Conveyor belt deviation correction system for coal mines based on 3D imaging of the Internet of Things

Abstract

The present invention discloses a conveyor belt deviation correction system for coal mines based on three-dimensional imaging of the Internet of Things, which specifically relates to the field of image processing technology, including a data acquisition module, a central processing module, a deviation correction control module, and an alarm module; the data acquisition module includes a sensor and a camera, which collects image information of the conveyor belt for coal mines and transmits it to the central processing module; the central processing module is used to receive and process the running image transmitted by the data acquisition module, calculate the position deviation of the conveyor belt through an image processing algorithm, and generate a deviation correction signal to send to the deviation correction control module; the deviation correction control module includes a deviation correction actuator, which corrects the conveyor belt according to the deviation correction signal sent by the central processing module; the alarm module dynamically adjusts the alarm signal according to the deviation degree and frequency of the conveyor belt. The present invention promotes the sustainable development of coal mines by optimizing the running state of the conveyor belt, reducing energy consumption, and promoting the sustainable development of coal mines.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and more specifically, to a conveyor belt deviation correction system for coal mines based on three-dimensional imaging of the Internet of Things. Background Art

[0002] In the coal mining industry, conveyor belts are important material transportation equipment and are widely used in coal mining, transportation and processing. However, conveyor belts often deviate during operation, which not only affects transportation efficiency but also may cause equipment damage and safety hazards. Therefore, it is particularly important to research and develop an efficient conveyor belt deviation correction system.

[0003] Traditional conveyor belt deviation correction methods rely on manual monitoring and mechanical adjustment, which are inefficient and prone to errors. The popularity of IoT technology makes it possible for devices to be interconnected, enabling real-time data collection and remote monitoring. With the development of IoT technology, the application of 3D imaging technology provides a new solution for conveyor belt monitoring and deviation correction. 3D imaging technology can capture the status of the conveyor belt in real time, accurately analyze the shape and motion trajectory of the conveyor belt, detect deviation problems in time, and automatically correct the deviation through an intelligent control system. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a conveyor belt correction system for coal mines based on three-dimensional imaging of the Internet of Things to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a conveyor belt deviation correction system for coal mines based on three-dimensional imaging of the Internet of Things, comprising a data acquisition module, a central processing module, a deviation correction control module, and an alarm module;

[0006] The data acquisition module is used to collect the operation image of the conveyor belt for coal mines and transmit the operation image to the central processing module;

[0007] The central processing module is used to receive and process the running image transmitted by the data acquisition module, calculate the position deviation of the conveyor belt through the image processing algorithm, and generate a correction signal to send to the correction control module;

[0008] The deviation correction control module corrects the conveyor belt according to the deviation correction signal sent by the central processing module;

[0009] The alarm module dynamically adjusts the alarm signal according to the deviation degree and frequency of the conveyor belt.

[0010] In a preferred embodiment, the data acquisition module collects image information of the conveyor belt for coal mines through a three-dimensional imaging sensor and a camera, and transmits it to the central processing module. The specific steps are as follows:

[0011] Step A1, image acquisition: setting the acquisition frequency of the 3D imaging sensor to once per second, collecting the 3D point cloud data of the conveyor belt, capturing the image data of the conveyor belt in real time through the camera to ensure that the entire conveyor belt is covered, and pre-processing the captured 3D point cloud and image data, including point cloud denoising and image denoising, and adjusting brightness and contrast to improve image quality;

[0012] Step A2, data transmission: Pack the processed image data and 3D point cloud data to create a data packet structure, including image data, timestamp, 3D point cloud data, and image sequence number, and send the packaged data packet to the central processing module through the wireless network interface.

[0013] In a preferred embodiment, the central processing module receives and processes the running image transmitted by the data acquisition module, calculates the position deviation of the conveyor belt through the image processing algorithm, and generates a correction signal to send to the correction control module. The specific steps are as follows:

[0014] Step B1, receiving an image: receiving an image data packet transmitted from a data acquisition module, unpacking the received data packet, extracting image data, timestamp, three-dimensional point cloud data and image sequence number, and scaling and converting the received image into a grayscale image;

[0015] Step B2, offset calculation: Use edge detection algorithm to process grayscale image and extract contour point set from edge detection result, and perform precise analysis based on 3D point cloud data, including shape analysis and motion trajectory analysis, to determine whether conveyor belt is offset, and calculate the deviation between actual position and expected position of conveyor belt;

[0016] Step B3, generating a correction signal: generating a correction signal according to the deviation calculation result, and sending it to the correction control module.

[0017] In a preferred embodiment, in the offset calculation of step B2, the shape analysis is to process the grayscale image using an edge detection algorithm to obtain a binary edge image, and to extract a contour point set from the edge image using a contour extraction algorithm, and to fit the contour using the least squares method, and to compare it with the three-dimensional model, and to detect any significant shape change by comparing the fitting results of the contour point set with the three-dimensional model, and the specific steps are as follows:

[0018] Step S1, edge detection: Use the edge detection algorithm to process the grayscale image to extract the edge features of the conveyor belt. The edge detection result is a binary image, which is expressed as The edge part is represented by 1 as white, the other part is represented by 0 as black, and ε is the threshold. is the edge intensity, I is the image gray value, and is the gradient of the image in the x and y directions;

[0019] Step S2, contour extraction: Apply the contour extraction algorithm from the edge detection result to identify the contour of the conveyor belt, and use the point set C = {(x k ,y k )|B(x k ,y k )=1,k=1,2,...,m}, where m is the number of contour points, (x k ,y k ) are the coordinates of the contour points;

[0020] Step S3, fitting the three-dimensional model: the obtained three-dimensional point cloud data of the conveyor belt is expressed as P = {(x j ,y j ,z j )|j=1,2,...,n}, where n is the number of point clouds, (x j ,y j ,z j ) represents the 3D coordinates of the jth point in the point cloud. The point cloud data is used to fit the 3D surface of the conveyor belt. The 3D plane model is fitted using the least squares method. The goal is to minimize the sum of the squares of the distances from the point to the plane: Solve for the plane model parameters a, b and c;

[0021] Step S4, shape matching: extract the contour point set C = {(x k ,y k )|B(x k ,y k )=1,k=1,2,...,m} are projected onto the fitted three-dimensional plane model to obtain the projection point set C'={(x k ,y k ,ax k +by k +c)|k=1,2,...,m}, when performing shape matching, calculate the distance D between the contour point and the fitting plane k ={z k -(ax k +by k+c), k=1,2,...,m}, the average distance and maximum distance of all contour points are counted to judge the shape matching quality. The specific calculation formula is as follows:

[0022]

[0023] D max =max(D 1 ,D 2 ,...,D m )

[0024] Among them, D avg is the average distance of contour points, D max is the average distance of contour points, and defines the distance threshold T shape , when D avg >T shape , D max >T shape , indicating that a significant shape change was detected.

[0025] In a preferred embodiment, the motion trajectory analysis is to record the contour point set and three-dimensional point cloud data at each moment to form time series data, analyze the contour point set at each moment, extract its position in three-dimensional space, obtain the actual position at each moment, calculate the centroid according to the contour point set, and analyze the motion trajectory of the conveyor belt with the motion trajectory of the centroid. The specific steps are as follows:

[0026] Step Y1: Construct time series data: For each time t o (o=1,2,...,T), record the contour point set as C o ={(x i,o ,y i,o )|i=1,2,...,m o}, calculate the centroid of the contour point set as Center of mass o The coordinates of (x γ,o ,y γ,o ), record the corresponding three-dimensional point cloud data as P o ={(x j,o ,y j,o ,z j,o )|j=1,2,...,n o}, and record the centroid position at each moment as time series data T = {(t o ,γ o )|o=1,2,..,T};

[0027] Step Y2, calculate the deviation: use the curve fitting method to fit the time series data, and get the fitting function as f(t)=λ 0 +λ1 t+λ 2 t 2 +...+λ d t d , determine the coefficient λ by the least squares method 0 ,λ 1 ,λ 2 ,...λ d : Set the expected trajectory E(t) and the deviation threshold ζ, for each time t o , calculate the deviation between the actual position of the center of mass and the expected trajectory as Among them, E(t o )=(x e (t o ),y e (t o )) is the expected trajectory, δ(t o ) is at time t o The deviation of (x γ,o ,y γ,o ) is the coordinate of the center of mass, when δ(t o )>ζ, it is judged as a deviation.

[0028] In a preferred embodiment, the correction control module includes a correction actuator. After receiving the correction control signal sent by the central processing module, the correction actuator performs a correction operation on the conveyor belt to return it to a normal operating position. The specific steps are as follows:

[0029] Step C1, calculation of the deviation correction amount: the deviation correction control module receives the deviation correction control signal from the central processing module through the communication interface, calculates the deviation correction amount using the control algorithm and generates a deviation correction instruction to the actuator. The specific calculation formula is as follows:

[0030]

[0031] Among them, K p , K i and K d are the proportional, integral and differential gain parameters, δ(t o ) is at time t o The deviation, U(t o ) is the amount of correction;

[0032] Step C2, generating a correction instruction: sending the calculated correction amount as an instruction to the correction actuator, and the actuator adjusts the position of the conveyor belt according to the instruction to return it to the normal operating trajectory.

[0033] In a preferred embodiment, the alarm module dynamically adjusts the alarm signal according to the deviation degree and frequency of the conveyor belt. The specific steps are as follows:

[0034] Step D1, calculation of the degree of deviation: according to the deviation δ(t o ), the average deviation is calculated as The calculated standard deviation of the deviation is used as the degree of deviation Among them, Q is the number of samples in the statistical time period;

[0035] Step D2, offset frequency calculation: set a deviation threshold Δ, calculate the frequency of offset events, where the offset event is the moment when the deviation is greater than the set threshold Δ. The specific calculation formula is as follows:

[0036]

[0037] in, is the offset frequency, 1 is the indicator function, when δ(t o )>Δ, it takes the value 1, otherwise it takes the value 0, β is the total time length of the statistical time period, and Q is the number of samples in the statistical time period;

[0038] Step D3, dynamic alarm signal adjustment: setting the level A of the alarm signal as a function of the degree of deviation and frequency: Among them, ω 1 and ω 2 is the weight coefficient, is the maximum allowed deviation frequency, set the alarm threshold A low and A medium , and set the alarm status according to the alarm signal level A:

[0039] When A≤A low , triggering a low-level alarm;

[0040] When A low <A≤A medium , triggering an intermediate alarm;

[0041] When A>A medium , triggering a high-level alarm.

[0042] The beneficial effects of the present invention are as follows: the present invention comprises a data acquisition module, a central processing module, a correction control module, and an alarm module; the data acquisition module comprises a sensor and a camera, which collects image information of the conveyor belt used in coal mines and transmits it to the central processing module; the central processing module is used to receive and process the operation image transmitted by the data acquisition module, calculate the position deviation of the conveyor belt through an image processing algorithm, and generate a correction signal to send to the correction control module; the correction control module comprises a correction actuator, which corrects the conveyor belt according to the correction signal sent by the central processing module; the alarm module dynamically adjusts the alarm signal according to the degree and frequency of the deviation of the conveyor belt. The present invention uses three-dimensional imaging technology to capture the state of the conveyor belt in real time, and accurately analyzes the shape and motion trajectory of the conveyor belt to timely discover the deviation problem, and automatically corrects the deviation through an intelligent control system, which can reduce the downtime of the conveyor belt caused by the deviation and maintain production continuity. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0045] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0046] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0047] Example 1

[0048] This embodiment provides Figure 1 The conveyor belt deviation correction system for coal mines based on the three-dimensional imaging of the Internet of Things shown in the figure specifically includes a data acquisition module, a central processing module, a deviation correction control module, and an alarm module;

[0049] The data acquisition module is used to collect the operation image of the conveyor belt for coal mines and transmit the operation image to the central processing module;

[0050] The central processing module is used to receive and process the running image transmitted by the data acquisition module, calculate the position deviation of the conveyor belt through the image processing algorithm, and generate a correction signal to send to the correction control module;

[0051] The deviation correction control module corrects the conveyor belt according to the deviation correction signal sent by the central processing module;

[0052] The alarm module dynamically adjusts the alarm signal according to the deviation degree and frequency of the conveyor belt.

[0053] In this embodiment, the data acquisition module specifically needs to be explained. The data acquisition module collects image information of the conveyor belt for coal mines through a three-dimensional imaging sensor and a camera, and transmits it to the central processing module. The specific steps are as follows:

[0054] Step A1, image acquisition: a three-dimensional imaging sensor and a camera are installed at key positions of the conveyor belt, and the three-dimensional imaging sensor is used to collect three-dimensional point cloud data of the conveyor belt. The position of the camera should be able to cover the entire operating area of ​​the conveyor belt to capture the image of the conveyor belt in real time. The acquisition frequency of the three-dimensional imaging sensor is set to once per second to collect the three-dimensional point cloud data of the conveyor belt. The image data of the conveyor belt is captured in real time by the camera to ensure that the state of the entire conveyor belt is covered, and the captured three-dimensional point cloud and image data are pre-processed, including point cloud denoising and image denoising, and adjusting brightness and contrast to improve image quality;

[0055] Step A2, data transmission: Pack the processed image data and 3D point cloud data to create a data packet structure, including image data, timestamp, 3D point cloud data, and image sequence number, and send the packaged data packet to the central processing module through the wireless network interface.

[0056] In this embodiment, the central processing module specifically needs to be explained. The central processing module receives and processes the running image transmitted by the data acquisition module, calculates the position deviation of the conveyor belt through the image processing algorithm, and generates a correction signal to send to the correction control module, processes the image data in real time, and can quickly respond to the state change of the conveyor belt to ensure timely correction of the deviation. The specific steps are as follows:

[0057] Step B1, receiving an image: receiving an image data packet transmitted from a data acquisition module, unpacking the received data packet, extracting image data, timestamp, 3D point cloud data and image sequence number, and scaling and converting the received image into a grayscale image I(x,y) to simplify subsequent processing, where x and y are pixel coordinates of the image;

[0058] Step B2, offset calculation: Use edge detection algorithm to process grayscale image and extract contour point set from edge detection result, capture subtle changes of conveyor belt, ensure sensitive detection of offset, and perform accurate analysis based on 3D point cloud data, including shape analysis and motion trajectory analysis, to determine whether conveyor belt is offset, and calculate the deviation between actual position and expected position of conveyor belt. Shape analysis can evaluate the overall status of conveyor belt, and motion trajectory analysis provides dynamic information of conveyor belt operation. The combination of the two provides comprehensive status evaluation. The combined analysis of edge detection algorithm and 3D point cloud data improves the accuracy and real-time performance of detection.

[0059] Step B3, generating a correction signal: generating a correction signal according to the deviation calculation result, and sending it to the correction control module;

[0060] The shape analysis is to process the grayscale image using an edge detection algorithm to obtain a binary edge image, and to extract a contour point set from the edge image using a contour extraction algorithm, and to fit the contour using the least squares method, and to compare the contour with the three-dimensional model. By comparing the fitting results of the contour point set with the three-dimensional model, any significant shape changes are detected. The specific steps are as follows:

[0061] Step S1, edge detection: Use the edge detection algorithm to process the grayscale image to extract the edge features of the conveyor belt. The edge detection result is a binary image, which is expressed as The edge part is represented by 1 as white, the other part is represented by 0 as black, and ε is the threshold. is the edge intensity, I is the image gray value, and is the gradient of the image in the x and y directions;

[0062] Step S2, contour extraction: Apply the contour extraction algorithm from the edge detection result to identify the contour of the conveyor belt, and use the point set C = {(x k ,y k )|B(x k ,y k )=1,k=1,2,...,m}, where m is the number of contour points, (x k ,y k ) are the coordinates of the contour points;

[0063] Step S3, fitting the three-dimensional model: the obtained three-dimensional point cloud data of the conveyor belt is expressed as P = {(x j ,y j ,z j )|j=1,2,...,n}, where n is the number of point clouds, (x j ,y j ,z j ) represents the 3D coordinates of the jth point in the point cloud. The point cloud data is used to fit the 3D surface of the conveyor belt. The 3D plane model is fitted using the least squares method. The goal is to minimize the sum of the squares of the distances from the point to the plane: Solve for the plane model parameters a, b and c;

[0064] Step S4, shape matching: extract the contour point set C = {(x k ,y k )|B(x k ,y k )=1,k=1,2,...,m} are projected onto the fitted three-dimensional plane model to obtain the projection point set C'={(x k ,y k ,ax k +by k+c)|k=1,2,...,m}, when performing shape matching, calculate the distance D between the contour point and the fitting plane k ={z k -(ax k +by k +c), k=1,2,...,m}, the average distance and maximum distance of all contour points are counted to judge the shape matching quality. The specific calculation formula is as follows:

[0065]

[0066] D max =max(D 1 ,D 2 ,...,D m )

[0067] Among them, D avg is the average distance of contour points, D max is the average distance of contour points, and defines the distance threshold T shape , when D avg >T shape , D max >T shape , indicating that a significant shape change is detected;

[0068] The motion trajectory analysis is to record the contour point set and three-dimensional point cloud data at each moment to form time series data, analyze the contour point set at each moment, extract its position in three-dimensional space, obtain the actual position at each moment, calculate the center of mass based on the contour point set, and analyze the motion trajectory of the conveyor belt based on the motion trajectory of the center of mass. The specific steps are as follows:

[0069] Step Y1: Construct time series data: For each time t o (o=1,2,...,T), record the contour point set as C o ={(x i,o ,y i,o )|i=1,2,...,m o}, calculate the centroid of the contour point set as Center of mass o The coordinates of (x γ,o ,y γ,o ), record the corresponding three-dimensional point cloud data as P o ={(x j,o ,y j,o ,z j,o )|j=1,2,...,n o}, and record the centroid position at each moment as time series data T = {(t o ,γ o )|o=1,2,..,T};

[0070] Step Y2, calculate the deviation: use the curve fitting method to fit the time series data, and get the fitting function as f(t)=λ 0 +λ 1 t+λ 2 t 2 +...+λ d t d , determine the coefficient λ by the least squares method 0 ,λ 1 ,λ 2 ,...λ d : Set the expected trajectory E(t) and the deviation threshold ζ, for each time t o , calculate the deviation between the actual position of the center of mass and the expected trajectory as Among them, E(t o )=(x e (t o ),y e (t o )) is the expected trajectory, δ(t o ) is at time t o The deviation of (x γ,o ,y γ,o ) is the coordinate of the center of mass, when δ(t o )>ζ, it is judged as a deviation.

[0071] In this embodiment, the correction control module specifically needs to be explained. The correction control module includes a correction actuator. After receiving the correction control signal sent by the central processing module, the correction actuator performs a correction operation on the conveyor belt to return it to a normal operating position. The specific steps are as follows:

[0072] Step C1, calculation of the deviation correction amount: the deviation correction control module receives the deviation correction control signal from the central processing module through the communication interface, calculates the deviation correction amount using the control algorithm and generates a deviation correction instruction to the actuator. The specific calculation formula is as follows:

[0073]

[0074] Among them, K p , K i and K d are the proportional, integral and differential gain parameters, δ(t o ) is at time t o The deviation, U(t o ) is the amount of correction;

[0075] Step C2, generate correction instructions: send the calculated correction amount as an instruction to the correction actuator, and the actuator adjusts the position of the conveyor belt according to the instruction to return it to the normal operating trajectory. The correction actuator is used to accurately adjust the conveyor belt, which improves the stability of the conveyor belt and enhances the automation level of the system.

[0076] In this embodiment, it is specifically necessary to explain the alarm module, which dynamically adjusts the alarm signal according to the degree of deviation and frequency of the conveyor belt. According to the degree of deviation, the alarm module can adjust the intensity and frequency of the alarm signal to ensure accurate transmission of the alarm information and avoid false alarms. The specific steps are as follows:

[0077] Step D1, calculation of the degree of deviation: according to the deviation δ(t o ), the average deviation is calculated as The calculated standard deviation of the deviation is used as the degree of deviation Among them, Q is the number of samples in the statistical time period;

[0078] Step D2, offset frequency calculation: set a deviation threshold Δ, calculate the frequency of offset events, where the offset event is the moment when the deviation is greater than the set threshold Δ. The specific calculation formula is as follows:

[0079]

[0080] in, is the offset frequency, 1 is the indicator function, when δ(t o )>Δ, it takes the value 1, otherwise it takes the value 0, β is the total time length of the statistical time period, and Q is the number of samples in the statistical time period;

[0081] Step D3, dynamic alarm signal adjustment: setting the level A of the alarm signal as a function of the degree of deviation and frequency: Among them, ω 1 and ω 2 is the weight coefficient, It is the maximum allowable deviation frequency. By setting different alarm thresholds, graded alarms can be implemented to help operators quickly determine the severity of the problem. low and A medium , and set the alarm status according to the alarm signal level A:

[0082] When A≤A low , triggering a low-level alarm;

[0083] When A low <A≤A medium , triggering an intermediate alarm;

[0084] When A>A medium , triggering a high-level alarm.

[0085] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0086] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0090] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0091] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. The conveyor belt deviation correction system for coal mines based on three-dimensional imaging of the Internet of Things is characterized by: It includes data acquisition module, central processing module, deviation correction control module, and alarm module; The data acquisition module is used to collect the operation image of the conveyor belt for coal mines and transmit the operation image to the central processing module; The central processing module is used to receive and process the running image transmitted by the data acquisition module, calculate the position deviation of the conveyor belt through the image processing algorithm, and generate a correction signal to send to the correction control module. The specific steps are as follows: Step B1, receiving an image: receiving an image data packet transmitted from a data acquisition module, unpacking the received data packet, extracting image data, timestamp, 3D point cloud data and image sequence number, scaling the received image and converting it into a grayscale image I(x,y), where x and y are pixel coordinates of the image; Step B2, offset calculation: Use edge detection algorithm to process grayscale image and extract contour point set from edge detection result, and perform precise analysis based on 3D point cloud data, including shape analysis and motion trajectory analysis, to determine whether conveyor belt is offset, and calculate the deviation between actual position and expected position of conveyor belt; Step B3, generating a correction signal: generating a correction signal according to the deviation calculation result, and sending it to the correction control module; In the offset calculation of step B2, shape analysis is to process the grayscale image using an edge detection algorithm to obtain a binary edge image, and to extract a contour point set from the edge image using a contour extraction algorithm, and to fit the contour using the least squares method, and to compare the contour with the three-dimensional model. By comparing the fitting results of the contour point set and the three-dimensional model, significant shape changes are detected. The specific steps are as follows: Step S1, edge detection: Use the edge detection algorithm to process the grayscale image to extract the edge features of the conveyor belt. The edge detection result is a binary image, which is expressed as The edge part is represented by 1 as white, the other part is represented by 0 as black, and ε is the threshold. is the edge intensity, I is the image gray value, and is the gradient of the image in the x and y directions; Step S2, contour extraction: Apply the contour extraction algorithm from the edge detection result to identify the contour of the conveyor belt, and use the point set C = {(x k ,y k )|B(x k ,y k )=1,k=1,2,...,m}, where m is the number of contour points, (x k ,y k ) are the coordinates of the contour points; Step S3, fitting the three-dimensional model: the obtained three-dimensional point cloud data of the conveyor belt is expressed as P = {(x j ,y j ,z j )|j=1,2,...,n}, where n is the number of point clouds, (x j ,y j ,z j ) represents the 3D coordinates of the jth point in the point cloud. The point cloud data is used to fit the 3D surface of the conveyor belt. The 3D plane model is fitted using the least squares method. The goal is to minimize the sum of the squares of the distances from the point to the plane: Solve for the plane model parameters a, b and c; Step S4, shape matching: extract the contour point set C = {(x k ,y k )|B(x k ,y k )=1,k=1,2,...,m} are projected onto the fitted three-dimensional plane model to obtain the projection point set C'={(x k ,y k ,ax k +by k +c)|k=1,2,...,m}, when performing shape matching, calculate the distance D between the contour point and the fitting plane k ={z k -(ax k +by k +c), k=1,2,...,m}, the average distance and maximum distance of all contour points are counted to judge the shape matching quality. The specific calculation formula is as follows: D max =max(D1,D2,...,D m ) Among them, D avg is the average distance of contour points, D max is the average distance of contour points, and defines the distance threshold T shape , when D avg >T shape , D max >T shape , indicating that a significant shape change is detected; In the offset calculation of step B2, the motion trajectory analysis is to record the contour point set and three-dimensional point cloud data at each moment to form time series data, analyze the contour point set at each moment, extract its position in three-dimensional space, obtain the actual position at each moment, calculate the center of mass based on the contour point set, and analyze the motion trajectory of the conveyor belt based on the motion trajectory of the center of mass. The specific steps are as follows: Step Y1: Construct time series data: For each time t o (o=1,2,...,T), record the contour point set as C o ={(x i,o ,y i,o )|i=1,2,...,m o }, calculate the centroid of the contour point set as Center of mass o The coordinates of (x γ,o ,y γ,o ), record the corresponding three-dimensional point cloud data as P o ={(x j,o ,y j,o ,z j,o )|j=1,2,...,n o }, and record the centroid position at each moment as time series data T = {(t o ,γ o )|o=1,2,..,T}; Step Y2, calculate the deviation: use the curve fitting method to fit the time series data, and get the fitting function as f(t)=λ0+λ1t+λ2t 2 +...+λ d t d , determine the coefficients λ0,λ1,λ2,...λ by the least squares method d : Set the expected trajectory E(t) and the deviation threshold ζ, for each time t o , calculate the deviation between the actual position of the center of mass and the expected trajectory as Among them, E(t o )=(x e (t o ),y e (t o )) is the expected trajectory, δ(t o ) is at time t o The deviation of (x γ,o ,y γ,o ) is the coordinate of the center of mass, when δ(t o )>ζ, it is judged as offset; The deviation correction control module corrects the conveyor belt according to the deviation correction signal sent by the central processing module; The alarm module dynamically adjusts the alarm signal according to the deviation degree and frequency of the conveyor belt.

2. The conveyor belt deviation correction system for coal mines based on Internet of Things three-dimensional imaging according to claim 1 is characterized in that: The data acquisition module collects image information of the conveyor belt for coal mines through a three-dimensional imaging sensor and a camera, and transmits it to the central processing module. The specific steps are as follows: Step A1, image acquisition: setting the acquisition frequency of the three-dimensional imaging sensor to once per second, collecting the three-dimensional point cloud data of the conveyor belt, capturing the image data of the conveyor belt in real time through the camera, and pre-processing the captured three-dimensional point cloud and image data, including point cloud denoising and image denoising, and adjusting brightness and contrast; Step A2, data transmission: Pack the processed image data and 3D point cloud data to create a data packet structure, including image data, timestamp, 3D point cloud data, and image sequence number, and send the packaged data packet to the central processing module through the wireless network interface.

3. The coal mine conveyor belt deviation correction system based on Internet of Things three-dimensional imaging according to claim 1 is characterized in that: The correction control module includes a correction actuator. After receiving the correction control signal sent by the central processing module, the correction actuator performs correction operation on the conveyor belt to return it to the normal operating position. The specific steps are as follows: Step C1, calculation of the deviation correction amount: the deviation correction control module receives the deviation correction control signal from the central processing module through the communication interface, calculates the deviation correction amount using the control algorithm and generates a deviation correction instruction to the actuator. The specific calculation formula is as follows: Among them, K p , K i and K d are the proportional, integral and differential gain parameters, δ(t o ) is at time t o The deviation, U(t o ) is the amount of correction; Step C2, generating a correction instruction: sending the calculated correction amount as an instruction to the correction actuator, and the actuator adjusts the position of the conveyor belt according to the instruction to return it to the normal operating trajectory.

4. The coal mine conveyor belt deviation correction system based on Internet of Things three-dimensional imaging according to claim 1 is characterized in that: The alarm module dynamically adjusts the alarm signal according to the deviation degree and frequency of the conveyor belt. The specific steps are as follows: Step D1, calculation of the degree of deviation: according to the deviation δ(t o ), the average deviation is calculated as The calculated standard deviation of the deviation is used as the degree of deviation Among them, Q is the number of samples in the statistical time period; Step D2, offset frequency calculation: set a deviation threshold Δ, calculate the frequency of offset events, where the offset event is the moment when the deviation is greater than the set threshold Δ. The specific calculation formula is as follows: in, is the offset frequency, 1 is the indicator function, when δ(t o )>Δ, it takes the value 1, otherwise it takes the value 0, β is the total time length of the statistical time period, and Q is the number of samples in the statistical time period; Step D3, dynamic alarm signal adjustment: setting the level A of the alarm signal as a function of the degree of deviation and frequency: Among them, ω1 and ω2 are weight coefficients, is the maximum allowed deviation frequency, set the alarm threshold A low and A medium , and set the alarm state according to the alarm signal level A: when A≤A low , triggering a low-level alarm; when A low <A≤A medium , triggering an intermediate alarm; when A>A medium , triggering a high-level alarm.

Images