Background
In recent years, with the rapid development of coal mine automation technology, some automatic monitoring devices are widely applied to underground coal mines. In the field of the current coal mine, a visual remote intervention intelligent coal mining control system is formed in the aspects of automatic and intelligent unmanned mining, and remote manual intervention automatic mining is realized on a mine ground with relatively ideal geological conditions to a certain extent. In the fully mechanized mining face, a coal mining machine is one of the key devices of the fully mechanized mining face, and the working conditions (such as the height of a roller and the posture of a rocker arm) of the coal mining machine and the surrounding environment state need to be grasped in real time in the fully mechanized mining process, so that a manual or unmanned automatic device is needed to monitor the working conditions of the coal mining machine and the surrounding environment space state of the operation in real time.
Because the environment of the underground fully mechanized coal mining face of the coal mine is complex, particularly under the production condition, the self condition and the surrounding environment of the coal mining machine under the coal cutting state are worse. Therefore, in the process of the automatic and intelligent unmanned mining technology, the related academic circles and the industrial circles at home and abroad carry out deep research on the automatic and intelligent monitoring and control technology of the fully-mechanized coal mining face coal mining machine, and a series of technical methods are provided. One of the typical methods is to install a corresponding sensor device on a coal mining machine body to monitor the condition of the coal mining machine and the state of the surrounding environment of operation in real time and perform manual remote control, but the monitoring device is affected by the destructive force of working conditions and severe environment, the reliability of the monitoring device is often not guaranteed, and the remote monitoring and manual control effects are not ideal. In this case, the related research institutions and the mining units collaborate to develop the inspection robot device and the inspection system platform of the fully mechanized working face. The method includes the steps that a walking track is built on the outer side of a working face scraper conveyor, an inspection robot system platform is carried on the walking track, a camera sensor is installed on the inspection robot system platform, and an inspection robot is controlled in an artificial underground mode or a ground remote mode and monitors the working condition and the surrounding environment state of a coal mining machine in a visual dynamic mode on the basis of inspection vision remote artificial real-time tracking.
Although the method is based on visual vision and realizes the real-time monitoring of the working condition and the environmental state of the coal mining machine on the fully mechanized mining face through manual intervention remotely, the urgent requirements of intelligent sensing, dynamic prediction and cooperative control of the unmanned intelligent production system of the coal mine are difficult to meet through remote manual real-time monitoring, manual sensing judgment and manual decision intervention control of the coal mining machine and the corresponding inspection robot in the fully mechanized mining production process. Therefore, the particularity of the scene of the underground fully-mechanized coal mining face of the coal mine is analyzed, the intelligent monitoring and automatic autonomous machine following method and system of the working condition of the coal mining machine based on the inspection vision of the fully-mechanized coal mining face are designed, the intelligent sensing of the working condition of the coal mining machine and the state of the surrounding environment is achieved, the autonomous cooperative control operation of the coal mining machine and the inspection robot of the fully-mechanized unmanned production system is achieved, and the intelligent unmanned mining process of the coal mine is assisted.
Content of application
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, the invention aims to provide an intelligent monitoring and autonomous cooperative tracking device of a coal mining machine based on inspection vision, which improves the battery cruising ability and the body reliability of an underground inspection robot. Meanwhile, real-time intelligent monitoring of the coal mining machine is achieved based on the patrol inspection vision.
The second purpose of the invention is to provide an inspection platform system.
The third purpose of the invention is to provide a method for intelligent monitoring and autonomous cooperative tracking of the coal mining machine based on inspection vision.
In order to achieve the above object, an embodiment of a first aspect of the present application provides a coal mining machine intelligent monitoring and autonomous collaborative tracking device based on inspection vision, including:
the acquisition module is used for acquiring the current position of the roller of the coal mining machine in the field of view of the inspection robot;
the first tracking module is used for determining the target moving direction of the coal mining machine according to the current position and controlling the inspection robot to track the movement of the coal mining machine at a first preset speed along the target moving direction; and
and the second tracking module is used for gradually reducing the moving speed of the inspection robot according to the distance between the inspection robot and the end head or the end tail when detecting that the inspection robot reaches the end head or the end tail area of the inspection track, and controlling the inspection robot to reversely advance until the distance meets the stop condition.
In addition, the intelligent monitoring and autonomous cooperative tracking device of the coal mining machine based on the inspection vision according to the embodiment of the invention can also have the following additional technical characteristics:
optionally, the acquisition module comprises:
the acquisition unit is used for acquiring visual data of the coal mining machine in the operation process;
the analysis unit is used for analyzing and obtaining the visual characteristics of the roller target object under the coal cutting condition in the advancing direction of the coal mining machine according to the visual data;
and the acquisition unit is used for inputting the visual characteristics into a preset target object intelligent detection model and acquiring the current position.
Optionally, the first tracking module includes:
the reading unit is used for reading the coal wall visual video stream of the inspection robot and detecting whether the roller target of the coal mining machine exists in the current image frame;
the first control unit is used for controlling the inspection robot to move on the track at a constant speed at a second preset speed when the target of the roller of the coal mining machine is not detected, and simultaneously acquiring the distance between the inspection robot and the end head or the end tail;
the judging unit is used for judging whether the inspection robot is in a machine following mode state or not when the roller target of the coal mining machine is detected;
the second control unit is used for controlling the inspection robot to decelerate until the inspection robot stops and enters the machine following mode state in the positioning mode state when the inspection robot is not in the machine following mode state;
and the tracking unit is used for starting tracking the movement of the coal mining machine along the target running direction at the first preset speed according to the target moving direction when the tracking unit is not in the machine following mode state.
Optionally, the method further comprises:
and the switching module is used for controlling the mode state of the inspection robot to be switched from the machine following mode to the positioning mode state if no continuous preset frame in the image frames of the coal wall visual video stream detects the target of the roller of the coal mining machine.
In order to achieve the above object, an embodiment of a second aspect of the present application provides a patrol platform system, which includes the above intelligent monitoring and autonomous cooperative tracking device for a coal mining machine based on patrol vision.
In order to achieve the above object, an embodiment of the third aspect of the present application provides a method for intelligent monitoring and autonomous cooperative tracking of a coal mining machine based on inspection vision, including the following steps:
acquiring the current position of a roller of the coal mining machine in the field of view of the inspection robot;
determining the target moving direction of the coal mining machine according to the current position, and controlling the inspection robot to track the movement of the coal mining machine at a first preset speed along the target moving direction; and
when the inspection robot is detected to reach an inspection track end or end tail area, the moving speed of the inspection robot is gradually reduced according to the distance between the inspection robot and the end or end tail, and the inspection robot is controlled to reversely advance until the distance meets the stop condition.
In addition, the intelligent monitoring and autonomous cooperative tracking method for the coal mining machine based on the inspection vision according to the embodiment of the invention can also have the following additional technical characteristics:
optionally, the acquiring of the current position of the shearer drum in the field of view of the inspection robot includes:
collecting visual data of the coal mining machine in the operation process;
analyzing according to the visual data to obtain the visual characteristics of the roller target object under the coal cutting condition in the advancing direction of the coal mining machine;
and inputting the visual characteristics into a preset target object intelligent detection model to obtain the current position.
Optionally, the controlling the inspection robot to track the movement of the shearer along the target moving direction at a first preset speed includes:
reading a coal wall visual video stream of the inspection robot, and detecting whether the roller target of the coal mining machine exists in a current image frame;
if the coal mining machine roller target is not detected, controlling the inspection robot to move on the track at a second preset speed at a constant speed, and simultaneously collecting the distance between the inspection robot and the end head or the end tail;
if the coal mining machine roller target is detected, judging whether the inspection robot is in a machine following mode state;
if the inspection robot is not in the machine following mode state, controlling the inspection robot to decelerate until the inspection robot stops in the positioning mode state, and entering the machine following mode state;
and if the coal mining machine is not in the machine following mode state, starting to track the motion of the coal mining machine along the target running direction at the first preset speed according to the target moving direction.
Optionally, the method further comprises:
and if no continuous preset frame in the image frames of the coal wall visual video stream detects the roller target of the coal mining machine, controlling the mode state of the inspection robot to be switched from the machine following mode to the positioning mode state.
Therefore, the method has the characteristics of intelligent sensing, autonomous and repositioning tracking of the target and cooperative control operation of the inspection robot and the coal mining machine. The problem of the manual control command issue too early under the manual control patrols and examines robot mode of work, or avoid the uncertainty of visual target monitoring state that the unreliability of data channel leads to is solved. The system intelligently senses and tracks the target of the coal mining machine, the automatic control inspection robot stably tracks coal mining movement, on one hand, the battery cruising ability of the underground inspection robot is improved, the reliability of the body is improved, on the other hand, the working strength of the underground limited space coal miner manually controlling the inspection robot is reduced, even the current posts of the underground working face coal miner can be reduced or completely replaced to a certain extent, the real-time dynamic monitoring of the working condition and the surrounding environment state of the coal mining machine is provided for the intelligent unmanned coal mining system, the comprehensive mining production effect of reducing and improving the efficiency is really achieved, and the intelligent unmanned coal mining process of the coal mine is assisted.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The intelligent monitoring and autonomous cooperative tracking device of the coal mining machine and the inspection platform system according to the embodiment of the invention are described below with reference to the accompanying drawings, and first, the intelligent monitoring and autonomous cooperative tracking device of the coal mining machine based on inspection vision according to the embodiment of the invention will be described with reference to the accompanying drawings.
Before introducing the intelligent monitoring and autonomous cooperative tracking device of the patrol inspection vision-based coal mining machine of the embodiment of the application, the defects in the related art are simply introduced.
In the related technology, a corresponding sensor device is arranged on a coal mining machine body to monitor the condition of the coal mining machine and the state of the surrounding environment of operation in real time, and the coal mining machine is controlled manually and visually in a remote way. The method is influenced by the destructive force of working conditions and severe environment, the reliability of a monitoring device of the method is often not guaranteed, the remote monitoring and manual intervention control effects are not ideal enough, and the existing posts of operators of the underground working face coal machine cannot be completely replaced or reduced to a certain extent. The inspection system platform technical method is based on the inspection robot device of the fully mechanized mining face, although the inspection robot is remotely controlled under the artificial well or on the ground, the operation working condition and the surrounding environment state of the coal mining machine are dynamically monitored in a remote artificial real-time tracking and visualization mode based on the vision of the inspection robot. However, in order to ensure that the underground inspection robot can completely capture the working condition and the surrounding environment state of the coal mining machine in real time in the inspection process, a worker is required to be specially arranged to remotely and manually monitor the working condition and the surrounding environment state of the coal mining machine in real time in an underground or ground way through a visual mode, so that the worker can sense and judge the working condition and the surrounding environment state in real time and control the inspection robot manually to realize the tracking and monitoring of the coal mining machine. Under the condition, on one hand, the following worker manually controls the inspection robot according to experience, the position of the coal mining machine in the visual monitoring video image is uncertain due to the fact that the control command is issued too early or not timely, even the coal mining machine is completely out of the monitoring visual field range at certain moments, and the effect of tracking the coal mining machine and the reliability of video image data are greatly reduced. On the other hand, the movement speed of the coal mining machine is low, the operator of the inspection robot usually needs to wait for the advance of the coal mining machine, the walking and the operation of the inspection robot can become very difficult for the working face with low coal seam thickness, and the trolley is started and stopped frequently, so that the operation endurance of the inspection robot is greatly reduced, and the reliability and the service life of the inspection robot body are influenced for a long time or even.
Specifically, fig. 1 is a block diagram schematically illustrating an intelligent monitoring and autonomous cooperative tracking device for a coal mining machine based on inspection vision according to an embodiment of the present application.
As shown in fig. 1, the intelligent monitoring and autonomous cooperative tracking method and device for the coal mining machine based on the inspection vision comprises the following steps:
and the acquisition module 100 is used for acquiring the current position of the roller of the coal mining machine in the field of view of the inspection robot.
Optionally, in some embodiments, the acquisition module 100 comprises: the acquisition unit is used for acquiring visual data of the coal mining machine in the operation process; the analysis unit is used for analyzing and obtaining the visual characteristics of the roller target object under the coal cutting condition in the advancing direction of the coal mining machine according to the visual data; and the acquisition unit is used for inputting the visual characteristics into a preset target object intelligent detection model and acquiring the current position.
It can be understood that, because the body structure of the coal mining machine is relatively bulky, the complete operation condition of the coal mining machine cannot be captured in the visual field of a camera of a visual video system in the process of close-distance follow-up under general conditions. Meanwhile, in the whole process of the fully-mechanized coal mining operation, the vision of a coal mining machine operator and a control system does not need to pay attention to the running condition of the whole machine body part of the coal mining machine all the time, but pay attention to the conditions of rocker arm lifting of the coal mining machine and coal cutting of a roller of the coal mining machine, so that the coal cutting can be completed safely and effectively. Therefore, according to the characteristics of the coal mine fully-mechanized mining process, a visual system of the inspection robot is designed based on the inspection platform system, and the construction schematic diagram is shown in fig. 2. The inspection robot vision system consists of three cameras, namely a camera 1, a camera 2 and a camera 3. The cameras 1 and 2 respectively perform vision before and after walking of the inspection robot, and the main vision range is a walking track of the inspection robot and a front working surface support and a rear working surface support area. The camera 3 is used for inspecting the coal wall vision of the robot, and the visual field range is a coal wall area. When the coal mining machine circularly runs in the fully mechanized mining face, the camera 3 is mainly responsible for the visual monitoring of the working conditions of the rocker arm and the roller in the advancing direction of the coal mining machine.
On the basis of the construction of a vision system of the inspection robot, video image data related to the operation process of the coal mining machine is collected and sorted based on the vision of the inspection robot, and the visual characteristic analysis is performed on a roller target object under the condition of cutting coal around the advancing direction of the coal mining machine. This is because the environment is relatively complicated and harsh under the coal cutting condition, the coal dust pollution is serious, and the rocker arm of the coal machine is usually in the shielding state of the coal dust splashed during the operation. Under the condition, the visual characteristics of the rocker arm of the coal machine are not obvious enough, and the automatic state detection effect is not reasonable enough, so that the automatic detection and tracking of the target object of the roller of the coal machine are focused on.
The first tracking module 200 is configured to determine a target moving direction of the coal mining machine according to the current position, and control the inspection robot to track the movement of the coal mining machine at a first preset speed along the target moving direction.
Optionally, in some embodiments, the first tracking module 200 comprises: the reading unit is used for reading the visual video stream of the coal wall of the inspection robot and detecting whether a roller target of the coal mining machine exists in the current image frame; the first control unit is used for controlling the inspection robot to move on the track at a constant speed at a second preset speed when the target of the roller of the coal mining machine is not detected, and meanwhile, the distance between the inspection robot and the end head or the end tail is obtained; the judging unit is used for judging whether the inspection robot is in a machine following mode state or not when a roller target of the coal mining machine is detected; the second control unit is used for controlling the inspection robot to decelerate until the inspection robot stops and enters the machine following mode state in the positioning mode state when the inspection robot is not in the machine following mode state; and the tracking unit is used for starting tracking the movement of the coal mining machine along the target running direction at a first preset speed according to the target moving direction when the tracking unit is not in the machine following mode state.
The method includes the steps that a system structure of condition and posture distribution of the environment, particularly the environment and main equipment of the fully mechanized coal mining face is established according to the underground scene environment of the coal mine, influence rules of factors such as illumination change, coal dust influence and shielding on visual perception are analyzed and summarized systematically, the influence rules of the illumination change, the coal dust influence and the shielding three influence factors are combined, a coal roller machine learning training sample image database set with strong diversity and a certain scale of the fully mechanized coal mining face based on the operation condition of the patrol visual related coal mining machine is constructed through arrangement and labeling, and an important data basis is provided for the construction of the intelligent perception of the coal mining machine based on the patrol visual sense and the automatic detection algorithm model training of the roller.
And then constructing an intelligent sensing and automatic drum detection algorithm model of the coal mining machine. On the basis of establishment of a database set of coal mining machine roller machine learning training sample images based on patrol visual related coal mining machine operation conditions, machine learning is carried out on sample image data through a convolutional neural network, visual features of a coal mining machine roller target object are extracted, and implicit representation of the visual features of the coal mining machine roller target object is achieved; and establishing an automatic detection and identification model of the target object of the roller of the coal mining machine through a Region Proposal network, pooling operation and a classification network. On the basis of the establishment of the automatic detection and identification model of the target object of the drum of the coal mining machine, information data of other sensors are fused, and the intelligent real-time perception of the target of the coal mining machine on the fully mechanized mining face is realized on the basis of the visual perception system of the inspection robot.
Through tests, the intelligent sensing automatic detection rate of the coal mining roller based on the inspection robot vision sensing system reaches a real-time detection rate of more than 25 frames per second, the detection accuracy rate is guaranteed to be more than 95%, and the visualization result is shown in fig. 3.
The second tracking module 300 is used for gradually reducing the moving speed of the inspection robot according to the distance between the inspection robot and the end head or the end tail when detecting that the inspection robot reaches the end head or the end tail area of the inspection track, and controlling the inspection robot to reversely advance until the distance meets the stop condition.
It can be understood that the method for intelligently monitoring the working condition of the coal mining machine and automatically tracking the inspection robot is designed on the basis of automatically detecting the coal mining roller by the intelligent coal mining roller sensing system of the inspection robot. In the inspection mode, in the operation process of the robot in the middle area of the working face, the vision system intelligently senses the coal mining machine roller and positions the coal mining machine roller according to the dynamic position information of the coal mining machine roller in the vision picture. And then the control system automatically adjusts and controls the speed of the polling robot, automatically tracks the coal machine target to move forward, and ensures that the coal machine roller is displayed in a visual picture of the polling visual system in real time. When the coal mining machine runs to the end head and the end tail of the working face, and the inspection robot tracks and runs to the two ends of the track, the inspection platform system conducts end head and end tail positioning sensing and performs speed reduction and U-turn control operation according to the infrared positioning sensors installed at the end head and the end tail of the working face in advance. The method for automatically and cooperatively tracking the coal mining machine by the inspection robot is convenient for the fully mechanized mining control system to monitor the operation condition and the surrounding environment of the coal mining machine, can replace the important function of operating workers of the underground working face coal mining machine to a great extent, and promotes the process of reducing the number of people and improving the efficiency of unmanned mining of coal mines. The flow of the method for the autonomous cooperative tracking of the coal mining machine by the inspection robot is shown in fig. 4.
The specific process flow of the autonomous collaborative tracking coal mining machine of the inspection robot is described as follows:
(1) reading a coal wall visual video stream of the inspection robot, and automatically detecting whether a roller target of the coal mining machine exists in a current image frame by using an intelligent sensing model;
(2) if the roller target of the coal mining machine is not detected, the inspection platform system controls the inspection robot to move on the rail at a constant speed, and simultaneously obtains the distance between the inspection robot and the end head or end tail support;
(3) returning to the step (1) to continuously read the visual video stream of the coal wall of the inspection robot and automatically detect the roller of the coal mining machine;
(4) if the target of the roller of the coal mining machine is automatically detected, the inspection robot is close to the coal mining machine, and whether the inspection robot is in a machine following mode state is further judged;
(5) if the inspection robot does not follow the machine but is in a positioning coal mining machine position mode state, the inspection platform system automatically controls the robot to decelerate until the robot stops;
(6) determining the running direction of the coal mining machine;
(7) according to the running direction of the coal mining machine, the inspection platform system controls the inspection robot to start tracking the movement of the coal mining machine at a certain speed along the running direction of the coal mining machine, and the running mode of the inspection robot is updated to be changed into a machine following mode state;
(8) in the process that the inspection robot tracks the coal mining machine, the inspection platform system conducts positioning perception of the end head and the end tail according to infrared positioning sensors of the end head and the end tail of the working surface, and if the inspection platform system is close to the position of the end head or the end tail, the inspection robot is controlled to decelerate until the inspection robot stops and reversely moves forwards;
(9) and then returning to the step (1) to continuously read the visual video stream of the coal wall of the inspection robot to automatically detect the roller of the coal mining machine.
Optionally, in some embodiments, the intelligent monitoring and autonomous cooperative tracking device 10 for a coal mining machine based on inspection vision of the embodiment of the present application further includes: and the switching module is used for controlling the mode state of the inspection robot to be switched from the machine following mode to the positioning mode state if no coal cutter roller target is detected in the continuous preset frames in the image frames of the coal wall visual video stream.
Whether to patrolling and examining the robot and being in the location mode to the coal-winning machine or with quick-witted mode state, specific process description is:
when the inspection platform system starts to work, the inspection robot is in a positioning mode state for the coal mining machine. Considering that the coal mining machine may be far away from the inspection robot at this time, the system controls the robot to move at a constant speed on the track, meanwhile, the automatic detection of the coal mining machine roller target is carried out according to the visual video streaming frame image of the coal wall, and if the coal mining machine roller target is detected, the system indicates that the inspection robot has moved to the vicinity around the coal mining machine target.
When the inspection robot moves to the vicinity of the periphery of the coal mining machine, before the inspection robot enters a machine following mode state, the running direction of the coal mining machine needs to be determined, and the running advancing direction of the coal mining machine is ensured to be consistent with the running direction of the coal mining machine. In the process of determining the current running direction of the tracking coal mining machine, the system is firstly required to control the inspection robot to decelerate until the inspection robot stops. For example, the coal mining machine runs leftwards, after the inspection robot decelerates and stops, within a certain time, the pixel coordinates of the coal mining machine roller are automatically detected to translate from the right side to the left side in the image frame of the coal wall visual video stream, the area of the detection rectangular frame of the coal mining machine roller target is reduced, and at the moment, the coal mining machine can be determined to move leftwards. And then the system controls the inspection robot to start tracking the coal mining machine along the advancing direction of the coal mining machine at the initial speed, and enters a machine following mode and state. When the coal mining machine runs leftwards, the condition of the roller of the coal mining machine visually detected by the coal wall of the inspection robot in a deceleration stop state is shown in fig. 5.
After the inspection robot enters the machine following mode state, the system needs to dynamically control the speed of the inspection robot in real time according to the movement speed of the coal mining machine. The left movement of the coal mining machine is also taken as an example. The inspection robot starts to follow the machine at a certain speed, pixel coordinates of a coal mining machine roller target detected by a coal wall visual video stream image frame in the machine following process are translated rightward, the area of a rectangular frame of the coal mining machine roller target is gradually increased, the current machine following speed of the inspection robot is higher than the running speed of a coal mining machine, and at the moment, the running speed of the inspection robot is controlled to be reduced by a system. On the contrary, the pixel coordinates of the coal mining machine roller target detected in the coal wall visual video stream image frame in the machine following process are translated leftwards, the area of the rectangular frame of the coal mining machine roller target is reduced, the current machine following speed of the inspection robot is smaller than the running speed of the coal mining machine, and the movement speed of the inspection robot is increased at the moment.
And under the state of the inspection robot in the machine following mode, if continuous multiframes in image frames of the coal wall visual video stream do not detect the roller target of the coal mining machine, switching the mode state of the inspection robot from the machine following mode to the positioning mode state.
In summary, the embodiment of the application is based on an artificial intelligence technology, the construction of a coal mining machine object intelligent detection model in a fully mechanized mining process is realized through deep learning, and a coal mining machine working condition intelligent monitoring and automatic autonomous machine following method and system based on inspection vision on a fully mechanized mining working surface are designed; and then according to the autonomous timely positioning function of the inspection platform system, the moving direction and speed of the inspection robot are dynamically and autonomously controlled, the coal mining machine is ensured to be always in the visual field of the inspection robot in real time, and the automatic autonomous tracking of the inspection robot on the movement of the coal mining machine is realized. Meanwhile, the automatic deceleration and autonomous circulation control operation of the inspection robot reaching the end of the inspection rail are realized at the end head and the end tail of the fully mechanized mining face based on infrared distance measurement.
According to the coal mining machine intelligent monitoring and autonomous cooperative tracking device based on the inspection vision, the coal mining machine intelligent monitoring and autonomous cooperative tracking device has the advantages of intelligent sensing, autonomous and repositioning tracking of targets and cooperative control and operation of an inspection robot and a coal mining machine. The problem of the manual control command issue too early under the manual control patrols and examines robot mode of work, or avoid the uncertainty of visual target monitoring state that the unreliability of data channel leads to is solved. The system intelligently senses and tracks the target of the coal mining machine, the automatic control inspection robot stably tracks coal mining movement, on one hand, the battery cruising ability of the underground inspection robot is improved, the reliability of the body is improved, on the other hand, the working strength of the underground limited space coal miner manually controlling the inspection robot is reduced, even the current posts of the underground working face coal miner can be reduced or completely replaced to a certain extent, the real-time dynamic monitoring of the working condition and the surrounding environment state of the coal mining machine is provided for the intelligent unmanned coal mining system, the comprehensive mining production effect of reducing and improving the efficiency is really achieved, and the intelligent unmanned coal mining process of the coal mine is assisted.
The intelligent monitoring and autonomous cooperative tracking device of the coal mining machine based on the patrol inspection vision, which is provided by the embodiment of the application, is described next with reference to the attached drawings.
Fig. 6 is a flowchart of a method for intelligent monitoring and autonomous cooperative tracking of a coal mining machine based on inspection vision according to an embodiment of the present application.
As shown in fig. 6, the inspection vision-based coal mining intelligent machine monitoring and autonomous cooperative tracking method comprises the following steps:
in step S101, the current position of the shearer drum in the field of view of the inspection robot is acquired.
In step S102, the target moving direction of the coal mining machine is determined according to the current position, and the inspection robot is controlled to track the movement of the coal mining machine at a first preset speed along the target moving direction.
In step S103, when it is detected that the inspection robot reaches the end or end-tail region of the inspection rail, the moving speed of the inspection robot is gradually reduced according to the distance between the inspection robot and the end or end-tail region, and the inspection robot is controlled to move forward in the reverse direction until the distance satisfies the stop condition.
Optionally, in some embodiments, acquiring the current position of the shearer drum in the field of view of the inspection robot includes: collecting visual data of the coal mining machine in the operation process; analyzing according to the visual data to obtain the visual characteristics of the roller target object under the coal cutting condition in the advancing direction of the coal mining machine; and inputting the visual characteristics into a preset target object intelligent detection model to obtain the current position.
Optionally, in some embodiments, controlling the inspection robot to track the shearer movement at a first preset speed along the target movement direction comprises: reading a coal wall visual video stream of the inspection robot, and detecting whether a roller target of a coal mining machine exists in a current image frame; if the target of the coal mining machine roller is not detected, controlling the inspection robot to move on the track at a second preset speed at a constant speed, and acquiring the distance between the inspection robot and the end head or the end tail; if the target of the roller of the coal mining machine is detected, judging whether the inspection robot is in a machine following mode state; if the inspection robot is not in the machine following mode state, controlling the inspection robot to decelerate until the inspection robot stops in the positioning mode state, and entering the machine following mode state; and if the coal mining machine is not in the following mode state, starting to track the motion of the coal mining machine along the target running direction at a first preset speed according to the target moving direction.
Optionally, in some embodiments, the method further comprises: and if no coal cutter roller target is detected in the continuous preset frames in the image frames of the coal wall visual video stream, controlling the mode state of the inspection robot to be switched from the machine following mode to the positioning mode.
It should be noted that the foregoing explanation of the embodiment of the intelligent monitoring and autonomous cooperative tracking device for a coal mining machine based on inspection vision is also applicable to the intelligent monitoring and autonomous cooperative tracking method for a coal mining machine based on inspection vision of this embodiment, and details are not repeated here.
The intelligent monitoring and autonomous cooperative tracking method of the coal mining machine based on the inspection vision, provided by the embodiment of the application, has the characteristics of intelligent sensing, autonomous and repositioning tracking of targets, and cooperative control and operation of an inspection robot and the coal mining machine. The problem of the manual control command issue too early under the manual control patrols and examines robot mode of work, or avoid the uncertainty of visual target monitoring state that the unreliability of data channel leads to is solved. The system intelligently senses and tracks the target of the coal mining machine, the automatic control inspection robot stably tracks coal mining movement, on one hand, the battery cruising ability of the underground inspection robot is improved, the reliability of the body is improved, on the other hand, the working strength of the underground limited space coal miner manually controlling the inspection robot is reduced, even the current posts of the underground working face coal miner can be reduced or completely replaced to a certain extent, the real-time dynamic monitoring of the working condition and the surrounding environment state of the coal mining machine is provided for the intelligent unmanned coal mining system, the comprehensive mining production effect of reducing and improving the efficiency is really achieved, and the intelligent unmanned coal mining process of the coal mine is assisted.
In addition, this application embodiment still provides a platform system patrols and examines, and should patrol and examine the platform system and include foretell coal-winning machine intelligent monitoring and independently cooperate with the machine based on patrolling and examining the vision.
According to the inspection platform system, the problems that manual control instructions are sent too early under the working mode of the manual control inspection robot or the uncertainty of the monitoring state of a visual target caused by the unreliability of a data channel is avoided through the intelligent monitoring and autonomous cooperative following device of the inspection vision-based coal mining machine are solved. The system intelligently senses and tracks the target of the coal mining machine, the automatic control inspection robot stably tracks coal mining movement, on one hand, the battery cruising ability of the underground inspection robot is improved, the reliability of the body is improved, on the other hand, the working strength of the underground limited space coal miner manually controlling the inspection robot is reduced, even the current posts of the underground working face coal miner can be reduced or completely replaced to a certain extent, the real-time dynamic monitoring of the working condition and the surrounding environment state of the coal mining machine is provided for the intelligent unmanned coal mining system, the comprehensive mining production effect of reducing and increasing the labor intensity is really achieved, and the intelligent unmanned coal mining process of the coal mine is assisted.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of implementing the embodiments of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.