CN110259438B - Intelligent monitoring method and device for coal mine water exploration and drainage and terminal equipment - Google Patents
Intelligent monitoring method and device for coal mine water exploration and drainage and terminal equipment Download PDFInfo
- Publication number
- CN110259438B CN110259438B CN201910545043.0A CN201910545043A CN110259438B CN 110259438 B CN110259438 B CN 110259438B CN 201910545043 A CN201910545043 A CN 201910545043A CN 110259438 B CN110259438 B CN 110259438B
- Authority
- CN
- China
- Prior art keywords
- drilling
- image
- detected
- determining
- detection model
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 239000003245 coal Substances 0.000 title claims abstract description 24
- 238000005553 drilling Methods 0.000 claims abstract description 208
- 238000001514 detection method Methods 0.000 claims abstract description 87
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 27
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 238000007599 discharging Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 8
- 238000012806 monitoring device Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/002—Survey of boreholes or wells by visual inspection
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/04—Measuring depth or liquid level
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F16/00—Drainage
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Physics & Mathematics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geophysics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- Earth Drilling (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The embodiment of the invention discloses a coal mine water detection and drainage intelligent monitoring method, a device and terminal equipment, wherein the method comprises the following steps: acquiring a drilling image to be detected; analyzing a drilling image to be detected by using a pre-constructed target detection model, and determining the times of unloading the drill rod; and determining the drilling depth according to the times of unloading the drill rods and the length of each drill rod. By the implementation mode, the pre-constructed target detection model is utilized to analyze the drilling image to be detected, and the times of unloading the drill rod can be accurately determined. Therefore, the drilling depth can be naturally and accurately determined, so that the follow-up intelligent monitoring on the water detecting and discharging process and quality in actual production is facilitated, the potential hazards of flood accidents are avoided as much as possible, and the life property and life safety of all workers are guaranteed.
Description
Technical Field
The embodiment of the invention relates to the technical field of artificial intelligence, in particular to a coal mine water exploration and drainage intelligent monitoring method, a coal mine water exploration and drainage intelligent monitoring device and terminal equipment.
Background
The water damage of coal mine is one of the major hazards threatening the safety production of coal mine. In production, a water detecting and releasing method is required to be used for detecting the water regime in front of a working face so as to eliminate the hidden danger of flood accidents and ensure the safety of mining work. In view of the large data volume of underground water exploration and drainage drill holes, the deep drill hole depth and potential safety hazards, effective monitoring management in the water exploration and drainage process becomes a guarantee for the smooth operation of water exploration and drainage. With the development of computer technology, intelligent monitoring of water detecting and discharging process and quality will become a future development trend.
At present, the main mode of coal mine water detection monitoring is that a counter counts drilling depth, for example, the drilling depth is represented by the number of drill pipes unloaded by a detector, and the concrete implementation process is as follows: the operation process of the drilling machine is converted into a oscillogram, namely, when the drilling machine runs through a wave crest and a wave trough, one return stroke is formed, and each return stroke is used for unloading one drill rod, so that the drilling depth can be obtained by counting the times that the drilling machine passes through the wave crest and the wave trough as the times for unloading the drill rods. However, this method has the following disadvantages:
1) in the actual process of unloading the drill rod, the unloading of one drill rod in each return trip cannot be guaranteed, and one drill rod can be completely unloaded only in 2-3 return trips, namely the number of the return trips required for unloading a single drill rod is not fixed and cannot be used as the basis for counting the drilling depth;
2) when the drill rod unloading work is close to the end, the last drill rods are stressed less, and the manual disassembling efficiency is higher than the drilling rig disassembling efficiency, so that the drill rods can be disassembled manually by underground operators, and the drill rod unloading times can not be obtained by analyzing the waveform of the drilling rig in the running process;
3) if the drilling rig idles, i.e. does not carry the drill rod to reciprocate, the drilling rig is determined to be in the drill rod unloading operation.
In conclusion, it can be found that the method for determining the drilling depth in the prior art is not suitable for the intelligent detection of the water detection and drainage in actual production. Therefore, how to accurately determine the drilling depth and further apply the drilling depth to the actual intelligent detection of the water detection and drainage becomes an urgent technical problem to be solved.
Disclosure of Invention
Therefore, the embodiment of the invention provides an intelligent monitoring method and device for water exploration and drainage of a coal mine and terminal equipment, and aims to solve the technical problem that the drilling depth cannot be accurately determined in the prior art, and further the intelligent monitoring method and device cannot be applied to actual intelligent detection of water exploration and drainage.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
according to a first aspect of the embodiments of the present invention, there is provided a method for intelligently monitoring water detection and drainage of a coal mine, the method including: acquiring a drilling image to be detected;
analyzing the drilling image to be detected by using a pre-constructed target detection model, and determining the times of unloading the drill rod;
and determining the drilling depth according to the times of unloading the drill rods and the length of each drill rod.
Further, analyzing the drilling image to be detected by using a pre-constructed target detection model, and determining the times of unloading the drill rod, specifically comprising:
when determining that the drilling machine is located at the leftmost position for the ith time from the drilling image to be detected, determining that a first preset number of continuous image frames in the drilling image to be detected show that the drilling machine runs on a track, and when determining that the drilling machine is located at the leftmost position for the (i + 1) th time from the drilling image to be detected, determining that a second preset number of continuous image frames in the drilling image to be detected show that the drilling machine runs on the track, and determining that one-time drill pipe unloading is finished, wherein i is a positive integer greater than or equal to 1.
Further, when i is equal to 1, determining that the drilling machine is at the leftmost position for the ith time from the drilling image to be detected, specifically comprising:
counting the minimum extreme value corresponding to the leftmost end of the drilling machine when the drilling machine runs on the track according to the drilling image to be detected;
determining a preset error range according to the minimum extreme value;
and when the continuous third preset number of image frames are determined from the drilling images to be detected and the drilling machine runs to the preset error range on the track, determining that the drilling machine is positioned at the leftmost position for the 1 st time.
Further, the target detection model is constructed based on a convolutional neural network, and the construction method of the target detection model comprises the following steps:
receiving a drilling image sample which is marked manually, wherein the manually marked object at least comprises a partial image corresponding to a drilling machine, a partial image corresponding to a drill pipe on a track and a partial image corresponding to drill pipe not on the track in the drilling image sample;
and training the target detection model by using the marked drilling image sample to obtain an optimal target detection model as a pre-constructed target detection model.
Further, the manually marked object further comprises: an image of a worker present in the drilling image sample.
Further, before analyzing the drilling image to be detected by using the pre-constructed target detection model and determining the drill rod unloading times, the method further comprises the following steps:
and converting the format of the image data so that the image data conforms to the input format of the pre-constructed object detection model.
Further, the drilling image to be detected and the drilling image sample to be detected are both video images, and the video acquisition device for acquiring the video images is positioned at the upper part of the drilling machine.
Further, a pre-constructed target detection model is used for analyzing the drilling image to be detected, and a frame-by-frame analysis mode or a frame skipping analysis mode is adopted when the number of times of unloading the drill rod is determined.
According to a second aspect of the embodiments of the present invention, there is provided a terminal device, including: a processor and a memory;
the memory is used for storing one or more program instructions;
a processor for executing one or more program instructions to perform any one of the above method steps of the above intelligent monitoring method for coal mine drainage.
According to a third aspect of embodiments of the present invention, there is provided a computer storage medium containing one or more program instructions for executing any one of the method steps of the above intelligent monitoring method for coal mine drainage by a terminal device.
The embodiment of the invention has the following advantages: firstly, a drilling image to be detected is obtained, then the drilling image to be detected is analyzed by utilizing a pre-constructed target detection model, and the times of unloading the drill rod are determined. And finally determining the drilling depth according to the times of unloading the drill rods and the length of each drill rod. And then, the method is applied to actual intelligent detection of water detection and drainage. By the implementation mode, the pre-constructed target detection model is utilized to analyze the drilling image to be detected, and the times of unloading the drill rod can be accurately determined. Therefore, the drilling depth can be naturally and accurately determined, so that the follow-up intelligent monitoring on the water detecting and discharging process and quality in actual production is facilitated, the potential hazards of flood accidents are avoided as much as possible, and the life property and life safety of all workers are guaranteed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used to limit the conditions that the present invention can be implemented, so that the present invention has no technical significance, and any structural modifications, changes in the ratio relationship, or adjustments of the sizes, without affecting the effects and the achievable by the present invention, should still fall within the range that the technical contents disclosed in the present invention can cover.
Fig. 1 is a schematic flow chart of an intelligent monitoring method for water detection and drainage of a coal mine, which is provided by embodiment 1 of the invention;
fig. 2 is a schematic structural diagram of an intelligent monitoring device for water detection and drainage in a coal mine, which is provided in embodiment 2 of the present invention;
fig. 3 is a schematic structural diagram of a terminal device according to embodiment 3 of the present invention;
fig. 4 is a schematic diagram of the present invention providing a method for marking all objects in a diagram in block form with a drill on a track,
fig. 5 is a schematic diagram of the present invention providing for marking all objects in the diagram in block form in the absence of a drill on the track.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Before the method is introduced, an intelligent monitoring system for coal mine water detection and drainage is introduced, and the system may include:
the device comprises an image acquisition device, terminal equipment, a drilling machine, a track convenient for the operation of the drilling machine, a drill rod and the like.
Preferably, the image acquisition device is arranged on the side surface of the track, and the image acquisition device is positioned at the upper part of the drilling machine. In this embodiment, the angle between the drilling machine and the image acquisition device is 90 °. The principle of installing the image acquisition device is to avoid sheltering from to see track and the drilling rod on the track clearly as basic requirement. After the image acquisition device is installed and started, the terminal equipment can acquire the drilling image to be detected from the image acquisition device in real time. For example, if the image capture device is a camera, the drilling image to be detected is a video image.
The drilling machine runs from left to right on the track or runs in the reverse direction from right to right. The drilling machine is fixed on the track and moves linearly along the track, and is used for driving the drill rod to move linearly along the track in the process of unloading the drill rod; the process of running from left to right is the process of taking out the drill rod, and when the rightmost end is reached, the drill rod is unloaded by a drilling machine or manually.
The drill rod unloading process of the drilling machine is as follows: the drilling machine moves on the track, the drilling rod is pulled to move on the track along the advancing direction of the drilling machine, and the drilling machine stops when moving to one end of the track, and the drilling rod is dismounted by an operator;
the process of manually unloading the drill rod comprises the following steps: the operator pulls the drill pipe from the borehole along the drill rig track and unloads the drill pipe. Preferably, the drill rod is only able to move along the track during extraction.
The drilling machine runs on the track until all operation processes such as drill rod unloading and the like are collected by the image collecting device and transmitted to the terminal equipment. And the terminal equipment analyzes the drilling image to be detected by utilizing the pre-constructed target detection model and determines the times of unloading the drill rod. Then, the drilling depth is determined based on the number of times the drill pipe is removed and the length of each drill pipe.
In the above, each component in the coal mine water exploration and drainage intelligent monitoring system and the function executed by each component are introduced simply. The intelligent monitoring method for coal mine water exploration and drainage will be described in detail below. Specifically, as shown in fig. 1, the method comprises the following steps:
And 120, analyzing the drilling image to be detected by using a pre-constructed target detection model, and determining the times of unloading the drill rod.
Specifically, the drilling image to be detected may be directly in the form of a photograph or may be in the form of a video image. Preferably, in this embodiment, a screen image captured by the image capturing device will be described as an example.
Optionally, before performing step 120, the method further comprises: and converting the format of the image data so that the image data conforms to the input format of the pre-constructed object detection model. For example, a preprocessing process of converting a video image into an image frame by frame, and converting the image into an image frame that can be adapted to the size of the target detection model. After the preprocessing process is executed, the data are input into a pre-constructed target detection model for analysis.
Optionally, analyzing the drilling image to be detected by using a pre-constructed target detection model, and determining the number of times of unloading the drill pipe, specifically including:
when determining that the drilling machine is located at the leftmost position for the ith time from the drilling image to be detected, determining that a first preset number of continuous image frames in the drilling image to be detected show that the drilling machine runs on a track, and when determining that the drilling machine is located at the leftmost position for the (i + 1) th time from the drilling image to be detected, determining that a second preset number of continuous image frames in the drilling image to be detected show that the drilling machine runs on the track, and determining that one-time drill pipe unloading is finished, wherein i is a positive integer greater than or equal to 1.
Specifically, if i is equal to 1, it indicates that the drill has not performed work before that, and the drill position needs to be initialized.
The specific initialization process is as follows:
and counting the minimum extreme value corresponding to the leftmost end of the drilling machine when the drilling machine runs on the track according to the drilling image to be detected.
The determination of the minimum extreme value is in fact a statistical calculation of the extreme value coordinates of the travel of the rig on the track, e.g. operating the rig several times on the track towards the leftmost end and then taking the minimum extreme value.
And determining a preset error range according to the minimum extreme value.
Specifically, the error is, for example, about ± 5% of the minimum limit value, and then, the preset error range is the minimum limit value ± 5%.
When it is determined from the drilling images to be detected that a third preset number (for example, 10 frames) of consecutive image frames each show that the drilling machine runs on the track to a preset error range, it is determined that the drilling machine is at the leftmost position for the 1 st time.
When i is not equal to 1, the above steps of determining the minimum extremum and determining the preset error range are not required. But is called directly, i.e. whenever it is determined from the drilling image to be detected whether the drilling machine is in the leftmost position for the ith time. The specific judgment process is similar to the process of judging whether the machine is positioned at the most end position for the first time, namely whether the continuous third preset number of image frames are displayed on the track of the drilling machine until the yoga stars reach the preset error range is judged.
When determining that the drilling machine is located at the leftmost position for the ith time from the drilling image to be detected, determining that a first preset number of continuous image frames in the drilling image to be detected show that the drilling machine runs on a track, and when determining that the drilling machine is located at the leftmost position for the (i + 1) th time from the drilling image to be detected, determining that a second preset number of continuous image frames in the drilling image to be detected show that the drilling machine runs on the track, and determining that one-time drill pipe unloading is finished, wherein i is a positive integer greater than or equal to 1.
In a specific example, after the drilling machine is judged to reach the leftmost end of the track, the detection of subsequent frame objects is started, the objects detected by the model comprise continuous 5 frames or a preset number of 'drill rods on the track' which is more than 5 frames, and then the target detection model judges that the drilling machine or a person pulls out one drill rod from the drilled hole; after the process is executed, after the drilling machine is determined to run to the leftmost end again, after the drilling machine is judged to reach the leftmost end of the track, the detection of subsequent frame objects is started, and the objects detected by the model comprise continuous 5 frames or a preset number of 'no drilling rods on the track' which is more than 5 frames; the object detection model determines that a drill pipe has been removed from the borehole. When the detection result of the target detection model is switched once between two results of detecting that the drill rod is on the track and not on the track, the drill rig or the manual work finishes the unloading of one drill rod. By the method, the times of unloading the drill rods can be counted until the drill rods are unloaded, and the total times of unloading the drill rods, namely the number of the drill rods, is counted correspondingly.
Optionally, before the above steps are performed, an object detection model actually needs to be constructed, in a specific example, the pre-constructed object detection model is an object detection model constructed based on a convolutional neural network, and the specific construction method includes:
receiving a drilling image sample which is marked manually, wherein the manually marked object at least comprises a partial image corresponding to a drilling machine, a partial image corresponding to a drill pipe on a track and a partial image corresponding to drill pipe not on the track in the drilling image sample;
and training the target detection model by using the marked drilling image sample to obtain an optimal target detection model as a pre-constructed target detection model.
The specific target detection model may be YOLO1，2Series or SSD3A series of single-ended target detection models.
Further optionally, the manually marked object further comprises: and partial images corresponding to each worker appearing in the drilling image sample. The drilling machine refers to a device which is used for pulling out a drill rod from a driving face and appears in a video of a water exploration and drainage operation field; the 'drill rod is arranged on the track', which means that in a video of a water detecting and discharging operation site, the drill rod is pulled out from 20% of a heading face to 100% of the heading face and stays on the track all the time to finish the process; no drill rod is arranged on the track, which means that no drill rod is arranged on the track in the water exploration and drainage operation site video. The partial images corresponding to the workers are determined, and the partial images are mainly used for preventing the workers from cheating, for example, the workers are at the same position, a drilling machine is also at the same position, and the workers continuously unload or load drill rods. The marked object may be a box or otherwise marked object. For example, as shown in fig. 4 and 5, fig. 4 shows a schematic diagram of marking all objects in the diagram in block form with a rig on the track. Fig. 5 shows a schematic representation of the marking of all objects in the figure in block form in the case of no rig on the track.
Specifically, it is determined whether the position of the drilling machine, the worker, or the drill rod is moved, and the position coordinates of the pixel points may be referred to. The above-mentioned minimum extreme value at the leftmost end is actually determined according to the position coordinates of the pixel points.
Alternatively, the drilling image sample can also be a video image or a picture, and preferably, the video image is taken as an example in this embodiment for illustration.
Alternatively, the drilling image and/or drilling image sample to be detected may be acquired in the form of 24 frames per second.
Optionally, a pre-constructed target detection model is used for analyzing the drilling image to be detected, and when the number of times of unloading the drill rod is determined, a frame-by-frame analysis mode or a frame skipping analysis mode is adopted.
When the frame skipping analysis mode is adopted, the analysis interval of each frame is not more than 10 frames.
And step 130, determining the drilling depth according to the times of unloading the drill rods and the length of each drill rod.
Specifically, the number of times of unloading the drill rods can actually correspond to the number of the drill rods. The number of times the drill pipe is removed multiplied by the length of each drill pipe, the drilling depth can be directly determined.
The intelligent monitoring method for the water exploration and drainage of the coal mine, provided by the embodiment of the invention, comprises the steps of firstly obtaining a drilling image to be detected, then analyzing the drilling image to be detected by utilizing a pre-constructed target detection model, and determining the times of unloading a drill rod. And finally determining the drilling depth according to the times of unloading the drill rods and the length of each drill rod. And then, the method is applied to actual intelligent detection of water detection and drainage. By the implementation mode, the pre-constructed target detection model is utilized to analyze the drilling image to be detected, and the times of unloading the drill rod can be accurately determined. Therefore, the drilling depth can be naturally and accurately determined, so that the follow-up intelligent monitoring on the water detecting and discharging process and quality in actual production is facilitated, the potential hazards of flood accidents are avoided as much as possible, and the life property and life safety of all workers are guaranteed.
Further, according to the embodiment of the invention, the states of the drilling machine on the operation site, the drill rods on the drilling machine track and the drill rod-free state on the drilling machine track are detected by using the target detection model, the number of the unloaded drill rods is determined through state detection and judgment, and the drilling depth is further calculated. Compared with the prior art, the technical scheme provided by the invention records the drill rod unloading process by using the object detection method, and realizes the accurate calculation of the drill rod unloading quantity, thereby achieving the purpose of automatic monitoring.
Corresponding to the foregoing embodiment 1, an embodiment 2 of the present invention further provides an intelligent monitoring device for water detection and drainage in a coal mine, specifically as shown in fig. 2, where the device includes: an acquisition unit 201 and a processing unit 202.
Acquiring a drilling image to be detected;
analyzing a drilling image to be detected by using a pre-constructed target detection model, and determining the times of unloading the drill rod;
and determining the drilling depth according to the times of unloading the drill rods and the length of each drill rod.
Optionally, the processing unit 202 is specifically configured to, after it is determined that the drilling machine is located at the leftmost position for the ith time in the drilling image to be detected, determine that there are drill rods on the track where the drilling machine runs in consecutive image frames of a first preset number in the drilling image to be detected, and after it is determined that the drilling machine is located at the leftmost position for the (i + 1) th time in the drilling image to be detected, determine that one-time drill rod unloading is completed when it is determined that there are no drill rods on the track where the drilling machine runs in consecutive image frames of a second preset number in the drilling image to be detected, where i is a positive integer greater than or equal to 1.
Optionally, when i is equal to 1, determining that the drilling machine is at the leftmost position for the ith time from the drilling image to be detected, specifically including:
counting the minimum extreme value corresponding to the leftmost end of the drilling machine when the drilling machine runs on the track according to the drilling image to be detected;
determining a preset error range according to the minimum extreme value;
and when the continuous third preset number of image frames are determined from the drilling images to be detected and the drilling machine runs to the preset error range on the track, determining that the drilling machine is positioned at the leftmost position for the 1 st time.
Optionally, the obtaining unit 201 is further configured to receive a drilling image sample that is manually marked, where the manually marked object includes at least a partial image corresponding to a drilling machine, "a partial image corresponding to a drill rod on a track" and a partial image corresponding to "no drill rod on a track" in the drilling image sample;
the processing unit 202 is further configured to train the target detection model with the marked drilling image samples to obtain an optimal target detection model as a pre-constructed target detection model.
Optionally, the manually marked object further comprises: and partial images corresponding to each worker appearing in the drilling image sample.
Optionally, the processing unit 202 is further configured to, before analyzing the drilling image to be detected by using the pre-constructed target detection model and determining the drill pipe unloading times, further:
and converting the format of the image data so that the image data conforms to the input format of the pre-constructed object detection model.
Optionally, the drilling image to be detected and the drilling image sample to be detected are both video images, and the video acquisition device for acquiring the video images is positioned at the upper part of the drilling machine.
Optionally, the processing unit 202 is specifically configured to: and analyzing the drilling image to be detected by using a pre-constructed target detection model, and adopting a frame-by-frame analysis mode or a frame skipping analysis mode when determining the times of unloading the drill rod.
The functions executed by each component in the intelligent monitoring device for water detection and drainage of the coal mine provided by the embodiment of the invention are described in detail in the embodiment 1, so that redundant description is not repeated here.
The intelligent monitoring device for water exploration and drainage of the coal mine, provided by the embodiment of the invention, is characterized in that a drilling image to be detected is firstly obtained, and then the drilling image to be detected is analyzed by utilizing a pre-constructed target detection model, so that the times of unloading a drill rod are determined. And finally determining the drilling depth according to the times of unloading the drill rods and the length of each drill rod. And then, the method is applied to actual intelligent detection of water detection and drainage. By the implementation mode, the pre-constructed target detection model is utilized to analyze the drilling image to be detected, and the times of unloading the drill rod can be accurately determined. Therefore, the drilling depth can be naturally and accurately determined, so that the follow-up intelligent monitoring on the water detecting and discharging process and quality in actual production is facilitated, the potential hazards of flood accidents are avoided as much as possible, and the life property and life safety of all workers are guaranteed.
Further, according to the embodiment of the invention, the states of the drilling machine on the operation site, the drill rods on the drilling machine track and the drill rod-free state on the drilling machine track are detected by using the target detection model, the number of the unloaded drill rods is determined through state detection and judgment, and the drilling depth is further calculated. Compared with the prior art, the technical scheme provided by the invention records the drill rod unloading process by using the object detection method, and realizes the accurate calculation of the drill rod unloading quantity, thereby achieving the purpose of automatic monitoring.
Corresponding to the foregoing embodiment, embodiment 3 of the present invention further provides a terminal device, specifically as shown in fig. 3, where the terminal device includes: a processor 301 and a memory 302;
the memory 302 is used to store one or more program instructions;
processor 301 is configured to execute one or more program instructions to perform any one of the method steps of a method for intelligent monitoring of coal mine drainage as described in the above embodiments.
According to the terminal equipment provided by the embodiment of the invention, the drilling image to be detected is firstly obtained, and then the drilling image to be detected is analyzed by utilizing the pre-constructed target detection model, so that the times of unloading the drill rod are determined. And finally determining the drilling depth according to the times of unloading the drill rods and the length of each drill rod. And then, the method is applied to actual intelligent detection of water detection and drainage. By the implementation mode, the pre-constructed target detection model is utilized to analyze the drilling image to be detected, and the times of unloading the drill rod can be accurately determined. Therefore, the drilling depth can be naturally and accurately determined, so that the follow-up intelligent monitoring on the water detecting and discharging process and quality in actual production is facilitated, the potential hazards of flood accidents are avoided as much as possible, and the life property and life safety of all workers are guaranteed.
Further, according to the embodiment of the invention, the states of the drilling machine on the operation site, the drill rods on the drilling machine track and the drill rod-free state on the drilling machine track are detected by using the target detection model, the number of the unloaded drill rods is determined through state detection and judgment, and the drilling depth is further calculated. Compared with the prior art, the technical scheme provided by the invention records the drill rod unloading process by using the object detection method, and realizes the accurate calculation of the drill rod unloading quantity, thereby achieving the purpose of automatic monitoring.
In correspondence with the above embodiments, embodiments of the present invention also provide a computer storage medium containing one or more program instructions therein. One or more program instructions are used for executing the intelligent monitoring method for coal mine water exploration and drainage on the terminal equipment.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (9)
1. An intelligent monitoring method for coal mine water exploration and drainage is characterized by comprising the following steps:
acquiring a drilling image to be detected;
analyzing the drilling image to be detected by using a pre-constructed target detection model, and determining the times of unloading the drill rod;
determining the drilling depth according to the times of unloading the drill rods and the length of each drill rod;
the method for analyzing the drilling image to be detected by using the pre-constructed target detection model to determine the times of unloading the drill rod specifically comprises the following steps:
and when determining that the ith time of the drilling machine is at the leftmost position from the drilling images to be detected, determining that a first preset number of continuous image frames in the drilling images to be detected display that the drilling machine runs on a track, and determining that one-time drill pipe unloading is completed when determining that a second preset number of continuous image frames in the drilling images to be detected display that the drilling machine runs on the track after determining that the (i + 1) th time of the drilling machine is at the leftmost position from the drilling images to be detected, wherein i is a positive integer greater than or equal to 1.
2. The method according to claim 1, wherein when i is equal to 1, said determining from said drilling image to be detected that the drilling machine is at the leftmost position the ith time, comprises:
counting the minimum extreme value corresponding to the leftmost end of the drilling machine when the drilling machine runs on the track according to the drilling image to be detected;
determining a preset error range according to the minimum extreme value;
and when it is determined from the drilling images to be detected that a third preset number of continuous image frames all display that the drilling machine runs to the preset error range on the track, determining that the drilling machine is positioned at the leftmost position for the 1 st time.
3. The method according to any one of claims 1-2, wherein the object detection model construction method comprises:
receiving a drilling image sample which is manually marked, wherein the manually marked object at least comprises a partial image corresponding to a drilling machine, a partial image corresponding to 'a drill pipe on a track' and a partial image corresponding to 'no drill pipe on the track' in the drilling image sample;
and training a target detection model by using the marked drilling image sample to obtain an optimal target detection model as the pre-constructed target detection model.
4. The method of claim 3, wherein the manually marked object further comprises: an image of a worker appearing in the drilling image sample.
5. The method according to any one of claims 1-2, wherein before analyzing the drilling image to be detected using a pre-constructed target detection model to determine the number of drill pipe trips, the method further comprises:
and carrying out format conversion on the image data so that the image data conforms to the input format of the pre-constructed target detection model.
6. The method according to claim 3, characterized in that the drilling image to be detected and the drilling image sample are video images, and a video acquisition device for acquiring the video images is located on the upper part of the drilling rig.
7. The method according to any one of claims 1-2, wherein the pre-constructed target detection model is used for analyzing the drilling image to be detected, and a frame-by-frame analysis mode or a frame skipping analysis mode is adopted when the drill pipe unloading times are determined.
8. A terminal device, characterized in that the terminal device comprises: a processor and a memory;
the memory is to store one or more program instructions;
the processor, configured to execute one or more program instructions to perform the method of any of claims 1-7.
9. A computer storage medium comprising one or more program instructions for execution by a terminal device to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910545043.0A CN110259438B (en) | 2019-06-21 | 2019-06-21 | Intelligent monitoring method and device for coal mine water exploration and drainage and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910545043.0A CN110259438B (en) | 2019-06-21 | 2019-06-21 | Intelligent monitoring method and device for coal mine water exploration and drainage and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110259438A CN110259438A (en) | 2019-09-20 |
| CN110259438B true CN110259438B (en) | 2020-12-04 |
Family
ID=67920496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910545043.0A Active CN110259438B (en) | 2019-06-21 | 2019-06-21 | Intelligent monitoring method and device for coal mine water exploration and drainage and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110259438B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112196517B (en) * | 2019-11-26 | 2021-05-04 | 中国科学院地质与地球物理研究所 | Drilling calibration method, device, equipment and medium based on image recognition |
| CN111178841B (en) * | 2019-12-27 | 2021-06-18 | 精英数智科技股份有限公司 | Water exploration tunneling management method and device and storage medium |
| CN111350488B (en) * | 2020-05-09 | 2022-12-30 | 新疆雪峰科技(集团)股份有限公司 | Method and device for monitoring drilling depth and drilling speed of mine down-the-hole drilling machine |
| CN112228036A (en) * | 2020-06-04 | 2021-01-15 | 精英数智科技股份有限公司 | Gas extraction monitoring method, system and equipment and readable storage medium |
| CN112561859B (en) * | 2020-11-20 | 2023-01-31 | 中国煤炭科工集团太原研究院有限公司 | Monocular vision-based steel belt drilling and anchor net identification method and device for anchoring and protecting |
| CN112738463B (en) * | 2020-12-24 | 2023-02-10 | 山西海平面智能科技有限公司 | Tracking and monitoring device for drill site |
| CN116824513B (en) * | 2023-08-29 | 2024-03-08 | 北京建工环境修复股份有限公司 | Drilling process automatic identification supervision method and system based on deep learning |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5274552A (en) * | 1992-04-20 | 1993-12-28 | M/D Totco | Drill string motion detection for bit depth calculation |
| RU2324812C1 (en) * | 2006-11-14 | 2008-05-20 | Виктор Степанович Бортасевич | Method of measuring length and displacement speed of pipe string while its tripping and device for impleneting thereof |
| CN104100256B (en) * | 2013-04-15 | 2017-04-12 | 西安科技大学 | Method for measuring coal mine underground drilling depth based on image processing technology |
| CN104389517B (en) * | 2014-10-14 | 2016-03-30 | 中煤科工集团西安研究院有限公司 | Vehicle-mounted drilling machine for coal bed gas hole depth on-line measurement device and method |
| US11261724B2 (en) * | 2014-12-19 | 2022-03-01 | Schlumberger Technology Corporation | Drill bit distance to hole bottom measurement |
| CN108764032B (en) * | 2018-04-18 | 2019-12-24 | 北京百度网讯科技有限公司 | Intelligent monitoring method and device for coal mine water exploration and drainage, computer equipment and storage medium |
| CN109267995B (en) * | 2018-10-16 | 2022-02-11 | 安徽理工大学 | Geological drill rod feeding depth measuring system based on aberration analysis drill rod node |
| CN109598710B (en) * | 2018-11-29 | 2023-04-11 | 中国科学院重庆绿色智能技术研究院 | Automatic counting method and system for coal mine drill rods |
| CN109800848B (en) * | 2019-01-23 | 2023-04-07 | 中国科学院重庆绿色智能技术研究院 | Automatic counting method for underground drilling number of coal mine |
-
2019
- 2019-06-21 CN CN201910545043.0A patent/CN110259438B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110259438A (en) | 2019-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110259438B (en) | Intelligent monitoring method and device for coal mine water exploration and drainage and terminal equipment | |
| Kopsida et al. | A review of automated construction progress monitoring and inspection methods | |
| CN112127896B (en) | Automatic acquisition and analysis system and method for TBM excavation rock slag information | |
| CN111598042B (en) | Visual statistical method for underground drill rod counting | |
| CN111612786A (en) | Concrete defect detection method and device based on full convolution neural network and storage medium | |
| CN113111805A (en) | Method for counting underground drilling number of coal mine based on machine vision | |
| CN117252042B (en) | Urban underground space comprehensive bearing capacity evaluation system and method | |
| KR20240051806A (en) | Deep learning based exterior inspection method using dron image | |
| CN115937684A (en) | Building construction progress identification method and electronic equipment | |
| Konstantinou et al. | 3D matching of resource vision tracking trajectories | |
| CN116245838A (en) | Monitoring method, monitoring device, equipment and medium for rock-soil exploration behaviors | |
| CN112696186A (en) | Method and system for automatically identifying drilling cuttings | |
| CN115393709A (en) | Intelligent surrounding rock grading system for rock tunnel engineering excavation surface based on machine vision | |
| CN110242297B (en) | Method, device and system for identifying super-cycle operation of tunneling working face | |
| Yin et al. | Standard closed-circuit television (CCTV) collection time extraction of sewer pipes with machine learning algorithm | |
| CN111784059B (en) | Method for predicting dominant development azimuth of coal seam macroscopic crack | |
| CN114387564A (en) | Head-knocking engine-off pumping-stopping detection method based on YOLOv5 | |
| CN113431561A (en) | Automatic rock recognition device for drilling | |
| CN114187245A (en) | Video contamination detection method and device, electronic equipment and storage medium | |
| Yang et al. | Automatic recognition of construction worker activities using dense trajectories | |
| Kim et al. | Integration of imaging and simulation for earthmoving productivity analysis | |
| Galantucci et al. | A rapid pipeline for periodic inspection and maintenance of architectural surfaces | |
| KR102555009B1 (en) | Damage detection method based on automatic image acquisition control | |
| CN116793264A (en) | Working face straightness and propelling degree measuring method and system based on machine vision | |
| CN117036399A (en) | Non-contact penetration or dynamic detection test data acquisition method and terminal equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |