Hydraulic support push rod perpendicularity identification method and system

Abstract

The application provides a hydraulic support push rod verticality identification method and system, the method comprising: acquiring a target image of an intersection area of a hydraulic support push rod and a scraper conveyor; applying a preset edge feature extraction model to determine edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image; obtaining respective corresponding edge straight lines of the hydraulic support push rod and the scraper conveyor according to the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor; and obtaining a verticality identification result of the hydraulic support push rod according to the respective corresponding edge straight lines of the hydraulic support push rod and the scraper conveyor. The application can improve the accuracy of hydraulic support push rod verticality identification.

Description

Technical Field

[0001] This application relates to the field of mechanized coal mining technology, and in particular to a method and system for identifying the verticality of a hydraulic support push rod. Background Technology

[0002] In automated operations at fully mechanized mining faces, the verticality of the hydraulic support push rod directly determines the straight-line running performance of the scraper conveyor. If the push rod is tilted, it will lead to conveyor deviation, chain jamming, accelerated chain wear, and even major safety accidents such as support stress imbalance and roof collapse. Therefore, achieving non-contact, high-precision, and real-time online monitoring of the verticality of the hydraulic support push rod has become a key technological requirement for the intelligent upgrading of coal mines.

[0003] In existing technologies, there are two main methods for identifying the verticality of hydraulic support push rods: a contact-based identification method using displacement sensors and a method combining manual visual inspection and measuring tools. The contact-based method involves installing multiple displacement sensors at the connecting pin between the hydraulic support push rod and the scraper conveyor, and then using relative displacement data to infer the angular deviation. The manual visual inspection and measuring tool method primarily involves inspection personnel periodically using tools such as angle gauges and laser rangefinders to measure the tilt angle of the push rod on-site.

[0004] The drawbacks of contact-based identification methods using displacement sensors include: the sensors are directly exposed to high dust, strong vibration, and humid environments, resulting in high failure rates and maintenance costs; they can only indirectly estimate angles and cannot directly obtain geometric posture, limiting detection accuracy (typically with an error > ±9°); installation space is limited, making them prone to interference with moving parts of the support structure, affecting equipment reliability. The drawbacks of manual visual inspection combined with measuring tools include: the existence of monitoring blind spots, low visibility and confined spaces underground, large manual measurement errors, poor safety, and difficulty in meeting the requirements of intelligent mining.

[0005] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section. Summary of the Invention

[0006] To address at least one problem in the prior art, this application proposes a method and system for identifying the verticality of a hydraulic support push rod, which can improve the accuracy of identifying the verticality of the hydraulic support push rod.

[0007] To address the aforementioned technical problems, this application provides the following technical solution: In a first aspect, this application provides a method for identifying the verticality of a hydraulic support push rod, including: Obtain a target image of the intersection area between the hydraulic support push rod and the scraper conveyor; The edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image are determined by applying a preset edge feature extraction model. Based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor, the corresponding edge lines of the hydraulic support push rod and the scraper conveyor are obtained respectively; The verticality identification result of the hydraulic support push rod is obtained based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor.

[0008] In one embodiment, acquiring a target image of the intersection area between the hydraulic support push rod and the scraper conveyor includes: The camera acquisition unit acquires a target image of the intersection area between the hydraulic support push rod and the scraper conveyor, wherein the camera acquisition unit is a camera that is detachably fixed to the outer cylinder of the hydraulic support column and faces the intersection area between the hydraulic support push rod and the scraper conveyor.

[0009] In one embodiment, obtaining the corresponding edge lines of the hydraulic support push rod and the scraper conveyor based on their respective edge pixel coordinates includes: The edge pixel coordinates of the hydraulic support push rod are fitted using the first linear fitting method to obtain the initial fitting result corresponding to the hydraulic support push rod; The initial fitting result corresponding to the hydraulic support push rod is fitted using the second straight line fitting method to obtain the edge straight line corresponding to the hydraulic support push rod. The edge pixel coordinates of the scraper conveyor are fitted using the first linear fitting method to obtain the initial fitting result corresponding to the scraper conveyor; The initial fitting result corresponding to the scraper conveyor is fitted using the second straight line fitting method to obtain the edge straight line corresponding to the scraper conveyor.

[0010] In one embodiment, obtaining the verticality identification result of the hydraulic support push rod based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor includes: The included angle between the hydraulic support push rod and the scraper conveyor is determined based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor, respectively. Determine whether the included angle meets the preset verticality tolerance condition. If yes, determine that the verticality identification result is normal; otherwise, determine that the verticality identification result is abnormal.

[0011] In one embodiment, after obtaining the verticality identification result of the hydraulic support push rod, the method further includes: If the verticality identification result is abnormal, the verticality identification result is sent to the stent electro-hydraulic control system so that the stent electro-hydraulic control system triggers a control operation based on the verticality identification result. The control operation includes at least one of the following: audible and visual alarm, automatic locking and pushing operation, and starting a preset correction program.

[0012] In one embodiment, the method for identifying the verticality of the hydraulic support push rod further includes: Obtain the labels corresponding to each batch of training samples. The training samples are images of the intersection area of ​​the historical hydraulic support push rod and the historical scraper conveyor. Each label includes: the actual edge pixel coordinates of the historical hydraulic support push rod and the historical scraper conveyor. The edge detection fusion algorithm is trained by applying the labels corresponding to each batch of training samples to obtain the preset edge feature extraction model.

[0013] Secondly, this application provides a hydraulic support push rod verticality recognition system, comprising: The camera acquisition unit is used to acquire target images of the intersection area between the hydraulic support push rod and the scraper conveyor; The image recognition processing unit is used to apply a preset edge feature extraction model to determine the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image; The unit is used to obtain the corresponding edge lines of the hydraulic support push rod and the scraper conveyor based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor. The verticality recognition unit is used to obtain the verticality recognition result of the hydraulic support push rod based on the corresponding edge straight lines of the hydraulic support push rod and the scraper conveyor.

[0014] In one embodiment, the camera acquisition unit includes: The first acquisition module is used to acquire target images of the intersection area between the hydraulic support push rod and the scraper conveyor, which are captured by the camera acquisition unit. The camera acquisition unit is a camera that is detachably fixed to the outer cylinder of the hydraulic support column and faces the intersection area between the hydraulic support push rod and the scraper conveyor.

[0015] In one embodiment, the obtaining unit includes: The first fitting module is used to fit the edge pixel coordinates of the hydraulic support push rod using a first straight line fitting method to obtain the initial fitting result corresponding to the hydraulic support push rod. The second fitting module is used to fit the initial fitting result corresponding to the hydraulic support push rod using the second straight line fitting method to obtain the edge straight line corresponding to the hydraulic support push rod. The third fitting module is used to fit the edge pixel coordinates of the scraper conveyor using the first straight line fitting method to obtain the initial fitting result corresponding to the scraper conveyor. The fourth fitting module is used to fit the initial fitting result corresponding to the scraper conveyor using the second straight line fitting method to obtain the edge straight line corresponding to the scraper conveyor.

[0016] In one embodiment, the verticality recognition unit includes: The determining module is used to determine the included angle between the hydraulic support push rod and the scraper conveyor based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor, respectively. The judgment module is used to determine whether the included angle meets the preset verticality tolerance condition. If it does, the verticality recognition result is determined to be normal; otherwise, the verticality recognition result is determined to be abnormal.

[0017] In one embodiment, the hydraulic support push rod verticality recognition system further includes: The sending unit is configured to send the verticality identification result to the stent electro-hydraulic control system if the verticality identification result is abnormal, so that the stent electro-hydraulic control system triggers a control operation based on the verticality identification result. The control operation includes at least one of the following: audible and visual alarm, automatic locking and pushing operation, and starting a preset correction program.

[0018] In one embodiment, the hydraulic support push rod verticality recognition system further includes: The acquisition unit is used to acquire the labels corresponding to each batch of training samples. The training samples are images of the intersection area of ​​the historical hydraulic support push rod and the historical scraper conveyor. Each label includes the actual edge pixel coordinates of the historical hydraulic support push rod and the historical scraper conveyor. The training unit is used to train the edge detection fusion algorithm by applying the labels corresponding to each batch of training samples to obtain the preset edge feature extraction model.

[0019] Thirdly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the hydraulic support push rod verticality recognition method.

[0020] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the hydraulic support push rod verticality identification method.

[0021] Fifthly, this application provides a computer program product, which includes a computer program that, when executed by a processor, implements the hydraulic support push rod verticality recognition method.

[0022] As can be seen from the above technical solution, this application provides a method and system for identifying the verticality of a hydraulic support push rod. The method includes: acquiring a target image of the intersection area of ​​the hydraulic support push rod and the scraper conveyor; applying a preset edge feature extraction model to determine the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image; obtaining the corresponding edge lines of the hydraulic support push rod and the scraper conveyor based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor; and obtaining the verticality identification result of the hydraulic support push rod based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor, which can improve the accuracy of the verticality identification of the hydraulic support push rod. Specifically, it eliminates the need for sensors, enabling non-contact verticality identification and improving robustness; it avoids sensor wear and adapts to high-dust, high-vibration underground environments; and it provides high-precision real-time monitoring: angle error ≤ ±0.5°, response time < 1 second. Superior to traditional methods; Intelligent closed-loop control: Deeply integrated with the electro-hydraulic system to achieve integrated "detection-decision-execution"; Visualization and traceability: The ground end provides full vertical situational awareness of the working face, supporting intelligent operation and maintenance; Strong engineering adaptability: Modular design, easy to deploy quickly on existing fully mechanized mining faces, without the need to modify the main structure of the support. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 This is a first flowchart illustrating the hydraulic support push rod verticality identification method in this application embodiment; Figure 2 This is a second flowchart illustrating the verticality identification method of the hydraulic support push rod in this application embodiment; Figure 3 This is a schematic diagram of the third process of the hydraulic support push rod verticality identification method in the embodiments of this application; Figure 4 This is a schematic diagram of the fourth process of the hydraulic support push rod verticality identification method in the embodiments of this application; Figure 5 This is a schematic diagram of the verticality recognition system of the hydraulic support push rod in the embodiments of this application; Figure 6 This is a schematic diagram showing the relationship between the hydraulic support push rod verticality recognition system and the support electro-hydraulic control system in an application example of this application; Figure 7 This is a schematic block diagram of the system configuration of an electronic device according to an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below 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 in this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0025] To facilitate understanding of this solution, the technical terms related to this solution are explained below.

[0026] Fully mechanized mining face: A coal mining area that uses a complete set of equipment such as coal mining machines, hydraulic supports, and scraper conveyors to work together.

[0027] Hydraulic supports are key equipment used to support the roof of fully mechanized mining faces and maintain a safe working space. Their push rods are used to traction the scraper conveyor to move forward.

[0028] Intrinsically safe camera: An intrinsically safe image acquisition device that complies with GB 3836.4-2021 standard, suitable for explosive gas environments in coal mines, and will not cause an explosion due to electrical sparks or thermal effects.

[0029] Hough Transform: An image processing algorithm for detecting geometric structures such as lines and circles from binary images, used to extract the edge line features of push rods and scraper conveyors.

[0030] Electro-hydraulic control system: The intelligent control core of the hydraulic support, which drives the solenoid valve through electrical signals to control the hydraulic circuit and realize the lifting, pushing and other actions of the support.

[0031] Verticality threshold: The preset allowable angle deviation range (default ±3°) is used to determine whether the push rod and the scraper conveyor are in an ideal vertical state. If it exceeds the limit, an abnormal response will be triggered.

[0032] To address the problems of contact-based vulnerability, slow manual inspection, insufficient accuracy, and inability to achieve closed-loop control in existing technologies, this invention proposes a method and device for identifying the verticality of a hydraulic support push rod. Combining intrinsically safe visual perception and intelligent image analysis, it enables highly reliable, non-contact, millisecond-level response verticality monitoring and automatic correction linkage. Specifically, by employing a special installation architecture for an intrinsically safe camera—a detachable bracket fixed to the outer cylinder of the column—it balances field-of-view coverage, explosion-proof safety, and support movement compatibility; it integrates edge extraction methods from deep learning and traditional image processing to improve feature robustness in low-contrast, high-noise downhole images; it uses an angle calculation mechanism based on geometric straight-line fitting, avoiding reliance on pixel distance conversion and directly obtaining the physical angle; and it integrates with the real-time linkage logic of the electro-hydraulic control system to achieve a millisecond-level closed-loop response from perception to execution.

[0033] The following examples illustrate this in detail.

[0034] To improve the accuracy of hydraulic support push rod verticality recognition, this embodiment provides a hydraulic support push rod verticality recognition method, the execution subject of which is a hydraulic support push rod verticality recognition system. This hydraulic support push rod verticality recognition system includes, but is not limited to, a server, such as... Figure 1 As shown, this method specifically includes the following: Step 100: Obtain the target image of the intersection area between the hydraulic support push rod and the scraper conveyor.

[0035] Specifically, existing methods combining manual visual inspection and measuring tool identification suffer from discontinuous monitoring, blind spots, and an inability to capture dynamic tilting processes. This solution continuously acquires real-time images of the target area where the hydraulic support push rod and the scraper conveyor intersect, enabling continuous monitoring and capturing of dynamic tilting processes. The intersection area can include the point where the hydraulic support push rod and the scraper conveyor intersect, as well as its surrounding area. The hydraulic support push rod can be used to traction the scraper conveyor forward. The target image represents the image of the intersection area between the hydraulic support push rod and the scraper conveyor.

[0036] Step 200: Apply a preset edge feature extraction model to determine the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image.

[0037] Specifically, the target image can be input into the preset edge feature extraction model, and the output of the preset edge feature extraction model can be determined as the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor. The edge pixel coordinates of the hydraulic support push rod can represent the pixel coordinates of the outline of the hydraulic support push rod, and the edge pixel coordinates of the scraper conveyor can represent the pixel coordinates of the outline of the scraper conveyor.

[0038] Specifically, the preset edge feature extraction model can be pre-trained using a hybrid algorithm that combines a deep neural network and Canny edge detection to improve the accuracy of edge extraction in coal dust interference environments; for example, the hybrid algorithm is a YOLOv5 + Canny edge detection fusion algorithm.

[0039] Step 300: Based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor, obtain the corresponding edge lines of the hydraulic support push rod and the scraper conveyor.

[0040] Specifically, the edge pixel coordinates of the hydraulic support push rod can be fitted to obtain the edge line corresponding to the hydraulic support push rod; the edge pixel coordinates of the scraper conveyor can be fitted to obtain the edge line corresponding to each scraper conveyor.

[0041] Step 400: Based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor, obtain the verticality identification result of the hydraulic support push rod.

[0042] Furthermore, to improve the reliability of the edge feature extraction model, multiple sets of standard vertical sample images can be acquired during the working surface initialization stage, i.e., before step 200. The weights of the YOLOv5 model are then fine-tuned using an online learning mechanism based on each set of standard vertical sample images until the angle detection error is ≤ ±0.5° and the single-frame processing latency is ≤ 800 ms. The standard vertical sample images represent images where the angle between the corresponding hydraulic support push rod and the scraper conveyor meets a preset verticality tolerance condition.

[0043] To improve the reliability of acquiring the target image, such as Figure 2 As shown, in one embodiment, step 100 includes: Step 101: Acquire the target image of the intersection area between the hydraulic support push rod and the scraper conveyor captured by the camera acquisition unit. The camera acquisition unit is a camera that is detachably fixed to the outer cylinder of the hydraulic support column and faces the intersection area between the hydraulic support push rod and the scraper conveyor.

[0044] Specifically, the camera can be an intrinsically safe camera, mounted on the outer cylinder of the hydraulic support column via a detachable bracket, for acquiring real-time images of the intersection area between the push rod and the scraper conveyor. The installation position of the intrinsically safe camera ensures that the field of view covers the connection area between the push rod and the scraper conveyor, and the mounting bracket does not affect the extension and retraction stroke of the hydraulic support column. Preferably, the camera can be installed at a height of 1.5–3.0 m from the centerline of the push rod, with a field of view covering the entire intersection area; it can use an M12 industrial-grade Ethernet interface with a transmission rate ≥100 Mbps and support PoE power supply; the camera acquisition unit can be fixed to the outer cylinder of the hydraulic support column via a detachable shock-resistant bracket. The detachable shock-resistant bracket uses a quick-release buckle structure for easy maintenance and disassembly without affecting the extension and retraction stroke of the column. An infrared supplementary lighting module can also be added to improve low-light imaging quality, suitable for extremely dark environments.

[0045] To improve the reliability of obtaining edge straight lines, such as Figure 3 As shown, in one embodiment, step 300 includes: Step 301: Use the first linear fitting method to fit the edge pixel coordinates of the hydraulic support push rod to obtain the initial fitting result corresponding to the hydraulic support push rod.

[0046] Step 302: Use the second straight line fitting method to fit the initial fitting result corresponding to the hydraulic support push rod to obtain the edge straight line corresponding to the hydraulic support push rod.

[0047] Step 303: The edge pixel coordinates of the scraper conveyor are fitted using the first linear fitting method to obtain the initial fitting result corresponding to the scraper conveyor.

[0048] Step 304: Use the second straight line fitting method to fit the initial fitting result corresponding to the scraper conveyor to obtain the edge straight line corresponding to the scraper conveyor.

[0049] Specifically, the first straight-line fitting method can be the Hough transform method, and the second straight-line fitting method can be the least squares straight-line fitting method. The initial fitting result corresponding to the hydraulic support push rod can represent the edge straight-line characteristics of the hydraulic support push rod; the initial fitting result corresponding to the scraper conveyor can represent the edge straight-line characteristics of the scraper conveyor.

[0050] To improve the reliability of the verticality identification results, such as Figure 4 As shown, in one embodiment, step 400 includes: Step 401: Determine the included angle between the hydraulic support push rod and the scraper conveyor based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor.

[0051] Furthermore, three laser rangefinders can be arranged on the column to determine the included angle between the hydraulic support push rod and the scraper conveyor using triangulation.

[0052] Step 402: Determine whether the included angle meets the preset verticality tolerance condition. If yes, determine that the verticality identification result is normal; otherwise, determine that the verticality identification result is abnormal.

[0053] Specifically, the preset verticality tolerance condition can be: |θ - 90°| ≤ Δθ, where θ is the included angle and Δθ is the verticality tolerance threshold. Δθ can be configured as: 1° ≤ Δθ ≤ 5°, preferably Δθ = 3°.

[0054] Existing manual visual inspection combined with gauge recognition methods suffers from limitations in integration with control systems and delayed correction responses. Therefore, to respond promptly to verticality anomalies, in one embodiment, after step 400, the following is also included: Step 500: If the verticality identification result is abnormal, the verticality identification result is sent to the stent electro-hydraulic control system so that the stent electro-hydraulic control system triggers a control operation based on the verticality identification result. The control operation includes at least one of the following: audible and visual alarm, automatic locking and pushing operation, and starting a preset correction program.

[0055] Furthermore, if the verticality identification result indicates normal verticality, the target image acquisition time, the angle between the hydraulic support push rod and the scraper conveyor, and the deviation value of the angle can be sent to the ground control center. The ground control center displays the verticality curve, deviation value, and alarm status in real time, and supports historical data storage (≥90 days), trend analysis, and report export. The verticality curve may include the correspondence between the angle between the hydraulic support push rod and the scraper conveyor and the acquisition time.

[0056] Specifically, it can acquire images of the intersection area in real time; extract the straight lines at the edges of the push rod and the scraper conveyor; calculate the included angle between them and compare it with 90°; if the deviation exceeds the threshold, it will trigger a drive signal to the electro-hydraulic control system of the support, which can control the movement of the hydraulic support push rod.

[0057] To improve the accuracy and reliability of the edge feature extraction model, in one embodiment, the hydraulic support push rod verticality recognition method further includes: Step 001: Obtain the labels corresponding to each batch of training samples. The training samples are images of the intersection area of ​​the historical hydraulic support push rod and the historical scraper conveyor. Each label includes the actual edge pixel coordinates of the historical hydraulic support push rod and the historical scraper conveyor.

[0058] Step 002: Use the labels corresponding to each batch of training samples to train the edge detection fusion algorithm to obtain the preset edge feature extraction model.

[0059] Specifically, the edge detection fusion algorithm can be the YOLOv5 + Canny edge detection fusion algorithm.

[0060] From a software perspective, to improve the accuracy of hydraulic support push rod verticality recognition, this application provides an embodiment of a hydraulic support push rod verticality recognition system for implementing all or part of the aforementioned hydraulic support push rod verticality recognition method. See [link to relevant documentation]. Figure 5 The hydraulic support push rod verticality recognition system specifically includes the following components: The camera acquisition unit 01 is used to acquire target images of the intersection area between the hydraulic support push rod and the scraper conveyor; Image recognition processing unit 02 is used to apply a preset edge feature extraction model to determine the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image; Unit 03 is used to obtain the corresponding edge lines of the hydraulic support push rod and the scraper conveyor based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor. The verticality recognition unit 04 is used to obtain the verticality recognition result of the hydraulic support push rod based on the corresponding edge straight lines of the hydraulic support push rod and the scraper conveyor.

[0061] In one embodiment, the camera acquisition unit includes: The first acquisition module is used to acquire target images of the intersection area between the hydraulic support push rod and the scraper conveyor, which are captured by the camera acquisition unit. The camera acquisition unit is a camera that is detachably fixed to the outer cylinder of the hydraulic support column and faces the intersection area between the hydraulic support push rod and the scraper conveyor.

[0062] In one embodiment, the obtaining unit includes: The first fitting module is used to fit the edge pixel coordinates of the hydraulic support push rod using a first straight line fitting method to obtain the initial fitting result corresponding to the hydraulic support push rod. The second fitting module is used to fit the initial fitting result corresponding to the hydraulic support push rod using the second straight line fitting method to obtain the edge straight line corresponding to the hydraulic support push rod. The third fitting module is used to fit the edge pixel coordinates of the scraper conveyor using the first straight line fitting method to obtain the initial fitting result corresponding to the scraper conveyor. The fourth fitting module is used to fit the initial fitting result corresponding to the scraper conveyor using the second straight line fitting method to obtain the edge straight line corresponding to the scraper conveyor.

[0063] In one embodiment, the verticality recognition unit includes: The determining module is used to determine the included angle between the hydraulic support push rod and the scraper conveyor based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor, respectively. The judgment module is used to determine whether the included angle meets the preset verticality tolerance condition. If it does, the verticality recognition result is determined to be normal; otherwise, the verticality recognition result is determined to be abnormal.

[0064] In one embodiment, the hydraulic support push rod verticality recognition system further includes: The sending unit is configured to send the verticality identification result to the stent electro-hydraulic control system if the verticality identification result is abnormal, so that the stent electro-hydraulic control system triggers a control operation based on the verticality identification result. The control operation includes at least one of the following: audible and visual alarm, automatic locking and pushing operation, and starting a preset correction program.

[0065] In one embodiment, the hydraulic support push rod verticality recognition system further includes: The acquisition unit is used to acquire the labels corresponding to each batch of training samples. The training samples are images of the intersection area of ​​the historical hydraulic support push rod and the historical scraper conveyor. Each label includes the actual edge pixel coordinates of the historical hydraulic support push rod and the historical scraper conveyor. The training unit is used to train the edge detection fusion algorithm by applying the labels corresponding to each batch of training samples to obtain the preset edge feature extraction model.

[0066] The embodiments of the hydraulic support push rod verticality recognition system provided in this specification can be used to execute the processing flow of the embodiments of the hydraulic support push rod verticality recognition method described above. Its functions will not be repeated here, but can be referred to the detailed description of the embodiments of the hydraulic support push rod verticality recognition method described above.

[0067] To further illustrate this solution, this application provides an application example of a hydraulic support push rod verticality recognition system. In this application example, the system includes: a camera acquisition unit, an image recognition and processing unit, an angle calculation unit, a status determination unit, a linkage control unit, and a ground monitoring unit; the support electro-hydraulic control system can be connected to the linkage control unit and the ground monitoring unit respectively; as follows: Figure 6 As shown, the camera acquisition unit acquires high-definition images in real time; the image recognition and processing unit outputs edge pixel coordinates; the angle calculation unit calculates the included angle data; the status determination unit sends abnormal signals to the linkage control unit and normal signals to the ground monitoring unit; the linkage control unit sends alarm / correction signals to the support electro-hydraulic control system, and the support electro-hydraulic control system provides feedback to the ground monitoring unit; the ground monitoring unit can perform threshold adjustment and edge feature extraction model parameter setting / adjustment, and can construct a closed-loop system of six units: "perception—recognition—calculation—determination—control—feedback"; the function achieved by the combination of the angle calculation unit and the status determination unit is equivalent to the function achieved by the combination of the acquisition unit and the verticality recognition unit, and the function achieved by the linkage control unit is equivalent to the function achieved by the sending unit. Specific details are as follows: 1) Camera acquisition unit: It adopts an intrinsically safe high-definition camera (≥1080P, ≥25 fps), which is fixed to the outer cylinder of the hydraulic support column through a detachable anti-vibration bracket, and is aligned with the intersection area of ​​the push rod and the scraper conveyor to achieve stable image acquisition.

[0068] 2) Image recognition processing unit: configured to run a deep learning model to extract the edge lines of the push rod and the scraper conveyor; embeds a deep learning-based edge feature extraction model (such as the improved YOLOv5 + Canny edge detection fusion algorithm) to accurately segment the outline of the push rod and the scraper conveyor and output the edge pixel coordinates.

[0069] During the initialization phase of the working face, ≥50 sets of standard vertical sample images are collected; the weights of the YOLOv5 model are fine-tuned through an online learning mechanism to ensure that the angle detection error is ≤ ±0.5° and the single-frame processing latency is ≤ 800 ms.

[0070] 3) Angle Calculation Unit: Using Hough transform combined with least squares line fitting, the line parameters of the two extracted edge lines are estimated, and their included angle θ is calculated. Alternatively, the included angle can be calculated by fitting the edge lines based on Hough transform or least squares method.

[0071] Hough transform, parameter space, most likely line segment, least squares line fitting of line segment, optimal line equation.

[0072] 4) Status determination unit: used to compare the included angle with the verticality threshold and output an abnormal signal; set the verticality tolerance threshold Δθ (default Δθ = 3°, configurable range 1°~5°), if |θ - 90°| > Δθ, it is determined as "verticality abnormal".

[0073] 5) Linkage Control Unit: Communicates with the support electro-hydraulic control system, and executes alarm or correction operations in response to the abnormal signals; the abnormal signals are transmitted to the support electro-hydraulic control system in real time via industrial Ethernet, triggering any of the following actions: Audible and visual alarm; Automatic locking and pushing operation; Initiate the preset correction program (such as fine-tuning the timing of adjacent support movement).

[0074] 6) Ground monitoring unit: Used to receive and visualize angle data and system status; deployed in the ground control center, it displays verticality curves, deviation values, and alarm status in real time, and supports historical data storage (≥90 days), trend analysis, and report export. All angle data, alarm events, and control commands can be timestamped and stored in the database; it supports multi-dimensional queries by support number, shift, and date, meeting the requirements of coal mine safety audits.

[0075] As described above, the hydraulic support push rod verticality recognition system provided in this application example can realize the following: continuous image acquisition by camera → edge pixel coordinates output by image recognition unit → angle calculation → threshold comparison by judgment module → linkage of electro-hydraulic system in case of abnormality → synchronous recording by ground terminal, thereby improving the accuracy of hydraulic support push rod verticality recognition.

[0076] Figure 7 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 7 As shown, the electronic device includes: a memory 701, a processor 702, and a computer program stored in the memory 701 and executable on the processor 702. When the processor 702 executes the computer program, it implements the following method: Obtain a target image of the intersection area between the hydraulic support push rod and the scraper conveyor; The edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image are determined by applying a preset edge feature extraction model. Based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor, the corresponding edge lines of the hydraulic support push rod and the scraper conveyor are obtained respectively; The verticality identification result of the hydraulic support push rod is obtained based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor.

[0077] This embodiment discloses a computer program product, which includes a computer program that, when executed by a processor, implements the following method: Obtain a target image of the intersection area between the hydraulic support push rod and the scraper conveyor; The edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image are determined by applying a preset edge feature extraction model. Based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor, the corresponding edge lines of the hydraulic support push rod and the scraper conveyor are obtained respectively; The verticality identification result of the hydraulic support push rod is obtained based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor.

[0078] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the following method: Obtain a target image of the intersection area between the hydraulic support push rod and the scraper conveyor; The edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image are determined by applying a preset edge feature extraction model. Based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor, the corresponding edge lines of the hydraulic support push rod and the scraper conveyor are obtained respectively; The verticality identification result of the hydraulic support push rod is obtained based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor.

[0079] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0080] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0081] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0082] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0083] In the description of this specification, the references to terms such as "an embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0084] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for identifying the verticality of a hydraulic support push rod, characterized in that, include: Obtain a target image of the intersection area between the hydraulic support push rod and the scraper conveyor; The edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image are determined by applying a preset edge feature extraction model. Based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor, the corresponding edge lines of the hydraulic support push rod and the scraper conveyor are obtained respectively; The verticality identification result of the hydraulic support push rod is obtained based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor.

2. The method for identifying the verticality of the hydraulic support push rod according to claim 1, characterized in that, The acquisition of the target image of the intersection area between the hydraulic support push rod and the scraper conveyor includes: The camera acquisition unit acquires a target image of the intersection area between the hydraulic support push rod and the scraper conveyor, wherein the camera acquisition unit is a camera that is detachably fixed to the outer cylinder of the hydraulic support column and faces the intersection area between the hydraulic support push rod and the scraper conveyor.

3. The method for identifying the verticality of the hydraulic support push rod according to claim 1, characterized in that, The step of obtaining the corresponding edge lines of the hydraulic support push rod and the scraper conveyor based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor includes: The edge pixel coordinates of the hydraulic support push rod are fitted using the first linear fitting method to obtain the initial fitting result corresponding to the hydraulic support push rod; The initial fitting result corresponding to the hydraulic support push rod is fitted using the second straight line fitting method to obtain the edge straight line corresponding to the hydraulic support push rod. The edge pixel coordinates of the scraper conveyor are fitted using the first linear fitting method to obtain the initial fitting result corresponding to the scraper conveyor; The initial fitting result corresponding to the scraper conveyor is fitted using the second straight line fitting method to obtain the edge straight line corresponding to the scraper conveyor.

4. The method for identifying the verticality of the hydraulic support push rod according to claim 1, characterized in that, The step of obtaining the verticality identification result of the hydraulic support push rod based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor includes: The included angle between the hydraulic support push rod and the scraper conveyor is determined based on the corresponding edge lines of the hydraulic support push rod and the scraper conveyor, respectively. Determine whether the included angle meets the preset verticality tolerance condition. If yes, determine that the verticality identification result is normal; otherwise, determine that the verticality identification result is abnormal.

5. The method for identifying the verticality of the hydraulic support push rod according to claim 1, characterized in that, After obtaining the verticality identification result of the hydraulic support push rod, the method further includes: If the verticality identification result is abnormal, the verticality identification result is sent to the stent electro-hydraulic control system so that the stent electro-hydraulic control system triggers a control operation based on the verticality identification result. The control operation includes at least one of the following: audible and visual alarm, automatic locking and pushing operation, and starting a preset correction program.

6. The method for identifying the verticality of the hydraulic support push rod according to claim 1, characterized in that, Also includes: Obtain the labels corresponding to each batch of training samples. The training samples are images of the intersection area of ​​the historical hydraulic support push rod and the historical scraper conveyor. Each label includes: the actual edge pixel coordinates of the historical hydraulic support push rod and the historical scraper conveyor. The edge detection fusion algorithm is trained by applying the labels corresponding to each batch of training samples to obtain the preset edge feature extraction model.

7. A hydraulic support push rod verticality recognition system, characterized in that, include: The camera acquisition unit is used to acquire target images of the intersection area between the hydraulic support push rod and the scraper conveyor; The image recognition processing unit is used to apply a preset edge feature extraction model to determine the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor in the target image; The unit is used to obtain the corresponding edge lines of the hydraulic support push rod and the scraper conveyor based on the edge pixel coordinates of the hydraulic support push rod and the scraper conveyor. The verticality recognition unit is used to obtain the verticality recognition result of the hydraulic support push rod based on the corresponding edge straight lines of the hydraulic support push rod and the scraper conveyor.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the hydraulic support push rod verticality identification method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the hydraulic support push rod verticality identification method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the hydraulic support push rod verticality identification method according to any one of claims 1 to 6.

Images