Industrial vision-based intelligent speed control method and system for coal mine conveyors

Abstract

The application provides a coal mine conveyor intelligent speed regulation control method and system based on industrial vision, and relates to the technical field of conveyor control. In the application, a coal flow image sequence of a conveyor belt is acquired and restored to obtain a target coal flow contour image. Based on the target coal flow contour image, the distribution dispersion of the coal flow in the width direction of the conveyor belt and the accumulation thickness of the coal flow in the conveying direction are analyzed. Then, the distribution dispersion and the accumulation thickness are fused to generate a morphology description parameter. Subsequently, the electrical signal parameters of the driving motor of the underground coal mine conveyor are acquired and are coupled with the morphology description parameter synchronously to output a speed regulation control instruction. Finally, the speed regulation control instruction is sent to the driving motor of the underground coal mine conveyor to adjust the running speed of the conveyor belt. The technical scheme provided by the application not only realizes the adaptive matching of the conveyor belt speed and the real-time coal flow load morphology, but also improves the operation energy efficiency and stability of the transportation system.

Description

Technical Field

[0001] This application relates to the field of conveyor control technology, and in particular to an intelligent speed control method and system for coal mine conveyors based on industrial vision. Background Technology

[0002] With the improvement of intelligent mining technology in coal mines, higher requirements are placed on the efficiency, energy saving, and stable operation of underground coal transportation systems. Among these requirements, the operating speed of belt conveyors, as the main transportation equipment, is crucial for energy saving, consumption reduction, and equipment wear reduction, as it must be matched with the real-time coal flow rate.

[0003] In order to accurately and in real time perceive the actual state of coal flow in complex underground environments and dynamically adjust the speed of the conveyor accordingly, the current technical solution is a coal flow detection method based on laser scanning or radar ranging. This method uses a ranging device installed above the conveyor belt to scan and obtain the contour height information of the coal flow surface, thereby calculating the approximate cross-sectional area or volumetric flow rate of the coal flow, and generating a speed adjustment command based on this flow rate value to control the conveyor drive motor.

[0004] However, this method can only obtain the contour information of the coal flow in a single direction and cannot effectively perceive the uniformity of the coal flow distribution in the width direction of the conveyor belt, resulting in a deviation in the judgment of the actual load state. Secondly, the coal dust that permeates underground will seriously interfere with the propagation and reception of optical or radar ranging signals, causing the measurement data to be distorted and lacking robustness. Furthermore, this method does not conduct collaborative analysis with the real-time operating electrical parameters of the drive motor (such as current fluctuations), and cannot promptly identify sudden working conditions such as large pieces of coal, gangue blockage, or instantaneous overload. The speed regulation response is lagging, making it difficult to effectively protect the motor and mechanical transmission components while ensuring transportation efficiency. Summary of the Invention

[0005] This application provides an intelligent speed control method and system for coal mine conveyors based on industrial vision, which solves the problems of insufficient accuracy and timeliness in speed control caused by the single dimension of coal flow state perception, weak resistance to environmental interference, and insufficient coordination with the real-time load status of equipment in the prior art.

[0006] Firstly, this application provides an intelligent speed control method for coal mine conveyors based on industrial vision, including: A sequence of coal flow images from a conveyor belt is acquired, and visibility under coal dust interference is restored from the sequence of coal flow images to obtain a target coal flow contour image. Based on the target coal flow profile image, the distribution dispersion of the coal flow in the width direction of the conveyor belt is analyzed, and the accumulation thickness of the coal flow in the conveying direction is analyzed simultaneously. The morphological description parameters are generated by combining the distribution dispersion of the coal flow in the width direction of the conveyor belt with the accumulation thickness of the coal flow in the conveying direction. The electrical signal parameters of the drive motor of the underground coal mine conveyor are obtained, and the electrical signal parameters are synchronously coupled with the morphological description parameters to output speed control commands; The speed control command is sent to the drive motor of the underground coal mine conveyor to adjust the running speed of the conveyor belt.

[0007] Optionally, a sequence of coal flow images from the conveyor belt is acquired, and visibility restoration under coal dust interference is performed on the coal flow image sequence to obtain a target coal flow contour image, including: By using industrial vision devices deployed at predetermined locations on underground coal mine conveyors, images of coal flow on the conveyor belt, including those affected by coal dust, are collected and integrated to obtain a sequence of coal flow images on the conveyor belt. Based on the scattering characteristics of coal dust under mine lighting conditions, coal dust layer images and initial coal flow images are decomposed from the coal flow image sequence of the conveyor belt; The coal dust layer image is subjected to concentration assessment to generate a coal dust concentration distribution map; Based on the coal dust concentration distribution map, pixel-level illumination compensation is performed on the initial coal flow image to obtain an enhanced coal flow image after illumination compensation; Edge information is extracted from the enhanced coal flow image to obtain the target coal flow contour image.

[0008] Optionally, based on the target coal flow profile image, the distribution dispersion of the coal flow in the width direction of the conveyor belt is analyzed, and the accumulation thickness of the coal flow in the conveying direction is analyzed simultaneously, including: A coordinate system is established on the target coal flow profile image, with the horizontal axis corresponding to the width direction of the conveyor belt and the vertical axis corresponding to the conveying direction. The width of the conveyor belt is divided into multiple continuous width intervals along the horizontal axis, and the number of contour pixels of the target coal flow contour image in each width interval is counted to obtain coal flow width distribution data. Based on the degree of difference in the number of contour pixels in the coal flow width distribution data between different width intervals, the distribution dispersion of the coal flow in the width direction of the conveyor belt is analyzed. The target coal flow profile image is scanned line by line along the vertical axis, and the height of the upper edge point of the coal flow profile in each line is identified and recorded to obtain the coal flow height sequence along the conveying direction. Based on the changing trend of height values ​​in the coal flow height sequence, local high points of coal flow accumulation are identified, and the accumulation thickness of the coal flow in the conveying direction is analyzed based on the height values ​​of the local high points.

[0009] Optionally, the morphological description parameters are generated by integrating the distribution dispersion of the coal flow in the width direction of the conveyor belt with the accumulation thickness of the coal flow in the conveying direction, including: The dispersion of the coal flow distribution in the width direction of the conveyor belt is quantified to obtain a quantified value of the width dispersion. The thickness of the coal flow in the conveying direction is quantified to obtain a quantified thickness value; Based on the operating characteristics of the coal mine conveyor, a first fusion weight for the width discrete quantization value and a second fusion weight for the thickness quantization value are determined. Based on the first fusion weight, the width discrete quantification value is proportionally adjusted to obtain the width influence factor; Based on the second fusion weight, the thickness quantization value is proportionally adjusted to obtain the thickness influence factor; The width influence factor and the thickness influence factor are combined to calculate the morphological description parameters.

[0010] Optionally, based on the operating characteristics of the coal mine conveyor, a first fusion weight for the width discrete quantization value and a second fusion weight for the thickness quantization value are determined, including: The historical operating status data of the underground coal mine conveyor under various historical coal flow patterns are obtained. The historical operating status data includes historical width dispersion, historical accumulation thickness and corresponding historical motor energy consumption data. The influence of the historical width dispersion on the historical motor energy consumption data is analyzed to obtain the width influence correlation degree. The influence of the historical accumulation thickness variation on the historical motor energy consumption data was analyzed to obtain the thickness influence correlation degree. The sum of the width influence correlation degree and the thickness influence correlation degree is taken as the total influence correlation degree; The numerical ratio of the width influence correlation degree to the total influence correlation degree is determined as the first fusion weight, and the numerical ratio of the thickness influence correlation degree to the total influence correlation degree is determined as the second fusion weight.

[0011] Optionally, the electrical signal parameters of the drive motor of the underground coal mine conveyor are acquired, and the electrical signal parameters are synchronously coupled with the morphological description parameters to output a speed control command, including: Real-time acquisition of current and voltage data of the drive motor of the underground conveyor in the coal mine during operation, as electrical signal parameters; Extract current fluctuation characteristics reflecting instantaneous changes in motor load from the electrical signal parameters; Obtain the acquisition timestamp corresponding to the coal flow image sequence of the conveyor belt, and map the morphological description parameters to the same time base as the electrical signal parameters according to the conveyor belt running speed; The morphological description parameters mapped to the same time base are paired and combined with the current fluctuation characteristics; Based on the preset coupling relationship, the morphological description parameters and current fluctuation characteristics after pairing are jointly calculated to obtain a comprehensive state index. Based on the comprehensive status index, a preset mapping relationship set is queried, and the corresponding speed control command is output.

[0012] Optionally, the speed control command is sent to the drive motor of the underground coal mine conveyor to adjust the conveyor belt speed, including: The speed control command is encapsulated into a data packet containing the target speed value; The data packet is sent to the conveyor controller in the coal mine via a pre-set industrial communication link. The received data packet is parsed using the conveyor controller to extract the target speed value; The target speed value is converted into a control signal for the motor driver; Based on the control signal, the frequency of the input voltage and current of the motor driven by the motor driver is adjusted to change the rotational speed of the motor. The conveyor belt transmission mechanism is driven by changing the rotational speed of the drive motor, so that the running speed of the conveyor belt is adjusted to the target speed value.

[0013] Secondly, this application provides an intelligent speed control system for coal mine conveyors based on industrial vision, comprising: The acquisition module is used to acquire a sequence of coal flow images from a conveyor belt, restore the visibility of the coal flow image sequence under coal dust interference, and obtain a target coal flow contour image. The analysis module is used to analyze the distribution dispersion of the coal flow in the width direction of the conveyor belt based on the target coal flow contour image, and simultaneously analyze the accumulation thickness of the coal flow in the conveying direction. The fusion module is used to fuse the distribution dispersion of the coal flow in the width direction of the conveyor belt with the accumulation thickness of the coal flow in the conveying direction to generate morphological description parameters. The coupling module is used to acquire the electrical signal parameters of the drive motor of the underground coal mine conveyor and synchronously couple the electrical signal parameters with the morphological description parameters to output speed control commands; The adjustment module is used to send the speed control command to the drive motor of the underground coal mine conveyor to adjust the running speed of the conveyor belt.

[0014] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the intelligent speed control method for coal mine conveyors based on industrial vision as described in the first aspect above.

[0015] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a method for intelligent speed control of a coal mine conveyor based on industrial vision as described in the first aspect.

[0016] This application restores clear outlines from coal dust interference images, analyzes the spatial distribution of coal flow, fuses and generates comprehensive morphological parameters, and couples them with motor electrical signals in real time to generate speed control commands, ultimately achieving closed-loop adjustment of conveyor belt speed. This constructs a complete intelligent speed control closed loop from visual perception to electrical response to execution control, effectively overcoming the interference of underground coal dust environment on visual monitoring, realizing adaptive matching between conveyor belt speed and real-time coal flow load pattern, and improving the operational efficiency and stability of the transportation system.

[0017] Furthermore, by decomposing the coal dust layer and performing pixel-level illumination compensation, the accuracy of contour extraction was ensured; by quantifying and analyzing the distribution dispersion and accumulation thickness, a precise digital description of the coal flow morphology was achieved; by dynamically determining the fusion weight based on historical operating data, the morphology description parameters could better reflect the actual load impact; by coupling the morphology parameters with current fluctuation characteristics through time synchronization, the real-time performance and accuracy of the control were enhanced; and finally, by reliably issuing commands through the industrial network to drive motor speed regulation, a safe, stable, and efficient closed-loop intelligent control of the conveying system was achieved under harsh operating conditions.

[0018] These or other aspects of this application will become more apparent from the description of the following embodiments. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of an intelligent speed control method for coal mine conveyors based on industrial vision, provided in this application, is shown. Figure 2 A schematic diagram of the structure of an intelligent speed control system for a coal mine conveyor based on industrial vision provided in this application is shown. Figure 3 A schematic diagram of the structure of a computing device provided in this application is shown. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present application, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0022] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0023] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] Figure 1 This application provides a flowchart of an intelligent speed control method for coal mine conveyors based on industrial vision, as shown below. Figure 1 As shown, the method includes: Step 101: Obtain the coal flow image sequence of the conveyor belt, restore the visibility of the coal flow image sequence under coal dust interference, and obtain the target coal flow contour image.

[0025] Optionally, step 101 may specifically include: Step 1011: Collect and integrate images of coal flow from the conveyor belt that include coal dust interference by using an industrial vision device deployed at a preset location on the underground conveyor in the coal mine to obtain a sequence of coal flow images from the conveyor belt.

[0026] Step 1012: Based on the scattering characteristics of coal dust under mine lighting conditions, decompose the coal dust layer image and the initial coal flow image from the coal flow image sequence of the conveyor belt.

[0027] Step 1013: Evaluate the concentration of the coal dust layer image to generate a coal dust concentration distribution map.

[0028] Step 1014: Based on the coal dust concentration distribution map, perform pixel-level illumination compensation on the initial coal flow image to obtain an enhanced coal flow image after illumination compensation.

[0029] Step 1015: Extract edge information from the enhanced coal flow image to obtain the target coal flow contour image.

[0030] In this application, the conveyor belt coal flow image sequence refers to a series of digital images that are continuously captured at certain time intervals by image acquisition equipment deployed along the conveyor in the coal mine, recording the coal transportation status on the conveyor belt. Due to the presence of suspended coal dust underground, the generated result of this image sequence is usually a collection of video frames or pictures with reduced clarity due to coal dust interference.

[0031] Visibility restoration under coal dust interference refers to a series of image processing methods adopted to address the problem of blurred and reduced contrast in coal flow images of conveyor belts caused by the absorption and scattering of light by suspended coal dust particles underground. The purpose of this process is to remove or reduce the visual noise caused by coal dust in the image and improve the recognizability of coal targets in the image.

[0032] The target coal flow profile image refers to the binarized or edge-emphasized image obtained after visibility restoration processing under coal dust interference, which mainly highlights the outer boundary of the coal material on the conveyor belt. The result of generating this image is the basis for subsequent coal flow identification, block size analysis or foreign object detection.

[0033] Industrial vision devices refer to image acquisition equipment specifically designed for harsh industrial environments such as explosion-proof, dust-proof, and low-light conditions in underground coal mines. They typically include components such as protective housings, industrial cameras, and supplementary lights. In this application, they are deployed at a preset position on the conveyor to acquire raw images of the coal flow on the conveyor belt.

[0034] A coal dust layer image is a digital image extracted from a raw conveyor belt coal flow image using image processing techniques. It primarily represents the image blurring caused by the scattering and shading effects of suspended coal dust on light. This image reflects the spatial distribution of coal dust.

[0035] The initial coal flow image refers to the underlying scene image of the conveyor belt and coal obtained after the coal dust layer image is decomposed, which is theoretically free of coal dust scattering interference. However, due to incomplete separation, the image usually still contains residual noise or distortion.

[0036] A coal dust concentration distribution map is a digital image generated after quantitative analysis of a coal dust layer image. It uses grayscale values ​​or pseudo-color to represent the relative concentration or optical thickness of coal dust at each pixel location in the image. This distribution map is used to guide subsequent compensation processes.

[0037] Pixel-level illumination compensation is an image enhancement operation that dynamically adjusts the brightness value of the corresponding pixel in the initial coal flow image based on the concentration value of each pixel in the coal dust concentration distribution map, in order to compensate for the light attenuation caused by coal dust occlusion at that point. Its purpose is to restore scene details weakened by coal dust.

[0038] Edge information extraction refers to a computer vision operation that detects and delineates the boundaries of regions in a clear image after illumination compensation, where there are significant changes in grayscale or color. In this application, it is mainly used to extract the outline of coal piles on a conveyor belt.

[0039] In this step, firstly, explosion-proof industrial vision devices are securely installed at key monitoring points (such as the head, tail, or middle) of the underground coal mine conveyor to continuously acquire raw images at a fixed frame rate during the operation of the conveyor, and these images arranged in chronological order are integrated into a coal flow image sequence of the conveyor belt. Next, based on the physical model of light scattering of coal dust particles under specific lighting conditions in the mine, each frame of the coal flow image sequence of the conveyor belt is processed using image prior or blind source separation algorithm, and decomposed into a coal dust layer image representing the coal dust scattering effect and an initial coal flow image representing the bottom conveyor belt and coal flow. Then, the coal dust layer image obtained by decomposition is analyzed. For example, by calculating the mean or variance of pixel grayscale in its local area, the relative concentration of coal dust in each part of the image is evaluated, thereby generating a coal dust concentration distribution map with the same resolution as the original image. Subsequently, based on the coal dust concentration distribution map, pixel-level illumination compensation was performed on the initial coal flow image. Specifically, for pixel areas with high coal dust concentration, the brightness gain was increased to compensate for light attenuation, while for areas with low concentration, a smaller adjustment was made, thereby obtaining an enhanced coal flow image with significantly enhanced contrast and detail. Finally, an edge detection algorithm is applied to the enhanced coal flow image to identify and extract the clear boundary between the coal and the conveyor belt background in the image, filter out non-contour texture noise, and generate a target coal flow contour image with lines as the main content.

[0040] For example, take a belt conveyor in the main transport roadway of a coal mine.

[0041] First, an explosion-proof network camera is installed as an industrial vision device about 50 meters away from the unloading point of the machine head. It captures images of the conveyor belt running at a resolution of 1920 x 1080 at a speed of 25 frames per second for 10 seconds, thus obtaining a sequence of 250 images of the coal flow of the conveyor belt. Then, one frame of the image is selected for processing. The image dehazing algorithm based on dark channel prior is used to decompose the frame image to obtain a coal dust layer image representing the coal dust blurring effect and an initial coal flow image with preliminary coal dust removal. Next, the average grayscale value within each 5-pixel multiplied block in the coal dust layer image is calculated. This grayscale value ranges from 0 to 255; a higher value indicates a higher relative visual concentration of coal dust in that block. Based on this, a coal dust concentration distribution map of the same size is generated. Then, according to this coal dust concentration distribution map, a compensation formula is applied to each pixel of the initial coal flow image. Assuming that the value of a pixel in the coal dust concentration distribution map is C (range 0-255), the output brightness I_out of that pixel in the enhanced coal flow image is calculated by the formula I_out = I_in + k × C, where I_in is the brightness of that pixel in the initial coal flow image, and k is a preset compensation coefficient (e.g., 0.3). After this operation, the area that was originally dark due to coal dust was brightened. Finally, the Canny edge detector was applied to the enhanced coal flow image, and high and low thresholds were set to extract the complete and continuous edge lines of the coal accumulation, generating a binary target coal flow contour image, in which white lines represent the contour and black lines represent the background.

[0042] Step 102: Based on the target coal flow profile image, analyze the distribution dispersion of the coal flow in the width direction of the conveyor belt, and simultaneously analyze the accumulation thickness of the coal flow in the conveying direction.

[0043] Optionally, step 102 may specifically include: Step 1021: Establish a coordinate system on the target coal flow profile image, where the horizontal axis of the coordinate system corresponds to the width direction of the conveyor belt and the vertical axis corresponds to the conveying direction.

[0044] Step 1022: Establish a coordinate system on the target coal flow profile image, where the horizontal axis of the coordinate system corresponds to the width direction of the conveyor belt and the vertical axis corresponds to the conveying direction.

[0045] Step 1023: Based on the degree of difference in the number of contour pixels in the coal flow width distribution data between different width intervals, the distribution dispersion of the coal flow in the width direction of the conveyor belt is analyzed.

[0046] Step 1024: Scan the target coal flow profile image line by line along the vertical axis, identify and record the height of the upper edge point of the coal flow profile in each line, and obtain the coal flow height sequence along the conveying direction.

[0047] Step 1025: Based on the changing trend of height values ​​in the coal flow height sequence, identify local high points of coal flow accumulation, and analyze the accumulation thickness of the coal flow in the conveying direction based on the height values ​​of the local high points.

[0048] In this application, the distribution dispersion refers to a numerical index used to quantify the uniformity of coal flow distribution along the entire width of the conveyor belt. The result is a scalar value that reflects whether the coal is concentrated in the middle of the conveyor belt, relatively uniformly spread across the entire effective width, or biased to one side. The higher the dispersion value, the more uneven and concentrated the coal flow distribution is generally.

[0049] Accumulation thickness refers to a numerical indicator used to quantify the degree of coal accumulation in the vertical direction of the conveyor belt (i.e., perpendicular to the belt surface, which is represented as the height along the conveying direction in the image). The result is usually a length value in pixels, which can be converted into the actual physical height after calibration, reflecting the instantaneous loading or accumulation height of the coal flow.

[0050] Coal flow width distribution data refers to a data sequence obtained by counting the number of contour pixels in each column of the target coal flow contour image along the width direction of the conveyor belt (horizontal axis of the image). Each data point in the sequence represents the vertical extension range of the coal flow contour at that width position, and its overall structure reflects the cross-sectional shape of the coal flow in the width dimension.

[0051] The coal flow height sequence refers to a data sequence obtained by scanning the target coal flow contour image line by line along the conveyor belt running direction (vertical axis of the image), identifying and recording the vertical coordinate value of the uppermost edge point of the coal flow contour in each line, and describing the undulations of the coal flow surface contour along the conveying direction.

[0052] In this step, a two-dimensional coordinate system is first defined on the target coal flow profile image. The horizontal axis of this coordinate system is aligned with the actual width direction of the conveyor belt, and the vertical axis is aligned with the actual running direction of the conveyor belt. Next, the image is scanned column by column from left to right along the horizontal axis. The number of white pixels belonging to the coal flow contour in each column of the target coal flow contour image is counted to obtain the coal flow width distribution data. Then, based on the coal flow width distribution data, its statistical characteristics are calculated. For example, the ratio of the standard deviation to the mean of the number of pixels in all column contours is calculated, or the kurtosis of the data distribution is analyzed. The calculated statistics are used to analyze and output the dispersion of the coal flow distribution in the width direction of the conveyor belt. At the same time, in another parallel processing stream, the image is scanned line by line along the vertical axis from the top (corresponding to the downstream of the conveying direction) to the bottom (upstream). In each line, the leftmost and rightmost pixels belonging to the coal flow contour are found, and the average width of the contour in that line is calculated. At the same time, the vertical coordinates (i.e., height) of the upper edge points of the contour found for the first or last time are recorded, thus obtaining the coal flow height sequence along the conveying direction. Finally, the coal flow height sequence was analyzed to identify local maxima in the sequence. These points correspond to the peak positions of coal flow accumulation. Representative values ​​(such as maximum or average values) of the heights of these local high points were selected, and the accumulation thickness of the coal flow in the conveying direction was analyzed using the pre-calibrated ratio between pixels and actual heights.

[0053] Following the embodiment of step 101, the target coal flow profile image with a width of 1920 pixels and a height of 1080 pixels is obtained.

[0054] First, establish a coordinate system with the top left corner of the target coal flow contour image as the origin. The horizontal axis (X-axis) corresponds to the width direction of the conveyor belt from left to right, and the vertical axis (Y-axis) corresponds to the coal flow conveying direction from top to bottom. Then, scan column by column from X=0 to X=1919, counting the number of contour pixels (white) in each column to obtain a coal flow width distribution data sequence W containing 1920 data points. Assuming the mean of sequence W is Avg_W and the standard deviation is Std_W, calculate the distribution dispersion D=Std_W / Avg_W. For example, if D=0.15 is obtained, this value represents the dispersion of the coal flow width distribution. Simultaneously, from Y=0 to Y=... 1079 line-by-line scanning. In each line Y, the leftmost X coordinate L_y and the rightmost X coordinate R_y of the contour pixel are found, and the height of the upper edge point of the contour in that line (i.e., the Y coordinate of the first detected contour pixel in that line) is recorded, resulting in a coal flow height sequence H containing 1080 height values. Sequence H is analyzed, and the sliding window method is used to find local high points. It is found that there is a peak with a height value of 120 pixels near Y=400. Assuming that 10 pixels in the known image correspond to an actual height of 1 cm through on-site calibration, the accumulation thickness corresponding to this local high point is 120 pixels ÷ 10 pixels / cm = 12 cm.

[0055] Step 103: Combine the distribution dispersion of the coal flow in the width direction of the conveyor belt with the accumulation thickness of the coal flow in the conveying direction to generate morphological description parameters.

[0056] Optionally, step 103 may specifically include: Step 1031: Quantify the dispersion of the coal flow distribution in the width direction of the conveyor belt to obtain a quantified value of the width dispersion.

[0057] Step 1032: Quantify the thickness of the coal flow in the conveying direction to obtain a thickness quantification value.

[0058] Step 1033: Based on the operating characteristics of the coal mine conveyor, determine the first fusion weight of the width discrete quantization value and the second fusion weight of the thickness quantization value.

[0059] Optionally, step 1033 may specifically include: Historical operating status data of the underground coal mine conveyor under various historical coal flow patterns are obtained. This historical operating status data includes historical width dispersion, historical accumulation thickness, and corresponding historical motor energy consumption data. The influence of changes in historical width dispersion on historical motor energy consumption data is analyzed to obtain the width influence correlation. The influence of changes in historical accumulation thickness on historical motor energy consumption data is analyzed to obtain the thickness influence correlation. The sum of the width influence correlation and the thickness influence correlation is taken as the total influence correlation. The numerical ratio of the width influence correlation to the total influence correlation is determined as the first fusion weight, and the numerical ratio of the thickness influence correlation to the total influence correlation is determined as the second fusion weight.

[0060] Step 1034: Adjust the width discrete quantification value proportionally based on the first fusion weight to obtain the width influence factor.

[0061] Step 1035: Adjust the thickness quantization value proportionally based on the second fusion weight to obtain the thickness influence factor.

[0062] Step 1036: Combine the width influence factor and the thickness influence factor to calculate the morphological description parameters.

[0063] In this application, the morphological description parameter refers to a single numerical index generated by weighted fusion of the dispersion of coal flow distribution in the width direction of the conveyor belt and the accumulation thickness in the conveying direction. The result of this parameter is a scalar value, which aims to comprehensively characterize the overall morphological features of the current coal flow cross section. It can simultaneously reflect the uniformity of coal flow distribution and the height of accumulation, and is a key input for subsequent operation status assessment or control decision-making.

[0064] The width discreteness quantification value refers to a standardized value obtained after scaling or normalizing the distribution discreteness. This value makes the discreteness calculated from different images or different time points comparable and is suitable for subsequent weighted fusion calculations.

[0065] Thickness quantization refers to a standardized value obtained after scaling or normalizing the stacked thickness. This value allows the thickness, expressed in pixels or physical units, to be fused with the width discrete quantization value within the same numerical range.

[0066] Fusion weights refer to the coefficients assigned to these two feature values ​​when combining the discrete quantized values ​​of width and the quantized values ​​of thickness into morphological description parameters. The first fusion weight is used for the width feature, and the second fusion weight is used for the thickness feature. The determination of these weights characterizes the relative importance of the uneven width distribution and the stacking thickness on the overall morphology under specific conveying system operating characteristics.

[0067] The width influence factor and the thickness influence factor refer to the two intermediate values ​​obtained after proportionally adjusting the width discrete quantization value using the first fusion weight and proportionally adjusting the thickness quantization value using the second fusion weight, respectively. These two influence factors are the contribution of the width and thickness features after being scaled according to their importance before participating in the final fusion.

[0068] In this step, the dispersion of the coal flow distribution in the width direction of the conveyor belt is first quantified, for example by linear scaling to map it to a preset standard numerical range such as 0 to 1, thereby obtaining a quantified value of the width dispersion; at the same time, a similar quantification is performed on the accumulation thickness of the coal flow in the conveying direction, for example by dividing it by a maximum allowable thickness reference value, thereby obtaining a quantified value of the thickness; Next, based on the specific operating characteristics of the coal mine conveyor, a first fusion weight and a second fusion weight are determined to integrate these two quantitative values. Specifically, historical operating status data of the conveyor under various coal flow patterns can be obtained, including historical width dispersion, historical accumulation thickness, and corresponding historical motor energy consumption data. Then, through correlation analysis or regression analysis, the influence of changes in historical width dispersion on historical motor energy consumption data is calculated to obtain the width influence correlation, and the influence of changes in historical accumulation thickness on historical motor energy consumption data is calculated to obtain the thickness influence correlation. Subsequently, the width influence correlation and the thickness influence correlation are added to obtain the total influence correlation. Finally, the width influence correlation is divided by the total influence correlation, and the quotient is determined as the first fusion weight; the thickness influence correlation is divided by the total influence correlation, and the quotient is determined as the second fusion weight. Then, the width discrete quantization value is multiplied and adjusted based on the determined first fusion weight to obtain the width influence factor; at the same time, the thickness quantization value is multiplied and adjusted based on the determined second fusion weight to obtain the thickness influence factor. Finally, the width influence factor and the thickness influence factor are combined, for example, by adding the two together, to calculate the morphological description parameters.

[0069] Following the embodiment of step 102, for the conveyor, the current coal flow width distribution dispersion D is 0.15, and the accumulation thickness T is 12 cm.

[0070] First, the distribution dispersion D is quantified. Assuming that its value falls within the preset range of 0-1, the width dispersion quantification value Qw is 0.15. At the same time, the stacking thickness T is quantified. Assuming that the maximum allowable stacking thickness of the conveyor is 30 cm, the thickness quantification value Qt = 12 / 30 = 0.4. Next, a set of data was retrieved from the historical database of the conveyor. Through analysis, it was found that the influence of the historical width dispersion on motor energy consumption (width influence correlation) was 0.6, and the influence of the historical stacking thickness on motor energy consumption (thickness influence correlation) was 0.4. Therefore, the total influence correlation was 0.6 plus 0.4 equals 1.0. Thus, the first fusion weight W1 = 0.6 / 1.0 = 0.6, and the second fusion weight W2 = 0.4 / 1.0 = 0.4. Then, the width influence factor Fw = Qw × W1 = 0.15 × 0.6 = 0.09 is calculated, and the thickness influence factor Ft = Qt × W2 = 0.4 × 0.4 = 0.16 is calculated. Finally, the width influence factor Fw and the thickness influence factor Ft are added together to obtain the morphological description parameter M = 0.09 + 0.16 = 0.25.

[0071] Step 104: Obtain the electrical signal parameters of the drive motor of the underground coal mine conveyor, and synchronously couple the electrical signal parameters with the morphological description parameters to output a speed control command.

[0072] Optionally, step 104 may specifically include: Step 1041: Real-time acquisition of current and voltage data of the drive motor of the underground coal mine conveyor during operation, as electrical signal parameters.

[0073] Step 1042: Extract the current fluctuation characteristics reflecting the instantaneous changes in motor load from the electrical signal parameters.

[0074] Step 1043: Obtain the acquisition timestamp corresponding to the coal flow image sequence of the conveyor belt, and map the morphological description parameters to the same time reference as the electrical signal parameters according to the conveyor belt running speed.

[0075] Step 1044: Pair and combine the morphological description parameters mapped to the same time base with the current fluctuation characteristics.

[0076] Step 1045: Based on the preset coupling relationship, the morphological description parameters and current fluctuation characteristics after pairing are jointly calculated to obtain a comprehensive state index.

[0077] Step 1046: Based on the comprehensive status index, query the preset mapping relationship set and output the corresponding speed control command.

[0078] In this application, electrical signal parameters refer to the raw measurement data that are collected in real time by sensors during the operation of the drive motor of the underground coal mine conveyor, which characterizes its electrical working status. In this application, the parameters specifically refer to the three-phase current data and line voltage data of the drive motor, which reflect the real-time load and energy consumption of the motor.

[0079] Current fluctuation characteristics refer to a feature value extracted from real-time acquired current data to quantify the severity of instantaneous changes in current. The result is a scalar, such as the standard deviation of the effective current value within a time window or the amplitude of energy in a specific frequency band. This value reflects the rapid fluctuation of the motor load and is related to the instantaneous impact or uneven distribution of coal flow.

[0080] The same time reference refers to the process of calculating and processing the state information represented by the morphological description parameters and electrical signal parameters to correspond to the same physical moment before associating them. Due to the delay in image processing and the transmission time of coal flow from the shooting point to the motor load response point, time alignment must be performed to ensure the correctness of data association.

[0081] Pairing and combining refers to establishing a one-to-one correspondence between the morphological description parameters and the current fluctuation characteristics calculated at the same time after mapping the morphological description parameters and the current fluctuation characteristics to the same time base, forming a data pair, which serves as the input for subsequent joint calculations.

[0082] The comprehensive state index refers to a single value obtained by performing mathematical operations on the paired and combined morphological description parameters and current fluctuation characteristics based on a preset coupling relationship. This index comprehensively represents the combined state of coal flow morphological abnormalities and motor electrical response, and is a direct basis for judging whether speed regulation is needed and the magnitude of speed regulation.

[0083] Speed ​​control commands are specific control commands generated based on the calculated comprehensive state indicators and after querying a preset command mapping table or rule. These commands are used to adjust the operating frequency or speed of the conveyor drive motor. The output can be a target frequency value, speed increase or decrease, or a specific control code.

[0084] In this step, firstly, the instantaneous values ​​of the three-phase current and the instantaneous values ​​of the line voltage of the motor are collected in real time at a high sampling rate by using a current transformer and a voltage sensor connected in the power supply circuit of the drive motor to form electrical signal parameters; Next, for the collected current data, the standard deviation of the effective current value within a short time window is calculated, or a short-time Fourier transform is performed on the current signal and the specific frequency band energy reflecting load fluctuations is extracted, thereby extracting the current fluctuation characteristics. Simultaneously, the acquisition timestamp of the one or more frames of conveyor belt coal flow image sequence on which the current morphology description parameters are based is obtained. Based on the actual running distance of the conveyor belt from the image acquisition point to the main load-affected point of the drive motor and the current belt speed, the theoretical time delay of the coal flow morphology at the time of image acquisition being transmitted to the motor to generate load response is calculated. This delay is added to the timestamp of the morphology description parameters, thereby mapping them to the same timeline as the electrical signal parameters, with the motor response time as the reference. Then, the time-aligned morphological description parameters are paired with the current fluctuation characteristics at the same time to form a data pair. Then, based on a preset coupling relationship, such as a weighted summation formula, the paired morphological description parameter values ​​and current fluctuation characteristic values ​​are substituted into the calculation to obtain a comprehensive state index. Finally, based on the calculated comprehensive state index, a preset mapping relationship set is queried. This set defines the output speed control command corresponding to different ranges of comprehensive state index. For example, "if the index is greater than threshold A, an acceleration command is output; if the index is less than threshold B, a deceleration command is output", thus outputting the final speed control command.

[0085] Following the embodiment of step 103, this applies to the underground coal mine conveyor.

[0086] First, the current and voltage of the drive motor are collected in real time by the sensors in the motor control cabinet at a sampling rate of 1000 times per second as electrical signal parameters. The standard deviation of the effective value of the current data in the most recent 0.1 seconds is calculated to obtain the current fluctuation characteristic value of 0.5. The current conveyor belt speed is 2 meters per second. The distance between the image acquisition point and the main load point of the motor is about 10 meters. The time delay is 10 meters divided by 2 meters per second, which equals 5 seconds. Assuming that the morphological description parameter M=0.25 is calculated based on the image acquired 5 seconds ago, it is mapped to the current moment. The mapped morphological description parameter value of 0.25 is paired with the current current fluctuation characteristic value of 0.5. The preset coupling relationship is the comprehensive state index S=0.6×morphological description parameter+0.4×current fluctuation characteristic. Substituting into the calculation, we get S=0.6×0.25+0.4×0.5=0.15+0.2=0.35. Finally, the preset mapping relationship set is queried. If 0.3≤S<0.5, the command "maintain current speed" is output; if S≥0.5, the command "decelerate" is output; if S<0.3, the command "accelerate" is output. Since S=0.35, the speed control command "maintain current speed" is finally output.

[0087] Step 105: The speed control command is sent to the drive motor of the underground coal mine conveyor to adjust the running speed of the conveyor belt.

[0088] Optionally, step 105 may specifically include: Step 1051: Encapsulate the speed control command into a data packet containing the target speed value.

[0089] Step 1052: The data packet is sent to the conveyor controller in the coal mine via a preset industrial communication link.

[0090] Step 1053: The received data packet is parsed using the conveyor controller to extract the target speed value.

[0091] Step 1054: Convert the target speed value into a control signal for the motor driver.

[0092] Step 1055: Based on the control signal, adjust the frequency of the input voltage and current of the motor driver to change the rotational speed of the motor.

[0093] Step 1056: Drive the conveyor belt transmission mechanism according to the change in the rotational speed of the drive motor, so that the running speed of the conveyor belt is adjusted to the target speed value.

[0094] In this application, industrial communication link refers to a dedicated physical channel and communication protocol used to connect a monitoring and control computer and a field device controller in an underground coal mine industrial environment. In this application, it specifically refers to a communication network used to issue speed control commands from a ground or underground central control center to a conveyor controller, such as a network based on industrial Ethernet, controller area network, or fieldbus.

[0095] A conveyor controller is a programmable logic controller or dedicated controller installed underground in a coal mine to directly control the conveyor drive motor and auxiliary equipment. It is the core field control unit that receives speed control commands, performs logical judgments, and outputs low-level control signals.

[0096] Control signals refer to the physical signals generated by the conveyor controller after parsing the target speed value, which can be recognized and executed by the motor driver. These signals are usually a standard analog voltage signal or pulse frequency signal, and their signal strength or frequency is proportional to the target speed value, used to precisely instruct the driver.

[0097] A motor driver refers to a power electronic device that drives and regulates the speed of a motor; in this application, it specifically refers to a frequency converter. It receives control signals from a controller and adjusts the voltage and frequency of the three-phase AC power output to the drive motor according to those signals, thereby steplessly changing the motor's rotational speed.

[0098] The conveyor belt drive mechanism refers to the general term for the mechanical devices that transmit the rotational motion of the drive motor to the conveyor belt, enabling it to run. It typically includes components such as a reducer, coupling, and drive roller. Its function is to convert the motor's speed and torque into the linear speed of the conveyor belt.

[0099] In this step, the speed setting information contained in the speed control command is first encapsulated into a data packet containing the target speed value, command type, check code, etc., according to a predefined communication protocol format. Then, through the pre-built and configured underground industrial communication network of the coal mine, the encapsulated data packet is sent from the upper control unit that generates the instruction to the conveyor controller located at the conveyor head or power distribution point; Then, after receiving the data packet, the data packet is decoded according to the same communication protocol to verify its integrity, and the required target speed value is extracted from the payload of the data packet. Then, according to the preset program, the extracted target speed value is converted into a standard analog control signal or a pulse signal with a specific pulse frequency through its internal digital-to-analog conversion module, and this signal is output to the motor driver connected to it. Then, based on the received control signal, the switching state of its power unit is adjusted accordingly through its internal core control algorithm, thereby precisely changing the voltage amplitude and frequency of the three-phase AC power output to the drive motor. The rotational speed of the drive motor will change proportionally with the change of the input voltage frequency. Finally, the change in the speed of the drive motor is reduced and amplified in torque through the conveyor belt transmission mechanism such as the coupling and reducer, and then transmitted to the drive drum, thereby ultimately driving the conveyor belt and smoothly adjusting its running speed to the target speed value, completing the entire closed-loop control.

[0100] Following the embodiment of step 104, for the underground coal mine conveyor, the output speed control command is "maintain current speed".

[0101] First, the control system parses the instruction to maintain the current target speed value, such as 2.0 meters per second, and encapsulates this target speed value of 2.0 together with the instruction identifier into a data packet that conforms to the controller local area network bus protocol; Next, the data packet is sent down to the conveyor controller installed in the control box at the conveyor head via the underground controller area network. After receiving the data packet, the communication module of the conveyor controller parses it, confirms the command is valid, and extracts the target speed value of 2.0. Simultaneously, the controller's internal program determines that the current speed is 2.0 meters per second, therefore no adjustment is needed. The analog control signal output to the frequency converter remains unchanged at 4 mA, corresponding to 2.0 meters per second. The frequency converter receives a constant 4 mA control signal, maintaining its current output voltage and frequency, and the drive motor continues to rotate at its original speed. This speed is transmitted to the drive drum through the reducer, ensuring the conveyor belt continues to operate at a speed of 2.0 meters per second. If the command is to accelerate or decelerate, the process is similar, except that the controller will output a new control signal to the frequency converter corresponding to a higher or lower target speed value, thereby triggering subsequent adjustments to the motor speed and conveyor belt speed.

[0102] Figure 2 This application provides a schematic diagram of the structure of an intelligent speed control system for coal mine conveyors based on industrial vision, as shown below. Figure 2 As shown, the system includes: The acquisition module 21 is used to acquire a coal flow image sequence of the conveyor belt, restore the visibility of the coal flow image sequence under coal dust interference, and obtain a target coal flow contour image. The analysis module 22 is used to analyze the distribution dispersion of the coal flow in the width direction of the conveyor belt based on the target coal flow contour image, and simultaneously analyze the accumulation thickness of the coal flow in the conveying direction. The fusion module 23 is used to fuse the distribution dispersion of the coal flow in the width direction of the conveyor belt with the accumulation thickness of the coal flow in the conveying direction to generate morphological description parameters. The coupling module 24 is used to acquire the electrical signal parameters of the drive motor of the underground coal mine conveyor and synchronously couple the electrical signal parameters with the morphological description parameters to output speed control commands; The adjustment module 25 is used to send the speed control command to the drive motor of the underground coal mine conveyor to adjust the running speed of the conveyor belt.

[0103] Figure 2 The aforementioned intelligent speed control system for coal mine conveyors based on industrial vision can execute... Figure 1 The implementation principle and technical effects of the intelligent speed control method for coal mine conveyors based on industrial vision described in the illustrated embodiment will not be repeated here. The specific operation methods of each module and unit in the intelligent speed control system for coal mine conveyors based on industrial vision in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0104] In one possible design, Figure 2 The intelligent speed control system for coal mine conveyors based on industrial vision, as shown in the embodiment, can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0105] The processing component 32 is used for the above Figure 1 The embodiment describes an intelligent speed control method for coal mine conveyors based on industrial vision.

[0106] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0107] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0108] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0109] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0110] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0111] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0112] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The embodiment shown is an intelligent speed control method for coal mine conveyors based on industrial vision.

[0113] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0114] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for intelligent speed control of coal mine conveyors based on industrial vision, characterized in that, include: A sequence of coal flow images from a conveyor belt is acquired, and visibility under coal dust interference is restored from the sequence of coal flow images to obtain a target coal flow contour image. Based on the target coal flow profile image, the distribution dispersion of the coal flow in the width direction of the conveyor belt is analyzed, and the accumulation thickness of the coal flow in the conveying direction is analyzed simultaneously. The morphological description parameters are generated by combining the distribution dispersion of the coal flow in the width direction of the conveyor belt with the accumulation thickness of the coal flow in the conveying direction. The electrical signal parameters of the drive motor of the underground coal mine conveyor are obtained, and the electrical signal parameters are synchronously coupled with the morphological description parameters to output speed control commands; The speed control command is sent to the drive motor of the underground coal mine conveyor to adjust the running speed of the conveyor belt.

2. The method according to claim 1, characterized in that, Acquire a sequence of coal flow images from a conveyor belt, restore visibility of the coal flow images under coal dust interference, and obtain a target coal flow contour image, including: By using industrial vision devices deployed at predetermined locations on underground coal mine conveyors, images of coal flow on the conveyor belt, including those affected by coal dust, are collected and integrated to obtain a sequence of coal flow images on the conveyor belt. Based on the scattering characteristics of coal dust under mine lighting conditions, coal dust layer images and initial coal flow images are decomposed from the coal flow image sequence of the conveyor belt; The coal dust layer image is subjected to concentration assessment to generate a coal dust concentration distribution map; Based on the coal dust concentration distribution map, pixel-level illumination compensation is performed on the initial coal flow image to obtain an enhanced coal flow image after illumination compensation; Edge information is extracted from the enhanced coal flow image to obtain the target coal flow contour image.

3. The method according to claim 1, characterized in that, Based on the target coal flow profile image, the distribution dispersion of the coal flow in the width direction of the conveyor belt is analyzed, and the accumulation thickness of the coal flow in the conveying direction is analyzed simultaneously, including: A coordinate system is established on the target coal flow profile image, with the horizontal axis corresponding to the width direction of the conveyor belt and the vertical axis corresponding to the conveying direction. The width of the conveyor belt is divided into multiple continuous width intervals along the horizontal axis, and the number of contour pixels of the target coal flow contour image in each width interval is counted to obtain coal flow width distribution data. Based on the degree of difference in the number of contour pixels in the coal flow width distribution data between different width intervals, the distribution dispersion of the coal flow in the width direction of the conveyor belt is analyzed. The target coal flow profile image is scanned line by line along the vertical axis, and the height of the upper edge point of the coal flow profile in each line is identified and recorded to obtain the coal flow height sequence along the conveying direction. Based on the changing trend of height values ​​in the coal flow height sequence, local high points of coal flow accumulation are identified, and the accumulation thickness of the coal flow in the conveying direction is analyzed based on the height values ​​of the local high points.

4. The method according to claim 1, characterized in that, By integrating the distribution dispersion of the coal flow along the width of the conveyor belt with the accumulation thickness of the coal flow along the conveying direction, morphological description parameters are generated, including: The dispersion of the coal flow distribution in the width direction of the conveyor belt is quantified to obtain a quantified value of the width dispersion. The thickness of the coal flow in the conveying direction is quantified to obtain a quantified thickness value; Based on the operating characteristics of the coal mine conveyor, a first fusion weight for the width discrete quantization value and a second fusion weight for the thickness quantization value are determined. Based on the first fusion weight, the width discrete quantification value is proportionally adjusted to obtain the width influence factor; Based on the second fusion weight, the thickness quantization value is proportionally adjusted to obtain the thickness influence factor; The width influence factor and the thickness influence factor are combined to calculate the morphological description parameters.

5. The method according to claim 4, characterized in that, Based on the operating characteristics of the coal mine conveyor, the first fusion weight of the width discrete quantization value and the second fusion weight of the thickness quantization value are determined, including: The historical operating status data of the underground coal mine conveyor under various historical coal flow patterns are obtained. The historical operating status data includes historical width dispersion, historical accumulation thickness and corresponding historical motor energy consumption data. The influence of the historical width dispersion on the historical motor energy consumption data is analyzed to obtain the width influence correlation degree. The influence of the historical accumulation thickness variation on the historical motor energy consumption data was analyzed to obtain the thickness influence correlation degree. The sum of the width influence correlation and the thickness influence correlation is taken as the total influence correlation. The numerical ratio of the width influence correlation degree to the total influence correlation degree is determined as the first fusion weight, and the numerical ratio of the thickness influence correlation degree to the total influence correlation degree is determined as the second fusion weight.

6. The method according to claim 1, characterized in that, Acquire the electrical signal parameters of the drive motor of the underground coal mine conveyor, and synchronously couple the electrical signal parameters with the morphological description parameters to output a speed control command, including: Real-time acquisition of current and voltage data of the drive motor of the underground conveyor in the coal mine during operation, as electrical signal parameters; Extract current fluctuation characteristics reflecting instantaneous changes in motor load from the electrical signal parameters; Obtain the acquisition timestamp corresponding to the coal flow image sequence of the conveyor belt, and map the morphological description parameters to the same time base as the electrical signal parameters according to the conveyor belt running speed; The morphological description parameters mapped to the same time base are paired and combined with the current fluctuation characteristics; Based on the preset coupling relationship, the morphological description parameters and current fluctuation characteristics after pairing are jointly calculated to obtain a comprehensive state index. Based on the comprehensive status index, a preset mapping relationship set is queried, and the corresponding speed control command is output.

7. The method according to claim 1, characterized in that, Sending the speed control command to the drive motor of the underground coal mine conveyor to adjust the conveyor belt speed includes: The speed control command is encapsulated into a data packet containing the target speed value; The data packet is sent to the conveyor controller in the coal mine via a pre-set industrial communication link. The received data packet is parsed using the conveyor controller to extract the target speed value; The target speed value is converted into a control signal for the motor driver; Based on the control signal, the frequency of the input voltage and current of the motor driven by the motor driver is adjusted to change the rotational speed of the motor. The conveyor belt transmission mechanism is driven by changing the rotational speed of the drive motor, so that the running speed of the conveyor belt is adjusted to the target speed value.

8. A smart speed control system for coal mine conveyors based on industrial vision, characterized in that, include: The acquisition module is used to acquire a sequence of coal flow images from a conveyor belt, restore the visibility of the coal flow image sequence under coal dust interference, and obtain a target coal flow contour image. The analysis module is used to analyze the distribution dispersion of the coal flow in the width direction of the conveyor belt based on the target coal flow contour image, and simultaneously analyze the accumulation thickness of the coal flow in the conveying direction. The fusion module is used to fuse the distribution dispersion of the coal flow in the width direction of the conveyor belt with the accumulation thickness of the coal flow in the conveying direction to generate morphological description parameters. The coupling module is used to acquire the electrical signal parameters of the drive motor of the underground coal mine conveyor and synchronously couple the electrical signal parameters with the morphological description parameters to output speed control commands; The adjustment module is used to send the speed control command to the drive motor of the underground coal mine conveyor to adjust the running speed of the conveyor belt.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the intelligent speed control method for coal mine conveyors based on industrial vision as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a method for intelligent speed control of a coal mine conveyor based on industrial vision, as described in any one of claims 1 to 7.

Images