A visual identification and positioning system for a mine belt conveyor belt tearing fault

Abstract

The present application relates to the technical field of mine belt conveyor, and particularly relates to a visual identification and positioning system for tear fault of a mine belt conveyor. The system comprises an industrial camera, a belt speed sensor and an industrial computer. The industrial camera is fixedly installed above a return conveyor belt and used for collecting images of surface cracks of the conveyor belt. The belt speed sensor is used for collecting the moving speed of the conveyor belt in real time. The industrial computer is connected with the industrial camera and the belt speed sensor. The industrial computer judges whether the conveyor belt has a tear fault according to the images of surface cracks of the conveyor belt collected by the industrial camera, and collects the moving speed of the conveyor belt collected by the belt speed sensor. An industrial frequency converter is controlled by a logic controller. The industrial frequency converter controls a drum motor to align the position of the conveyor belt with a maintenance area.

Description

Technical Field

[0001] This invention relates to the field of mining belt conveyor technology, specifically a visual recognition and location system for conveyor belt tearing faults in mining belt conveyors. Background Technology

[0002] Currently, belt conveyors are widely used in the field of material transportation in mines due to their advantages of large capacity and long-distance transportation. However, during material transportation, impurities from the material or sharp objects such as angle iron that fall off the belt due to vibration and become stuck between the belt and the support can easily scratch the bearing surface of the conveyor belt. Scratches can be detected using tear detection devices such as mechanical pull-rope detection devices, X-ray devices, and weighing sensor detection devices. However, due to technological limitations, in practical applications, there are situations where the belt is torn but the tear detection device fails to detect it. Furthermore, because conveyor belts are long, when small-scale tears occur, maintenance workers find it difficult to locate the fault, which seriously affects maintenance timeliness and consequently impacts enterprise production efficiency. Summary of the Invention

[0003] This invention provides a visual recognition and positioning system for conveyor belt tearing faults in mining conveyors, enabling workers to repair belts promptly and conveniently, preventing belt cracks from worsening and causing belt slippage accidents, reducing economic losses, and ensuring personnel safety.

[0004] This invention adopts the following technical solution: a visual recognition and location system for tearing faults in mining conveyor belts, comprising: An industrial camera, which is fixedly mounted above the return conveyor belt, is used to capture images of cracks on the surface of the belt conveyor. A belt speed sensor, which is used to collect the movement speed of the conveyor belt in real time; An industrial computer is connected to an industrial camera and a belt speed sensor. The industrial computer determines whether the conveyor belt has torn based on the crack images on the surface of the conveyor belt captured by the industrial camera, and collects the movement speed of the conveyor belt from the belt speed sensor. An industrial frequency converter, controlled by a logic controller, controls a roller motor to align the location of the conveyor belt malfunction with the maintenance area.

[0005] In some embodiments, the step of an industrial computer determining whether a conveyor belt has experienced a tearing failure includes: Segmented images of conveyor belt cracks were obtained using PCNN; Extract the region of interest; Maximum contour selection and calibration of the crack; Calculate the crack area; A crack area exceeding a threshold is considered a tear.

[0006] In some embodiments, the location of the conveyor belt failure is aligned with the maintenance area using the following method. S1: Paste the calibration image below the conveyor belt, and mark two lines, M and N, on the calibration image, with a distance between them of [missing information]. ; S2: Adjust the angle and focal length of the industrial camera so that the image edge coincides exactly with the M and N marking lines, while keeping the position of the industrial camera unchanged; S3: Take a test image and calculate the horizontal pixel value of the image, denoted as... ; S4: Calculate the scale , ; S5: According to the scale Calculate the actual distance from the geometric center of the conveyor belt crack to the marked line: S2 represents the pixel distance from the geometric center of the conveyor belt crack to the edge of the image; S6: Calculate stopping distance , The angle between the conveyor belt and the horizontal direction; S7: Calculate the downtime based on the downtime distance, input the downtime into the logic controller, and make it control the power-on time of the roller motor to align the torn position of the conveyor belt with the maintenance area.

[0007] In some embodiments, step S7 includes: S71: Calculate the number of revolutions n required for the drive motor based on the stopping distance. ; S72: Calculate the drive motor energizing time t based on the stopping distance and the current conveyor belt speed v measured by the speed sensor. ; S73: Calculate downtime. ,in f is the frequency of the frequency converter. This represents the number of pole pairs of the motor. S74: Input the downtime t0 into the logic controller so that it controls the energization time t of the roller motor and aligns the torn position of the conveyor belt with the maintenance area.

[0008] In some embodiments, the industrial camera is at a 45° angle to the return speed direction of the return conveyor belt.

[0009] In some embodiments, a lighting device is also included, which is a linear industrial lighting device fixed above the return conveyor belt and below the industrial camera, and at a 135° angle to the speed direction of the return conveyor belt.

[0010] In some embodiments, the belt speed sensor is mounted above the return conveyor belt and fixed on the idler bracket, and the idler bracket has a tension spring at its tail end so that the measuring wheel of the belt speed sensor is in close contact with the surface of the return conveyor belt.

[0011] In some embodiments, the maintenance area is located at the tail of the machine, away from the drive drum motor.

[0012] Compared with the prior art, the present invention has the following beneficial effects: In this invention, the conveyor belt tear fault identification and positioning system comprises two main parts: tear fault identification and fault point positioning. The tear fault identification part collects image information of the lower surface of the conveyor belt and transmits the image information back to an industrial computer. The industrial computer performs edge segmentation processing on the image information and determines whether a tear fault has occurred. If a fault is determined to have occurred, it automatically measures the distance from the geometric center of the tear to the marked edge of the image and converts it into an actual distance according to a calibrated scale. Then, adding this distance to the distance from the camera's calibrated position to the center of the repair area yields the distance that the tear position needs to be moved to align with the repair area. Furthermore, by combining the current conveyor belt speed returned by the belt speed sensor, the number of rotations required for the drive roller can be calculated. Then, the PLC combined with the frequency converter controls the drive roller motor to automatically align the conveyor belt tear position with the marked repair area, facilitating timely repair by personnel. Attached Figure Description

[0013] Figure 1 A schematic diagram of the alignment of the maintenance area provided as an example of the present invention; Figure 2 A flowchart of PCNN image segmentation processing provided as an example of the present invention; Figure 3 A flowchart for conveyor belt tearing fault identification and location provided as an example of the present invention; Figure 4 This is a schematic diagram of industrial camera distance calibration provided as an example of the present invention; Figure 5 This invention provides an industrial camera calibration pattern as an example of the present invention. Figure 6 This is a schematic diagram of a conveyor belt tear fault identification and location system provided as an example of the present invention; Explanation of reference numerals in the attached figures: 1. Industrial camera bracket; 2. Industrial camera; 3. Maintenance area; 4. Logic controller; 5. Frequency converter; 6. Industrial computer; 7. Return conveyor belt; 8. Belt speed sensor; 9. Belt speed sensor bracket; 101. Industrial camera field of view; 102. Drive roller motor; 103. Top view of maintenance area; L1. Distance from the center of the maintenance area to the center of the first idler frame; L2. Distance from the first idler frame to the marker line M; 1. Angle between the conveyor belt and the horizontal direction; D. Diameter of the drive roller; 401. Camera calibration grid diagram; 402. Computer-processed image of the conveyor belt crack; S1. Actual distance from the camera CMOS (sensor) to the bottom of the conveyor belt; S2. Horizontal distance from the geometric center of the crack in the image to the edge of the field of view; S3. Vertical distance from the geometric center of the crack in the image to the edge of the field of view; M. Marker line on the right side of the camera; N. Marker line on the left side of the camera; L'. Actual distance between marker lines M and N; L''. Horizontal pixel value of the image. Detailed Implementation

[0014] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of the present invention. However, the present invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0015] In the description of this invention, it should be understood that the terms "center", "vertical", "horizontal", "above", "below", etc., are used to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.

[0016] Furthermore, in this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "fixation," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection such as a bolted connection, or a connection welded together; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0017] This embodiment provides a conveyor belt tear fault identification and location system, which has the advantages of identifying conveyor belt tear faults and aligning the tear location with the maintenance area, reducing economic losses, improving conveyor belt maintenance efficiency, and ensuring personnel safety. The following will be described in detail with reference to the accompanying drawings.

[0018] like Figure 6 As shown, a visual recognition and location system for tearing faults in mining conveyor belts includes: Industrial camera 2, which is fixedly installed above the return conveyor belt 7, is used to collect images of cracks on the surface of the belt conveyor. Belt speed sensor 8, which is used to collect the movement speed of the conveyor belt in real time; Industrial computer 6 is connected to industrial camera 2 and belt speed sensor 8. It determines whether the conveyor belt has torn based on the crack image of the conveyor belt surface collected by industrial camera 2, and collects the movement speed of the conveyor belt collected by belt speed sensor 8. Industrial frequency converter 5, which is controlled by logic controller 4, controls the roller motor to align the location of the conveyor belt failure with the maintenance area 3.

[0019] The industrial camera 2 and the return speed direction of the return conveyor belt 7 form a 45° angle.

[0020] It also includes lighting equipment, which is a linear industrial lighting device, fixed above the return conveyor belt 7 and below the industrial camera 2, and at a 135° angle to the speed direction of the return conveyor belt 7.

[0021] The belt speed sensor 8 is installed above the return conveyor belt 7 and fixed on the idler bracket. The idler bracket has a tension spring at the tail end, so that the measuring wheel of the belt speed sensor 8 is in close contact with the surface of the return conveyor belt.

[0022] Maintenance area 3 is located at the tail of the machine, away from the drive drum motor.

[0023] For identification of conveyor belt tearing faults, please refer to [reference needed]. Figure 2 .

[0024] The conveyor belt image captured by the industrial camera is input into the algorithm. An appropriate number of iterations is set, and the algorithm iterates through steps (1) to (5) to output the segmented image. The computer program determines whether a tearing fault has occurred based on the segmented image. The specific discrimination method is as follows: 1. Obtain the segmentation image of the conveyor belt crack through PCNN; 2. Extract the ROI (Region of Interest) using the contour function in OpenCV; 3. Calculate the crack area by counting the pixels within the ROI; 4. A crack area exceeding the threshold is considered a tear.

[0025] If a tearing fault occurs, the shutdown parameters are calculated; otherwise, the next frame is processed.

[0026] The PCNN model is developed based on the neuron model proposed from the phenomenon of synchronous pulse firing of neurons in the visual cortex of mammals such as cats. A neuron consists of three parts: input, modulation, and pulse generator. Its model can be described by the following equation: (1) (2) (3) (4) (5) Wherein, equation (1) represents the feedback input part of the model, Indicates coordinates The feedback input of the neuron at the nth iteration. This represents the external stimulus received by the neuron, corresponding to the image in coordinates. The grayscale value of the pixel at that location; in equation (2) This represents the input portion of a neuron's connection. and Equation (3) represents the link coefficients between neurons; Equation (3) represents the modulation part. This represents the internal activity terms of a neuron, which are fed back by feedback. and link input Modulation obtained, In equation (4), the modulation coupling coefficient is represented. Equation (5) represents the dynamic ignition threshold of the neuron; Equation (5) represents the neuron's impulse generation part, which is determined by the neuron's internal activity terms. With dynamic ignition threshold The magnitude of the signal is compared to determine whether the neuron produces a pulse output. Greater than At that time, the neuron ignites and outputs... ,otherwise .parameter , , These represent the amplification factors for the feedback input, the link input, and the dynamic threshold, respectively.

[0027] PCNN is composed of individual neurons arranged in a matrix. M and W Information transmission between neurons is typically local and follows a Gaussian-normal distribution, but this is not strictly required. (Matrix) During initialization, all matrix elements are set to 0. The initial value of the elements can be 0, or it can be set to some larger value as needed. Any excited neuron will be excited in the first loop, resulting in a large threshold. Several more loops are needed for the threshold to decay enough to excite the neuron again. The latter tends to occur around these initial loops with smaller amounts of information.

[0028] For tear location information, please refer to [reference needed]. Figure 1 and Figure 4 .

[0029] When the computer determines a tearing fault has occurred based on the image transmitted from the industrial camera, it calculates an important parameter S2, which represents the pixel distance from the geometric center of the conveyor belt tear to the image edge. Multiplying this parameter by the actual scale yields the actual distance from the geometric center of the conveyor belt tear to the conveyor belt positioning point M. The scale is determined by camera calibration, and the specific steps are as follows (refer to...). Figure 4 : 1. Paste calibration image 401 below the conveyor belt and draw two marker lines, M and N, with the distance between them being known. .

[0030] 2. Adjust the camera angle and focal length so that the edge of the image coincides exactly with the M and N marking lines.

[0031] 3. Lock the camera to keep it in a fixed position.

[0032] 4. Take a test image and calculate the horizontal pixel value of the image, denoted as . .

[0033] 5. Scale Then it is represented as .

[0034] Therefore, the actual distance from the geometric center of the conveyor belt crack to the marked line is calculated by the following formula: (6) Calculate stopping distance: Reference Figure 1 The stopping distance is calculated using the following formula, where The angle between the conveyor belt and the horizontal direction: (7) Calculate the number of revolutions n required for the drive motor based on the stopping distance: (8) The driving motor energizing time t is calculated based on the stopping distance and the current conveyor belt speed v measured by the speed sensor: (9) Given inverter frequency Calculate motor speed ,in The number of pole pairs of the motor: (10) Finally, calculate the downtime t0: (11) Finally, the downtime t0 is input into the PLC to control the power-on time of the drive motor and align the torn position of the conveyor belt with the maintenance area.

[0035] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0036] The above-described embodiments are merely one implementation of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the scope of protection of the present invention. Therefore, the scope of protection of this invention should be determined by the appended claims.

Claims

1. A visual recognition and location system for tear faults in mining conveyor belts, characterized in that, include: An industrial camera (2) is fixedly installed above the return conveyor belt (7) to collect images of cracks on the surface of the conveyor belt. Belt speed sensor (8), the belt speed sensor (8) is used to collect the movement speed of the conveyor belt in real time; An industrial computer (6) is connected to an industrial camera (2) and a belt speed sensor (8). The industrial computer (6) determines whether the conveyor belt has a tearing fault based on the crack image of the conveyor belt surface collected by the industrial camera (2) and collects the movement speed of the conveyor belt by the belt speed sensor (8). The steps for the industrial computer (6) to determine whether the conveyor belt has torn include: Segmented images of conveyor belt cracks were obtained using PCNN; Extracting the Region of Interest (ROI) using the contour function in OpenCV; Calculate the crack area by counting the pixels within the ROI; A crack area exceeding a threshold is considered a tear. Industrial frequency converter (5), which is controlled by logic controller (4), controls the drive motor to align the location of the conveyor belt failure with the maintenance area (3). Align the location of the conveyor belt failure with the maintenance area using the following method (3). S1: Paste the calibration image (401) below the conveyor belt, and mark two lines, M and N, on the calibration image (401), with a distance between them of . ; S2: Adjust the angle and focal length of the industrial camera (2) so that the edge of the image coincides with the M and N marking lines, and keep the position of the industrial camera (2) unchanged; S3: Take a test image and calculate the horizontal pixel value of the image, denoted as... ; S4: Calculate the scale , ; S5: According to the scale Calculate the actual distance from the geometric center of the conveyor belt crack to the marker line: S2 represents the pixel distance from the geometric center of the conveyor belt crack to the edge of the image; S6: Calculate stopping distance , L1 is the angle between the conveyor belt and the horizontal direction; L2 is the distance from the center of the roller to the center of the first idler; L2 is the distance from the center of the first idler to the edge of the field of view of the industrial camera. S7: Calculate the downtime based on the downtime distance, input the downtime into the logic controller (4), so that it controls the power-on time of the drive motor and aligns the torn position of the conveyor belt with the maintenance area; Step S7 includes: S71: Calculate the number of revolutions n required for the drive motor based on the stopping distance. D is the diameter of the drive roller; S72: Calculate the drive motor energizing time t based on the stopping distance and the current conveyor belt speed v measured by the belt speed sensor (8). ; S73: Calculate downtime. ,in f is the frequency of the frequency converter. This represents the number of pole pairs of the motor. S74: Input the downtime t0 into the logic controller (4) to control the power-on time t of the drive motor and align the torn position of the conveyor belt with the maintenance area (3).

2. The visual recognition and positioning system for tear faults in mining conveyor belts according to claim 1, characterized in that, The industrial camera (2) and the return speed direction of the return conveyor belt (7) are at a 45° angle.

3. The visual recognition and positioning system for tear faults in mining belt conveyors according to claim 1, characterized in that, It also includes lighting equipment, which is a linear industrial lighting device, fixed above the return conveyor belt (7) and below the industrial camera (2), and at a 135° angle to the speed direction of the return conveyor belt (7).

4. The visual recognition and positioning system for tear faults in mining belt conveyors according to claim 1, characterized in that, The belt speed sensor (8) is installed above the return conveyor belt (7) and fixed on the idler bracket. The idler bracket has a tension spring at the tail end so that the measuring wheel of the belt speed sensor (8) is in close contact with the surface of the return conveyor belt.

5. The visual recognition and positioning system for tear faults in mining conveyor belts according to claim 1, characterized in that, The maintenance area (3) is located at the tail of the machine, away from the drive motor.

Images