CN116977941A - Method and system for detecting key working procedures of tunneling roadway - Google Patents

Method and system for detecting key working procedures of tunneling roadway Download PDF

Info

Publication number
CN116977941A
CN116977941A CN202311227661.3A CN202311227661A CN116977941A CN 116977941 A CN116977941 A CN 116977941A CN 202311227661 A CN202311227661 A CN 202311227661A CN 116977941 A CN116977941 A CN 116977941A
Authority
CN
China
Prior art keywords
frame
target
procedure
state
center coordinates
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311227661.3A
Other languages
Chinese (zh)
Inventor
陶磊
张之好
王宏伟
刘峰
李永安
耿毅德
王浩然
闫志蕊
梁威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Taiyuan University of Technology
Original Assignee
Taiyuan University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Taiyuan University of Technology filed Critical Taiyuan University of Technology
Priority to CN202311227661.3A priority Critical patent/CN116977941A/en
Publication of CN116977941A publication Critical patent/CN116977941A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/06—Recognition of objects for industrial automation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a method and a system for detecting key procedures of a tunneling roadway, and relates to the technical field of mine detection. Comprising the following steps: acquiring target images corresponding to each key procedure in a tunneling roadway, wherein the key procedures comprise a temporary supporting procedure, a permanent supporting procedure, a walking procedure and a cutting procedure; identifying at least one target object in each target image by using a trained target detection model, and extracting the center coordinates of a target frame where each target object is located; and determining real-time operation information of each key process based on the center coordinates of each target frame, wherein the real-time operation information at least comprises an operation state identification and operation time information. According to the invention, the machine vision recognition is carried out on the tunneling process, so that the tunneling scene is more transparent and visual, the tunneling process is convenient to be standardized in time, the tunneling safety can be improved, and the tunneling efficiency can be improved.

Description

Method and system for detecting key working procedures of tunneling roadway
Technical Field
The invention relates to the technical field of mine detection, in particular to a method and a system for detecting key working procedures of a tunneling roadway.
Background
The underground tunnel construction is a hidden high-risk underground construction project, at present, the problems of delayed intelligent construction, shortage of excavation engagement and the like are particularly outstanding, and the mechanization, automation, informatization and intellectualization of tunnel excavation are necessary ways for solving the unbalance of coal mine excavation.
Because the coal mine tunnel tunneling scene has complex environment, huge and concentrated equipment and larger danger coefficient, the process of the key working procedure of the tunneling tunnel needs to be accurately mastered. However, the intelligent visual construction of the current tunneling working face is mainly focused on video monitoring and equipment digital and network transformation, and the tunneling working procedure of the tunnel cannot be accurately identified, so that the safe tunneling of the tunnel cannot be ensured. In addition, the links of the roadway tunneling process are more, the operation among devices is independent and disordered, and only the practical experience can be relied on during underground operation, so that the tunneling efficiency of the roadway can be affected to a certain extent.
Disclosure of Invention
The invention aims to provide a method and a system for detecting key working procedures of a tunneling roadway, which can solve the problems of lower tunneling safety and lower tunneling efficiency caused by the fact that the tunneling working procedures of the roadway cannot be accurately identified in the related art.
The invention provides a method for detecting key working procedures of a tunneling roadway, which comprises the following steps:
acquiring target images corresponding to each key procedure in a tunneling roadway, wherein the key procedures comprise a temporary supporting procedure, a permanent supporting procedure, a walking procedure and a cutting procedure;
identifying at least one target object in each target image by using a trained target detection model, and extracting the center coordinates of a target frame where each target object is located;
and determining real-time operation information of each key process based on the center coordinates of each target frame, wherein the real-time operation information at least comprises an operation state identification and operation time information.
Optionally, the target image comprises a first image corresponding to the temporary support procedure, the target object comprises a support frame and an anchor net, and the target frame comprises a first detection frame and a second detection frame;
the identifying at least one target object in each target image by using the trained target detection model, and extracting the center coordinates of the target frame where each target object is located, includes:
and identifying the support frame and the anchor net in the first image by using the trained target detection model, and extracting the center coordinates of a first detection frame where the support frame is positioned and the center coordinates of a second detection frame where the anchor net is positioned.
Optionally, the determining the real-time job information of each key procedure based on the center coordinates of each target frame includes:
identifying a support frame in a first image of the temporary support procedure in different operation states by using the trained target detection model, and respectively extracting the center coordinates of the support frame, wherein each operation state comprises a temporary support state and an non-temporary support state;
generating a first movable range frame of the support frame according to the central coordinate of the support frame in the temporary support state, and generating a second movable range frame of the support frame according to the central coordinate of the support frame in the non-temporary support state;
and determining real-time operation information of the temporary support procedure according to the first movable range frame, the second movable range frame of the support frame, the central coordinate of the first detection frame where the support frame is located and the central coordinate of the second detection frame where the anchor net is located.
Optionally, the determining the real-time operation information of the temporary support procedure according to the first movable range frame, the second movable range frame, the central coordinate of the first detection frame where the support frame is located, and the central coordinate of the second detection frame where the anchor net is located includes:
If the center coordinate of the first detection frame where the support frame is located in the first movable range frame, determining that the support frame is currently in the temporary support state, and recording the operation state identification and the operation time information of the temporary support state;
if the center coordinate of the first detection frame where the support frame is located in the second movable range frame, determining that the support frame is in the non-temporary support state currently, and recording the operation state identification and the operation time information of the non-temporary support state;
if the center coordinates of the first detection frame where the support frame is located are not in the first movable range frame and the second movable range frame, detecting the distance between the center coordinates of the first detection frame where the support frame is located and the center coordinates of the second detection frame where the anchor net is located;
if the distance is unchanged along with the change of time, determining that the current support frame is in an uplink state, and recording an operation state identifier and operation time information of the uplink state of the support frame;
if the distance is continuously increased along with the time change, determining that the support frame is in a descending state currently, and recording an operation state identifier and operation time information of an ascending state of the support frame.
Optionally, the target image comprises a second image corresponding to the permanent support procedure, the target object comprises a tunneler and a drilling machine, and the target frame comprises a third detection frame and a fourth detection frame;
the determining the real-time operation information of each key procedure based on the center coordinates of each target frame includes:
after extracting the center coordinates of a third detection frame where the tunneling personnel are located and the center coordinates of a fourth detection frame where the drilling machine is located, if the center coordinates of the third detection frame where the tunneling personnel are located and the center coordinates of the fourth detection frame where the drilling machine are located in the second image at the same time, determining that the tunneling personnel are in a permanent supporting state at present, and recording the operation state identification and the operation time information of the permanent supporting state;
if the center coordinates of the third detection frame where the tunneling personnel are located and the center coordinates of the fourth detection frame where the drilling machine is located are not located in the second image at the same time, determining that the tunneling personnel are in an unfinished supporting state currently, and recording operation state identification and operation time information of the unfinished supporting state.
Optionally, the target image includes a third image corresponding to the walking procedure, the target object includes at least one anchor rod located on a side wall of the roadway, and the target frame includes a fifth detection frame where each anchor rod is located;
The determining the real-time operation information of each key procedure based on the center coordinates of each target frame includes:
after the central coordinates of the fifth detection frames where the anchor rods are located are extracted, determining whether the central coordinates of the fifth detection frames where the target anchor rods are located are changed or not by utilizing a target tracking algorithm;
if the central coordinate of the fifth detection frame where the target anchor rod is located is unchanged along with the change of time, determining that the target anchor rod is in a non-walking state currently, and recording an operation state identifier and operation time information of the non-walking state;
if the central coordinate of the fifth detection frame where the target anchor rod is located changes along with the time change, determining that the target anchor rod is currently in a walking state, and recording the operation state identification and the operation time information of the walking state.
Optionally, the target image comprises a fourth image corresponding to the cutting procedure, the target object comprises a cantilever and a cutting head which are positioned on a heading machine, and the target frame comprises a sixth detection frame where the cantilever and the cutting head are positioned;
the determining the real-time operation information of each key procedure based on the center coordinates of each target frame includes:
identifying a cantilever and a cutting head in the fourth image in an unclamped state by using the trained target detection model, and respectively extracting center coordinates of the cantilever and the cutting head in the unclamped state;
Generating a third movable range frame of the cantilever and the cutting head according to the center coordinates of the cantilever and the cutting head in the non-cutting state;
after extracting the center coordinates of a sixth detection frame where the cantilever and the cutting head are located, if the center coordinates of the sixth detection frame where the cantilever and the cutting head are located in the third movable range frame, determining that the cantilever and the cutting head are in an unclamped state currently, and recording the operation state identification and the operation time information of the unclamped state;
if the center coordinates of the sixth detection frame where the cantilever and the cutting head are located are not in the third movable range frame, determining that the cutting state is currently in, and recording the operation state identification and the operation time information of the cutting state.
Optionally, the acquiring the target image corresponding to each key procedure in the tunneling roadway includes:
acquiring original images corresponding to each key procedure in a tunneling roadway;
and respectively carrying out denoising treatment and defogging treatment on each original image by using an image filtering algorithm and an image defogging algorithm to obtain a target image corresponding to each original image.
Optionally, the target detection model comprises a YOLOv5 model.
In a second aspect of the present invention, there is provided a system for detecting key process of a driving tunnel, comprising:
The target image acquisition module is used for acquiring target images corresponding to each key procedure in the tunneling roadway, wherein the key procedures comprise a temporary supporting procedure, a permanent supporting procedure, a walking procedure and a cutting procedure;
the feature information extraction module is used for identifying at least one target object in each target image by utilizing the trained target detection model and extracting the center coordinates of a target frame where each target object is located;
and the operation information determining module is used for determining real-time operation information of each key process based on the center coordinates of each target frame, and the real-time operation information at least comprises an operation state identification and operation time information.
The invention has the following beneficial effects:
the method for machine vision identification of the key working procedures of the tunneling roadway is provided, so that the tunneling scene is transparent and visual, the key working procedures of the tunneling roadway are standardized in time conveniently, and the tunneling safety of the roadway is improved; compared with the prior art that complicated tunneling procedures are executed according to the practical experience, the method and the device can clearly determine the next tunneling procedure after accurately identifying the current tunneling tunnel key procedure, further shorten the connection time between procedures, avoid the occurrence of additional auxiliary labor and other conditions, and further improve the tunneling efficiency of the tunnel.
Drawings
Fig. 1 shows a schematic diagram of a system architecture to which the method for detecting a key process of a driving roadway according to an embodiment of the present invention can be applied.
Fig. 2 is a schematic flow chart of a method for detecting a key procedure of a tunneling roadway in an embodiment of the invention.
Fig. 3 shows a schematic process flow diagram of a temporary support procedure in an embodiment of the invention.
Fig. 4 shows a schematic diagram of a system for detecting a key process of a tunneling roadway in an embodiment of the invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known aspects have not been shown or described in detail to avoid obscuring aspects of the invention.
Fig. 1 shows a system architecture diagram to which the method for detecting a key process of a driving roadway according to an embodiment of the present invention can be applied.
The system architecture 100 may include one or more of a smart phone 101, a portable computer 102, a desktop computer 103, and other terminal devices, a network 104, and a server 105, among others. The network 104 is the medium used to provide communication links between the terminal devices and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others. The server 105 can communicate with acquisition equipment such as a camera device configured in the coal mine tunnel to acquire relevant data in the coal mine tunnel acquired by the acquisition equipment in real time. The camera device can select the existing network camera of the mine, each procedure is collected by using one camera, the installation position of each camera can ensure that the construction process of each procedure is seen, and the shielding is less.
The terminal device may be various electronic devices having data processing functions including, but not limited to, a desktop computer, a portable computer, a smart phone, a tablet computer, and the like as described above. The terminal device may be placed at a mine site, such as a mine room, as the invention is not limited in this regard. The terminal equipment is provided with a processor, a code memory, a data memory, a display and the like, wherein the code memory is used for storing algorithm codes, the processor is used for executing the codes in the code memory to complete algorithm reasoning, and the data memory is used for receiving and storing images and parameter information of each procedure, such as showing collected images in a coal mine tunnel and real-time operation information of each key procedure to a user.
It should be noted that, the image capturing device in the present invention may also have a data processing function, for example, when the image capturing device is an intelligent camera, the code memory and the processor of the intelligent camera may directly detect and calculate the real-time operation information of the key process according to the collected image, and then transmit the calculated image and the real-time operation information to the terminal device or the server.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, the server 105 may be a server cluster formed by a plurality of servers.
The embodiment provides a key procedure detection method for a tunneling roadway. Referring to fig. 2, the method for detecting a key process of a driving roadway may include the following steps S210 to S230:
step S210, obtaining target images corresponding to key procedures in a tunneling roadway, wherein the key procedures comprise a temporary supporting procedure, a permanent supporting procedure, a walking procedure and a cutting procedure;
step S220, identifying at least one target object in each target image by using the trained target detection model, and extracting the center coordinates of a target frame where each target object is located;
And step S230, determining real-time operation information of each key process based on the center coordinates of each target frame, wherein the real-time operation information at least comprises operation state identification and operation time information.
Next, the above steps of the present exemplary embodiment will be described in more detail.
In step S210, target images corresponding to each of the key processes including the temporary support process, the permanent support process, the traveling process, and the cutting process in the tunnel are acquired.
The tunneling process flow of the roadway can comprise a plurality of working procedures such as geological exploration, rock blasting, ventilation, drainage, power distribution, support, walking and cutting, and the like, and the invention is not limited in particular. The multiple working procedures can be divided into a key working procedure and an auxiliary working procedure, wherein the key working procedure is a working procedure for directly finishing the progress of the working surface on the working surface of the roadway, or the working procedure with complicated process, such as supporting, walking, cutting and the like, and the auxiliary working procedure is a working procedure for ensuring the normal operation of the key working procedure, such as address exploration, rock blasting, ventilation and the like.
In an exemplary embodiment, three steps of supporting, walking and cutting can be selected as key steps, wherein the supporting steps can further comprise a temporary supporting step and a permanent supporting step. Specifically, the temporary support procedure is to use a support frame and an anchor net to prop against the top of a roadway so as to prevent coal falling from smashing the supporting personnel on a working surface. For example, when the support frame is not lifted, the anchor net can be laid on the support frame, and then the support frame is lifted after the anchor net is laid, so that the anchor net is supported at the top of a roadway for supporting, and after the temporary supporting procedure is finished, the support frame is fallen down, and the temporary supporting is finished. The permanent supporting procedure is that after temporary supporting construction is completed, a tunneler carries a drilling machine to enter a roadway working surface to support the top and the side walls of the roadway, for example, steel belts can be arranged at the positions of the top and the side walls of the roadway to be supported, after the steel belts are arranged, the tunneler uses the drilling machine to conduct punching operation, and a fixing point is provided for subsequent anchor rod installation. Thus, after drilling is completed, the tunneler inserts the bolt into the hole and secures it using the bolt securing tool. The steel strip may be made of high strength steel for increasing the stability and load carrying capacity of the roadway. The anchor rod can be made of steel, has good tensile strength, and can effectively increase the stability of a roadway. The walking process is to control the track of the heading machine to move the heading machine forwards or rotate left and right after the permanent supporting process is finished so as to adjust the position of the heading machine to be a position capable of cutting. The cutting procedure refers to cutting the coal wall by a tunneller such as a tunneller driver operating a cantilever and a cutting head of the tunneller after the tunneller walks in place.
In addition to critical processes, other processes can be accurately fed back through the control system. For the key working procedures, the construction process of each key working procedure can be acquired through a camera pre-configured in the roadway, so that the original image corresponding to each key working procedure is obtained, namely, the image of the working area where each key working procedure is located is obtained. Then, the original image obtained by acquisition can be preprocessed to improve the definition of the original image, so that the accuracy of target detection is improved.
For example, the image filtering algorithm and the image defogging algorithm may be used to perform denoising processing and defogging processing on each original image, respectively, to obtain a target image corresponding to each original image. The image filtering algorithm can comprise an arithmetic mean filtering algorithm, a Gaussian filtering algorithm, a bilateral filtering algorithm and the like, and the image defogging algorithm can be a dark channel priori defogging algorithm, a histogram equalization defogging algorithm and a neural network-based defogging algorithm, and the invention is not limited to the above.
In the example, dust fog generated in the tunneling process in the acquired original image can be removed through the image defogging algorithm, so that shielding of the image recognition process on the target object is reduced, and the accuracy of target detection is improved. The signal-to-noise ratio of the original image can be improved through the image denoising algorithm, image blurring caused by factors such as dim light in the pit, poor effect of imaging transmission equipment and the like is reduced, and the accuracy of target detection is further improved.
In step S220, at least one target object in each target image is identified by using the trained target detection model, and the center coordinates of the target frame where each target object is located are extracted.
After the target images corresponding to the original images are obtained, the trained target detection model can be utilized to carry out image recognition on the target images so as to determine the current tunneling procedure according to the image recognition result. The target detection model may be a YOLOv5 (single-Stage target detection) model, or other models such as EfficientDet, FCOS (Fully Convolutional One-Stage, full convolution single-Stage target detection model), which is not limited in this invention.
In an exemplary embodiment, the target image may include a first image of the working area where the temporary support procedure is located, that is, an image of the support frame and the anchor net is collected by a camera, a second image of the working area where the permanent support procedure is located, that is, an image of the top and the two sides of the tunnel in front of the heading machine collected by the camera, a third image of the working area where the walking procedure is located, that is, an image of the tunnel in side of the heading machine collected by the camera, and a fourth image of the working area where the cutting procedure is located, that is, an image of the cutting head and the cantilever of the heading machine collected by the camera.
For example, at least one target object in each target image may be identified, and the center coordinates of the target frame where each target object is located may be extracted, so that the real-time operation information of each key process may be determined according to the center coordinates of the target frame. The size of the target frame, that is, the parameter information such as the length and width of the target frame, may be extracted, which is not limited in the present invention.
Specifically, for a first image of an operation area where a temporary support procedure is located, a target object in the first image comprises a support frame and an anchor net, and correspondingly, a target frame comprises a first detection frame and a second detection frame. For example, the trained YOLOv5 model may be used to identify the support frame and the anchor net in the first image, and extract the center coordinates of the first detection frame where the support frame is located and the center coordinates of the second detection frame where the anchor net is located. For example, the first image is used as input of the YOLOv5 model to detect the first image, and identification results of the support frame and the anchor net are extracted according to corresponding category labels, wherein each identification result contains information such as position coordinates, edge coordinates, center coordinates, size and the like of the detection frame. Therefore, the central coordinates of the first detection frame where the support frame is located and the central coordinates of the second detection frame where the anchor net is located can be obtained, and the real-time operation state in the temporary support procedure can be determined according to the central coordinates of the first detection frame where the support frame is located and the central coordinates of the second detection frame where the anchor net is located.
And for a second image of the working area where the permanent support procedure is located, the target object in the second image comprises a tunneling person and a drilling machine, and correspondingly, the target frame comprises a third detection frame and a fourth detection frame. Similarly, the trained YOLOv5 model can be used for identifying the tunneling personnel and the drilling machine in the second image, and extracting the center coordinates of the third detection frame where the tunneling personnel are located and the center coordinates of the fourth detection frame where the drilling machine is located, so that the real-time operation state in the permanent support process is determined according to the center coordinates of the third detection frame where the tunneling personnel are located and the center coordinates of the fourth detection frame where the drilling machine is located.
And for a third image of the working area where the walking working procedure is located, the target object in the third image comprises at least one anchor rod positioned on the side wall of the roadway, and the corresponding target frame comprises a fifth detection frame where each anchor rod is located. Similarly, each anchor rod positioned on the side wall of the roadway in the third image can be identified by using the trained YOLOv5 model, and the center coordinates of the fifth detection frame where each anchor rod is positioned are extracted, so that the real-time operation state in the walking process is determined according to the center coordinates of the fifth detection frame where each anchor rod is positioned.
And for a fourth image of the working area where the cutting procedure is located, the target object in the fourth image comprises a cantilever and a cutting head which are positioned on the heading machine, and correspondingly, the target frame comprises a sixth detection frame where the cantilever and the cutting head are located. Similarly, the cantilever and the cutting head of the heading machine in the fourth image can be identified by using the trained YOLOv5 model, and the center coordinates of a sixth detection frame where the cantilever and the cutting head are located are extracted, so that the real-time working state in the cutting procedure is determined according to the sixth detection frame where the cantilever and the cutting head are located.
In the example, the machine vision is applied to the identification of the tunneling process, and objects, equipment and the like in the tunneling process can be quickly and accurately identified, so that timely information and guidance can be conveniently provided later, the tunneling personnel can be helped to make decisions and adjust, and the working efficiency and the production level are improved. And the potential safety hazards in the tunneling process can be monitored and identified, for example, whether collapse risks exist or not, whether personnel or equipment enter a dangerous area or not is checked, and the like, an alarm is sent out in time, measures are taken, accidents are avoided, and the safety of a tunneling roadway is improved.
In step S230, real-time job information of each of the critical processes is determined based on the center coordinates of each of the target frames, the real-time job information including at least a job status identification and job time information.
After obtaining the center coordinates of each target frame as described in step S220, real-time operation information of the corresponding key process may be determined according to the center coordinates of each target frame, where the real-time operation information includes at least an operation status identifier and operation time information. Taking a temporary support process as an example, the real-time operation information of the process may include a process name and an operation time of the process, and the operation time may also include a start time point, an end time point, a continuous operation time, etc. of each link in the process, which is not limited in the present invention.
For example one, for the temporary support procedure, the center coordinates of the first detection frame where the support frame is located and the center coordinates of the second detection frame where the anchor net is located are obtained, and when the real-time operation state of the temporary support procedure is determined according to the center coordinates of the first detection frame where the support frame is located and the center coordinates of the second detection frame where the anchor net is located, the support frame in the first image of the temporary support procedure in different operation states can be identified by using a trained target detection model such as a YOLOv5 model, and the center coordinates of the support frame can be extracted respectively. The operation states in the temporary support procedure can comprise a temporary support state and an non-temporary support state. Correspondingly, the temporary support state refers to a state when the support frame is supported in place, and the non-temporary support state refers to a state when the support frame is not lifted. Then, a first movable range frame of the support frame can be generated according to the central coordinates of the support frame in the temporary support state, and a second movable range frame of the support frame can be generated according to the central coordinates of the support frame in the non-temporary support state. That is, the first movable range frame refers to a movable range frame of the central coordinate of the support frame when the support frame is in place, and the second movable range frame refers to a movable range frame of the central coordinate of the support frame when the support frame is not lifted.
Further, the real-time operation information of the temporary support procedure can be determined according to the first movable range frame and the second movable range frame of the support frame, the center coordinate of the first detection frame where the support frame is located, and the center coordinate of the second detection frame where the anchor net is located. Specifically, if the center coordinate of the first detection frame where the support frame is located in the first movable range frame, determining that the support frame is currently in a temporary support state, and recording the operation state identification and the operation time information of the temporary support state; if the center coordinate of the first detection frame where the support frame is located in the second movable range frame, determining that the support frame is in an un-temporary support state currently, and recording operation state identification and operation time information of the un-temporary support state; if the center coordinates of the first detection frame where the support frame is located are not in the first movable range frame and the second movable range frame, detecting the distance between the center coordinates of the first detection frame where the support frame is located and the center coordinates of the second detection frame where the anchor net is located. If the distance is unchanged along with the time change, determining that the current support frame is in an uplink state, and recording an operation state identifier and operation time information of the uplink state of the support frame; if the distance is continuously increased along with the time change, determining that the support frame is in the descending state currently, and recording the operation state identification and the operation time information of the ascending state of the support frame.
For example, referring to fig. 3, after the central coordinates of the support frame (i.e., the central coordinates of the first detection frame where the support frame is located) and the central coordinates of the anchor net (i.e., the central coordinates of the second detection frame where the anchor net is located) in the first image are identified, if the central coordinates of the support frame are the central coordinates of the support frame when the support frame is not liftedIn the movable range frame (i.e. the second movable range frame), the current operation state can be determined to be the non-temporary support state, and the time t at the moment can be recorded 1 The method comprises the steps of carrying out a first treatment on the surface of the If the center coordinates of the support frame are not in the movable range frame of the center coordinates of the support frame when the support frame is not lifted, or in the movable range frame (i.e. the first movable range frame) of the center coordinates of the support frame when the support frame is in place, and the distance between the center coordinates of the support frame and the center coordinates of the anchor net is kept unchanged, the current operation state can be judged to be the ascending state of the support frame, and the time t at the moment is recorded 2 The method comprises the steps of carrying out a first treatment on the surface of the If the center coordinates of the support frame are within the movable range of the center coordinates of the support frame when the support frame is in place, the current operation state can be judged to be the temporary support state, and the time t at the moment is recorded 3 The method comprises the steps of carrying out a first treatment on the surface of the If the central coordinate of the support frame is not in the two movable range frames, the distance between the central coordinate of the support frame and the central coordinate of the anchor net is continuously increased, the current operation state can be judged to be the descending state of the support frame, and the time t at the moment is recorded 4 The method comprises the steps of carrying out a first treatment on the surface of the Until the non-temporary support state is identified again, recording the time t at the moment 5 。
So far, a complete temporary support workflow is finished; the starting time node, the ending time node and the duration of each link in the temporary support procedure can be calculated through the five recorded time points. For example, the duration of the non-temporary support state is T 1 The duration time of the ascending state of the support frame is T 2 The duration of the temporary support state is T 3 The duration time of the descending state of the support frame is T 4 。
For the permanent support procedure, obtaining the center coordinates of a third detection frame where a tunneling person is located and the center coordinates of a fourth detection frame where a drilling machine is located, determining real-time operation information of the permanent support procedure according to the center coordinates of the third detection frame where the tunneling person is located and the center coordinates of the fourth detection frame where the drilling machine is located, and if the center coordinates of the third detection frame where the tunneling person is located and the center coordinates of the fourth detection frame where the drilling machine is located are located in the second image at the same time, determining that the tunneling person is in a permanent support state at present, and recording operation state identification and operation time information of the permanent support state; if the center coordinates of the third detection frame where the tunneling personnel are located and the center coordinates of the fourth detection frame where the drilling machine is located are not located in the second image at the same time, determining that the tunneling personnel are in an unfinished supporting state currently, and recording operation state identification and operation time information of the unfinished supporting state.
Specifically, when the drilling machine and the tunneling personnel can be identified in the second image at the same time, judging that the current working state is a permanent supporting state, and recording the time at the moment; and when the drilling machine and the tunneling personnel cannot be identified in the second image, judging that the current working state is an unfinished supporting state, and recording the time at the moment. Also, the time taken for the permanent support process and the time not in the permanent support process can be calculated from the recorded time points.
In an example three, for the walking procedure, the center coordinates of the fifth detection frame where each anchor rod is located are obtained, and when the real-time working state of the walking procedure is determined according to the center coordinates of the fifth detection frame where each anchor rod is located, whether the center coordinates of the fifth detection frame where the target anchor rod is located are changed or not can be determined by using a target tracking algorithm. If the central coordinate of the fifth detection frame where the target anchor rod is located is unchanged along with the change of time, determining that the target anchor rod is in a non-walking state currently, and recording an operation state identifier and operation time information of the non-walking state; if the central coordinate of the fifth detection frame where the target anchor rod is located changes along with the time change, determining that the target anchor rod is in a walking state currently, and recording the operation state identification and the operation time information of the walking state.
Specifically, the center coordinates of the detection frames where different anchor rods are located can be obtained by identifying the anchor rods leaked from the side wall of the tunnel after the permanent support. The detection frames corresponding to the same anchor rod at different moments can be associated by using a target tracking algorithm such as a deep sort algorithm. If the position of the detection frame where the same anchor rod is located is not recognized to be changed, the position of the heading machine is not moved, and if the position of the target frame where the same anchor rod is recognized to be changed, the position of the heading machine is moved, namely the heading machine performs a walking action, and the time at the moment is recorded.
For example four, for the cutting procedure, after obtaining the center coordinates of the sixth detection frame where the cantilever and the cutting head are located, the trained target detection model, such as the YOLOv5 model, may be used to identify the cantilever and the cutting head in the fourth image in the non-cutting state, extract the center coordinates of the cantilever and the cutting head in the non-cutting state, and generate the third movable range frame of the cantilever and the cutting head according to the center coordinates of the cantilever and the cutting head in the non-cutting state. Further, the real-time operation information of the cutting process may be obtained according to the positional relationship between the center coordinates of the sixth detection frame where the cantilever and the cutting head are located and the third movable range frame.
Specifically, if the center coordinates of the sixth detection frame where the cantilever and the cutting head are located in the third movable range frame, determining that the cantilever and the cutting head are currently in an unclamped state, and recording the operation state identifier and the operation time information of the unclamped state, such as recording the name of the unclamped state and the time at the moment; if the center coordinates of the cantilever and the sixth detection frame where the cutting head is located are not in the third movable range frame, the current cutting state can be determined, and the operation state identification and the operation time information of the cutting state, such as the name of the cutting state and the time at the moment, are recorded. The time taken to be in the cut state and the time to be in the uncut state can be calculated from the recorded time points.
After the cutting process is finished, the cantilever and the cutting head are lowered to the designated positions for facilitating other processes, and the positions are required to be different from the movable ranges of the cantilever and the cutting head when the cutting process is not cut, so that the operation links of the cutting process can be accurately identified, and the accuracy of target detection is improved.
In the example, the intelligent level of the tunneling roadway can be improved by applying the machine vision to the recognition of the tunneling process, the tunneling working scene becomes transparent and visual, the recognition is carried out while the monitoring function is considered, the requirements of manual inspection and monitoring are reduced, and therefore the labor cost is reduced.
It can be understood that the obtained target image of each key procedure and the procedure parameters of each procedure, namely, the real-time operation information, can be transmitted and stored in a data memory of a mine machine room tunneling database, and related data in the tunneling database can be called by the tunneling management platform and displayed on a display. In the example of the invention, the collected procedure images and the identified procedure parameters are all recorded in the tunneling database, so that the follow-up calling out and checking are facilitated, and the statistical analysis is performed, thereby facilitating the improvement of the tunneling process, optimizing the production process and the production organization, and further improving the tunneling efficiency.
In the method for detecting the key working procedures of the tunneling roadway, which is provided by the example embodiment of the invention, target images corresponding to each key working procedure in the tunneling roadway are acquired, wherein the key working procedures comprise a temporary supporting working procedure, a permanent supporting working procedure, a walking working procedure and a cutting working procedure; identifying at least one target object in each target image by using a trained target detection model, and extracting the center coordinates of a target frame where each target object is located; and determining real-time operation information of each key process based on the center coordinates of each target frame, wherein the real-time operation information at least comprises an operation state identification and operation time information. According to the invention, the machine vision recognition is carried out on the tunneling process, so that the tunneling scene is more transparent and visual, on one hand, the tunneling process is convenient to be standardized in time, and the tunneling safety is improved; on the other hand, compared with the prior art that complicated tunneling procedures are executed according to the practical experience, the method can definitely determine the next tunneling procedure after accurately identifying the current tunneling procedure, shortens the connection time between procedures, avoids the occurrence of additional auxiliary labor and other conditions, and further improves the tunneling efficiency of the roadway.
In this example embodiment, a system for detecting a key process of a tunneling roadway is also provided. Referring to fig. 4, the roadway key process detection system 400 may include a target image acquisition module 410, a feature information extraction module 420, and a job information determination module 430, wherein:
the target image acquisition module 410 is configured to acquire target images corresponding to each key procedure in the tunneling roadway, where the key procedures include a temporary support procedure, a permanent support procedure, a walking procedure and a cutting procedure;
the feature information extraction module 420 is configured to identify at least one target object in each target image by using a trained target detection model, and extract a center coordinate of a target frame where each target object is located;
the job information determining module 430 is configured to determine real-time job information of each of the key processes based on the center coordinates of each of the target frames, where the real-time job information includes at least a job status identifier and job time information.
The specific details of each module in the above-mentioned system for detecting the key working procedure of the tunnelling roadway are described in detail in the corresponding method for detecting the key working procedure of the tunnelling roadway, and are not described in detail here.
Furthermore, the above-described drawings are only schematic illustrations of processes included in the method according to the exemplary embodiment of the present invention, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. It is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

Claims (10)

1. The detection method for the key working procedures of the tunneling roadway is characterized by comprising the following steps:
Acquiring target images corresponding to each key procedure in a tunneling roadway, wherein the key procedures comprise a temporary supporting procedure, a permanent supporting procedure, a walking procedure and a cutting procedure;
identifying at least one target object in each target image by using a trained target detection model, and extracting the center coordinates of a target frame where each target object is located;
and determining real-time operation information of each key process based on the center coordinates of each target frame, wherein the real-time operation information at least comprises an operation state identification and operation time information.
2. The method for detecting a key working procedure of a tunneling roadway according to claim 1, wherein the target image comprises a first image corresponding to the temporary supporting working procedure, the target object comprises a supporting frame and an anchor net, and the target frame comprises a first detection frame and a second detection frame;
the identifying at least one target object in each target image by using the trained target detection model, and extracting the center coordinates of the target frame where each target object is located, includes:
and identifying the support frame and the anchor net in the first image by using the trained target detection model, and extracting the center coordinates of a first detection frame where the support frame is positioned and the center coordinates of a second detection frame where the anchor net is positioned.
3. The method for detecting a key process of a tunneling roadway according to claim 2, wherein said determining real-time operation information of each of said key processes based on the center coordinates of each of said target frames comprises:
identifying a support frame in a first image of the temporary support procedure in different operation states by using the trained target detection model, and respectively extracting the center coordinates of the support frame, wherein each operation state comprises a temporary support state and an non-temporary support state;
generating a first movable range frame of the support frame according to the central coordinate of the support frame in the temporary support state, and generating a second movable range frame of the support frame according to the central coordinate of the support frame in the non-temporary support state;
and determining real-time operation information of the temporary support procedure according to the first movable range frame, the second movable range frame of the support frame, the central coordinate of the first detection frame where the support frame is located and the central coordinate of the second detection frame where the anchor net is located.
4. The method for detecting a critical process of a tunneling roadway according to claim 3, wherein determining the real-time operation information of the temporary support process according to the first movable range frame, the second movable range frame, the center coordinates of the first detection frame where the support frame is located, and the center coordinates of the second detection frame where the anchor net is located, comprises:
If the center coordinate of the first detection frame where the support frame is located in the first movable range frame, determining that the support frame is currently in the temporary support state, and recording the operation state identification and the operation time information of the temporary support state;
if the center coordinate of the first detection frame where the support frame is located in the second movable range frame, determining that the support frame is in the non-temporary support state currently, and recording the operation state identification and the operation time information of the non-temporary support state;
if the center coordinates of the first detection frame where the support frame is located are not in the first movable range frame and the second movable range frame, detecting the distance between the center coordinates of the first detection frame where the support frame is located and the center coordinates of the second detection frame where the anchor net is located;
if the distance is unchanged along with the change of time, determining that the current support frame is in an uplink state, and recording an operation state identifier and operation time information of the uplink state of the support frame;
if the distance is continuously increased along with the time change, determining that the support frame is in a descending state currently, and recording an operation state identifier and operation time information of an ascending state of the support frame.
5. The method of claim 1, wherein the target image comprises a second image corresponding to the permanent support procedure, the target object comprises a tunnelling person and a drilling machine, and the target frame comprises a third detection frame and a fourth detection frame;
the determining the real-time operation information of each key procedure based on the center coordinates of each target frame includes:
after extracting the center coordinates of a third detection frame where the tunneling personnel are located and the center coordinates of a fourth detection frame where the drilling machine is located, if the center coordinates of the third detection frame where the tunneling personnel are located and the center coordinates of the fourth detection frame where the drilling machine are located in the second image at the same time, determining that the tunneling personnel are in a permanent supporting state at present, and recording the operation state identification and the operation time information of the permanent supporting state;
if the center coordinates of the third detection frame where the tunneling personnel are located and the center coordinates of the fourth detection frame where the drilling machine is located are not located in the second image at the same time, determining that the tunneling personnel are in an unfinished supporting state currently, and recording operation state identification and operation time information of the unfinished supporting state.
6. The method for detecting a key working procedure of a tunneling roadway according to claim 1, wherein the target image comprises a third image corresponding to the walking working procedure, the target object comprises at least one anchor rod positioned on the side wall of the roadway, and the target frame comprises a fifth detection frame where each anchor rod is positioned;
the determining the real-time operation information of each key procedure based on the center coordinates of each target frame includes:
after the central coordinates of the fifth detection frames where the anchor rods are located are extracted, determining whether the central coordinates of the fifth detection frames where the target anchor rods are located are changed or not by utilizing a target tracking algorithm;
if the central coordinate of the fifth detection frame where the target anchor rod is located is unchanged along with the change of time, determining that the target anchor rod is in a non-walking state currently, and recording an operation state identifier and operation time information of the non-walking state;
if the central coordinate of the fifth detection frame where the target anchor rod is located changes along with the time change, determining that the target anchor rod is currently in a walking state, and recording the operation state identification and the operation time information of the walking state.
7. The method for detecting the key working procedures of the tunneling roadway according to claim 1, wherein the target image comprises a fourth image corresponding to the cutting working procedure, the target object comprises a cantilever and a cutting head which are positioned on a tunneling machine, and the target frame comprises a sixth detection frame where the cantilever and the cutting head are positioned;
The determining the real-time operation information of each key procedure based on the center coordinates of each target frame includes:
identifying a cantilever and a cutting head in the fourth image in an unclamped state by using the trained target detection model, and respectively extracting center coordinates of the cantilever and the cutting head in the unclamped state;
generating a third movable range frame of the cantilever and the cutting head according to the center coordinates of the cantilever and the cutting head in the non-cutting state;
after extracting the center coordinates of a sixth detection frame where the cantilever and the cutting head are located, if the center coordinates of the sixth detection frame where the cantilever and the cutting head are located in the third movable range frame, determining that the cantilever and the cutting head are in an unclamped state currently, and recording the operation state identification and the operation time information of the unclamped state;
if the center coordinates of the sixth detection frame where the cantilever and the cutting head are located are not in the third movable range frame, determining that the cutting state is currently in, and recording the operation state identification and the operation time information of the cutting state.
8. The method for detecting key working procedures of a tunneling roadway according to claim 1, wherein the step of acquiring the target image corresponding to each key working procedure in the tunneling roadway comprises the steps of:
Acquiring original images corresponding to each key procedure in a tunneling roadway;
and respectively carrying out denoising treatment and defogging treatment on each original image by using an image filtering algorithm and an image defogging algorithm to obtain a target image corresponding to each original image.
9. The roadway key process detection method of claim 1, wherein the target detection model comprises a YOLOv5 model.
10. A tunnelling critical procedure detection system, characterized in that the system is based on a tunnelling critical procedure detection method as claimed in any one of claims 1-9, comprising:
the target image acquisition module is used for acquiring target images corresponding to each key procedure in the tunneling roadway, wherein the key procedures comprise a temporary supporting procedure, a permanent supporting procedure, a walking procedure and a cutting procedure;
the feature information extraction module is used for identifying at least one target object in each target image by utilizing the trained target detection model and extracting the center coordinates of a target frame where each target object is located;
and the operation information determining module is used for determining real-time operation information of each key process based on the center coordinates of each target frame, and the real-time operation information at least comprises an operation state identification and operation time information.
CN202311227661.3A 2023-09-22 2023-09-22 Method and system for detecting key working procedures of tunneling roadway Pending CN116977941A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311227661.3A CN116977941A (en) 2023-09-22 2023-09-22 Method and system for detecting key working procedures of tunneling roadway

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311227661.3A CN116977941A (en) 2023-09-22 2023-09-22 Method and system for detecting key working procedures of tunneling roadway

Publications (1)

Publication Number Publication Date
CN116977941A true CN116977941A (en) 2023-10-31

Family

ID=88471624

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311227661.3A Pending CN116977941A (en) 2023-09-22 2023-09-22 Method and system for detecting key working procedures of tunneling roadway

Country Status (1)

Country Link
CN (1) CN116977941A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112033977A (en) * 2020-08-04 2020-12-04 太原理工大学 Automatic detection and accurate positioning device and method for bubble defects in sapphire crystal bar
CN114821478A (en) * 2022-05-05 2022-07-29 北京容联易通信息技术有限公司 Process flow detection method and system based on video intelligent analysis
CN115497039A (en) * 2022-09-13 2022-12-20 北京天玛智控科技股份有限公司 Intelligent identification method and device for video images of fully mechanized coal mining face
CN115661729A (en) * 2022-10-19 2023-01-31 国家能源集团宁夏煤业有限责任公司 Support determining method and support determining device for front canopy of coal mine heading machine
CN115937575A (en) * 2022-11-08 2023-04-07 广域铭岛数字科技有限公司 Equipment accessory detection method, device, system, equipment and storage medium
CN115984762A (en) * 2022-12-02 2023-04-18 精英数智科技股份有限公司 Underground support process identification method and system based on computer vision algorithm
CN116146548A (en) * 2023-01-09 2023-05-23 中国煤炭科工集团太原研究院有限公司 Full-automatic electrohydraulic control system of water detection drilling machine

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112033977A (en) * 2020-08-04 2020-12-04 太原理工大学 Automatic detection and accurate positioning device and method for bubble defects in sapphire crystal bar
CN114821478A (en) * 2022-05-05 2022-07-29 北京容联易通信息技术有限公司 Process flow detection method and system based on video intelligent analysis
CN115497039A (en) * 2022-09-13 2022-12-20 北京天玛智控科技股份有限公司 Intelligent identification method and device for video images of fully mechanized coal mining face
CN115661729A (en) * 2022-10-19 2023-01-31 国家能源集团宁夏煤业有限责任公司 Support determining method and support determining device for front canopy of coal mine heading machine
CN115937575A (en) * 2022-11-08 2023-04-07 广域铭岛数字科技有限公司 Equipment accessory detection method, device, system, equipment and storage medium
CN115984762A (en) * 2022-12-02 2023-04-18 精英数智科技股份有限公司 Underground support process identification method and system based on computer vision algorithm
CN116146548A (en) * 2023-01-09 2023-05-23 中国煤炭科工集团太原研究院有限公司 Full-automatic electrohydraulic control system of water detection drilling machine

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
王国法 等: "煤矿智能化(初级阶段)研究与实践", 《煤炭科学技术》, vol. 47, no. 8, pages 1 - 36 *
王宏伟 等: "煤矿掘进多行为协同控制智能决策模型", 《工矿自动化》, vol. 49, no. 6, pages 120 - 127 *

Similar Documents

Publication Publication Date Title
US20200218944A1 (en) Method, Apparatus, and Electronic Device for Processing Point Cloud Data, and Computer Readable Storage Medium
CN112347916A (en) Power field operation safety monitoring method and device based on video image analysis
CN111197500B (en) Method and system suitable for real-time judgment of surrounding rock grade of TBM tunneling tunnel
CN112031839B (en) Mine pressure space-time bi-periodic prediction method, device and equipment under limited data condition
CN115456206A (en) BIM + GIS-based tunnel construction visual control method and system
CN110929565B (en) Risk monitoring method and device based on machine learning, storage medium and electronic equipment
CN115937213A (en) Visual defect identification system of automatic inspection robot for mining monorail crane track
CN114445398A (en) Method and device for monitoring state of side protection plate of hydraulic support of coal mining machine
CN115773723A (en) Roadbed section goaf deformation monitoring method and system based on BIM
CN114565908A (en) Lane line detection method and device, electronic device and storage medium
CN114359137A (en) Satellite-ground integrated transmission line external damage monitoring method and device
CN116977941A (en) Method and system for detecting key working procedures of tunneling roadway
CN112528825A (en) Station passenger recruitment service method based on image recognition
CN109977884B (en) Target following method and device
CN111273352A (en) Intelligent detection method and device for geological structure and electronic equipment
CN116718593A (en) Quick and accurate asphalt pavement damage analysis method and system
CN113235681B (en) Unmanned bulldozer operation method and device, bulldozer and medium
CN111485943B (en) Mine excavation water detection and drainage auxiliary system and method
CN113591569A (en) Obstacle detection method, obstacle detection device, electronic apparatus, and storage medium
Zheng et al. Simulation of bench stepping and optimization of bolt parameters based on multiple geological information fusion
CN113780178A (en) Road detection method, road detection device, electronic equipment and storage medium
CN113962955A (en) Method and device for identifying target object from image and electronic equipment
CN113642765B (en) Mine monitoring equipment optimizing deployment method, equipment, electronic equipment and storage medium
KR102193830B1 (en) Apparatus and method for predicting front geological features based on indicatingtendency to change according to measuring data for a blind end in a tunnel
CN115507764A (en) Tunnel deformation real-time automatic monitoring system and monitoring method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination