Method, device and storage medium for identifying underground pipelines during drilling construction
Through machine learning models, we can identify drilling parameters and determine whether the drilling rig encounters underground pipelines, solve the problems of difficulty and high cost in the existing technology, realize efficient underground pipeline identification, and reduce construction costs and risks.
Patent Information
- Application Number
- CN202311111741.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-30
- Publication Date
- 2024-12-27
- Estimated Expiration
- 2043-08-30
AI Technical Summary
During the drilling and construction process, it is difficult for the existing technology to effectively identify underground pipelines, resulting in increased equipment costs and time costs, and it is easy to damage pipelines and affect construction efficiency.
Using machine learning model, by obtaining the drilling parameters of the drilling rig during the drilling process, we can determine whether underground pipelines are encountered, including decision trees and random forest models, and combine the labels of geotechnical and pipeline types to generate underground pipeline identification models to directly judge whether the drilling rig is When encountering pipelines, the traditional digging process is omitted.
Reduce equipment and time cost investment, improve drilling construction efficiency, avoid pipeline damage, and improve construction safety.
Smart Images
Figure CN117150691B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of satellite navigation and positioning, and in particular to an underground pipeline identification method, device and storage medium during drilling construction. Background Art
[0002] Urban underground pipelines are an important part of urban infrastructure construction. Due to the complex ownership of underground pipelines in various cities, there are too many ownership units, the design and layout of pipelines lack unified management, and the spatial pattern of underground pipelines is chaotic. Major accidents that damage underground pipelines occur from time to time during urban road exploration and construction, causing heavy losses to life and property. Usually, the "dig three and penetrate six" method is adopted in the process of pipeline inspection, that is, using excavation tools such as Luoyang shovels to dig down three meters, and then using a drilling rig hammer to hammer and penetrate within the range of three to six meters. If it is visible to the naked eye or there is difficulty in penetrating downwards when hammering, it means that underground pipelines are encountered. That is, although this method avoids underground pipelines to a certain extent, it consumes more equipment costs and time costs in the digging and hammering process, which is not conducive to improving drilling construction efficiency. Summary of the invention
[0003] The present invention provides a method, device and storage medium for identifying underground pipelines during drilling construction. During the drilling construction, an underground pipeline identification model can be used to determine whether a drilling rig encounters an underground pipeline during the drilling process, thereby omitting the conventional process of deepening the excavation first, reducing the equipment cost and time cost required during the drilling construction process, and improving the drilling construction efficiency.
[0004] The present invention provides an underground pipeline identification method during a drilling construction process, comprising: obtaining drilling parameters of a drilling rig during the drilling construction process;
[0005] Inputting the drilling parameters into an underground pipeline identification model, so that the underground pipeline identification model determines whether the drilling rig encounters an underground pipeline during the drilling construction according to the drilling parameters;
[0006] The generation of the underground pipeline identification model includes:
[0007] Acquire a first drilling parameter for drilling rock and soil by a drilling rig, and a rock and soil label corresponding to the first drilling parameter;
[0008] Acquire a second drilling parameter for the drilling rig to drill the pipeline, and a pipeline label corresponding to the second drilling parameter;
[0009] Taking the first drilling parameters and the second drilling parameters as input and the geotechnical labels or pipeline labels as output, the preset machine learning training model is trained, and the machine learning training model after training is used as the underground pipeline recognition model.
[0010] Furthermore, the types of rock and soil include: gravel soil, sandy soil, silt soil, clay soil and artificial fill;
[0011] The obtaining of a first drilling parameter for a drilling rig to drill rock and soil, and a rock and soil label corresponding to the first drilling parameter, includes:
[0012] First drilling parameters of the drilling rig for drilling gravel soil, sandy soil, silt soil, clay soil and artificial fill are respectively obtained, and the gravel soil, sandy soil, silt soil, clay soil and artificial fill labels corresponding to each of the first drilling parameters are determined.
[0013] Furthermore, the types of the pipeline include: iron pipeline, steel pipeline, copper pipeline and concrete pipeline;
[0014] The step of obtaining a second drilling parameter for a drilling rig to drill a pipeline, and a pipeline label corresponding to the second drilling parameter, includes:
[0015] Second drilling parameters of the drilling rig for drilling the iron pipe, the steel pipe, the copper pipe and the concrete pipe are respectively obtained, and the iron pipe, the steel pipe, the copper pipe and the concrete pipe labels corresponding to each of the second drilling parameters are determined.
[0016] Furthermore, the machine learning training model includes: a decision tree model and a random forest model;
[0017] The method of taking the first drilling parameter and the second drilling parameter as input and taking the geotechnical label or the pipeline label as output, training the preset machine learning training model, and using the trained machine learning training model as the underground pipeline recognition model includes:
[0018] Taking the first drilling parameters corresponding to the rock and soil types as input and the rock and soil labels as output, training a first preset decision tree model to generate a first decision tree model;
[0019] Taking the second drilling parameters corresponding to each of the pipeline types as input and taking each of the pipeline labels as output, training the second preset decision tree model to generate a second decision tree model;
[0020] The first decision tree model and the second decision tree model are combined to generate a random forest model, and the random forest model is used as an underground pipeline identification model.
[0021] Furthermore, the drilling parameters include: torque parameters, rotation speed parameters, drilling depth parameters, drilling pressure parameters, drilling back pressure parameters, slurry inlet pressure parameters, slurry inlet flow parameters and slurry outlet flow parameters.
[0022] Based on the above method embodiment, the present invention provides a corresponding device embodiment;
[0023] The present invention provides an underground pipeline identification device in a drilling construction process, comprising: a drilling parameter acquisition module and an underground pipeline identification module:
[0024] The drilling parameter acquisition module is used to acquire the drilling parameters of the drilling rig during the drilling construction process;
[0025] The underground pipeline identification module is used to input the drilling parameters into the underground pipeline identification model, so that the underground pipeline identification model determines whether the drilling rig encounters an underground pipeline during the drilling construction according to the drilling parameters;
[0026] The generation of the underground pipeline identification model includes:
[0027] Acquire a first drilling parameter for drilling rock and soil by a drilling rig, and a rock and soil label corresponding to the first drilling parameter;
[0028] Acquire a second drilling parameter for the drilling rig to drill the pipeline, and a pipeline label corresponding to the second drilling parameter;
[0029] Taking the first drilling parameters and the second drilling parameters as input and the geotechnical labels or pipeline labels as output, the preset machine learning training model is trained, and the machine learning training model after training is used as the underground pipeline recognition model.
[0030] Furthermore, the types of rock and soil include: gravel soil, sandy soil, silt soil, clay soil and artificial fill;
[0031] The obtaining of a first drilling parameter for a drilling rig to drill rock and soil, and a rock and soil label corresponding to the first drilling parameter, includes:
[0032] First drilling parameters of the drilling rig for drilling gravel soil, sandy soil, silt soil, clay soil and artificial fill are respectively obtained, and the gravel soil, sandy soil, silt soil, clay soil and artificial fill labels corresponding to each of the first drilling parameters are determined.
[0033] Further, the types of the pipeline include: iron pipeline, steel pipeline, copper pipeline and concrete pipeline;
[0034] The step of obtaining a second drilling parameter for a drilling rig to drill a pipeline, and a pipeline label corresponding to the second drilling parameter, includes:
[0035] Second drilling parameters of the drilling rig for drilling the iron pipe, the steel pipe, the copper pipe and the concrete pipe are respectively obtained, and the iron pipe, the steel pipe, the copper pipe and the concrete pipe labels corresponding to each of the second drilling parameters are determined.
[0036] Furthermore, the machine learning training model includes: a decision tree model and a random forest model;
[0037] The method of taking the first drilling parameter and the second drilling parameter as input and taking the geotechnical label or the pipeline label as output, training the preset machine learning training model, and using the trained machine learning training model as the underground pipeline recognition model includes:
[0038] Taking the first drilling parameters corresponding to the rock and soil types as input and the rock and soil labels as output, training a first preset decision tree model to generate a first decision tree model;
[0039] Taking the second drilling parameters corresponding to each of the pipeline types as input and taking each of the pipeline labels as output, training the second preset decision tree model to generate a second decision tree model;
[0040] The first decision tree model and the second decision tree model are combined to generate a random forest model, and the random forest model is used as an underground pipeline identification model.
[0041] Based on the above method embodiment, the present invention provides a storage medium embodiment;
[0042] The present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the underground pipeline identification method during the drilling construction process described in any one of the present inventions.
[0043] The embodiments of the present invention have the following beneficial effects:
[0044] The present invention provides a method, device and storage medium for identifying underground pipelines during a drilling construction process; the method, after obtaining drilling parameters during the drilling construction process, inputs the obtained drilling parameters into an underground pipeline identification model, and then the underground pipeline model can judge whether the drill bit is drilling rock or a pipeline during the drilling construction process according to the drilling parameters; that is, by implementing the present invention, during the drilling construction process, the traditional "dig three and penetrate six" method can be directly skipped, which is equivalent to omitting the deep digging process, and directly using the drilling rig for drilling, and obtaining the drilling parameters of the drilling rig during drilling, and then inputting the drilling parameters into the underground pipeline identification model, and the underground pipeline identification model can be used to judge whether the drilling rig encounters an underground pipeline during the drilling process, which directly reduces the investment in equipment cost and time cost and improves the drilling construction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 It is a schematic flow chart of a method for identifying underground pipelines during drilling construction provided by an embodiment of the present invention;
[0046] Figure 2 It is a structural schematic diagram of an underground pipeline identification device during a drilling construction process provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0047] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0048] like Figure 1 As shown, an embodiment provides a method for identifying underground pipelines during drilling construction, including:
[0049] Step S101: Acquire drilling parameters of the drilling rig during the drilling construction process;
[0050] Step S102: inputting the drilling parameters into an underground pipeline identification model, so that the underground pipeline identification model determines whether the drilling rig encounters an underground pipeline during the drilling construction according to the drilling parameters;
[0051] The generation of the underground pipeline identification model includes:
[0052] Acquire a first drilling parameter for drilling rock and soil by a drilling rig, and a rock and soil label corresponding to the first drilling parameter;
[0053] Acquire a second drilling parameter for the drilling rig to drill the pipeline, and a pipeline label corresponding to the second drilling parameter;
[0054] Taking the first drilling parameters and the second drilling parameters as input and the geotechnical labels or pipeline labels as output, the preset machine learning training model is trained, and the machine learning training model after training is used as the underground pipeline recognition model.
[0055] For step S101, in a preferred embodiment, during the drilling construction process, the drilling parameters of the drilling rig are obtained in real time.
[0056] Before the drilling construction is officially carried out, the present invention adopts a protective drill bit by default, collects the underground pipeline data of the area, and extracts the material, outer diameter, thickness and other information of pipelines for different purposes (such as water supply, sewage, etc.); then these data are used as the basis for drilling construction; at the same time, the type of drill bit can be flexibly selected according to the underground pipeline data, which can protect and avoid the underground pipeline to a certain extent.
[0057] For step S102, in a preferred embodiment, the drilling parameters acquired in real time during the drilling construction process are input into the underground pipeline identification model. The underground pipeline prediction model will determine whether the drilling rig is drilling rock or underground pipelines during the drilling process based on the drilling parameters acquired in real time. When the drill bit encounters an underground pipeline, the underground pipeline identification model can determine that the drill bit has encountered the underground pipeline before the drill bit damages the underground pipeline.
[0058] For the generation of the underground pipeline identification model, first obtain the first drilling parameters of the drilling rig for drilling rock and soil, and determine the corresponding rock and soil labels; and obtain the second drilling parameters of the drilling rig for drilling the pipeline, and determine the corresponding pipeline labels; use the first drilling parameters and the second drilling parameters as inputs and the rock and soil labels or pipeline labels as outputs to train the preset machine learning training model, and use the machine learning training model after the training as the underground pipeline identification model.
[0059] In a preferred embodiment, the types of rock and soil include: gravel soil, sandy soil, silt soil, clay soil and artificial fill;
[0060] The obtaining of a first drilling parameter for a drilling rig to drill rock and soil, and a rock and soil label corresponding to the first drilling parameter, includes:
[0061] First drilling parameters of the drilling rig for drilling gravel soil, sandy soil, silt soil, clay soil and artificial fill are respectively obtained, and the gravel soil, sandy soil, silt soil, clay soil and artificial fill labels corresponding to each of the first drilling parameters are determined.
[0062] Specifically, the types of rock and soil include but are not limited to: gravel soil, sandy soil, silt soil, clay soil and artificial fill;
[0063] Before training the model, it is necessary to obtain the first drilling parameters of the drill when drilling gravel soil, sandy soil, silt soil, clay soil and artificial fill, and the geotechnical labels corresponding to these first parameters.
[0064] In a preferred embodiment, the types of the pipeline include: iron pipeline, steel pipeline, copper pipeline and concrete pipeline;
[0065] The step of obtaining a second drilling parameter for a drilling rig to drill a pipeline, and a pipeline label corresponding to the second drilling parameter, includes:
[0066] Second drilling parameters of the drilling rig for drilling the iron pipe, the steel pipe, the copper pipe and the concrete pipe are respectively obtained, and the iron pipe, the steel pipe, the copper pipe and the concrete pipe labels corresponding to each of the second drilling parameters are determined.
[0067] Specifically, the types of pipes include, but are not limited to: iron pipes, steel pipes, copper pipes and concrete pipes;
[0068] Before training the model, it is necessary to obtain the second drilling parameters of the drill rig when drilling iron pipes, steel pipes, copper pipes and concrete pipes, and the pipe labels corresponding to these second parameters.
[0069] In a preferred embodiment, the machine learning training model includes: a decision tree model and a random forest model;
[0070] The method of taking the first drilling parameter and the second drilling parameter as input and taking the geotechnical label or the pipeline label as output, training the preset machine learning training model, and using the trained machine learning training model as the underground pipeline recognition model includes:
[0071] Taking the first drilling parameters corresponding to the rock and soil types as input and the rock and soil labels as output, training a first preset decision tree model to generate a first decision tree model;
[0072] Taking the second drilling parameters corresponding to each of the pipeline types as input and taking each of the pipeline labels as output, training the second preset decision tree model to generate a second decision tree model;
[0073] The first decision tree model and the second decision tree model are combined to generate a random forest model, and the random forest model is used as an underground pipeline identification model.
[0074] Specifically, the machine learning training model includes but is not limited to: a decision tree model and a random forest model; taking the first drilling parameters corresponding to each rock and soil type as input and each rock and soil label as output, the first preset decision tree model is trained to generate a first decision tree model; at the same time, taking the second drilling parameters corresponding to each pipeline type as input and each pipeline label as output, the second preset decision tree model is trained to generate a second decision tree model; it should be noted that the first and second preset decision tree models are only used to distinguish between two preset decision tree models.
[0075] The first decision tree model and the second decision tree model are combined to generate a random forest model, and the random forest model is used as an underground pipeline identification model. Optionally, the number of decision tree models is not specifically limited, and after combining the decision tree models, a random forest model is generated, and then the generated random forest model is used as an underground pipeline identification model.
[0076] In an optional embodiment, the training method in the present invention can be any training method in the prior art. For example, in addition to using the random forest method, the present invention can also use a neural network method to train the underground pipeline recognition model.
[0077] In a preferred embodiment, the drilling parameters include: torque parameter, rotation speed parameter, drilling depth parameter, drilling pressure parameter, drilling back pressure parameter, slurry inlet pressure parameter, slurry inlet flow parameter and slurry outlet flow parameter.
[0078] Specifically, these drilling parameters are detected and acquired by various sensors, including but not limited to: torque sensor, rotation speed sensor, drilling depth sensor, drilling pressure sensor, drilling back pressure sensor, slurry pressure sensor, slurry flow sensor and slurry discharge flow sensor.
[0079] For the torque sensor, a pressure sensor is used and installed on the torque pressure pipeline through a three-way joint. The sensor uses a 4-20mA analog signal and transmits it to the monitoring host through a signal line.
[0080] For the speed sensor, the speed measurement uses an electromagnetic sensor. The sensor body is installed on the power head assembly through a fixed bracket. It is a switching signal and is transmitted to the monitoring host through the signal line.
[0081] For the drilling depth sensor, the drilling depth uses a laser sensor, which is installed on the lifting cylinder of the power head assembly and uses RS485 signal to transmit to the monitoring host through the signal line.
[0082] For the drilling pressure sensor, a pressure sensor is used and installed on the drilling pressure pipeline through a three-way joint. The sensor uses 4-20mA analog signal and transmits it to the monitoring host through a signal line.
[0083] For the drilling back pressure sensor, a pressure sensor is used and installed on the drilling back pressure pipeline through a three-way joint. The sensor uses 4-20mA analog signal; it is transmitted to the monitoring host through a signal line.
[0084] For the slurry inlet pressure sensor, the slurry inlet pressure sensor is installed on the slurry inlet pressure pipeline through a three-way joint. The sensor adopts 4-20mA analog signal; it is transmitted to the monitoring host through a signal line.
[0085] For the slurry flow sensor, the slurry flow rate uses an electromagnetic sensor, and the sensor body is installed on the mud pump body through a fixed bracket. The slurry flow rate is obtained by collecting the number of piston strokes and using a specific algorithm. The sensor is a switching signal, which is transmitted to the monitoring host through a signal line; wherein, the specific algorithm is any existing flow algorithm.
[0086] For the slurry flow sensor, an ultrasonic sensor is used for the slurry flow. The probe is installed at the mud outlet through a fixed bracket to obtain the mud outlet liquid level in real time. The real-time flow is obtained through a specific algorithm and the RS485 signal is used to transmit it to the monitoring host through a signal line.
[0087] In an optional embodiment, the drill bit used in the present invention is any protective drill bit on the market, so as to reduce the probability of the drill bit damaging the pipeline during the drilling process, that is, when the drill bit encounters an underground pipeline and before the underground pipeline recognition model recognizes it, it can prevent the underground pipeline from being damaged. It should be noted that the underground pipeline mentioned in the present invention also means the underground pipeline.
[0088] Based on the above method embodiment, the present invention provides a corresponding device embodiment.
[0089] like Figure 2 As shown, an embodiment of the present invention provides an underground pipeline identification device during drilling construction, including: a drilling parameter acquisition module and an underground pipeline identification module:
[0090] The drilling parameter acquisition module is used to acquire the drilling parameters of the drilling rig during the drilling construction process;
[0091] The underground pipeline identification module is used to input the drilling parameters into the underground pipeline identification model, so that the underground pipeline identification model determines whether the drilling rig encounters an underground pipeline during the drilling construction according to the drilling parameters;
[0092] The generation of the underground pipeline identification model includes:
[0093] Acquire a first drilling parameter for drilling rock and soil by a drilling rig, and a rock and soil label corresponding to the first drilling parameter;
[0094] Acquire a second drilling parameter for the drilling rig to drill the pipeline, and a pipeline label corresponding to the second drilling parameter;
[0095] Taking the first drilling parameters and the second drilling parameters as input and the geotechnical labels or pipeline labels as output, the preset machine learning training model is trained, and the machine learning training model after training is used as the underground pipeline recognition model.
[0096] In a preferred embodiment, the types of rock and soil include: gravel soil, sandy soil, silt soil, clay soil and artificial fill;
[0097] The obtaining of a first drilling parameter for a drilling rig to drill rock and soil, and a rock and soil label corresponding to the first drilling parameter, includes:
[0098] First drilling parameters of the drilling rig for drilling gravel soil, sandy soil, silt soil, clay soil and artificial fill are respectively obtained, and the gravel soil, sandy soil, silt soil, clay soil and artificial fill labels corresponding to each of the first drilling parameters are determined.
[0099] In a preferred embodiment, the types of the pipeline include: iron pipeline, steel pipeline, copper pipeline and concrete pipeline;
[0100] The step of obtaining a second drilling parameter for a drilling rig to drill a pipeline, and a pipeline label corresponding to the second drilling parameter, includes:
[0101] Second drilling parameters of the drilling rig for drilling the iron pipe, the steel pipe, the copper pipe and the concrete pipe are respectively obtained, and the iron pipe, the steel pipe, the copper pipe and the concrete pipe labels corresponding to each of the second drilling parameters are determined.
[0102] In a preferred embodiment, the machine learning training model includes: a decision tree model and a random forest model;
[0103] The method of taking the first drilling parameter and the second drilling parameter as input and taking the geotechnical label or the pipeline label as output, training the preset machine learning training model, and using the trained machine learning training model as the underground pipeline recognition model includes:
[0104] Taking the first drilling parameters corresponding to the rock and soil types as input and the rock and soil labels as output, training a first preset decision tree model to generate a first decision tree model;
[0105] Taking the second drilling parameters corresponding to each of the pipeline types as input and taking each of the pipeline labels as output, training the second preset decision tree model to generate a second decision tree model;
[0106] The first decision tree model and the second decision tree model are combined to generate a random forest model, and the random forest model is used as an underground pipeline identification model.
[0107] It should be noted that the device embodiments described above are merely schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without paying creative labor.
[0108] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0109] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.
[0110] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the underground pipeline identification method during the drilling construction process of any embodiment of the present invention.
[0111] In this embodiment, the storage medium is a computer-readable storage medium, and the computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.
[0112] By implementing the above-mentioned embodiments of the present invention, during the drilling construction process, the underground pipeline identification model can be used to determine whether the drilling rig encounters an underground pipeline during the drilling process, and the conventional process of deepening the excavation can be omitted, thereby reducing the equipment cost and time cost required in the drilling construction process and improving the drilling construction efficiency.
[0113] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A method for identifying underground pipelines during drilling construction, characterized in that: include: Obtain drilling parameters of the drilling rig during drilling construction; Inputting the drilling parameters into an underground pipeline identification model, so that the underground pipeline identification model determines whether the drilling rig encounters an underground pipeline during the drilling construction according to the drilling parameters; The generation of the underground pipeline identification model includes: Acquire a first drilling parameter for drilling rock and soil by a drilling rig, and a rock and soil label corresponding to the first drilling parameter; Acquire a second drilling parameter for the drilling rig to drill the pipeline, and a pipeline label corresponding to the second drilling parameter; Taking the first drilling parameter and the second drilling parameter as input and taking the geotechnical label or the pipeline label as output, training the preset machine learning training model, and using the trained machine learning training model as an underground pipeline recognition model; The types of rock and soil include: gravel soil, sandy soil, silt soil, clay soil and artificial fill; The obtaining of a first drilling parameter for a drilling rig to drill rock and soil, and a rock and soil label corresponding to the first drilling parameter, includes: Respectively obtain first drilling parameters of the drilling rig for drilling gravel soil, sandy soil, silt soil, clay soil and artificial fill, and determine the gravel soil, sandy soil, silt soil, clay soil and artificial fill labels corresponding to each of the first drilling parameters; The types of pipes include: iron pipes, steel pipes, copper pipes and concrete pipes; The step of obtaining a second drilling parameter for a drilling rig to drill a pipeline, and a pipeline label corresponding to the second drilling parameter, includes: Respectively obtain second drilling parameters for drilling the iron pipe, the steel pipe, the copper pipe and the concrete pipe by the drilling rig, and determine the iron pipe, the steel pipe, the copper pipe and the concrete pipe labels corresponding to each of the second drilling parameters; The drilling parameters include: torque parameter, rotation speed parameter, drilling depth parameter, drilling pressure parameter, drilling back pressure parameter, slurry inlet pressure parameter, slurry inlet flow parameter and slurry outlet flow parameter.
2. The underground pipeline identification method during drilling construction as claimed in claim 1, characterized in that: The machine learning training model includes: a decision tree model and a random forest model; The method of taking the first drilling parameter and the second drilling parameter as input and taking the geotechnical label or the pipeline label as output, training the preset machine learning training model, and using the trained machine learning training model as the underground pipeline recognition model includes: Taking the first drilling parameters corresponding to the rock and soil types as input and the rock and soil labels as output, training a first preset decision tree model to generate a first decision tree model; Taking the second drilling parameters corresponding to each of the pipeline types as input and taking each of the pipeline labels as output, training the second preset decision tree model to generate a second decision tree model; The first decision tree model and the second decision tree model are combined to generate a random forest model, and the random forest model is used as an underground pipeline identification model.
3. An underground pipeline identification device during drilling construction, characterized in that: include: Drilling parameter acquisition module and underground pipeline identification module: The drilling parameter acquisition module is used to acquire the drilling parameters of the drilling rig during the drilling construction process; The underground pipeline identification module is used to input the drilling parameters into the underground pipeline identification model, so that the underground pipeline identification model determines whether the drilling rig encounters an underground pipeline during the drilling construction according to the drilling parameters; The generation of the underground pipeline identification model includes: Acquire a first drilling parameter for drilling rock and soil by a drilling rig, and a rock and soil label corresponding to the first drilling parameter; Acquire a second drilling parameter for the drilling rig to drill the pipeline, and a pipeline label corresponding to the second drilling parameter; Taking the first drilling parameter and the second drilling parameter as input and taking the geotechnical label or the pipeline label as output, training the preset machine learning training model, and using the trained machine learning training model as an underground pipeline recognition model; The types of rock and soil include: gravel soil, sandy soil, silt soil, clay soil and artificial fill; The obtaining of a first drilling parameter for a drilling rig to drill rock and soil, and a rock and soil label corresponding to the first drilling parameter, includes: Respectively obtain first drilling parameters of the drilling rig for drilling gravel soil, sandy soil, silt soil, clay soil and artificial fill, and determine the gravel soil, sandy soil, silt soil, clay soil and artificial fill labels corresponding to each of the first drilling parameters; The types of pipes include: iron pipes, steel pipes, copper pipes and concrete pipes; The step of obtaining a second drilling parameter for a drilling rig to drill a pipeline, and a pipeline label corresponding to the second drilling parameter, includes: Respectively obtain second drilling parameters for drilling the iron pipe, the steel pipe, the copper pipe and the concrete pipe by the drilling rig, and determine the iron pipe, the steel pipe, the copper pipe and the concrete pipe labels corresponding to each of the second drilling parameters; The drilling parameters include: torque parameter, rotation speed parameter, drilling depth parameter, drilling pressure parameter, drilling back pressure parameter, slurry inlet pressure parameter, slurry inlet flow parameter and slurry outlet flow parameter.
4. The underground pipeline identification device in the drilling construction process according to claim 3, characterized in that: The machine learning training model includes: a decision tree model and a random forest model; The method of taking the first drilling parameter and the second drilling parameter as input and taking the geotechnical label or the pipeline label as output, training the preset machine learning training model, and using the trained machine learning training model as the underground pipeline recognition model includes: Taking the first drilling parameters corresponding to the rock and soil types as input and the rock and soil labels as output, training a first preset decision tree model to generate a first decision tree model; Taking the second drilling parameters corresponding to each of the pipeline types as input and taking each of the pipeline labels as output, training the second preset decision tree model to generate a second decision tree model; The first decision tree model and the second decision tree model are combined to generate a random forest model, and the random forest model is used as an underground pipeline identification model.
5. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the underground pipeline identification method during the drilling construction process as described in any one of claims 1 to 2.