A method for municipal drilling positioning

Abstract

The embodiment of the present application provides a municipal drilling positioning method, in the method, a specific type of preset detection signal is emitted to a to-be-drilled area, and a specific type of feature signal generated based on the preset detection signal by different types of objects in the to-be-drilled area can be received. Further, the specific type of feature signal is analyzed by a preset neural network, and then the probability of drilling obstruction occurring in the to-be-drilled area is determined, whether the underground metal object or the cultural relic can appear in the to-be-drilled area can be effectively perceived, damage to the underground metal object or the cultural relic in the drilling process is avoided, and the safety of the drilling head itself in the drilling positioning process and the safety of the underground metal object and the cultural relic in the city are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mechanical control, and more particularly, to a municipal drilling positioning method. BACKGROUND

[0002] In the current positioning drilling process for municipal projects, the drilling equipment and drilling method used in field drilling are usually directly applied to the drilling work for municipal projects. However, in the drilling work for municipal projects, the environment for implementing drilling is often in the city, and therefore, in the process of positioning drilling, the underground metal objects (seismographs, strong motion instruments, etc.), cables and possible cultural relics buried in the city need to be considered, which factors are not within the consideration range of field drilling. Therefore, directly applying the drilling equipment and drilling method used in field drilling to the drilling work based on the urban environment is easy to cause damage to the underground metal objects or cultural relics in the city. SUMMARY

[0003] In view of the above problems, in order to prevent damage to underground equipment or cultural relics in the city in the drilling work based on the urban environment, the embodiments of the present application provide a municipal drilling positioning method.

[0004] In a first aspect, the embodiments of the present application provide a municipal drilling positioning method, comprising:

[0005] a detection module is configured to emit a preset detection signal to a to-be-drilled area, and receive a characteristic signal fed back to the preset detection signal;

[0006] a signal analysis module is configured to perform signal analysis on the characteristic signal according to a preset neural network model, to determine a drilling obstruction probability; the drilling obstruction probability is used to represent the probability of drilling obstruction occurring in the drilling process;

[0007] a drilling control module is configured to perform drilling control on a driving drill bit according to the drilling obstruction probability.

[0008] In a possible implementation manner, the detection module comprises a GRP detection unit and an NLJD detection unit; the preset detection signal comprises a high-frequency electromagnetic wave signal and a fundamental wave signal; the characteristic signal corresponding to the high-frequency electromagnetic wave signal is a reflected wave signal, and the characteristic signal corresponding to the fundamental wave signal is a harmonic wave signal;

[0009] the GRP detection unit is configured to emit the high-frequency electromagnetic wave signal to the to-be-drilled area, to receive the reflected wave signal;

[0010] the NLJD detection unit is configured to emit the fundamental wave signal to the to-be-drilled area, to receive the harmonic wave signal.

[0011] In a possible implementation, the GRP detection unit and the NLJD detection unit are configured to be alternately turned on, and the preset neural network model comprises an image recognition neural network.

[0012] The signal analysis on the feature signal according to the preset neural network model comprises:

[0013] When the GRP detection unit is turned on, image data conversion is performed on the reflected wave signal to obtain a reflected gray-scale image.

[0014] Image analysis is performed on the reflected gray-scale image by the image recognition neural network to obtain a gray-scale image analysis result.

[0015] Based on the gray-scale image analysis result and a real-time on duration of the GRP detection unit, a running state of the GRP detection unit and the NLJD detection unit is controlled.

[0016] In a possible implementation, the preset neural network model comprises a signal analysis neural network, and the drilling obstruction probability comprises a metal object obstruction probability.

[0017] The control of the running state of the GRP detection unit and the NLJD detection unit based on the gray-scale image analysis result and the real-time on duration of the GRP detection unit specifically comprises:

[0018] When the gray-scale image analysis result is that a bright spot region exists, the GRP detection unit is turned off, and the NLJD detection unit is driven to emit the fundamental wave signal to the area to be drilled to receive the corresponding harmonic wave signal.

[0019] Signal analysis is performed on the harmonic wave signal by the signal analysis neural network to obtain the metal object obstruction probability.

[0020] If the metal object obstruction probability is not less than a preset first threshold, the drilling speed of the driving bit is reduced according to the metal object obstruction probability.

[0021] In a possible implementation, after the metal object obstruction probability is obtained, the method further comprises:

[0022] When the metal object obstruction probability is less than the preset first threshold, if the real-time on duration of the GRP detection unit is less than a preset second threshold, the NLJD detection unit is turned off, and the GRP detection unit is driven to run based on a corresponding remaining on duration; the remaining on duration is obtained based on a first preset on duration corresponding to the GRP detection unit and the real-time on duration of the GRP detection unit.

[0023] When the metal object obstruction probability is less than the preset first threshold, if the real-time opening duration of the GRP detection unit is not less than the preset second threshold, the remaining opening duration of the GRP detection unit is skipped, and the NLJD detection unit is driven to operate based on the corresponding second preset opening duration.

[0024] In a possible implementation, the drilling obstruction probability includes a non-metal object obstruction probability.

[0025] The control of the operating states of the GRP detection unit and the NLJD detection unit based on the grayscale image analysis result and the real-time opening duration of the GRP detection unit further includes:

[0026] If the grayscale image analysis result is that there is no bright spot region, the non-metal object obstruction probability is obtained by performing obstruction probability analysis on the reflected grayscale image by using the image recognition neural network.

[0027] In a possible implementation, the drilling control of the driving drill bit according to the drilling obstruction probability includes:

[0028] When the drilling obstruction probability is greater than a preset third threshold, the drilling process of the driving drill bit is terminated.

[0029] In a possible implementation, there is a preset buffer stage between the end of the opening stage of any one of the GRP detection unit and the NLJD detection unit and the entry of the other into the opening stage.

[0030] In a possible implementation, the ratio of the first preset opening duration, the second preset opening duration, and the duration of the preset buffer stage is 16:4:1.

[0031] In a possible implementation, the drilling control of the driving drill bit according to the drilling obstruction probability includes:

[0032] The drilling speed of the driving drill bit is controlled according to the drilling obstruction probability; and the drilling obstruction probability and the drilling speed are in inverse proportion.

[0033] The technical scheme provided by the embodiment of the present application can have the following beneficial effects: the embodiment of the present application provides a municipal drilling positioning method, in which a preset detection signal is first emitted to a to-be-drilled area by a detection module to receive a characteristic signal fed back to the preset detection signal. Then, a signal analysis is performed on the characteristic signal according to a preset neural network model to determine a drilling obstruction probability. The drilling obstruction probability is used to represent the probability of drilling obstruction in the to-be-drilled area. Finally, drilling control is performed on a driving drill bit according to the drilling obstruction probability. In this way, by emitting a specific type of preset detection signal to the to-be-drilled area, a specific type of characteristic signal generated by different types of objects in the to-be-drilled area based on the preset detection signal can be received. Further, by performing a signal analysis on the specific type of characteristic signal by the preset neural network, the probability of the presence of a drilling obstruction in the to-be-drilled area can be determined, which can effectively perceive whether underground metal objects or cultural relics are likely to appear in the to-be-drilled area, avoid damage to them during drilling, and effectively improve the safety of the drill bit itself and the safety of urban underground metal objects and cultural relics during drilling positioning.

[0034] The technical scheme of the present application will be described in further detail below with reference to the accompanying drawings and embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0036] Figure 1 A flowchart of a municipal drilling positioning method provided by the embodiment of the present application;

[0037] Figure 2 A structural diagram of a detection module provided by the embodiment of the present application;

[0038] Figure 3 A flowchart of a characteristic signal analysis method provided by the embodiment of the present application;

[0039] Figure 4 A flowchart of a control method for a GRP detection unit and a NLJD detection unit provided by the embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to specific embodiments and drawings. It should be particularly pointed out that the embodiments described in the embodiments of the present application are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0041] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be understood as the general meaning understood by those of ordinary skill in the art to which the present application belongs. The terms "first", "second" and the like used in the embodiments of the present application do not represent any order, number or importance, but are only used to distinguish different components. The terms "include" or "contain" and the like mean that the elements or objects before the terms cover the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" and the like are not limited to physical or mechanical connection, but can include electrical connection, whether direct or indirect. The terms "up", "down", "left", "right" and the like are only used to represent relative positional relationships, and when the absolute positions of the described objects change, the relative positional relationships may also change accordingly.

[0042] As described above, in the current positioning drilling process for municipal projects, the drilling equipment and drilling methods used in field drilling are usually directly applied to the drilling work for municipal projects. However, in the drilling work for municipal projects, since the environment for implementing drilling is often in the city, the underground metal objects (seismographs, strong motion instruments, etc.), cables and possible cultural relics buried in the city need to be considered in the process of positioning drilling. These factors are not within the scope of consideration for field drilling. Therefore, directly applying the drilling equipment and drilling methods used in field drilling to the drilling work based on the urban environment is easy to cause damage to the underground metal objects or cultural relics in the city.

[0043] To solve this problem, the embodiment of the present application provides a municipal drilling positioning method, in which, first, a preset detection signal is emitted to a to-be-drilled area by a detection module to receive a characteristic signal fed back to the preset detection signal. Then, the characteristic signal is analyzed according to a preset neural network model to determine a drilling obstruction probability. The drilling obstruction probability is used to represent the probability of the existence of a drilling obstruction in the to-be-drilled area. Finally, the drilling control of the driving drill bit is performed according to the drilling obstruction probability. In this way, by emitting a specific type of preset detection signal to the to-be-drilled area, a specific type of characteristic signal generated by different types of objects in the to-be-drilled area based on the preset detection signal can be received. Further, by analyzing the specific type of characteristic signal by the preset neural network, the probability of the existence of a drilling obstruction in the to-be-drilled area is determined, which can effectively perceive whether underground metal objects or cultural relics are likely to appear in the to-be-drilled area, avoid damage to them in the drilling process, and effectively improve the safety of the drill bit itself in the drilling positioning process and the safety of the city underground metal objects and cultural relics.

[0044] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0045] Referring to Figure 1 The figure is a flowchart of a municipal drilling positioning method provided by the embodiment of the present application, which specifically includes the following steps:

[0046] S101: Emitting a preset detection signal to a to-be-drilled area by a detection module to receive a characteristic signal fed back to the preset detection signal.

[0047] When the driving drill bit is drilling or before starting drilling, the detection module arranged on the drill bit emits a preset detection signal to the to-be-drilled area. The signal receiving device is also arranged on the drill bit. If there is an underground metal object or cultural relics or similar obstacles in the to-be-drilled area, the signal receiving device will receive the characteristic signal reflected by the obstacles, so as to analyze whether these obstacles will bring safety risks to the drilling process based on the characteristic signal.

[0048] In the embodiments of the present application, the detection module is divided into a GRP (Ground Radar Probe Unit, ground radar detection unit) detection unit and a NLJD (Non-Linear Junction Detector, non-linear junction detector) detection unit. Among them, the NLJD detection unit is used to emit a fundamental wave signal, and the fundamental wave signal is used to detect whether the area to be drilled (underground) contains metal objects such as seismographs, optical fiber sensing systems, and other metal objects unique to urban underground. When the fundamental wave signal encounters metal objects containing non-linear electronic components (such as diodes, transistors), etc., these electronic components will generate harmonic signals due to their non-linear characteristics. Therefore, the harmonic signal is used as a characteristic signal fed back after the transmission of the fundamental wave signal, which can effectively determine whether there are underground metal objects in the area to be drilled.

[0049] Correspondingly, the GRP detection unit is used to emit a high-frequency electromagnetic wave signal, and the high-frequency electromagnetic wave signal is used to detect whether the area to be drilled contains non-metallic objects such as historical relics, pipelines, stones, etc. When the high-frequency electromagnetic wave signal contacts such non-metallic objects, a reflected wave signal will be generated. As described above, the reflected wave signal generated by such non-metallic objects is used as a characteristic signal, and then it can be determined whether there are non-metallic objects in the area to be drilled.

[0050] It should be noted that the high-frequency electromagnetic wave signal emitted by the GRP detection unit has a frequency range of 10 MHz-2.6 GHz (microwave); such high-frequency electromagnetic wave signal has the signal characteristics of short pulse and wide band for reflection imaging. The fundamental wave signal (usually low-frequency continuous wave) emitted by the NLJD detection unit has a frequency range of 1 MHz-3 GHz; such fundamental wave signal has the signal characteristics of continuous wave, aiming to stimulate the target harmonic response

[0051] In this way, by emitting a specific type of detection signal through a specific detection unit, it can be effectively determined whether the area to be drilled contains metal objects and non-metallic objects unique to urban drilling scenarios, and prevent damage to metal objects or cultural relics in the urban underground during the drilling process.

[0052] S102: performing signal analysis on the characteristic signal according to a preset neural network model to determine a drilling obstruction probability; the drilling obstruction probability is used to represent the probability that the area to be drilled contains drilling obstructions.

[0053] If the characteristic signal (i.e. the reflected wave signal or the harmonic signal) reflected by the metal object or the non-metal object is received, the characteristic signal is analyzed by the preset neural network model to determine the probability of being hindered by the obstacle during the drilling process. Among them, the preset neural network model is divided into two types according to the type of the characteristic signal. For the harmonic signal, since the traditional harmonic signal data is displayed in the form of signal waveform and signal power, the corresponding preset neural network model is a signal analysis neural network. Similarly, for the reflected wave signal, by converting the reflected wave signal image data, the corresponding gray image of the reflected wave signal can be obtained to determine whether there is a non-metal object in the gray image. Therefore, the preset neural network model corresponding to the reflected wave signal is an image recognition neural network.

[0054] S103: Controlling the drilling of the driving bit according to the drilling hindering probability.

[0055] Finally, the drilling speed of the bit is controlled in real time according to the drilling hindering probability output by the preset neural network model. Among them, the drilling hindering probability and the drilling speed are inversely proportional, the higher the drilling hindering probability, the lower the drilling speed. When the drilling hindering probability is too high to exceed the preset third threshold, it indicates that the obstacle existing in the to-be-drilled area exists the risk of hindering the drilling of the bit, at this time, the drilling process of the driving bit needs to be stopped to prevent the driving bit from causing damage to the underground metal object or the cultural relic, and to ensure the safety of the bit equipment during the drilling process.

[0056] In addition, the drilling hindering probability in the embodiment of the present application is divided into metal object hindering probability and non-metal object hindering probability according to the requirement of preventing damage to underground electronic equipment and cultural relics in the embodiment of the present application, and the specific application will be introduced below.

[0057] Referring to Figure 2 The figure is a structure schematic diagram of a detection module according to an embodiment of the present application. As can be seen from the figure, in the actual application scenario, the GRP detection unit and the NLJD detection unit adopt different transmission links, that is, the transmission links corresponding to the transmission of the fundamental wave signal and the transmission of the high-frequency electromagnetic wave signal are different, and the corresponding receiving links also differ. When the NLJD detection unit is running, sometimes the fundamental wave signal transmitted by it will be partially reflected to the receiving link of the GRP detection unit, causing the GRP detection unit to make a false judgment. Therefore, in order to prevent the mutual influence of the two when transmitting detection signals, the GRP detection unit and the NLJD detection unit are configured to work alternately, only when one of them is completely closed, the other can be opened, so as to prevent the occurrence of false judgment.

[0058] Specifically, when the GRP detection unit and the NLJD detection unit work alternately, after the end of the start stage of any one of the two to before the other enters the start stage, both need to go through a preset buffer stage. The preset start duration of the GRP detection unit and the NLJD detection unit is different, so it is necessary to ensure the complete closing or complete opening of the detection unit after the preset start duration is reached. The working timing between the two is as follows: after the GRP detection unit is started for the first preset start duration, the GRP detection unit enters the preset buffer stage (at this time the NLJD detection unit is closed), after the GRP detection unit is completely closed, the NLJD detection unit is started based on the second preset start duration, and enters the preset buffer stage when the second preset duration is reached (at this time the GRP detection unit is closed), and so on.

[0059] In addition, in actual application scenarios, when determining whether the area to be drilled contains non-metallic objects based on reflected wave signals, it is necessary to involve the process of converting reflected wave signals into grayscale images and analyzing the probability of obstacles based on grayscale images. The conversion and analysis of grayscale images often require the emission of continuous reflected waves with long duration, and compared with the fundamental wave signal, the corresponding harmonic signal can be obtained by emitting the fundamental wave signal for a short time. Therefore, the first preset start duration corresponding to the GRP detection unit needs to be much longer than the second preset start duration corresponding to the NLJD detection unit. In the application scenario of the embodiment of the present application, the ratio of the first preset start duration, the second preset start duration and the buffer stage duration is 16:4:1, so that the GRP detection unit has sufficient time to emit reflected wave signals to ensure accurate detection of non-metallic objects.

[0060] In addition to being affected by the simultaneous start of the NLJD detection unit, the GRP detection unit may also be affected by underground metal objects. As known from the foregoing, the GRP detection unit detects non-metallic objects such as underground cultural relics by emitting high-frequency electromagnetic wave signals. However, if the area to be drilled also contains a large number of metal objects, the echoes generated by these metal objects may weaken the characteristic signals reflected by non-metallic objects. The echoes generated by these metal objects will appear in the form of large-area bright spots on the converted grayscale image, thereby affecting the probability analysis of the grayscale image by the image recognition neural network.

[0061] Therefore, in order to avoid this situation, the embodiment of the present application needs to control the opening of the GRP detection unit and the NLJD detection unit according to the actual situation of the gray image. If there is a certain bright spot area in the gray image, the NLJD detection unit needs to be started to determine whether the bright spot area in the image is caused by a metal object, so as to ensure the detection accuracy. Next, this process will be introduced in combination with specific embodiment drawings.

[0062] Referring to Figure 3 The figure is a flowchart of a feature signal analysis method provided by the embodiment of the present application, which specifically includes the following steps:

[0063] S1021: When the GRP detection unit is opened, the reflected wave signal is subjected to image data conversion to obtain a reflected gray image.

[0064] S1022: The reflected gray image is subjected to image analysis by the image recognition neural network to obtain a gray image analysis result.

[0065] In the process of emitting a high-frequency emission wave signal by the GRP detection unit to the area to be drilled, the reflected feedback wave signal is received in real time, and image data conversion is performed thereon to convert the reflected wave signal into a reflected recovery image. Subsequently, the reflected gray image is subjected to image analysis by the image recognition neural network, and whether there is a bright spot area therein is judged according to the corresponding gray image analysis result.

[0066] S1023: Based on the gray image analysis result and the real-time opening duration of the GRP detection unit, the running state of the GRP detection unit and the NLJD detection unit is controlled.

[0067] In the process of controlling the GRP detection unit and the NLJD detection unit according to whether there is a bright spot area in the gray image, if the gray image analysis result indicates that there is no bright spot area in the gray image, the non-metallic object blocking probability can be analyzed based on the image recognition network normally. If there is a bright spot area in the gray image, the NLJD detection unit needs to be run to determine whether the bright spot area in the gray image is caused by the underground metal object.

[0068] Since the first preset opening duration of the GRP detection unit is much longer than the preset second opening duration of the NLJD detection unit, in order to prevent the GRP detection unit from being interrupted too early, the real-time opening duration of the two needs to be combined for control and judgment. Next, this process will be introduced in combination with specific embodiment drawings.

[0069] Referring to Figure 4, the figure is a flow diagram of a control method for a GRP detection unit and a NLJD detection unit provided by the embodiment. As shown in the figure, first, it is necessary to determine whether there is a bright spot area in the gray-scale image according to the gray-scale image analysis result. If it is determined that the gray-scale image analysis result is that there is a bright spot area, it is necessary to close the GRP detection unit and drive the NLJD detection unit to emit a fundamental wave signal to the area to be drilled according to the mechanism of the alternating work between the GRP detection unit and the NLJD detection unit, and to determine whether the bright spot area appearing in the gray-scale image is caused by a metal object by directly detecting whether there is a metal object in the area to be drilled. If the NLJD detection unit receives the corresponding harmonic signal, the signal analysis neural network is used to analyze the received harmonic signal to determine the probability of the existence of a metal object in the area to be drilled, i.e., the metal object obstruction probability.

[0070] If the metal object obstruction probability is not less than a preset first threshold, it indicates that there is indeed a risk of metal object obstruction in the area to be drilled, and at this time, the drilling speed of the driving drill bit can be reduced based on the inverse proportional relationship between the obstruction probability and the drilling speed to prevent damage to underground electronic equipment such as underground metal objects caused by the drilling process.

[0071] On the contrary, if the metal object obstruction probability is less than the preset first threshold, it indicates that the bright spot existing in the gray-scale image is not caused by the underground metal object, and therefore, it is necessary to combine the real-time opening duration of the GRP detection unit to determine whether it is necessary to restart the GRP detection unit to complete the remaining opening duration, so as to prevent the GRP detection unit from interrupting too early.

[0072] If the real-time opening duration of the GRP detection unit is less than a preset second threshold, it indicates that the GRP detection unit has interrupted too early, and therefore, it is necessary to close the NLJD detection unit and drive the GRP detection unit to run based on its corresponding remaining opening duration, so as to ensure that a gray-scale image can be generated through a sufficient reflected wave signal. Correspondingly, if the real-time opening duration of the GRP detection unit is not less than the preset second threshold, it indicates that the GRP detection unit has been running for a period of time, and even if the GRP detection unit is restarted, since it still needs to go through a buffering stage, the actual running duration of the GRP detection unit is not much. Therefore, in this case, the remaining opening duration of the GRP detection unit is directly skipped, and the NLJD detection unit is driven to run normally, so as to comprehensively improve the detection efficiency.

[0073] The embodiment of the present application provides a municipal drilling positioning method, in the method, first, a preset detection signal is emitted to a to-be-drilled area through a detection module, so that a characteristic signal fed back to the preset detection signal is received. Then, a signal analysis is performed on the characteristic signal according to a preset neural network model, so that a drilling obstruction probability is determined. Wherein, the drilling obstruction probability is used for representing a probability of drilling obstruction occurring in the to-be-drilled area. Finally, drilling control is performed on a driving drill bit according to the drilling obstruction probability. In this way, by emitting a specific type of preset detection signal to the to-be-drilled area, a specific type of characteristic signal generated by different types of objects in the to-be-drilled area based on the preset detection signal can be received. Further, by performing signal analysis on the specific type of characteristic signal through the preset neural network, the probability of the existence of a drilling obstruction in the to-be-drilled area is determined, whether the underground metal object or cultural relic in the to-be-drilled area can be effectively perceived, damage to the underground metal object or cultural relic in the drilling process is avoided, and the safety of the drill bit itself in the drilling positioning process and the safety of the underground metal object and cultural relic in the city are effectively improved.

[0074] It should be noted that each of the embodiments in the specification adopts a progressive manner for description, and the same and similar parts between each of the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. Especially, for the method, since it is basically similar to the method embodiment, the description is relatively simple, and the related parts can be referred to the part of the method embodiment. The above-described method is only schematic, and the units described as separate components can or can not be physically separate, and the components prompted as units can or can not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. According to the actual needs, some or all of the modules can be selected to achieve the purpose of the embodiment. Those skilled in the art can understand and implement without creative labor.

[0075] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited to this. Any skilled person in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of municipal drilling positioning, characterized by, The method comprises the following steps: a preset detection signal is emitted to a to-be-drilled area by a detection module to receive a characteristic signal fed back to the preset detection signal; a signal analysis is performed on the characteristic signal according to a preset neural network model to determine a drilling obstruction probability; the drilling obstruction probability is used to represent a probability of occurrence of drilling obstruction in a drilling process; a drilling control is performed on a driving drill bit according to the drilling obstruction probability; the detection module comprises a GRP detection unit and a NLJD detection unit; the preset detection signal comprises a high-frequency electromagnetic wave signal and a fundamental wave signal; the characteristic signal corresponding to the high-frequency electromagnetic wave signal is a reflected wave signal, and the characteristic signal corresponding to the fundamental wave signal is a harmonic wave signal; the GRP detection unit and the NLJD detection unit are configured to be alternately started; the preset neural network model comprises an image recognition neural network and a signal analysis neural network; the drilling obstruction probability comprises a metal object obstruction probability; the signal analysis performed on the characteristic signal according to the preset neural network model comprises the following steps: when the GRP detection unit is started, an image data conversion is performed on the reflected wave signal to obtain a reflected gray-scale image; an image analysis is performed on the reflected gray-scale image by the image recognition neural network to obtain a gray-scale image analysis result; when the gray-scale image analysis result is that there is a bright spot area, the GRP detection unit is stopped, and the NLJD detection unit is driven to emit the fundamental wave signal to the to-be-drilled area to receive the corresponding harmonic wave signal; a signal analysis is performed on the harmonic wave signal by the signal analysis neural network to obtain the metal object obstruction probability; if the metal object obstruction probability is not less than a preset first threshold, the drilling speed of the driving drill bit is reduced according to the metal object obstruction probability.

2. The method according to claim 1, wherein: the GRP detection unit is used to emit the high-frequency electromagnetic wave signal to the to-be-drilled area to receive the reflected wave signal; the NLJD detection unit is used to emit the fundamental wave signal to the to-be-drilled area to receive the harmonic wave signal.

3. The method of claim 1, wherein, After the metal object obstruction probability is obtained, the method further comprises the following steps: when the metal object obstruction probability is less than the preset first threshold, if a real-time starting time length of the GRP detection unit is less than a preset second threshold, the NLJD detection unit is stopped, and the GRP detection unit is driven to run based on a corresponding remaining starting time length; the remaining starting time length is obtained based on a first preset starting time length corresponding to the GRP detection unit and the real-time starting time length of the GRP detection unit; when the metal object obstruction probability is less than the preset first threshold, if the real-time starting time length of the GRP detection unit is not less than the preset second threshold, the remaining starting time length of the GRP detection unit is skipped, and the NLJD detection unit is driven to run based on a second preset starting time length corresponding to the NLJD detection unit.

4. The method of claim 1, wherein, the drilling obstruction probability comprises a non-metallic object obstruction probability; Based on the grayscale image analysis result and the real-time opening duration of the GRP detection unit, the running state of the GRP detection unit and the NLJD detection unit is controlled, and the method further comprises: If the grayscale image analysis result is that there is no bright spot area, the image recognition neural network is used to analyze the blockage probability of the reflected grayscale image to obtain the non-metal object blockage probability.

5. The method of claim 1, wherein, The drilling control of the driving drill bit according to the drilling blockage probability comprises: When the drilling blockage probability is greater than a preset third threshold, the drilling process of the driving drill bit is stopped.

6. The method of claim 3, wherein, There is a preset buffer stage between the end of the opening stage of any one of the GRP detection unit and the NLJD detection unit and the entry of the other into the opening stage.

7. The method of claim 6, wherein, The ratio of the first preset opening duration, the second preset opening duration and the duration of the preset buffer stage is 16:4:

1.

8. The method of claim 1, wherein, The drilling control of the driving drill bit according to the drilling blockage probability comprises: According to the drilling blockage probability, the drilling speed of the driving drill bit is controlled; the drilling blockage probability and the drilling speed are in inverse proportion.

Images