CN116398134A - Coal cutter cutting planning method and equipment based on inspection and perception - Google Patents

Abstract

The invention provides a cutting planning method and equipment of a coal mining machine based on inspection perception, wherein the method combines a space mapping relation between a stope moving platform coordinate system and a geological coordinate system to carry out stope space digital construction and automatic detection and identification of the coal mining machine; performing perception analysis on the motion state of the coal mining machine to acquire the motion state information of the coal mining machine, and performing capture tracking of the coal mining machine; and performing state sensing on a target object of the coal cutter component in the cutting space, and determining an optimal safe cutting curve based on the state sensing data. The invention can complete real-time cutting planning by visually and intelligently sensing the equipment and the environment state of the cutting space, and has stronger timeliness of data information and continuity of engineering implementation; and carrying out real-time visual interaction on associated equipment in a cutting space and surrounding environment state sensing results so as to facilitate the real-time auxiliary intervention of cutting by staff and obtain more accurate cutting planning data.

Description

A shearer cutting planning method and equipment based on inspection visual perception

technical field

The invention relates to the technical field of coal mining, in particular to a shearer cutting planning method, device, equipment, and storage medium based on inspection visual perception.

Background technique

At present, in the fully mechanized mining process, memory cutting is still the main technical method and means for automatic height adjustment control of the coal machine drum in the current coal mining process. Usually, the preliminary planning of shearer cutting is firstly carried out based on the prior geological exploration data, and then on this basis, the relevant state data of the shearer during the demonstration operation process is obtained through the system record of the demonstration operation of the shearer driver. Finally, the shearer memory cutting system analyzes and processes the acquired data, generates a memory cutting curve, and provides data support for subsequent shearer cutting operations. However, the current automatic control method of shearer height adjustment based on memory cutting requires frequent manual intervention to assist in completing the entire cutting process when the coal seam has large fluctuations, which reduces the automatic production efficiency of the working face. Moreover, this method and system cannot accurately perceive and capture the space status of the shearer drum and the hydraulic support top beam in real time, resulting in the possibility of dangerous anomalies in the actual operation process where the shearer drum cuts the hydraulic support top beam, so manual real-time monitoring is required Intervene.

Based on this, this program will propose a safer, more accurate and more efficient shearer cutting planning method based on the mobile platform (robot) vision, combined with the reality capture and perception system of the coal mine underground scene. This method can detect and capture the stope and the spatial state of the operating equipment in real time through inspection vision for the undulation and change of the coal seam, adaptively adjust the cutting curve, realize continuous operation cutting planning, and improve the automatic production efficiency of the working face. Moreover, this method can avoid the dangerous abnormality of cutting the hydraulic support roof beam by the shearer drum during the process of autonomous follow-up on the basis of the perception and capture of the space state of the shearer drum and the hydraulic support top beam, and improve the intelligent and safe production of the working face control level.

Contents of the invention

The present invention provides a shearer cutting planning method, device, equipment, and storage medium based on inspection visual perception, aiming at realizing real-time visual dynamic monitoring of stope environmental target objects and providing perception basis for intelligent mining.

For this reason, the first purpose of the present invention is to propose a cutting planning method for shearers based on inspection visual perception, including:

Set up a mobile platform with prior information identification at a specific location in the stope environment, and obtain the spatial mapping relationship between the mobile platform coordinate system and the geological coordinate system;

The mobile platform equipped with visual sensors and state-aware sensors searches for coal shearers, and based on the spatial mapping relationship between the mobile platform coordinate system and the geological coordinate system, digitally constructs the stope space, and at the same time detects and judges coal mining in the stope space Whether the shearer is within the visual monitoring range, to realize the automatic detection and identification of the coal shearer;

When the shearer appears within the range of visual monitoring, perform perception analysis on the motion state of the shearer, obtain the motion state information of the shearer, and capture and track the shearer based on the motion state information of the shearer;

The state perception of the target object of the shearer components in the cutting space is carried out, and the optimal safe cutting curve is determined based on the state perception data.

Among them, the mobile platform equipped with visual sensors and state perception sensors searches for coal shearers, and based on the spatial mapping relationship between the coordinate system of the mobile platform and the geological coordinate system, the digital construction of the stope space is carried out, and the detection and judgment in the stope space are carried out at the same time. Whether the shearer is within the scope of visual monitoring, the automatic detection and identification of the shearer includes steps:

Initialize the movement position of the mobile platform, combine the working conditions of the fully mechanized mining face, and carry out pre-planning of the movement path around the detection and identification target object of the coal mining machine;

During the movement, the mobile platform combines the system space coordinate mapping relationship to obtain its own absolute coordinate information in the geological coordinate system. Based on the visual sensor data and state perception sensor data, the real-time positioning and mapping system (SLAM) realizes the real-time positioning of the mobile platform. ; Wherein, the visual sensor data includes data collected by various types of visual cameras and various types of laser radars, and the state perception sensor includes data collected by various types of inertial navigation odometers, wheel speedometers, and UWB devices;

At the same time, the digital construction of the stope space is carried out, and the visual perception and intelligent detection are used to judge whether the shearer is within the visual monitoring range, so as to realize the automatic detection and identification of the shearer.

Among them, in the step of realizing the automatic detection and recognition of the coal mining machine, it includes:

The machine learning algorithm is used to detect and identify the shearer in real time based on the visual sensor data. When the shearer appears within the visual monitoring range, the mobile platform performs perceptual analysis on the motion state of the shearer to obtain the motion state information of the shearer;

According to the state data of shearer positioning, running speed and acceleration, the motion state control and planning of the mobile platform are carried out;

Adjust the posture of the visual sensor in real time to achieve stable capture and tracking of the target object, ensuring that the shearer is always within the visual monitoring range of the system;

When the mobile platform detects an obstacle in the stope during the movement, it will plan the local obstacle avoidance path based on the robot platform model and the stope local map, complete the autonomous detour of the obstacle, and then re-execute the capture of the coal mining machine track.

Wherein, in the step of performing state perception on the target object of the shearer component in the cutting space, it includes:

Combining the digital construction of stope space with map data, the physical model of the shearer, and the capture and tracking result data of the shearer, the instance segmentation of the shearer drum is carried out; based on the analysis of the instance segmentation results, combined with the operating status of the drum, the upper edge of the drum is calculated and obtained , the lower edge, and the center point position information data;

Real-time detection and identification of the hydraulic support roof and mutual support plate status in the cutting space; combined with the digital construction of the stope space map data, the hydraulic support physical model, and the hydraulic support space state data, the instance segmentation of the hydraulic support roof is carried out, and the edge of the roof beam is calculated and obtained Space information data of the line roof;

Based on the digital construction of stope space map data, instance segmentation is carried out for the local coal wall area in the cutting space, and the coal wall space surface is calculated and obtained.

Wherein, the steps of determining the optimal safety cutting curve based on the state perception data include:

Combined with cutting space state perception data, artificial intelligence algorithm is used to desensitize, screen and optimize data, and carry out construction and optimization of digital twin physical simulation model and scene model;

Real-time judgment of the safety status of the cutting space based on the state perception data of the cutting space; when there is a preset abnormal situation during the follow-up process, a cutting safety warning will be given;

Combining the perception information obtained by calculation in the cutting space, the physical simulation model of the digital twin target object, and the prior information of the cutting planning, the optimization algorithm is used to construct the cutting height optimization model of the shearer drum, and the safe cutting of the shearer is obtained by real-time calculation. optimal curve.

Among them, in the step of predicting the movement direction and movement speed of the target object based on the movement model, the state perception data includes:

Real-time spatial status of shearer drums in the cutting space;

The real-time space status of the hydraulic support roof in the cutting space;

The space surface of the coal wall in the cutting space.

Among them, the cutting curve optimization processing and analysis are carried out for the area where the shearer has completed the operation, and the prior information of the cutting plan for the next cutting operation is saved and updated; when the first cutting operation is performed, the prior information of the cutting plan can be based on the geological exploration data to calculate and obtain;

Based on the perception result information obtained in the cutting space and the optimal safe cutting curve, it drives the real-time construction of the digital twin real-scene dynamic simulation, and completes the visual interaction, so that the staff can carry out auxiliary intervention in cutting planning according to the scene requirements.

The second object of the present invention is to propose a shearer cutting planning device based on inspection visual perception, including:

The spatial mapping module is used to set up a mobile platform with prior information identification at a specific position in the stope environment, and obtain the spatial mapping relationship between the mobile platform coordinate system and the geological coordinate system;

The digital construction module of the stope space is used to search for coal shearers through the mobile platform equipped with visual sensors and state perception sensors, and based on the spatial mapping relationship between the coordinate system of the mobile platform and the geological coordinate system, the digital construction of the stope space is carried out. At the same time, it detects and judges whether the shearer is within the visual monitoring range in the stope space, and realizes the automatic detection and identification of the shearer;

The shearer capture and tracking module is used to perform perception analysis on the motion state of the shearer when the shearer appears within the visual monitoring range, obtain the motion state information of the shearer, and carry out coal mining based on the motion state information of the shearer machine capture and tracking;

The cutting planning module is used to perform state perception on the target object of the shearer components in the cutting space, and combine the digital twin physical simulation model and the scene model to determine the optimal safe cutting curve based on the state perception data.

The third object of the present invention is to provide an electronic device, including: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by at least one processor. Execution by one processor, so that at least one processor can execute each step in the method of the foregoing technical solution.

The fourth object of the present invention is to provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make a computer execute the steps in the method according to the aforementioned technical solutions.

Different from the prior art, the shearer cutting planning method based on inspection visual perception provided by the present invention obtains the spatial mapping relationship between the stope mobile platform coordinate system and the geological coordinate system, digitally constructs the stope space, and Carry out automatic detection and identification of the shearer in the stope space; when the shearer appears within the visual monitoring range, perform perception analysis on the motion state of the shearer, obtain the motion state information of the shearer, and capture and track the shearer ; Perform state perception for the target object of the shearer components in the cutting space, and determine the optimal safe cutting curve based on the state perception data. Through the present invention, it is possible to visually and intelligently perceive the equipment and environmental status of the cutting space to complete real-time cutting planning, which has strong timeliness of data information and continuity of project implementation; it is aimed at the perception of associated equipment in the cutting space and the state of the surrounding environment The results are visualized and interacted in real time, so that the staff can perform cutting assistance intervention in real time and obtain more accurate cutting planning data.

Description of drawings

The present and/or additional aspects and advantages will become apparent and comprehensible from the following description of the embodiments in conjunction with the accompanying drawings, in which:

Fig. 1 is a schematic flow chart of a shearer cutting planning method based on inspection visual perception provided by the present invention.

Fig. 2 is a logical schematic diagram of a shearer cutting planning method based on inspection visual perception provided by the present invention.

Fig. 3 is a schematic structural diagram of a shearer cutting planning device based on inspection visual perception provided by the present invention.

Fig. 4 is a schematic structural diagram of a non-transitory computer-readable storage medium storing computer instructions provided by the present invention.

Detailed ways

Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

As shown in Figure 1, it is a shearer cutting planning method based on inspection visual perception provided by the embodiment of the present invention. The logic of the shearer cutting planning in the present invention is shown in Figure 2. The method includes :

S110: Set up a mobile platform with prior information identification at a specific location in the stope environment, and obtain the spatial mapping relationship between the coordinate system of the mobile platform and the geological coordinate system.

Based on the geological model, the spatial mapping relationship between the mobile platform coordinate system and the geological coordinate system is obtained by setting up a priori information identification at a specific location in the stope environment, and the system spatial coordinate integration is realized.

S120: The mobile platform equipped with visual sensors and state perception sensors searches for coal shearers. At the same time, based on the spatial mapping relationship between the coordinate system of the mobile platform and the geological coordinate system, digital construction of the stope space is carried out, and detection and judgment are carried out in the stope space Whether the shearer is within the scope of visual monitoring, realize the automatic detection and identification of the shearer.

The motion position of the mobile platform is initialized, combined with the working conditions of the fully-mechanized mining face, the motion path pre-planning is carried out around the detection and identification target object of the shearer in a specific way and with a specific strategy.

During the movement, the mobile platform combines the system space coordinate mapping relationship to obtain its own absolute coordinate information in the geological coordinate system. Based on the visual sensor data and state perception sensor data, the real-time positioning and mapping system (SLAM) realizes the real-time positioning of the mobile platform. ; Wherein, the visual sensor data includes data collected by various types of visual cameras and laser radars, and the state-aware sensor includes data collected by various types of inertial navigation odometers, wheel speedometers, and UWB devices.

At the same time, the digital construction of the stope space is carried out, and the visual perception and intelligent detection are used to judge whether the shearer is within the visual monitoring range, so as to realize the automatic detection and identification of the shearer.

S130: When the shearer appears within the visual monitoring range, perform perception analysis on the motion state of the shearer, obtain motion state information of the shearer, and capture and track the shearer based on the motion state information of the shearer.

The machine learning algorithm is used to detect and identify the shearer in real time based on the visual sensor data. When the shearer appears within the visual monitoring range, the mobile platform performs perceptual analysis on the motion state of the shearer to obtain the motion state information of the shearer. According to the state data such as the positioning, running speed, and acceleration of the shearer, the corresponding motion state control and planning are carried out for the mobile platform. At the same time, the posture of the visual sensor is adjusted in real time to achieve stable capture and tracking of the target, ensuring that the shearer is always within the visual monitoring range of the system. When the mobile platform detects an obstacle in the stope during the movement, the system will plan the local obstacle avoidance path based on the robot platform model and the stope local map, complete the autonomous detour of the obstacle, and then re-execute the shearer capture tracking.

S140: Perform state perception for target objects of the shearer components in the cutting space, and determine an optimal safe cutting curve based on the state perception data.

Based on the stable capture and tracking of the shearer by the mobile platform, the state perception is performed on target objects such as the shearer drum and the hydraulic support top beam in the cutting space, as follows:

Combining digital construction of stope space with map data, physical model of the shearer, and capture and tracking result data of the shearer, instance segmentation is carried out for the shearer drum. Based on the analysis of the instance segmentation results, combined with the running status of the drum, the information data such as the upper edge, the lower edge, and the position of the center point of the drum are calculated and obtained;

Real-time detection and identification of the hydraulic support top plate and mutual support plate status in the cutting space. Also combined with digital construction of stope space map data, hydraulic support physical model, and hydraulic support space state data, hydraulic support roof instance segmentation is performed, and roof space information data such as roof beam edge lines are calculated and obtained;

Based on the digital construction of stope space map data, instance segmentation is carried out for the local coal wall area in the cutting space, and the coal wall space surface is calculated and obtained.

For cutting space state perception data, artificial intelligence algorithm is used to optimize data desensitization and screening;

Combined with the cutting space status perception data, the safety status of the cutting space can be judged in real time. When the hydraulic support is not closed normally, the distance between the shearer drum and the top beam is too close, the shearer is tilted and other abnormal conditions occur during the follow-up process, the cutting safety warning will be given;

Combining the perception information obtained by calculation in the cutting space, the physical simulation model of the digital twin target object, and the prior information of the cutting planning, the cutting height optimization model of the shearer drum is constructed by using machine learning, particle filter and other optimization algorithms, and the real-time calculation and acquisition Optimal curve for safe cutting of coal shearer. The sensory information used therein includes:

①The real-time space state of the shearer drum in the cutting space;

②Real-time spatial status of the hydraulic support roof in the cutting space;

③The spatial surface of the coal wall in the cutting space.

The cutting curve optimization processing and analysis are carried out for the completed operation area of the coal shearer, and the prior information is saved and updated as the cutting plan for the next cutting operation. During the first cutting operation, the prior information of the cutting plan can be calculated and obtained according to the geological exploration data;

Based on the perception result information obtained in the cutting space and the optimal safe cutting curve, it drives the real-time construction of the digital twin real-scene dynamic simulation, and completes the visual interaction, so that the staff can carry out auxiliary intervention in cutting planning according to the scene requirements.

Different from the prior art, the solution of the present invention has the following advantages:

1. This scheme does not need to modify the operating equipment, the difficulty of project implementation is small, and the maintenance cost is low;

2. This program completes real-time cutting planning through the mobile platform (robot) visual intelligence perception of cutting space equipment and environmental status, which has strong timeliness of data information and continuity of project implementation;

3. This solution can monitor the associated equipment in the cutting space visually and in real time, as well as the state of the surrounding environment, avoiding the dangerous abnormality of the shearer drum cutting the hydraulic support roof beam during the autonomous follow-up process, and the intelligent control level of safe production is high;

4. This solution can realize the real-time visual interaction of the system for the associated equipment in the cutting space and the perception results of the surrounding environment, so that the staff can perform cutting auxiliary intervention in real time and obtain more accurate cutting planning data;

5. The solution system is highly scalable and can be linked with other sensing systems to achieve more robust and accurate cutting planning.

As shown in Fig. 3, the present invention provides a shearer cutting planning device 300 based on inspection visual perception, including:

The spatial mapping module 310 is used to set up a mobile platform with prior information identification at a specific position in the stope environment, and obtain the spatial mapping relationship between the mobile platform coordinate system and the geological coordinate system;

The stope space digital construction module 320 is used to carry out digital construction of the stope space based on the spatial mapping relationship between the mobile platform coordinate system and the geological coordinate system during the coal shearer search process through the mobile platform equipped with visual sensors and state perception sensors , and detect and judge whether the shearer is within the visual monitoring range in the stope space, and realize the automatic detection and identification of the shearer;

The coal mining machine capturing and tracking module 330 is used to perform perception analysis on the motion status of the coal mining machine after the coal mining machine appears in the visual monitoring range, obtain the motion status information of the coal mining machine, and perform mining based on the motion state information of the coal mining machine. Coal machine capture and tracking;

The cutting planning module 340 is configured to perform state perception on target objects of shearer components in the cutting space, and determine an optimal safe cutting curve based on state perception data.

In order to realize the embodiment, the present invention also proposes an electronic device, including: at least one processor; and a memory connected in communication with the at least one processor; wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by at least one processor. Executed by one processor, so that at least one processor can execute each step in the inspection-based visual perception-based shearer cutting planning method of the foregoing technical solution.

The non-transitory computer readable storage medium 800 includes a memory 810 of instructions, an interface 830, executable by a shearer cutting planning processor 820 based on patrol visual perception to complete the method. Alternatively, the storage medium may be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. .

In order to realize the embodiment, the present invention also proposes a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the coal shearer based on inspection visual perception according to the embodiment of the present invention is realized. Cut planning.

In the description of this specification, descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific examples", or "some examples" mean that specific features described in connection with the embodiment or example , structure, material or characteristic is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms are not necessarily directed to the same embodiment or example. Furthermore, the described specific features, structures, materials or characteristics may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine different embodiments or examples and features of different embodiments or examples described in this specification without conflicting with each other.

In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

Any process or method descriptions in flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing custom logical functions or steps of a process , and the scope of preferred embodiments of the invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including substantially concurrently or in reverse order depending on the functions involved, which shall It is understood by those skilled in the art to which the embodiments of the present invention pertain.

The logic and/or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium, For use with instruction execution systems, devices, or devices (such as computer-based systems, systems including processors, or other systems that can fetch instructions from instruction execution systems, devices, or devices and execute instructions), or in conjunction with these instruction execution systems, devices or equipment for use. For the purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use in or in conjunction with an instruction execution system, device or device. More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection with one or more wires (electronic device), portable computer disk case (magnetic device), random access memory (RAM), Read Only Memory (ROM), Erasable and Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program can be printed, as it may be possible, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or other suitable processing if necessary. The program is processed electronically and stored in computer memory.

It should be understood that various parts of the present invention can be realized by hardware, software, firmware or their combination. In the described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: a discrete Logic circuits, ASICs with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

Those of ordinary skill in the art can understand that all or part of the steps carried by the method of the embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, the program When executed, one or a combination of the steps of the method embodiments is included.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing module, each unit may exist separately physically, or two or more units may be integrated into one module. The integrated modules can be implemented in the form of hardware or in the form of software function modules. If the integrated modules are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium.

The mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like. Although the embodiment of the present invention has been shown and described above, it can be understood that the embodiment is exemplary and should not be construed as a limitation of the present invention. The described embodiments are subject to alterations, modifications, substitutions and variations.

Claims (10)

1. A shearer cutting planning method based on inspection visual perception, characterized in that it comprises: Setting up a mobile platform with a priori information identification at a specific position in the stope environment, and obtaining the spatial mapping relationship between the coordinate system of the mobile platform and the geological coordinate system; The mobile platform equipped with visual sensors and state perception sensors searches for coal shearers, and based on the spatial mapping relationship between the coordinate system of the mobile platform and the geological coordinate system, the digital construction of the stope space is carried out, and the detection and judgment in the stope space are carried out at the same time Whether the shearer is within the scope of visual monitoring, to realize the automatic detection and identification of the shearer; When the shearer appears within the scope of visual monitoring, perform perceptual analysis on the motion state of the shearer, obtain the motion state information of the shearer, combine the digital twin physical simulation model and the scene model, and based on the motion state information of the shearer, Carry out shearer capture tracking; The state perception of the target object of the shearer components in the cutting space is carried out, and the optimal safe cutting curve is determined based on the state perception data. 2. The shearer cutting planning method based on inspection visual perception according to claim 1, characterized in that, the mobile platform equipped with visual sensors and state perception sensors searches for coal shearers, and based on the coordinates of the mobile platform Based on the spatial mapping relationship between the coordinate system and the geological coordinate system, digital construction of the stope space is carried out, and at the same time, it is detected in the stope space to determine whether the shearer is within the visual monitoring range, and the automatic detection and identification of the shearer includes the following steps: Initialize the movement position of the mobile platform, combine the working conditions of the fully mechanized mining face, and carry out pre-planning of the movement path around the detection and identification target object of the coal mining machine; During the movement, the mobile platform combines the system space coordinate mapping relationship to obtain its own absolute coordinate information in the geological coordinate system. Based on the visual sensor data and state perception sensor data, the real-time positioning and mapping system (SLAM) realizes the real-time positioning of the mobile platform. ; Wherein, the visual sensor data includes data collected by various types of visual cameras and various types of laser radars, and the state perception sensor includes data collected by various types of inertial navigation odometers, wheel speedometers, and UWB devices; At the same time, the digital construction of the stope space is carried out, and the visual perception and intelligent detection are used to judge whether the shearer is within the visual monitoring range, so as to realize the automatic detection and identification of the shearer. 3. the shearer cutting planning method based on inspection visual perception according to claim 2, characterized in that, in the step of realizing the automatic detection and identification of the shearer, comprising: The machine learning algorithm is used to detect and identify the shearer in real time based on the visual sensor data. When the shearer appears within the visual monitoring range, the mobile platform performs perceptual analysis on the motion state of the shearer to obtain the motion state information of the shearer; According to the state data of shearer positioning, running speed and acceleration, the motion state control and planning of the mobile platform are carried out; Adjust the posture of the visual sensor in real time to achieve stable capture and tracking of the target object, ensuring that the shearer is always within the visual monitoring range of the system; When the mobile platform detects an obstacle in the stope during the movement, it will plan the local obstacle avoidance path based on the robot platform model and the stope local map, complete the autonomous detour of the obstacle, and then re-execute the capture of the coal mining machine track. 4. The shearer cutting planning method based on inspection visual perception according to claim 1, characterized in that, in the step of state perception for the target object of the shearer component in the cutting space, comprising: Combining the digital construction of stope space with map data, the physical model of the shearer, and the capture and tracking result data of the shearer, the instance segmentation of the shearer drum is carried out; based on the analysis of the instance segmentation results, combined with the operating status of the drum, the upper edge of the drum is calculated and obtained , the lower edge, and the center point position information data; Real-time detection and identification of the hydraulic support roof and mutual support plate status in the cutting space; combined with the digital construction of the stope space map data, the hydraulic support physical model, and the hydraulic support space state data, the instance segmentation of the hydraulic support roof is carried out, and the edge of the roof beam is calculated and obtained Space information data of the line roof; Based on the digital construction of stope space map data, instance segmentation is carried out for the local coal wall area in the cutting space, and the coal wall space surface is calculated and obtained. 5. The shearer cutting planning method based on inspection visual perception according to claim 3, wherein the step of determining the optimal safety cutting curve based on state perception data comprises: Combined with cutting space state perception data, artificial intelligence algorithm is used to desensitize, screen and optimize data, and carry out construction and optimization of digital twin physical simulation model and scene model; Real-time judgment of the safety status of the cutting space based on the state perception data of the cutting space; when there is a preset abnormal situation during the follow-up process, a cutting safety warning will be given; Combining the perception information obtained by calculation in the cutting space, the physical simulation model of the digital twin target object, and the prior information of the cutting planning, the optimization algorithm is used to construct the cutting height optimization model of the shearer drum, and the safe cutting of the shearer is obtained by real-time calculation. optimal curve. 6. The shearer cutting planning method based on inspection visual perception according to claim 5, wherein the state perception data comprises: Real-time spatial status of shearer drums in the cutting space; The real-time space status of the hydraulic support roof in the cutting space; The space surface of the coal wall in the cutting space. 7. The shearer cutting planning method based on inspection visual perception according to claim 6, characterized in that, the cutting curve optimization processing and analysis are performed on the area where the shearer has completed the operation, and it is saved and updated as the next cutting operation The prior information of the cutting plan; when the first cutting operation is performed, the prior information of the cutting plan can be calculated and obtained according to the geological exploration data; Based on the perception result information obtained in the cutting space and the optimal safe cutting curve, it drives the real-time construction of the digital twin real-scene dynamic simulation, and completes the visual interaction, so that the staff can carry out auxiliary intervention in cutting planning according to the scene requirements. 8. A shearer cutting planning device based on inspection visual perception, characterized in that it includes: The spatial mapping module is used to set up a mobile platform with prior information identification at a specific position in the stope environment, and obtain the spatial mapping relationship between the mobile platform coordinate system and the geological coordinate system; The stope space digitization building block is used to search for coal shearers through the mobile platform equipped with visual sensors and state perception sensors, and to digitize the stope space based on the spatial mapping relationship between the mobile platform coordinate system and the geological coordinate system Construction, and at the same time detect and judge whether the shearer is within the visual monitoring range in the stope space, and realize the automatic detection and identification of the shearer; The shearer capturing and tracking module is used to perform perceptual analysis on the motion state of the shearer when the shearer appears within the visual monitoring range, obtain the motion state information of the shearer, and perform Shearer capture and tracking; The cutting planning module is used to perform state perception for the target object of the shearer components in the cutting space, and combine the digital twin physical simulation model and the scene model to determine the optimal safe cutting curve based on the state perception data. 9. An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are The at least one processor executes, so that the at least one processor can execute the steps in the method of any one of claims 1-7. 10. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make the computer execute the steps in the method according to any one of claims 1-7.

Images