conveyor according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] According to an embodiment of the present invention, a wear detection method for a screw conveyor is provided. It should be noted that in the flowchart in the accompanying drawings, the steps shown therein can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0033] The wear detection method of the screw conveyor according to the embodiment of the present invention is introduced below.

[0034] Figure 1 is a flow chart of a wear detection method for a screw conveyor according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0035] Step S101, in response to the working state of the screw conveyor being a start state, controlling the rotation state of the blades in the screw conveyor to be a constant speed rotation state.

[0036] In the technical solution provided in the above step S101 of the present invention, after the screw conveyor stops operating and the internal material is discharged, the visual inspection module is installed in the guide groove of the screw conveyor to control the working state of the screw conveyor so that the working state of the screw conveyor is in a starting state, and in the starting state, the rotation state of the blades in the screw conveyor is controlled to be a constant speed rotation state.

[0037] Optionally, the target speed may be a preset speed. The constant speed rotation state is used to characterize that the blades rotate at the target speed, for example, the blades rotate at a constant speed. The screw conveyor is a commonly used conveying equipment, mainly used for conveying bulk materials, powders, granular materials, etc. For example, in the process of preparing activated carbon, the screw conveyor is often used for conveying, mixing and unloading raw materials.

[0038] For example, after the screw conveyor that transports activated carbon stops operating and the internal materials are drained, the detection window steel plate of the conveyor shell is removed, the visual inspection module is installed in the guide groove of the screw conveyor, and then the window steel plate is installed back to the shell of the screw conveyor.

[0039] Furthermore, the screw conveyor is started to rotate the blades in the screw conveyor at a constant speed, thereby driving the visual inspection module in the screw conveyor to move in a straight line. It should be noted that this is only a preferred implementation method for determining that the rotation state of the blades in the screw conveyor is a constant speed rotation state, and does not specifically limit the process and method for determining that the rotation state of the blades in the screw conveyor is a constant speed rotation state.

[0040] Step S102, under a constant speed rotation state, using a visual detection module in the screw conveyor, obtains a first captured video of one side of the blade and a second captured video of the other side corresponding to the one side of the blade.

[0041] In the technical solution provided in the above step S102 of the present invention, under constant speed rotation state, the visual detection module in the screw conveyor can be used to obtain a first captured video of one side of the blade and a second captured video of the other side corresponding to the one side of the blade.

[0042] Optionally, the blades of the screw conveyor are controlled to rotate at a constant speed to push the visual inspection module to move in a straight line. When the visual inspection module moves from one end to the other end in the screw conveyor, a first captured video can be obtained; the blades are controlled to rotate at a constant speed in the opposite direction to push the visual inspection module to move in a straight line in the opposite direction to obtain a second captured video.

[0043] For example, after starting the screw conveyor and making the blades of the screw conveyor rotate at a constant speed, the visual inspection module can be pushed to move in a straight line to photograph the wear and damage on one side of the blade; when the visual inspection module moves to the other end and completes the video sampling of one side of the blade, the screw conveyor blades are rotated in the opposite direction at a constant speed, and the visual inspection module is pushed to move in a straight line in the opposite direction to photograph the wear and damage on the other side of the blade.

[0044] It should be noted that this is only a preferred implementation method for obtaining the first captured video and the second captured video, and the process and method for obtaining the first captured video and the second captured video are not specifically limited. As long as the blade rotation state is a constant speed rotation state, the process and method for obtaining the first captured video and the second captured video using the visual detection module are within the protection scope of the present invention and are not listed here.

[0045] Step S103, combining the first captured video and the second captured video to form a target captured video of the leaf.

[0046] In the technical solution provided in the above step S103 of the present invention, after the first collected video and the second collected video are obtained, the target collected video of the blade can be determined based on the first collected video and the second collected video.

[0047] Optionally, the first acquired video and the second acquired video are combined to form a target acquired video of the leaf, wherein the target acquired video can be called a sampling video, or a acquired video. It should be noted that only the name of the target acquired video is given as an example here, and the name type of the target acquired video is not specifically limited.

[0048] It can be understood that this is only a preferred implementation method for obtaining the target acquisition video of the blade, and the process and method for obtaining the target acquisition video of the blade are not specifically limited. As long as the process and method for determining the target acquisition video of the blade are based on the first acquisition video and the second acquisition video, they are within the protection scope of the present invention and will not be repeated here.

[0049] Step S104: Based on the target acquisition video, the rotation state of the blade is controlled to stop rotating.

[0050] In the technical solution provided in step S104 of the present invention, based on the target acquisition video obtained in the above step, it is necessary to control the rotation state of the blade at this time to be a stopped rotation state. The stopped rotation state can be referred to as stopped rotation. For example, when the visual detection module completes the video sampling, it is necessary to control the blade of the screw conveyor to stop rotating.

[0051] It can be understood that this is only a preferred implementation method for controlling the rotation state of the blades to be in a stopped rotation state, and the process and method of controlling the rotation state of the blades to be in a stopped rotation state are not specifically limited. As long as the video is collected according to the target, the process and method of controlling the rotation state of the blades to be in a stopped rotation state are within the protection scope of the present invention and are not listed here.

[0052] Step S105, in a state of stopping rotation, analyzing the target captured video to obtain the wear result and wear position of the blade.

[0053] In the technical solution provided in the above step S105 of the present invention, when the rotation state of the blade is in a stopped rotation state, the visual inspection module needs to be removed from the guide groove in the screw conveyor, and the target acquisition video collected by the visual inspection module can be analyzed to achieve the purpose of obtaining the wear result and wear position of the blade, wherein the wear result is used to characterize the wear degree of the blade, which can be called a damage result. The wear position can be called a loss position.

[0054] For example, after the blades of the screw conveyor stop rotating, the visual inspection module is located in the guide groove of the inspection window steel plate. It is necessary to remove the window steel plate and take out the visual inspection module. Then, the video collected by the visual inspection module is analyzed and processed to obtain the wear and damage of the blades and determine the location of the damage.

[0055] It should be noted that this is only a preferred implementation method for obtaining the wear results and wear positions of the blades, and the process and method for obtaining the wear results and wear positions of the blades are not specifically limited. As long as the rotation state of the blades is a stopped rotation state, the target acquisition video is analyzed to obtain the process and method for obtaining the wear results and wear positions of the blades are within the protection scope of the present invention and are not listed here.

[0056] In the above steps S101 to S105 of the present invention, when the working state of the screw conveyor is the start-up state, the rotation state of the blade in the screw conveyor can be controlled to be a constant speed rotation state, and then in the constant speed rotation state, the visual detection module in the screw conveyor is used to obtain the first acquisition video on one side of the blade and the second acquisition video on the other side of the blade, and the first acquisition video and the second acquisition video can constitute the target acquisition video. After obtaining the target acquisition video, the rotation state of the blade can be controlled to be a stop rotation state, and in this stop rotation state, the above-mentioned target acquisition video is analyzed to obtain the wear result and wear position of the blade. Considering that when the blade is in a constant speed rotation state, the visual detection module is used to obtain the first acquisition video and the second acquisition video of the blade, and then the first acquisition video and the second acquisition video are composed of the target acquisition video, the blade is controlled to be in a stop rotation state at this time, so as to analyze the target acquisition video to achieve the purpose of determining the wear result and wear position of the blade, so as to solve the technical problems of low wear detection efficiency of the screw conveyor and high cost of the detection equipment, and achieve the technical effect of improving the wear detection efficiency of the screw conveyor and controlling the low cost of the detection equipment.

[0057] The above method of this embodiment is further introduced below.

[0058] As an optional implementation method, in a state of stopped rotation, the target acquisition video is analyzed to obtain the wear result of the blade, including: in a state of stopped rotation, carbon powder detection is performed on the target acquisition video to obtain a first detection result, wherein the first detection result is used to characterize whether carbon powder adheres to the blade; based on the first detection result, the wear result of the blade is determined.

[0059] In this embodiment, when the rotation stops, it is necessary to perform a carbon powder detection on the target captured video to obtain a first detection result, and the wear result of the blade can be determined according to the first detection result.

[0060] Optionally, when performing carbon powder detection on the target acquisition video, if the blade is damaged, the carbon powder may adhere to the damaged area, but it may not adhere to the damaged area of ​​the blade. Different processing is required for different detection situations in order to achieve the purpose of obtaining the wear results of the blade.

[0061] For example, the video collected by the visual inspection module is analyzed and processed. On the one hand, when the blade is damaged, carbon powder may adhere to the damaged area, and the damage condition can be obtained by detecting the carbon powder area on the blade; on the other hand, when there is no carbon powder adhered to the damaged area, the degree of wear and damage can be detected through algorithms.

[0062] As an optional embodiment, based on the first detection result, the wear result of the blade is determined, including: in response to the first detection result that carbon powder is adhered to the blade, obtaining an initial adhesion image of carbon powder adhered to the blade from the target acquisition video; grayscale processing is performed on the initial adhesion image to obtain a target adhesion image; based on the adhesion area of ​​the carbon powder on the blade, the target adhesion image is segmented to obtain a carbon powder area where the carbon powder is adhered to the blade; based on the carbon powder area, the wear result is determined.

[0063] In this embodiment, if the first detection result is that carbon powder adheres to the blade, the initial adhesion image of carbon powder adhering to the blade can be obtained from the target acquisition video, and then the initial adhesion image can be gray-processed to obtain the target adhesion image, and then the target adhesion image is segmented according to the adhesion area of ​​carbon powder on the blade using a threshold segmentation algorithm to obtain the carbon powder area where carbon powder adheres to the blade, and finally the purpose of determining the wear result can be achieved according to the carbon powder area obtained above. Among them, the adhesion area can be called the carbon powder adhesion area. Among them, the threshold segmentation algorithm is used to classify the pixels in the image according to their gray value and a pre-set threshold value, so as to segment the image into different areas or objects.

[0064] For example, if carbon powder adheres to the blade, the area where carbon powder adheres can be determined from the target acquisition video. By performing damage detection on the area where carbon powder adheres, the wear result can be obtained. The principle of damage detection through the area where carbon powder adheres is as follows: after a large number of experiments, the relationship between the area where carbon powder adheres and the damage is determined, the acquired image information is grayed out, and since the gray value of the carbon powder area is relatively low, these areas are segmented out through a threshold segmentation algorithm, and damage is identified based on the area of ​​these areas.

[0065] As an optional embodiment, based on the first detection result, the wear result of the blade is determined, including: in response to the first detection result that carbon powder is not adhered to the blade, the target acquisition video is input into the wear detection model of the screw conveyor for analysis to obtain the wear result, wherein the wear detection model is established through multiple acquisition images in the historical target acquisition video of the blade.

[0066] In this embodiment, after obtaining the first detection result, if the first detection result is that the carbon powder is not adhered to the blade, it is necessary to obtain multiple collected images with different wear degrees and different damages, and the multiple collected images obtained above constitute a data set, and the wear detection model is trained using the data set to obtain a trained wear detection model, and multiple images in the target collected video are input into the trained wear detection model of the screw conveyor for analysis to obtain the wear result. Among them, the wear detection model includes multiple neural networks.

[0067] Optionally, if the worn area is not adhered to carbon powder, further detection of the worn area is required, wherein the worn area can also be referred to as a damaged area. For example, the principle of detecting the damaged area without carbon powder is as follows: by constructing data sets of different wear degrees and different damages, training the neural network, obtaining a model that can accurately identify the wear degree and damage, and then inputting the collected video into the model to detect the wear condition in the blade.

[0068] As an optional implementation method, in a stopped rotation state, the target acquisition video is analyzed to obtain the wear position of the blade, including: in a stopped rotation state, acquiring a target image in the target acquisition video and a target time corresponding to the acquired target image; determining the target position of the blade based on the target rotation speed, target time and the pitch of the blade; in response to the target position being greater than or equal to the length of the screw conveyor, determining the position at a first length away from the detection point in the target image as the wear position; in response to the target position being less than the length of the screw conveyor, determining the position at a second length away from the detection point in the target image as the wear position.

[0069] In this embodiment, when the blade is in a stopped rotating state, the target image in the target acquisition video and the target time corresponding to the acquired target image can be obtained, and then the target position of the blade can be determined according to the target speed, target time and the pitch of the blade, and the target position and the length of the screw conveyor are compared. If the target position is greater than or equal to the length of the screw conveyor, the position at a first length away from the detection point in the target image can be determined as the wear position; if the target position is less than the length of the screw conveyor, the position at a second length away from the detection point in the target image can be determined as the wear position. Among them, the wear position can be called the damage position.

[0070] Optionally, the target image may be a preset damaged image, for example, the damage may be at the midline of the target image. The target time corresponding to the target image is the time when the blade is damaged, for example, t seconds. The target speed may be the speed of the blade of the screw conveyor, which may be represented by n, in revolutions per minute. The pitch of the blade may be referred to as the pitch of the spiral blade, which may be represented by P. The length of the screw conveyor may be represented by C.

[0071] Optionally, the target speed is divided by sixty to obtain a first value; the first value is multiplied by the target time to obtain a second value; the second value is multiplied by the pitch of the blade to obtain a third value, and the third value is determined as the target position, wherein the target position can be obtained by To express.

[0072] Optionally, the detection point may be a pre-set point, which may be referred to as a detection start point. The first length may be The second length can be expressed in millimeters. It is expressed in millimeters, where x is used to represent the frame rate of the camera in the visual inspection module.

[0073] For example, the location of the damage is determined by the time when the damage appears in the video. The timing starts from when the visual inspection module starts to be pushed by the blade. Suppose that after t seconds, the damage appears at the midline of the image. If ≥ the length C of the screw conveyor, the damage is located at the distance from the start point of the detection mm; if < the length of the screw conveyor C, the damage is located at the distance from the detection starting point mm.

[0074] As an optional implementation mode, the method also includes: the visual inspection module is installed in the guide groove of the screw conveyor, the guide groove is on the outer shell of the screw conveyor, and the structure of the guide groove is a T-shaped groove, and the structure of the visual inspection module is a T-shaped structure corresponding to the T-shaped groove.

[0075] In this embodiment, the visual inspection module can be installed in the guide groove of the screw conveyor. The guide groove exists on the shell of the screw conveyor, and the structure of the guide groove is a T-shaped groove. The structure of the visual inspection module is also a T-shaped structure.

[0076] For example, the guide groove on the outer shell of the screw conveyor is a T-shaped groove, and the visual inspection module has a T-shaped structure corresponding to the T-shaped groove, thereby limiting the visual inspection module to move only along the axial direction of the screw conveyor.

[0077] As an optional embodiment, the visual inspection module includes: a protective shell, a camera, a lighting lamp and a roller, wherein the protective shell includes two cavities, in which the camera and the lighting lamp are installed respectively.

[0078] In this embodiment, the visual inspection module includes: a protective shell, a camera, a lighting lamp and a roller, wherein the protective shell is divided into two cavities by using opaque material, and the camera and the lighting lamp are installed respectively. The camera has a storage function for storing the collected video, and after the inspection is completed, the video is exported and processed and analyzed.

[0079] Optionally, in order to prevent residual carbon powder in the screw conveyor from damaging the electronic equipment inside the visual inspection module, the protective shell should be completely sealed; the two end faces of the protective shell perpendicular to the axis of the screw conveyor are made of transparent materials so that the lighting and camera can perform lighting and video sampling.

[0080] Optionally, it is necessary to set the angle between the axis of the camera and the axis of the lighting lamp so that the area photographed by the camera has sufficient brightness.

[0081] Optionally, in order to prevent the transparent material on the end face of the protective shell from affecting the camera sampling due to the light emitted by the reflected illuminator, the protective shell needs to be divided into two cavities using opaque material, and the camera and illuminator are installed respectively. Since it is necessary to sample the two surfaces of the blades of the screw conveyor, two cameras and two illuminators need to be installed, and they need to be arranged in opposite directions in the visual inspection module.

[0082] Optionally, the visual inspection module needs to have two rollers, which are respectively installed on two diagonal corners of the protective shell. When the blades of the screw conveyor push the visual inspection module to reciprocate, the rollers are in direct contact with the blades and transmit the motion.

[0083] In this embodiment, the wear detection method of the screw conveyor can be applied to the wear detection system of the screw conveyor, which includes: a screw conveyor, a visual inspection module and a computer. Among them, the inner surface of the outer shell of the screw conveyor is processed with a T-slot for installing the visual inspection module. Considering the feasibility of processing, the surface of the outer shell with the T-slot is spliced ​​by multiple steel plates, and each steel plate is processed with a T-slot separately; considering the sealing of the outer shell of the screw conveyor, sealant is applied at the joints of the steel plates; since the sealing groove of the outer shell of the screw conveyor is spliced ​​by many steel plates, in order to ensure that the visual inspection module can move smoothly and avoid jamming, the T-shaped structure on the outer shell of the visual inspection module has a chamfer; the visual inspection module can be used for the collection and storage of the video of the blades of the screw conveyor.

[0084] As an optional implementation mode, the method also includes: obtaining the angle between the axis of the camera and the axis of the lighting lamp; adjusting the angle to a target angle, wherein the target angle is determined by the axis of the camera, the pitch of the blade, the distance from the center of the roller to the axis of the camera, the helix angle of the blade, and the radius of the roller.

[0085] In this embodiment, the angle between the axis of the camera and the axis of the lighting lamp can be obtained, and then the angle is adjusted to a target angle, wherein the target angle is calculated using the axis of the camera, the pitch of the blade, the distance from the center of the roller to the axis of the camera, the helix angle of the blade, and the radius of the roller.

[0086] Optionally, the target angle may be the angle ultimately formed by the axis of the camera and the axis of the lighting lamp, which may be represented by β, and the target angle must satisfy the following formula:

[0087]

[0088] In the above formula, S is used to represent the distance between the two intersections formed by the camera axis, the camera axis, the lighting axis and the vertical plane where the center of the roller is located. L is used to represent the distance from the center of the roller to the axis of the camera. α is used to represent the helix angle of the blade, and the helix angle of the blade can be called the helix angle of the spiral blade. r is used to represent the radius of the roller.

[0089] As an optional implementation method, under a constant speed rotation state, a visual detection module in a screw conveyor is used to obtain a first captured video of one side of the blade and a second captured video of the other side corresponding to the one side of the blade, including: under a constant speed rotation state, in response to a target speed being less than a speed threshold corresponding to the target speed, the visual detection module is used to obtain the first captured video and the second captured video, wherein the speed threshold is determined by the field of view angle of the camera lens in the visual detection module and the helix angle of the blade.

[0090] In this embodiment, in the constant speed rotation state, the target speed needs to be controlled to be less than the speed threshold, and then the visual detection module can be used to obtain the first acquisition video and the second acquisition video, wherein the speed threshold can be referred to as the threshold and can be obtained by n max To express.

[0091] For example, in order to ensure that the visual inspection module can capture the complete blade video of the screw conveyor, that is, there is no blind spot between the two frames of the video, the speed of the blade of the screw conveyor should be lower than the threshold n. max , and the threshold can be determined according to the following formula:

[0092]

[0093] In the above formula, γ is used to represent the field of view of the camera lens, f is used to represent the distance from the camera lens to the blade, R is used to represent the distance between the camera axis and the screw conveyor axis, and x is used to represent the frame rate of the camera. After the blade of the screw conveyor is represented as a straight line, the ray emitted by the field of view and the straight line have two intersection points: the first intersection point and the second intersection point, where the camera is the origin of the rectangular coordinate system, and the abscissa of the first intersection point is smaller than the abscissa of the second intersection point, then the ordinate of the first intersection point can be represented by a, and the ordinate of the second intersection point can be represented by b.

[0094] In this embodiment, when the working state of the screw conveyor is the starting state, the rotation state of the blade in the screw conveyor can be controlled to be a constant speed rotation state, and then in the constant speed rotation state, the visual detection module in the screw conveyor is used to obtain a first acquisition video on one side of the blade and a second acquisition video on the other side of the blade. The first acquisition video and the second acquisition video can constitute a target acquisition video. After obtaining the target acquisition video, the rotation state of the blade can be controlled to be a stopped rotation state, and in this stopped rotation state, the above-mentioned obtained target acquisition video is analyzed to obtain the wear result and wear position of the blade. Considering that when the blade is in a constant speed rotation state, the visual detection module is used to obtain the first acquisition video and the second acquisition video of the blade, and then the first acquisition video and the second acquisition video are composed of the target acquisition video, the blade is controlled to be in a stopped rotation state at this time, so as to analyze the target acquisition video to achieve the purpose of determining the wear result and wear position of the blade, so as to solve the technical problems of low wear detection efficiency of the screw conveyor and high cost of detection equipment, and achieve the technical effect of improving the wear detection efficiency of the screw conveyor and controlling the low cost of detection equipment.

[0095] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0096] Activated carbon is a porous carbon adsorption material. Due to its developed pore structure, large surface area, stable chemical properties and the advantages of being reusable after regeneration, it is widely used in many fields such as chemical industry, environmental protection, metallurgy, and materials. In the process of preparing activated carbon, screw conveyors are often used for the transportation, mixing and unloading of raw materials.

[0097] When the screw conveyor pushes the material to move, the interaction between the material and the blades may cause the blades in the screw conveyor to fail due to excessive wear. Therefore, it is necessary to promptly detect the wear of the blades in the screw conveyor.

[0098] At present, the methods for detecting the blades of screw conveyors can be divided into disassembly detection methods and non-disassembly detection methods. Among them, the disassembly detection method is to open the outer shell or observation window of the screw conveyor, and the technician visually judges the degree of wear inside the screw conveyor, but this method takes a long time to detect, is very dependent on the professional ability of the detection personnel, and the detection results are highly subjective; the non-disassembly detection method is to obtain the internal wear of the screw conveyor through built-in sensors, but this method requires the design of a complex structure on the blades and blade shafts where sensors and signal lines can be installed, but this will lead to excessively high equipment costs, and this method can only detect the parts where the sensors are installed, and fails to achieve overall detection of the blades. From the above, it can be seen that the commonly used detection methods for the blades of screw conveyors are prone to low wear detection efficiency of screw conveyors and high cost of detection equipment.

[0099] In order to solve the above problems, the present invention proposes a wear detection method for a screw conveyor. The method can control the rotation state of the blade in the screw conveyor to be a constant speed rotation state when the working state of the screw conveyor is a starting state, and then, in the constant speed rotation state, the visual detection module in the screw conveyor is used to obtain a first acquisition video on one side of the blade and a second acquisition video on the other side of the blade. The first acquisition video and the second acquisition video can constitute a target acquisition video. After obtaining the target acquisition video, the rotation state of the blade can be controlled to be a stop rotation state, and in this stop rotation state, the above-mentioned target acquisition video is analyzed to obtain the wear result and wear position of the blade. Considering that when the blade is in a constant speed rotation state, the visual detection module is used to obtain the first acquisition video and the second acquisition video of the blade, and then the first acquisition video and the second acquisition video are composed of the target acquisition video. At this time, the blade is controlled to be in a stop rotation state so as to analyze the target acquisition video to achieve the purpose of determining the wear result and wear position of the blade, so as to solve the technical problems of low wear detection efficiency of the screw conveyor and high cost of detection equipment, and achieve the technical effect of improving the wear detection efficiency of the screw conveyor and controlling the low cost of detection equipment.

[0100] Figure 2 1 is a flow chart of a wear detection method for a screw conveyor based on visual activated carbon according to an embodiment of the present invention, and the flow chart may include the following steps:

[0101] Step S201, after the screw conveyor for conveying activated carbon stops operating and the internal material is discharged, the detection window steel plate of the conveyor shell is removed, the visual inspection module is installed in the guide groove of the screw conveyor, and then the window steel plate is installed to the shell of the screw conveyor.

[0102] In this embodiment, the visual inspection module is installed in the guide groove of the screw conveyor. The guide groove exists on the shell of the screw conveyor, and the structure of the guide groove is a T-shaped groove. The structure of the visual inspection module is also a T-shaped structure.

[0103] For example, the guide groove on the outer shell of the screw conveyor is a T-shaped groove, and the visual inspection module has a T-shaped structure corresponding to the T-shaped groove, thereby limiting the visual inspection module to move only along the axial direction of the screw conveyor.

[0104] Step S202, start the screw conveyor, make the blades of the screw conveyor rotate at a constant speed, push the visual inspection module to move along a straight line, realize video acquisition of the blades, and when the sampling of one side of the blade is completed, control the blades of the screw conveyor to rotate at a constant speed in the opposite direction to sample the other side of the blade.

[0105] In this embodiment, the screw conveyor is started to rotate the blades of the screw conveyor at a constant speed, pushing the visual inspection module to move in a straight line, and photographing the wear and damage on one side of the blade; when the visual inspection module moves to the other end and completes the video sampling of one side of the blade, the screw conveyor blades are rotated in the opposite direction at a constant speed, pushing the visual inspection module to move in a straight line in the opposite direction, and photographing the wear and damage on the other side of the blade.

[0106] Step S203, when the visual inspection module completes the video sampling, the blades of the screw conveyor stop rotating. At this time, the visual inspection module is located in the guide groove of the inspection window steel plate. The window steel plate is removed and the visual inspection module is taken out.

[0107] Step S204: Analyze and process the video collected by the visual detection module to obtain the wear and damage of the blade and determine the location of the damage.

[0108] In this embodiment, the video collected by the visual detection module is analyzed and processed. On the one hand, when the blade is damaged, carbon powder may adhere to the damaged area, and the damage condition can be obtained by detecting the carbon powder area on the blade; on the other hand, when carbon powder is not adhered to the damaged area, the degree of wear and damage can be detected through an algorithm.

[0109] For example, if carbon powder adheres to the blade, the area where carbon powder adheres can be determined from the target acquisition video. By performing damage detection on the area where carbon powder adheres, the wear result can be obtained. The principle of damage detection through the area where carbon powder adheres is as follows: after a large number of experiments, the relationship between the area where carbon powder adheres and the damage is determined, the acquired image information is grayed out, and since the gray value of the carbon powder area is relatively low, these areas are segmented out through a threshold segmentation algorithm, and damage is identified based on the area of ​​these areas.

[0110] For another example, if there is no carbon powder adhered to the damaged area, further inspection of the damaged area is required. The principle of detecting the damaged area without carbon powder adhered is: by constructing data sets with different wear degrees and different damages, the neural network is trained to obtain a model that can accurately identify the degree of wear and damage, and then the collected video is input into the model to detect the wear condition in the blade.

[0111] Optionally, the location of the damage is determined by the time when the damage appears in the video. The timing starts from when the visual inspection module starts to be pushed by the blade. Suppose that after t seconds, the damage appears at the midline position of the image. If ≥ the length C of the screw conveyor, the damage is located at the distance from the start point of the detection mm; if < the length of the screw conveyor C, the damage is located at the distance from the detection starting point Millimeters. Among them, n is used to represent the speed of the screw conveyor blades, and the unit is revolutions per minute.

[0112] In an embodiment of the present invention, the wear detection method of a screw conveyor can be applied to a wear detection system of a screw conveyor. Figure 3 is a schematic diagram of a wear detection system for a screw conveyor based on visual activated carbon according to an embodiment of the present invention, such as Figure 3 As shown, the system includes: a screw conveyor 301, a visual detection module 302 and a computer 303. The computer 303 is used to process the video, and an image processing module and various data algorithm modules are set in the computer.

[0113] Optionally, the inner surface of the outer shell of the screw conveyor 301 is processed with a T-slot for installing the visual inspection module 302. Considering the feasibility of processing, the surface of the outer shell with the T-slot is made of multiple steel plates, and each steel plate is processed with a T-slot; considering the sealing performance of the screw conveyor outer shell, sealant is applied to the joints of the steel plates; since the sealing groove of the screw conveyor outer shell is made of many steel plates, in order to ensure that the visual inspection module can move smoothly and avoid jamming, the T-shaped structure on the outer shell of the visual inspection module has a chamfer; the visual inspection module can be used for the collection and storage of video of the screw conveyor blades.

[0114] Further, Figure 4 is a schematic diagram of a visual detection module in a wear detection system for a screw conveyor according to an embodiment of the present invention, such as Figure 4 As shown, the left side shows the appearance of the visual detection module, and the right side shows the internal structure of the visual detection module, wherein the visual detection module includes: a protective shell 401, a camera 402, a lighting lamp 403 and a roller 404.

[0115] The protective shell 401 is used to protect the visual detection module.

[0116] Optionally, the T-shaped structure on the housing of the visual inspection module has a chamfered structure.

[0117] Optionally, in order to prevent residual carbon powder in the screw conveyor from damaging the electronic equipment inside the visual inspection module, the protective shell should be completely sealed; the two end faces of the protective shell perpendicular to the axis of the screw conveyor are made of transparent materials so that the lighting and camera can perform lighting and video sampling.

[0118] The camera 402 is used to store the collected video, export the video after the detection is completed, and process and analyze it, and has a storage function.

[0119] Optionally, it is necessary to set the angle between the axis of the camera and the axis of the lighting lamp so that the area photographed by the camera has sufficient brightness.

[0120] The lighting lamp 403 is used to provide light to brighten the surrounding environment.

[0121] The roller 404 is used to facilitate the movement of the visual inspection module.

[0122] Optionally, the visual inspection module needs to have two rollers, which are respectively installed on two diagonal corners of the protective shell. When the blades of the screw conveyor push the visual inspection module to reciprocate, the rollers are in direct contact with the blades and transmit the motion.

[0123] Optionally, in order to prevent the transparent material on the end face of the protective shell from affecting the camera sampling due to the light emitted by the reflected illuminator, the protective shell needs to be divided into two cavities using opaque material, and the camera and illuminator are installed respectively. Since it is necessary to sample the two surfaces of the blades of the screw conveyor, two cameras and two illuminators need to be installed, and they need to be arranged in opposite directions in the visual inspection module.

[0124] In this embodiment, Figure 5 is a schematic diagram of determining the maximum detection speed of a screw conveyor blade according to an embodiment of the present invention, such as Figure 5 As shown, the schematic diagram includes a screw conveyor blade 501. In order to ensure that the visual detection module can capture the complete screw conveyor blade video, that is, there is no blind area between the two frames of the video, the speed of the screw conveyor blade should be lower than the threshold value n max , and the threshold can be determined according to the following formula:

[0125]

[0126] In the above formula, γ is used to represent the field of view of the camera lens, f is used to represent the distance from the camera lens to the blade, R is used to represent the distance between the camera axis and the screw conveyor axis, and x is used to represent the frame rate of the camera. After the screw conveyor blade is represented as a straight line, the ray emitted by the field of view angle has two intersections with the straight line: the first intersection and the second intersection. With the camera as the origin of the rectangular coordinate system, the abscissa of the first intersection is smaller than the abscissa of the second intersection. Then the ordinate of the first intersection can be represented by a, and the ordinate of the second intersection can be represented by b.

[0127] In this embodiment, Figure 6 is a schematic diagram of determining the angle between the illumination axis and the camera axis according to an embodiment of the present invention, such as Figure 6 As shown, the camera and the lighting lamp are installed in the visual inspection module, and the roller is installed on the housing of the visual inspection module. In order to ensure that the lighting lamp can provide good lighting conditions for camera sampling, the angle formed by the axis of the camera and the axis of the lighting lamp should satisfy the following formula:

[0128]

[0129] In the above formula, S is used to represent the distance between the two intersections formed by the camera axis, the camera axis, the lighting axis and the vertical plane where the center of the roller is located. L is used to represent the distance from the center of the roller to the axis of the camera. α is used to represent the helix angle of the blade, and the helix angle of the blade can be called the helix angle of the spiral blade. r is used to represent the radius of the roller. β is used to represent the angle formed by the camera axis and the lighting axis. P is used to represent the pitch of the spiral blade.

[0130] In this embodiment, when the working state of the screw conveyor is the starting state, the rotation state of the blade in the screw conveyor can be controlled to be a constant speed rotation state, and then in the constant speed rotation state, the visual detection module in the screw conveyor is used to obtain a first acquisition video on one side of the blade and a second acquisition video on the other side of the blade. The first acquisition video and the second acquisition video can constitute a target acquisition video. After obtaining the target acquisition video, the rotation state of the blade can be controlled to be a stopped rotation state, and in this stopped rotation state, the above-mentioned obtained target acquisition video is analyzed to obtain the wear result and wear position of the blade. Considering that when the blade is in a constant speed rotation state, the visual detection module is used to obtain the first acquisition video and the second acquisition video of the blade, and then the first acquisition video and the second acquisition video are composed of the target acquisition video, the blade is controlled to be in a stopped rotation state at this time, so as to analyze the target acquisition video to achieve the purpose of determining the wear result and wear position of the blade, so as to solve the technical problems of low wear detection efficiency of the screw conveyor and high cost of detection equipment, and achieve the technical effect of improving the wear detection efficiency of the screw conveyor and controlling the low cost of detection equipment.

[0131] According to an embodiment of the present invention, a wear detection device for a screw conveyor is provided. It should be noted that the wear detection device for a screw conveyor can be used to execute a wear detection method for a screw conveyor in an embodiment.

[0132] Figure 7 Schematic diagram of a wear detection device for a screw conveyor according to an embodiment of the present invention. Figure 7 As shown, a wear detection device 700 for a screw conveyor may include: a first control unit 701 , a first acquisition unit 702 , a composition unit 703 , a second control unit 704 and an analysis unit 705 .

[0133] The first control unit 701 is used for controlling the rotation state of the blades in the screw conveyor to be a constant speed rotation state in response to the working state of the screw conveyor being a start state, wherein the constant speed rotation state is used to indicate that the blades rotate at a target speed.

[0134] The first acquisition unit 702 is used to acquire a first acquired video of one side of the blade and a second acquired video of the other side corresponding to the one side of the blade by using a visual detection module in the screw conveyor under a constant speed rotation state.

[0135] The composition unit 703 is used to combine the first collected video and the second collected video to form a target collected video of the leaf.

[0136] The second control unit 704 is used to control the rotation state of the blade to stop rotating based on the target acquisition video.

[0137] The analysis unit 705 is used to analyze the target acquisition video in a stopped rotation state to obtain the wear result and wear position of the blade, wherein the wear result is used to characterize the wear degree of the blade.

[0138] Optionally, the analysis unit 705 may include: a detection module, used to perform carbon powder detection on the target captured video in a stopped rotating state to obtain a first detection result, wherein the first detection result is used to characterize whether carbon powder adheres to the blade; a first determination module, used to determine the wear result of the blade based on the first detection result.

[0139] Optionally, the first determination module may include: a first acquisition submodule, used to obtain an initial adhesion image of carbon powder adhering to the blade from the target acquisition video in response to the first detection result that carbon powder is adhered to the blade; a second acquisition submodule, used to perform grayscale processing on the initial adhesion image to obtain a target adhesion image; a segmentation submodule, used to segment the target adhesion image based on the adhesion area of ​​the carbon powder on the blade to obtain a carbon powder area where the carbon powder is adhered to the blade; the first determination submodule, used to determine the wear result based on the carbon powder area.

[0140] Optionally, the first determination module may also include: an analysis submodule, for, in response to the first detection result that carbon powder is not adhered to the blade, inputting the target acquisition video into the wear detection model of the screw conveyor for analysis to obtain a wear result, wherein the wear detection model is established through multiple acquisition images in the historical target acquisition video of the blade.

[0141] Optionally, the analysis unit 705 may also include: a first acquisition module, used to acquire a target image in a target acquisition video and a target time corresponding to the acquired target image in a stopped rotation state; a second determination module, used to determine the target position of the blade based on the target rotation speed, target time and the pitch of the blade; a third determination module, used to determine the position at a first length away from the detection point in the target image as a wear position in response to the target position being greater than or equal to the length of the screw conveyor; and a fourth determination module, used to determine the position at a second length away from the detection point in the target image as a wear position in response to the target position being less than the length of the screw conveyor.

[0142] Optionally, the device also includes: a visual inspection module installed in a guide groove of the screw conveyor, the guide groove is on the outer shell of the screw conveyor, and the structure of the guide groove is a T-slot, and the structure of the visual inspection module is a T-slot corresponding to the T-slot.

[0143] Optionally, the visual inspection module includes: a protective shell, a camera, a lighting lamp and a roller, wherein the protective shell contains two cavities, in which the camera and the lighting lamp are installed respectively.

[0144] Optionally, the device also includes: a second acquisition unit, used to acquire the angle between the axis of the camera and the axis of the lighting lamp; an adjustment unit, used to adjust the angle to a target angle, wherein the target angle is determined by the axis of the camera, the pitch of the blade, the distance from the center of the roller to the axis of the camera, the helix angle of the blade, and the radius of the roller.

[0145] Optionally, the first acquisition unit 702 may include: a second acquisition module, which is used to acquire the first captured video and the second captured video using a visual detection module in response to a target speed being less than a speed threshold corresponding to the target speed in a constant rotation state, wherein the speed threshold is determined by the field of view angle of the camera lens in the visual detection module and the helix angle of the blade.

[0146] In this embodiment, in response to the working state of the screw conveyor being the start state, the first control unit controls the rotation state of the blade in the screw conveyor to be a constant speed rotation state, wherein the constant speed rotation state is used to characterize that the blade rotates at a target speed; the first acquisition unit uses the visual detection module in the screw conveyor to acquire a first acquisition video of one side of the blade and a second acquisition video of the other side corresponding to one side of the blade in the constant speed rotation state; the composition unit combines the first acquisition video and the second acquisition video to form a target acquisition video of the blade; the second control unit controls the rotation state of the blade to be a stopped rotation state based on the target acquisition video; the analysis unit analyzes the target acquisition video in the stopped rotation state to obtain the wear result and wear position of the blade, wherein the wear result is used to characterize the degree of wear of the blade, thereby solving the technical problems of low wear detection efficiency of the screw conveyor and high cost of detection equipment, and achieving the technical effect of improving the wear detection efficiency of the screw conveyor and controlling the low cost of detection equipment.

[0147] An embodiment of the present invention further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0148] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0149] An embodiment of the present invention further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0150] An embodiment of the present invention further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0151] An embodiment of the present invention further provides a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0152] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0153] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0154] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units can be a logical function division, and there can be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0155] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0156] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0157] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0158] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting wear of a screw conveyor, characterized in that: include: In response to the working state of the screw conveyor being the start state, controlling the rotation state of the blades in the screw conveyor to be a constant speed rotation state, wherein the constant speed rotation state is used to indicate that the blades rotate at a target speed; In the constant speed rotation state, using the visual detection module in the screw conveyor, a first captured video of one side of the blade and a second captured video of the other side corresponding to the one side of the blade are acquired; The first collected video and the second collected video form a target collected video of the leaf; Based on the target acquisition video, controlling the rotation state of the blade to a stop rotation state; In the stopped rotation state, the target acquisition video is analyzed to obtain the wear result and wear position of the blade, wherein the wear result is used to characterize the wear degree of the blade.

2. The method according to claim 1, characterized in that: In the stopped rotation state, the target acquisition video is analyzed to obtain the wear result of the blade, including: In the stopped rotation state, performing a carbon powder detection on the target acquisition video to obtain a first detection result, wherein the first detection result is used to indicate whether carbon powder adheres to the blade; Based on the first detection result, a wear result of the blade is determined.

3. The method according to claim 2, characterized in that Determining the wear result of the blade based on the first detection result includes: In response to the first detection result that the carbon powder is adhered to the blade, acquiring an initial adhesion image of the carbon powder adhering to the blade from the target acquisition video; Performing grayscale processing on the initial adhesion image to obtain a target adhesion image; Based on the adhesion area of ​​the toner on the blade, segmenting the target adhesion image to obtain the toner area where the toner adheres to the blade; Based on the carbon powder area, the wear result is determined.

4. The method according to claim 2, characterized in that: Determining the wear result of the blade based on the first detection result includes: In response to the first detection result that the carbon powder is not adhered to the blade, the target acquisition video is input into the wear detection model of the screw conveyor for analysis to obtain the wear result, wherein the wear detection model is established through multiple acquisition images in the historical target acquisition video of the blade.

5. The method according to claim 1, characterized in that In the stopped rotation state, analyzing the target acquisition video to obtain the wear position of the blade includes: In the stopped rotation state, acquiring a target image in the target acquisition video and a target time corresponding to acquiring the target image; determining a target position of the blade based on the target rotation speed, the target time and the pitch of the blade; In response to the target position being greater than or equal to the length of the screw conveyor, determining a position at a first length away from a detection point in the target image as the wear position; In response to the target position being smaller than the length of the screw conveyor, a position at a second length away from the detection point in the target image is determined as the wear position.

6. The method according to claim 1, characterized in that The method also includes: the visual inspection module is installed in the guide groove of the screw conveyor, the guide groove is on the shell of the screw conveyor, and the structure of the guide groove is a T-slot, and the structure of the visual inspection module is a T-shaped structure corresponding to the T-slot.

7. The method according to claim 1, characterized in that The visual inspection module includes: a protective shell, a camera, a lighting lamp and a roller, wherein the protective shell contains two cavities, in which the camera and the lighting lamp are installed respectively.

8. The method according to claim 7, characterized in that The method further comprises: Obtaining the angle between the axis of the camera and the axis of the lighting lamp; The angle is adjusted to a target angle, wherein the target angle is determined by the axis of the camera, the pitch of the blade, the distance from the center of the roller to the axis of the camera, the helix angle of the blade, and the radius of the roller.

9. The method according to claim 1, characterized in that: In the constant speed rotation state, using the visual detection module in the screw conveyor, a first captured video of one side of the blade and a second captured video of the other side corresponding to the one side of the blade are obtained, including: In the constant speed rotation state, in response to the target rotation speed being less than a rotation speed threshold corresponding to the target rotation speed, the first captured video and the second captured video are acquired using the visual detection module, wherein the rotation speed threshold is determined by the field of view angle of the camera lens in the visual detection module and the helix angle of the blade.

10. A wear detection device for a screw conveyor, characterized in that: include: A first control unit is used for controlling the rotation state of the blades in the screw conveyor to be a constant speed rotation state in response to the working state of the screw conveyor being a start state, wherein the constant speed rotation state is used to indicate that the blades rotate at a target speed; A first acquisition unit is used to acquire, in the constant speed rotation state, a first acquisition video of one side of the blade and a second acquisition video of the other side corresponding to the one side of the blade by using a visual detection module in the screw conveyor; A composition unit, configured to combine the first collected video and the second collected video to form a target collected video of the blade; A second control unit is used to control the rotation state of the blade to stop rotating based on the target acquisition video; The analysis unit is used to analyze the target acquisition video in the stopped rotation state to obtain the wear result and wear position of the blade, wherein the wear result is used to characterize the wear degree of the blade.

Images