Fully-mechanized coal mining face cooperative control method, device and electronic equipment

Abstract

The application discloses a fully-mechanized coal mining face cooperative control method and device and electronic equipment, and relates to the technical field of coal mining control. The method comprises the following steps: continuously collecting image data of a trailing area of a working face after a coal mining machine passes through by using a backward vision acquisition unit arranged on the coal mining machine and facing the opposite direction of the running direction of the coal mining machine; identifying the spatial state of the working face equipment and the space-time relationship between the equipment according to the image data, wherein the working face equipment comprises the coal mining machine, hydraulic supports and a scraper conveyor; constructing a space-time cooperative model between the working face equipment according to the spatial state and the space-time relationship; judging whether the fully-mechanized coal mining face meets a preset cooperative safety condition based on the space-time cooperative model between the working face equipment, and if not, performing linkage control on the hydraulic supports, the scraper conveyor and / or the coal mining machine; after the linkage control is performed, returning to and repeating the above-mentioned steps of collecting, identifying, constructing and judging until the cooperative safety condition is met.

Description

Technical Field

[0001] This invention relates to the field of coal mining control technology, specifically to a collaborative control method, device, and electronic equipment for fully mechanized mining faces. Background Technology

[0002] The fully mechanized longwall face is the core production unit of mechanized coal mining in underground coal mines. It consists of a coal mining machine, hydraulic supports, and a scraper conveyor. The face advances through coordinated operations of cutting, coal cutting, coal transportation, and roof support. These three components must maintain a strict spatial and temporal sequence: after the coal mining machine passes, the hydraulic supports must be moved / pushed in a timely and accurate manner to achieve effective support; otherwise, problems such as missing supports, roof spalling, coal pile-up, and poor face straightness can easily occur. Current control methods are still mainly focused on the level of individual equipment, making it difficult to achieve coordinated control based on the overall state of the longwall face.

[0003] Currently, automated systems primarily rely on sensors mounted on hydraulic supports to obtain status information, such as stroke, pressure, and tilt angle data. This data is affected by the working conditions at the face and is also subject to sensor drift or error accumulation, making it difficult to accurately reflect the actual spatial geometry of the equipment. Therefore, it is challenging to ensure the coordinated operation of the coal mining machine, hydraulic supports, and scraper conveyor. Currently, cameras installed at the working face are mostly used for monitoring, not for establishing continuous spatiotemporal relationship models. Consequently, they cannot be used to judge the overall state of the working face or serve as a basis for automatic control.

[0004] Currently, hydraulic supports are typically equipped with pressure sensors, stroke sensors, tilt sensors, and solenoid valve feedback signals to determine whether the support action has been performed and its subsequent state. Coal mining machines achieve traction control through encoders, tilt sensors, and motor current and speed signals. Scraper conveyors reflect the load state through motor current or speed and use this information for start / stop or linkage control. This type of control method uses internal equipment status detection: it only reflects the working status of a single piece of equipment, the acquired data is the result of the action of a single piece of equipment, and it cannot determine the spatial relationship between equipment.

[0005] In automated fully mechanized mining faces, the trigger conditions for support movement are set according to the position or running distance of the coal mining machine to execute functions such as automatic conveyor pushing / automatic support movement. The control system executes the hydraulic support actions according to preset logic. This method is a rule-based open-loop automation control, characterized by: control based on position or time parameters; no comparison or correction between the control results and the spatial geometry of the equipment; and the inability to judge the operational quality of the hydraulic support.

[0006] The cameras used on the working face are mostly installed on hydraulic supports to achieve remote visual monitoring. Dispatchers observe the support movements, coal flow, and equipment operating status through video, and intervene manually or remotely in case of abnormalities. This method is actually an auxiliary control system based on human interpretation, with the following characteristics: video is only used as a basis for human observation, does not participate in automatic decision-making, and relies on operational experience.

[0007] While the aforementioned technologies have improved automation to some extent, they still have significant limitations: They lack the ability to perceive the overall state of the working face. Existing systems primarily acquire signals from individual devices, failing to describe the true state of the working face and unable to determine: whether the supports are truly following the machine, whether the conveyor push is complete, whether the hydraulic supports are properly moved, whether the sidewalls are supporting the coal face, whether there are any abnormalities in the coal transported by the scraper conveyor, or whether the coal mining machine cable is in normal condition. They also cannot identify the quality of action completion: although sensor signals reflect the movement process and results of the actuators, they are not compared with the spatial constraints of the three machines. Under complex geological conditions, this often leads to: missing supports, sidewalls not adhering to the coal face, conveyor deviation, hydraulic support skew, localized coal accumulation on the conveyor, and abnormal dragging of the coal mining machine cable. Furthermore, the control is open-loop or semi-closed-loop: automatic support movement is often triggered by the position of the coal mining machine, rather than by the actual state of the working face. When the coal seam changes or equipment is obstructed, the predetermined sequence is still followed, easily causing problems such as missing supports and delayed support. The system lacks the ability to automatically adjust based on the results. The video system is not involved in automatic control: Although video surveillance exists, its information is not used in a structured way by the system and still relies on manual observation and judgment. It cannot be used as input parameters for equipment control and cannot form a basis for automatic decision-making. There is a lack of effective perception of the area after the coal mining machine has passed: Existing monitoring is mostly concentrated in the area in front of the coal mining machine, while actual dangers often occur in the support area after the machine has passed, such as delayed supports, inadequate conveyor pushing, or coal accumulation on the conveyor. Current technology lacks automatic assessment methods for the continuous state of this area.

[0008] 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

[0009] In order to solve at least one of the above-mentioned problems in the prior art, embodiments of the present invention provide a method, apparatus and electronic device for coordinated control of fully mechanized mining faces.

[0010] This invention provides a method for coordinated control of a fully mechanized mining face, which performs the following steps in each detection cycle: Using the rearward vision acquisition unit on the coal mining machine that faces the opposite direction of its movement, image data of the working face trailing behind the coal mining machine are continuously acquired. Based on the image data, the spatial state of the working face equipment and the spatiotemporal relationship between the equipment are identified, wherein the working face equipment includes a coal mining machine, a hydraulic support, and a scraper conveyor; Based on the identified spatial state and spatiotemporal relationship, a spatiotemporal collaboration model among the working face equipment is constructed. Based on the spatiotemporal coordination model among the working face equipment, it is determined whether the fully mechanized mining face meets the preset coordination safety conditions. If not, linkage control is performed on the hydraulic support, scraper conveyor and / or coal mining machine. After executing the linkage control, return and repeat the above steps of data collection, identification, construction and judgment until the collaborative security conditions are met.

[0011] In some embodiments, the trailing area of ​​the working face includes at least: a hydraulic support area, a scraper conveyor area, a side guard plate area, a cable trough area, and a cut coal face area.

[0012] In some embodiments, identifying the spatial state and spatiotemporal relationship of the work surface equipment based on the image data specifically includes: Based on the image data, the spatial status of the working face equipment and the spatial relationship between the equipment at each acquisition time are determined. The spatial status of the working face equipment includes the position and / or posture of the hydraulic support, the position of the pusher device, the status of the side guard plate, the position of the scraper conveyor and the coal flow pattern, and the cable dragging pattern. The spatial relationship between the equipment includes the relative positional relationship between the coal mining machine and the hydraulic support. Based on the spatial state of the working surface equipment at each acquisition moment, the dynamic change trend of equipment actions is identified; Based on the spatial relationship between the devices at each acquisition time, the spatiotemporal relationship of the working face devices is identified.

[0013] In some embodiments, the collaborative security conditions include: The hydraulic support has been moved into place; The pushing action is completed and the position of the scraper conveyor meets the set geometric requirements; The side guard plate is in the attached position; The scraper conveyor's coal conveying capacity meets the cutting speed requirements; The cable condition trend is normal.

[0014] In some embodiments, the linkage control includes at least one of the following control methods: Control the hydraulic support to continue moving or prevent the next support from moving; Control the scraper conveyor to accelerate, decelerate, or stop; Control the coal mining machine to slow down, stop, or wait; Issue a warning signal.

[0015] In some embodiments, the relative positional relationship between the coal mining machine and the hydraulic support includes the following distance. By calculating the following distance and comparing it with a preset maximum allowable following distance, when the following distance is less than or equal to the preset maximum allowable following distance, it is determined that the hydraulic support has completed the shift and reached the preset position. The hydraulic support's operating state includes a pushing action. The lateral offset of the scraper conveyor is detected and compared with a preset maximum allowable offset threshold. When the lateral offset is less than or equal to the preset maximum allowable offset threshold, the pushing action is determined to be complete. The coal transport state of the scraper conveyor includes the coal pile state. The coal pile index is obtained by calculating the ratio of the coal flow area to the reference area of ​​the scraper conveyor trough cross section. The coal pile index is then compared with a preset coal pile threshold. When the coal pile index is greater than the preset coal pile threshold, it is determined that there is abnormal coal pile. The cable dragging pattern of the coal mining machine includes abnormal dragging state. By extracting at least one feature of the cable bending arc, lateral offset, and tangled area ratio, the cable abnormality degree is calculated. The cable abnormality degree is compared with a preset abnormality threshold. When the cable abnormality degree is greater than the preset abnormality threshold, the cable dragging is determined to be abnormal. The working surface equipment space status also includes the action completion status. By calculating the time window mean of the action status in multiple consecutive frames of images, an estimated value of action completion is obtained. When the estimated value is greater than the preset completion threshold, it is determined that the action has been stably completed.

[0016] In some embodiments, the method further includes: using a forward vision acquisition unit installed on the coal mining machine to acquire image data of the cable trough area and the scraper conveyor area in front of the coal mining machine, so as to assist in determining the status of the cable trough area and the scraper conveyor area.

[0017] This invention also provides a collaborative control device for a fully mechanized mining face, comprising: The acquisition module is used to continuously acquire image data of the trailing area of ​​the working face after the coal mining machine has passed by, using the rearward vision acquisition unit set on the coal mining machine facing the opposite direction of its travel. The recognition module is used to identify the spatial status of the working face equipment and the spatiotemporal relationship between the equipment based on the image data, wherein the working face equipment includes a coal mining machine, a hydraulic support, and a scraper conveyor. The module is used to build a spatiotemporal collaboration model between working face equipment based on the identified spatial state and spatiotemporal relationship; The linkage control module is used to determine whether the fully mechanized mining face meets the preset collaborative safety conditions based on the spatiotemporal coordination model between the working face equipment. If not, linkage control is performed on the hydraulic support, scraper conveyor and / or coal mining machine. The loop control module is used to return to and repeat the above acquisition, identification, construction and judgment steps after the linkage control is executed, until the coal mining machine is restored after the collaborative safety conditions are met, and the above steps are continuously executed in a loop.

[0018] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the program to implement the method described in any of the above embodiments.

[0019] This invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any of the above embodiments.

[0020] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the methods described in any of the above embodiments.

[0021] The fully mechanized mining face collaborative control method, device, and electronic equipment proposed in this invention continuously acquire image data of the area traversed by the coal mining machine using a rear-facing camera installed on the machine. This constructs a spatiotemporal collaborative model of the face equipment. Based on this model, it determines whether the face meets collaborative safety conditions. If the conditions are not met, it implements coordinated control of the hydraulic supports, scraper conveyor, and / or the coal mining machine, thereby achieving closed-loop collaborative control based on the actual spatial state of the face and realizing closed-loop safe production control of the fully mechanized mining face. Compared with existing technologies, this invention uses the overall spatial state of the face as the control basis, rather than single-device signals; it judges the action quality of the equipment based on the spatial geometric relationship of the three machines; it establishes a continuous time-series analysis mechanism to identify action trends and abnormal evolution processes; and it achieves collaborative closed-loop control among multiple devices in the fully mechanized mining face, improving support quality and production safety. Attached Figure Description

[0022] 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 only 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 flowchart illustrating a collaborative control method for a fully mechanized mining face provided in an embodiment of the present invention.

[0023] Figure 2 This is a partial flowchart illustrating a collaborative control method for a fully mechanized mining face provided in an embodiment of the present invention.

[0024] Figure 3This is a schematic diagram of the structure of a fully mechanized mining face collaborative control device provided in an embodiment of the present invention.

[0025] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] Detailed reference is made to exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings, wherein the same reference numerals in different drawings denote the same or similar elements unless otherwise stated. In the following description of exemplary embodiments, the described embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with several aspects of the invention as described in the appended claims.

[0027] The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In this invention and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein is intended to represent and include any or all possible combinations of one or more of the associated listed items.

[0028] It should be understood that although the terms “first,” “second,” “third,” etc., may be used herein to describe various types of information, such information should not be limited by these terms. These terms are only used to distinguish the types of information. For example, without departing from the scope of the invention, first information may be referred to as second information, and similarly, second information may be referred to as first information. The term “if” as used herein may be understood, depending on the context, to mean “at the time,” “at this moment,” or “in response to a judgment.”

[0029] To address the problems of existing fully mechanized mining face control systems that rely on equipment sensors, lack the ability to judge overall spatial geometric relationships, and are unable to form closed-loop collaborative control based on the actual working face state, this invention provides a collaborative control method for fully mechanized mining faces.

[0030] Figure 1 This is a flowchart illustrating a collaborative control method for a fully mechanized mining face provided by an embodiment of the present invention. Figure 1 As shown, the fully mechanized mining face collaborative control method provided in this embodiment of the invention performs the following steps in each detection cycle: S1. Using the rearward vision acquisition unit set on the coal mining machine facing the opposite direction of its travel, continuously acquire image data of the working face trailing area after the coal mining machine has passed. In step S1, a camera can be installed on the side of the cable trough of the coal mining machine, with the camera's optical axis facing the opposite direction of the coal mining machine's movement, to continuously collect image data of the trailing area of ​​the working face after the coal mining machine has passed. The trailing area of ​​the working face includes at least: the hydraulic support area, the scraper conveyor area, the side guard plate area, the cable trough area, and the cut coal face area.

[0031] S2. Based on the image data, identify the spatial state of the working face equipment and the spatiotemporal relationship between the equipment, wherein the working face equipment includes a coal mining machine, a hydraulic support, and a scraper conveyor; In step S2, the spatial state of the equipment on the working face and the spatiotemporal relationship between the equipment are identified. This includes identifying and locating the spatial state of the equipment, as well as extracting the spatial distance, relative angle and geometric relationship between the equipment. It also includes performing time series analysis on continuous frames to identify the dynamic change trend of the equipment's actions, such as dynamic change curves.

[0032] S3. Based on the identified spatial status and spatiotemporal relationships, construct a spatiotemporal collaboration model among the working face equipment; In step S3, based on the identified spatial state and spatiotemporal relationship, a collaborative relationship model between the coal mining machine, hydraulic support, and scraper conveyor is established. Specifically, this model may include at least one of the following: support relocation positioning model, conveyor positioning determination model, sidewall support status model, and cable dragging abnormal status determination model. Support relocation model: The following distance between the coal mining machine and the hydraulic support is used as the criterion. Let the working face direction coordinate of the coal mining machine at time t be x_shearer(t), and the coordinate of the nth hydraulic support be x_support,n(t). The following distance is defined as: D_follow(t) = | x_shearer(t) - x_support,n(t) | When D_follow(t) <= D_max, it is determined that the hydraulic support has completed the shift and is within the allowable following range; otherwise, the supplementary support control is triggered. D_max is the preset maximum allowable following distance, typically 1.5 to 3 times the center-to-center distance of the hydraulic supports.

[0033] Push-to-position determination model: The lateral offset of the scraper conveyor is used as the criterion. Let the measured lateral position of the scraper conveyor in the image be L_conv(t), the standard target position be L_ref, and the offset be defined as: Delta_s(t) = | L_conv(t) - L_ref | When Delta_s(t) <= Delta_s_max, the push-pull action is considered complete; otherwise, a push-pull retry or a reduction in traction speed is triggered. Delta_s_max is the maximum allowable offset threshold.

[0034] Side protection plate support status model: The contact status between the side protection plate and the coal wall is identified by image recognition. When the contact status detection value contact_state = True, it is determined that the side protection plate is in place. Otherwise, the side protection plate is triggered to extend again.

[0035] Cable dragging anomaly determination model: The model uses cable anomaly degree as the criterion. Multi-dimensional features such as cable bending radius, lateral offset, and tangled area proportion are extracted from the image, and weighted summation is used to obtain the cable anomaly degree. E_cable(t) = SUM_k [omega_k] f_k(t) Where omega_k is the weight coefficient of the k-th feature, and f_k(t) is the normalized value of the k-th feature. When E_cable(t) > E_th, an abnormal cable dragging is determined, triggering the coal mining machine to reduce speed or stop.

[0036] S4. Based on the spatiotemporal coordination model between the working face equipment, determine whether the fully mechanized mining face meets the preset coordination safety conditions. If not, perform linkage control on the hydraulic support, scraper conveyor and / or coal mining machine. In step S4, the coordinated safety conditions include: the hydraulic support is in place, the pusher action is completed and the scraper conveyor position meets the set geometric requirements, the side guard plate is in place, the scraper conveyor's coal conveying capacity meets the cutting speed requirements (i.e., the coal pile index is normal), and the cable dragging status is normal. If any condition is not met, it is determined that the coordinated safety conditions are not met. Specifically: Based on the spatiotemporal coordination model among the working face equipment, the judgment results of each sub-model are logically combined to obtain the comprehensive coordinated safety state. Let the five sub-conditions be: Cond1: The hydraulic support has been moved into place (D_follow(t) <= D_max) Cond2: The pushing action is completed and the position of the scraper conveyor meets the geometric requirements (Delta_s(t) <= Delta_s_max). Cond3: The side panel is properly attached (contact_state = True) Cond4: The scraper conveyor's coal transport capacity meets the cutting speed requirements (i.e., the coal pile index is normal) (I_pile(t) <= I_max). Cond5: Cable dragging status is normal (E_cable(t) <= E_th) The cooperative security state is defined as the logical intersection of five sub-conditions: S_safe(t) = Cond1(t) ∧ Cond2(t) ∧ Cond3(t) ∧ Cond4(t) ∧ Cond5(t) If and only if S_safe(t) = True, the fully mechanized mining face is determined to meet the preset collaborative safety conditions, and cutting is allowed to continue; if any sub-condition is not met, the corresponding linkage control strategy is triggered according to the specific sub-condition that is not met, forming a closed-loop adjustment until all conditions are met again.

[0037] When the cooperative security conditions are not met, a control strategy is executed based on the cooperative determination result, specifically including at least one of the following control methods: Control the hydraulic support to continue moving or prevent the next support from moving; Control the scraper conveyor to accelerate, decelerate, or stop; Control the coal mining machine to slow down, stop, or wait; Issue a warning signal.

[0038] S5. After executing the linkage control, return and repeat the above collection, identification, construction and judgment steps until the collaborative safety conditions are met.

[0039] In step S5, the collaborative control method for the fully mechanized mining face is a closed-loop control, namely: judgment → execution → re-detection → re-judgment, until the collaborative safety conditions are met.

[0040] In each inspection cycle, perform steps S1 to S5 as described above until the production of the working face is completed.

[0041] The fully mechanized mining face collaborative control method provided in this invention continuously acquires image data of the area traversed by the coal mining machine using a rear-facing camera installed on the machine. This constructs a spatiotemporal collaborative model of the face equipment. Based on this model, it determines whether the face meets collaborative safety conditions. If the conditions are not met, it implements coordinated control of the hydraulic supports, scraper conveyor, and / or the coal mining machine, thereby achieving closed-loop collaborative control based on the actual spatial state of the face and realizing closed-loop safe production control of the fully mechanized mining face. Compared with existing technologies, this invention uses the overall spatial state of the face as the control basis, rather than single-device signals; it judges the quality of equipment action based on the spatial geometric relationship of the three machines; it establishes a continuous time-series analysis mechanism to identify action trends and abnormal evolution processes; and it achieves collaborative closed-loop control among multiple devices in the fully mechanized mining face, improving support quality and production safety.

[0042] like Figure 2As shown, in some embodiments, identifying the spatial state and spatiotemporal relationship of the work surface equipment based on the image data specifically includes: S21. Based on the image data, determine the spatial status of the working face equipment and the spatial relationship between the equipment at each acquisition time. The spatial status of the working face equipment includes the position and / or posture of the hydraulic support, the position of the pusher device, the status of the side guard plate, the position of the scraper conveyor and the coal flow pattern, and the cable dragging pattern. The spatial relationship between the equipment includes the relative positional relationship between the coal mining machine and the hydraulic support. In step S21, the spatial state of the working face equipment is extracted based on the image data at each acquisition time, that is, single-frame image processing is performed. Specifically, this includes identifying and locating the following targets: the position and / or attitude of the hydraulic support, the position of the pusher device, the state of the side guard plate, the position of the scraper conveyor and the coal flow area, and the cable dragging pattern; it also includes extracting the spatial distance, relative angle and / or geometric relationship between the equipment, such as the relative positional relationship between the coal mining machine and the hydraulic support.

[0043] S22. Based on the spatial state of the working surface equipment at each acquisition time, identify the dynamic change trend of the equipment actions; In step S22, time series analysis is performed on the continuous frames to identify the support shifting process, the pusher action process, the side plate support process, the coal flow change trend of the conveyor, and the cable status trend, so as to obtain the dynamic change trend of the equipment action.

[0044] S23. Based on the spatial relationship between the devices at each acquisition time, identify the spatiotemporal relationship of the working face devices.

[0045] In step S23, the spatiotemporal relationship of the working face equipment includes the relative positional relationship between the coal mining machine and the hydraulic support at each sampling moment.

[0046] In some embodiments, the relative positional relationship between the coal mining machine and the hydraulic support includes the following distance; by calculating the following distance and comparing it with a preset maximum allowable following distance, it is determined whether the hydraulic support has completed the shifting and reached the preset position.

[0047] Specifically, the method for calculating the following distance is as follows: Let the coordinates of the coal mining machine in the working face direction at time t be x_shearer(t), and the coordinates of the nth hydraulic support be x_support,n(t). Then the following distance D_follow(t) between the coal mining machine and the nth hydraulic support is defined as follows: D_follow(t) = |x_shearer(t) - x_support,n(t)| When D_follow(t) ≤ D_max, it is determined that the hydraulic support has completed the shift and is within the allowable following range, where D_max is the preset maximum allowable following distance, typically 1.5 to 3 times the center-to-center distance of the hydraulic support.

[0048] In some embodiments, the hydraulic support operation includes a pushing action; the lateral offset of the scraper conveyor is detected and compared with a preset maximum allowable offset threshold to determine whether the pushing action is complete.

[0049] Specifically, the calculation method for the push-off offset is as follows: Let L_conv(t) be the measured lateral position of the scraper conveyor in the image, and L_ref be the standard target position. Then the push offset Δs(t) is: Δs(t) = |L_conv(t) - L_ref| The condition for determining whether the push is completed is: Δs(t) ≤ Δs_max, where Δs_max is the maximum allowable offset threshold.

[0050] In some embodiments, the coal transport state of the scraper conveyor includes the coal piling state; the coal piling index is obtained by calculating the ratio of the coal flow area to the reference area of ​​the scraper conveyor trough cross section, and the coal piling index is compared with a preset coal piling threshold to determine whether there is abnormal coal piling.

[0051] Specifically, the coal stockpiling index is calculated as follows: Let the area of ​​the coal flow region detected in the image be A_coal(t), and the reference area of ​​the scraper conveyor trough cross-section be A_conv, then the coal pile index I_pile(t) is defined as: I_pile(t) = A_coal(t) / A_conv When I_pile(t) > I_max (recommended threshold I_max = 0.85), an abnormal coal pile is determined, triggering the conveyor to decelerate or the coal mining machine to slow down.

[0052] In some embodiments, the cable dragging pattern of the coal mining machine includes an abnormal dragging state; by extracting at least one feature of the cable, such as the bending arc, lateral offset, and tangled area ratio, the cable abnormality degree is calculated, and the cable abnormality degree is compared with a preset abnormality threshold to determine whether the cable dragging is abnormal.

[0053] Specifically, the formula for calculating the cable drag anomaly can be as follows: The cable's multidimensional feature vector is extracted from the image, including bending curvature, lateral offset, and proportion of tangled areas. A weighted sum is then used to obtain the cable anomaly degree. E_cable(t) = Σ_k ω_k f_k(t) Where ω_k is the weight coefficient of the k-th feature, and f_k(t) is the normalized value of the k-th feature. When E_cable(t) > E_th, the coal mining machine is triggered to slow down or stop, and an early warning signal is issued.

[0054] In some embodiments, the work surface equipment space state also includes the action completion state; by calculating the time window mean of the single frame action state in multiple consecutive frames of images, an estimated value of action completion is obtained; when the estimated value is greater than a preset completion threshold, it is determined that the action has been stably completed.

[0055] Specifically, the formula for calculating the estimated time sequence action completion rate is as follows: The time window mean of the single-frame action state c(τ) (completed = 1, incomplete = 0) in T consecutive frames is used to obtain the estimated action completion rate. (t) = (1 / T) Σ[τ=tT to t] c(τ) when (t) ≥ Time (Recommended) = 0.8), indicating that the action has been stably completed within the current cycle.

[0056] In some embodiments, the specific method for comprehensive collaborative security determination is as follows: Based on the above five sub-conditions, the specific definitions are as follows: Cond1: Hydraulic support shifted into position (D_follow(t) ≤ D_max); Cond2: Pushing action completed and scraper conveyor position meets geometric requirements (Δs(t) ≤ Δs_max); Cond3: Side guard plate in place (contact_state = True); Cond4: Scraper conveyor coal conveying capacity meets cutting speed requirements (i.e., coal pile index is normal) (I_pile(t) ≤ I_max); Cond5: Cable dragging status is normal (E_cable(t) ≤ E_th). The collaborative safety state S_safe(t) is defined as the logical intersection of the five sub-conditions: S_safe(t) = Cond1(t) ∧ Cond2(t) ∧ Cond3(t) ∧ Cond4(t) ∧ Cond5(t) If and only if S_safe(t) = True, the fully mechanized mining face is determined to meet the preset collaborative safety conditions, and cutting is allowed to continue; if any sub-condition is not met, the corresponding linkage control strategy is triggered according to the specific sub-condition that is not met, forming a closed-loop adjustment until all conditions are met again.

[0057] In some embodiments, when it is determined in step S4 that the hydraulic support has not been moved (following distance ≤ D_max indicates the hydraulic support has been moved, otherwise it is not moved), the linkage control includes controlling the support to be repositioned or pausing cutting; when it is determined in step S4 that the pushing action has not been completed (pushing offset ≤ Δs_max indicates the pushing action has been completed, otherwise it is not completed), the linkage control includes controlling the pushing action to be retried or reducing the traction speed; when it is determined in step S4 that the side guard plate has not been in place (contact state = True indicates it is in place, otherwise it is not in place), the linkage control includes controlling the side guard plate to extend again; when it is determined in step S4 that the coal flow is abnormal (coal pile index > I_max indicates the coal flow is abnormal, otherwise it is normal), the linkage control includes slowing down the scraper conveyor or pausing cutting; when it is determined in step S4 that the cable dragging is abnormal (abnormality > E_th indicates the cable dragging is abnormal, otherwise it is normal), the linkage control includes stopping the coal mining machine and issuing a warning. When it is determined in step S4 that all conditions are met, cutting is allowed to continue, and closed-loop feedback is given to the next cycle.

[0058] In some embodiments, the method further includes: using a forward vision acquisition unit installed on the coal mining machine to acquire image data of the cable trough area and the scraper conveyor area in front of the coal mining machine, so as to assist in judging the status of the cable trough area and the scraper conveyor area.

[0059] Specifically, for the cable trough area: the forward-looking vision acquisition unit continuously acquires images of the cable dragging ahead of the coal mining machine's travel direction, extracts features such as cable bending curvature and lateral offset, and calculates the cable anomaly degree according to the following formula: E_cable_fwd(t) = SUM_k [ omega_k f_k_fwd(t) The forward detection result E_cable_fwd(t) is then weighted and fused with the E_cable(t) obtained from the backward vision acquisition unit: E_cable_final(t) = alpha E_cable(t) + (1 - alpha) E_cable_fwd(t) Where alpha is the backward cable weighting coefficient (recommended 0.6~0.8). The fused E_cable_final(t) is compared with the preset threshold E_th to improve the reliability of cable abnormality determination.

[0060] For the scraper conveyor area: The forward vision acquisition unit detects the coal flow accumulation pattern and lateral position of the conveyor in front of the coal mining machine to obtain the forward coal flow area A_coal_fwd(t), and calculates the forward coal accumulation index according to the following formula: I_pile_fwd(t) = A_coal_fwd(t) / A_conv The forward detection result is then fused with I_pile(t) obtained from the backward vision acquisition unit: I_pile_final(t) = beta I_pile(t) + (1 - beta) I_pile_fwd(t) Where beta is the backward coal piling weight coefficient (recommended 0.6~0.8). The fused I_pile_final(t) is compared with the preset coal piling threshold I_max to assist in correcting the comprehensive judgment result of the conveyor state, thereby improving the accuracy of the collaborative safety condition judgment.

[0061] Specifically, cameras are installed on the coal mining machine and observed in the opposite direction of the machine's movement to view the working face area after the machine has passed. The coal mining machine is used as a mobile observation platform to obtain the actual status of support and transportation, while the status of the cable dragging in front of the coal mining machine and the coal transportation status of the scraper conveyor are observed as secondary measures.

[0062] To achieve the goal of obtaining the working face status through backward observation of the coal mining machine and performing coordinated control accordingly, the acquisition and determination of the working face status can be based on image contour extraction, or it can be achieved by any one or more of the following technical means, all of which are equivalent technical solutions of the embodiments of the present invention: Feature point tracking method: Track the structural feature points of hydraulic supports, pusher devices, side guards, scraper conveyors or coal mining machine cables in continuous images, and calculate the relative positional relationship of the equipment and the completion status of the action through the displacement trajectory of the feature points.

[0063] Structural identification method: Set reflective marks, color codes, coded marks or fixed structural identification parts on the equipment, and determine the displacement of the pusher, the following distance and the status trend of the coal mining machine cable by the change in the spacing between the identification marks.

[0064] Depth ranging method: Use binocular vision, structured light, laser profilometry or other imaging devices that can obtain distance information to directly acquire the spatial distance relationship between devices, and judge whether the action is in place.

[0065] Action timing recognition method: Instead of directly measuring geometric dimensions, the completion status of actions is determined by recognizing the time sequence characteristics of actions such as support movement, scraper conveyor pushing, and coal flow growth through continuous image recognition.

[0066] Vision and sensor fusion method: The visual observation results are combined with pressure, displacement, current or tilt angle signals for joint judgment, where the sensor is only used as auxiliary verification information, and the control basis is still the overall state of the working surface.

[0067] Other observation methods that can reflect the spatial geometric relationship between the three machines: Any observation and analysis method that can characterize the relative positional relationship or action results between the coal mining machine, hydraulic support and scraper conveyor can be used to achieve the collaborative control purpose of this invention.

[0068] The above-mentioned alternative methods are merely different implementations of the technical concept of this invention. Their changes do not affect the technical essence of establishing and controlling the spatiotemporal coordination relationship of the working face based on the backward observation of the coal mining machine, and should all be considered to fall within the protection scope of this invention.

[0069] The method provided in this invention does not rely on hydraulic support cylinder stroke or pressure signals as the basis for judgment. Instead, it determines whether the pushing conveyor, moving support, side guard plate, and cable dragging states are truly in place by observing the spatial geometric relationship of the working face. A model of the relative position and time correspondence between the coal mining machine, hydraulic support, and scraper conveyor is established, including the following distance, support lag, coal flow status, and cable status trend. Through continuous observation, a time series analysis is formed to comprehensively judge the equipment action process and results, rather than single-frame detection or single-moment signal judgment. Using the actual state of the working face as the control basis, the hydraulic support, scraper conveyor, and coal mining machine are implemented in a coordinated manner, realizing the transformation from "single-machine control" to "working face collaborative control".

[0070] Based on the same inventive concept, embodiments of the present invention also provide a collaborative control device for fully mechanized mining faces.

[0071] Figure 3 This is a schematic diagram of the structure of a fully mechanized mining face collaborative control device provided in an embodiment of the present invention. Figure 3 As shown in the figure, an embodiment of the present invention provides a fully mechanized mining face collaborative control device, comprising: The acquisition module 21 is used to continuously acquire image data of the working face trailing area after the coal mining machine has passed by by using the rearward vision acquisition unit set on the coal mining machine facing the opposite direction of its travel. The identification module 22 is used to identify the spatial state of the working face equipment and the spatiotemporal relationship between the equipment based on the image data, wherein the working face equipment includes a coal mining machine, a hydraulic support and a scraper conveyor; Module 23 is used to construct a spatiotemporal collaboration model between working face equipment based on the identified spatial state and spatiotemporal relationship. The linkage control module 24 is used to determine whether the fully mechanized mining face meets the preset collaborative safety conditions based on the spatiotemporal coordination model between the working face equipment. If not, linkage control is performed on the hydraulic support, scraper conveyor and / or coal mining machine. The loop control module 25 is used to return to and repeat the above acquisition, identification, construction and judgment steps after the linkage control is executed, until the coal mining machine is restored after the collaborative safety conditions are met, and to continuously execute the above steps in a loop.

[0072] The fully mechanized mining face collaborative control device provided in this invention continuously acquires image data of the area traversed by the coal mining machine using a rear-facing camera installed on the machine. This constructs a spatiotemporal collaborative model of the face equipment. Based on this model, it determines whether the face meets collaborative safety conditions. If the conditions are not met, it implements coordinated control of the hydraulic supports, scraper conveyor, and / or the coal mining machine, thereby achieving closed-loop collaborative control based on the actual spatial state of the face and realizing closed-loop safe production control of the fully mechanized mining face. Compared with existing technologies, this invention uses the overall spatial state of the face as the control basis, rather than single-device signals; it judges the quality of equipment action based on the spatial geometric relationship of the three machines; it establishes a continuous time-series analysis mechanism to identify action trends and abnormal evolution processes; and it achieves collaborative closed-loop control among multiple devices in the fully mechanized mining face, improving support quality and production safety.

[0073] Figure 4 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the electronic device may include a processor 301, a communications interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communications interface 302, and the memory 303 communicate with each other via the communication bus 304. The processor 301 may call logical instructions in the memory 303 to execute the methods described in any of the above embodiments.

[0074] Furthermore, the logical instructions in the aforementioned memory 303 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0075] This embodiment of the invention provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can perform the methods provided in the above-described method embodiments.

[0076] This embodiment provides a computer-readable storage medium storing a computer program that causes the computer to perform the methods provided in the above-described method embodiments.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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 collaborative control method for a fully mechanized mining face, characterized in that, In each detection cycle, perform the following steps: Using the rearward vision acquisition unit on the coal mining machine that faces the opposite direction of its movement, image data of the working face trailing behind the coal mining machine are continuously acquired. Based on the image data, the spatial state of the working face equipment and the spatiotemporal relationship between the equipment are identified, wherein the working face equipment includes a coal mining machine, a hydraulic support, and a scraper conveyor; Based on the identified spatial state and spatiotemporal relationship, a spatiotemporal collaboration model among the working face equipment is constructed. Based on the spatiotemporal coordination model among the working face equipment, it is determined whether the fully mechanized mining face meets the preset coordination safety conditions. If not, linkage control is performed on the hydraulic support, scraper conveyor and / or coal mining machine. After executing the linkage control, return and repeat the above steps of data collection, identification, construction and judgment until the collaborative security conditions are met.

2. The method according to claim 1, characterized in that, The trailing area of ​​the working face includes at least the following areas: the hydraulic support area, the scraper conveyor area, the side guard plate area, the cable trough area, and the cut coal wall area.

3. The method according to claim 1 or 2, characterized in that, The step of identifying the spatial state and spatiotemporal relationship of the work surface equipment based on the image data specifically includes: Based on the image data, the spatial status of the working face equipment and the spatial relationship between the equipment at each acquisition time are determined. The spatial status of the working face equipment includes the position and / or posture of the hydraulic support, the position of the pusher device, the status of the side guard plate, the position of the scraper conveyor and the coal flow pattern, and the cable dragging pattern. The spatial relationship between the equipment includes the relative positional relationship between the coal mining machine and the hydraulic support. Based on the spatial state of the working surface equipment at each acquisition moment, the dynamic change trend of equipment actions is identified; Based on the spatial relationship between the devices at each acquisition time, the spatiotemporal relationship of the working face devices is identified.

4. The method according to claim 1, characterized in that, The collaborative security conditions include: The hydraulic support has been moved into place; The pushing action is completed and the position of the scraper conveyor meets the set geometric requirements; The side guard plate is in the attached position; The scraper conveyor's coal conveying capacity meets the cutting speed requirements; The cable condition trend is normal.

5. The method according to claim 1, characterized in that, The linkage control includes at least one of the following control methods: Control the hydraulic support to continue moving or prevent the next support from moving; Control the scraper conveyor to accelerate, decelerate, or stop; Control the coal mining machine to slow down, stop, or wait; Issue a warning signal.

6. The method according to claim 3, characterized in that, The relative positional relationship between the coal mining machine and the hydraulic support includes the following distance. By calculating the following distance and comparing it with the preset maximum allowable following distance, when the following distance is less than or equal to the preset maximum allowable following distance, it is determined that the hydraulic support has completed the shift and reached the preset position. The hydraulic support's operating state includes a pushing action. The lateral offset of the scraper conveyor is detected and compared with a preset maximum allowable offset threshold. When the lateral offset is less than or equal to the preset maximum allowable offset threshold, the pushing action is determined to be complete. The coal transport state of the scraper conveyor includes the coal pile state. The coal pile index is obtained by calculating the ratio of the coal flow area to the reference area of ​​the scraper conveyor trough cross section. The coal pile index is then compared with a preset coal pile threshold. When the coal pile index is greater than the preset coal pile threshold, it is determined that there is abnormal coal pile. The cable dragging pattern of the coal mining machine includes abnormal dragging state. By extracting at least one feature of the cable bending arc, lateral offset, and tangled area ratio, the cable abnormality degree is calculated. The cable abnormality degree is compared with a preset abnormality threshold. When the cable abnormality degree is greater than the preset abnormality threshold, the cable dragging is determined to be abnormal. The working surface equipment space status also includes the action completion status. By calculating the time window mean of the action status in multiple consecutive frames of images, an estimated value of action completion is obtained. When the estimated value is greater than the preset completion threshold, it is determined that the action has been stably completed.

7. The method according to claim 1, characterized in that, Also includes: Using the forward vision acquisition unit installed on the coal mining machine, image data of the cable trough area and scraper conveyor area in front of the coal mining machine are collected to help determine the status of the cable trough area and scraper conveyor area.

8. A collaborative control device for a fully mechanized mining face, characterized in that, include: The acquisition module is used to continuously acquire image data of the trailing area of ​​the working face after the coal mining machine has passed by, using the rearward vision acquisition unit set on the coal mining machine facing the opposite direction of its travel. The recognition module is used to identify the spatial status of the working face equipment and the spatiotemporal relationship between the equipment based on the image data, wherein the working face equipment includes a coal mining machine, a hydraulic support, and a scraper conveyor. The module is used to build a spatiotemporal collaboration model between working face equipment based on the identified spatial state and spatiotemporal relationship; The linkage control module is used to determine whether the fully mechanized mining face meets the preset collaborative safety conditions based on the spatiotemporal coordination model between the working face equipment. If not, linkage control is performed on the hydraulic support, scraper conveyor and / or coal mining machine. The loop control module is used to return to and repeat the above acquisition, identification, construction and judgment steps after the linkage control is executed, until the coal mining machine is restored after the collaborative safety conditions are met, and the above steps are continuously executed in a loop.

9. 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 program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images