Self-adaptive control method for water conservancy and hydropower engineering inclined shaft advanced detection, advanced detection body and readable storage medium

Abstract

The invention provides a self-adaptive control method for water conservancy and hydropower engineering inclined shaft advanced detection, an advanced detection body and a readable storage medium. The method comprises the steps that inclined shaft initial model data are obtained from a control platform; processing detection data acquired by the detection equipment to obtain first model data; obtaining first BIM model data according to the first model data and the initial model data; inputting the first BIM model data into a driving model to obtain first driving data; driving the advanced detection body to move according to the first driving data; updating the initial model data by using the first BIM model data; and the execution is repeated until advanced detection of the inclined shaft is completed. Advanced detection of the inclined shaft is achieved through the self-adaptive detection body, and the inclined shaft detection efficiency and accuracy are improved.

Description

Technical Field

[0001] This invention belongs to the field of construction control of water conservancy and hydropower projects, and specifically relates to an adaptive control method, an advanced detection body, and a readable storage medium for advanced detection of inclined shafts in water conservancy and hydropower projects. Background Technology

[0002] Inclined shafts, as core structures in water conservancy and hydropower projects, are widely used in critical stages such as water diversion and flow guidance. Their construction quality determines the overall stability of the project. However, inclined shafts generally face challenges such as steep terrain, complex geological conditions, and limited working space. Obtaining accurate geological data is extremely difficult, posing significant safety risks and making them a critical area prone to accidents. Therefore, obtaining high-precision geological data is a core prerequisite for optimizing construction plans and ensuring the inherent safety of inclined shafts.

[0003] Existing methods for obtaining geological data for inclined shafts mainly include preliminary exploration, construction logging, and tunnel advance detection, all of which have significant limitations and cannot meet the requirements for refined management and safe operation during inclined shaft construction. Preliminary exploration relies on a limited number of boreholes along the inclined shaft, which is costly and inaccurate, and cannot fully and continuously reflect the geological structural characteristics of the entire cross-section of the inclined shaft, making it difficult to support the needs of refined construction. During the construction phase, geological personnel need to enter the working face to supplement the logging to make up for the deficiencies in the preliminary exploration. However, the inclined shaft working face has a large slope, narrow space, and is prone to collapse and rockfall hazards, which not only results in low logging efficiency and lack of personnel safety, but also makes the results susceptible to interference from human experience and the site environment, limiting the completeness and accuracy of the data and failing to provide reliable support for construction decisions.

[0004] Existing tunnel detection technologies such as TSP, TRT, and ground-penetrating radar are poorly suited for inclined shaft scenarios. These technologies require specialized personnel to enter the inclined shaft working face for detection operations. Constrained by the inclined shaft environment, they suffer from low detection efficiency and high safety risks, failing to meet the timeliness requirements of construction schedules for advanced detection and hindering efficient and safe detection. Furthermore, using detection vehicles equipped with laser scanners and high-definition cameras for tunnel detection is also poorly suited for inclined shaft scenarios. Inclined shaft detection requires lightweight detection vehicles, which are not available for tunnels. Additionally, these vehicles lack adaptive speed control, preventing detailed data collection of key features in critical areas, resulting in low data accuracy and poor applicability.

[0005] In summary, existing methods generally suffer from poor applicability, low accuracy, low efficiency, high safety risks, and incomplete data, making them unsuitable for the unique construction environment of inclined shafts. Therefore, developing an advanced detection technology applicable to the construction environment of inclined shafts in water conservancy and hydropower projects, capable of comprehensively detecting the geological conditions of the inclined shaft through an adaptive advanced detection body, obtaining rich and high-precision geological data, while simultaneously mitigating the risks of on-site personnel operations and ensuring construction safety, is a key technical challenge urgently needing to be solved in the field of inclined shaft construction in water conservancy and hydropower projects. Summary of the Invention

[0006] The present invention aims to improve the accuracy and automation of advanced detection of inclined shafts in water conservancy and hydropower projects. It proposes an adaptive control method, an advanced detection body, and a readable storage medium for advanced detection of inclined shafts in water conservancy and hydropower projects.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is as follows: an adaptive control method for advanced detection of inclined shafts in water conservancy and hydropower projects, applied to an advanced detection body, the method comprising: S1: Obtain the initial model data of the deviated well from the control platform. The initial model data is obtained based on the deviated well drilling data. S2: Acquire the detection data collected by the detection equipment, and process the detection data to obtain the first model data; S3: Merge the first model data and the initial model data to obtain the first BIM model data; S4: Input the first BIM model data into the driving model to obtain the first driving data; S5: Drive the advanced detector to move according to the first driving data; S6: Update the initial model data using the first BIM model data; S7: Repeat steps S2-S6 until the advance detection of the inclined shaft is completed.

[0008] Furthermore, the detection data in step S2 includes three-dimensional point cloud data and imaging data. The processing of the detection data to obtain the first model data specifically includes: The first recognition model, which is pre-trained, is used to identify three-dimensional point cloud data and obtain the geometric parameters of the inclined shaft. The geometric parameters of the inclined shaft include at least the location and the contour of the inclined shaft corresponding to the location. The pre-trained second recognition model identifies the imaging data to obtain the geological parameters of the inclined well. The geological parameters of the inclined well include at least the location and the type, occurrence and lithology of the geological body corresponding to the location.

[0009] Furthermore, in step S3, the first model data and the initial model data are merged to obtain the first BIM model data, specifically including: The first sub-model data is constructed based on the geometric parameters of the inclined shaft; The second sub-model data was constructed based on the geological parameters of the inclined shaft; The first sub-model data, the second sub-model data, and the initial model data are merged to obtain the first BIM model data.

[0010] Further, in step S4, the first BIM model data is input into the driving model to obtain the first driving data, specifically including: Obtain a pre-trained driving model; obtain second driving data at multiple time points of the advanced probe; input the first BIM model data and the second driving data at multiple time points into the driving model to generate the first driving data.

[0011] Furthermore, the method also includes: transmitting the first sub-model data and the second sub-model data to the integrated control platform in real time, wherein the integrated control platform generates a BIM model of the inclined shaft based on the first sub-model data, the second sub-model data and the initial model data.

[0012] Meanwhile, this invention also proposes an adaptive control method for advanced detection of inclined shafts in water conservancy and hydropower projects, applied to an integrated control platform. This method includes: Acquire deviated well drilling sequence data; The deviated well drilling sequence data is input into a preset third identification model to obtain initial model data; In response to the request to acquire the advanced probe, the initial model data is sent to the advanced probe as described above.

[0013] Furthermore, the deviated well drilling sequence data includes at least time, location, drilling pressure, torque, rotational speed, drilling speed, and displacement; the initial model data includes at least location, lithology, rock mass compressive strength, rock mass integrity, and surrounding rock grade; the pre-trained third recognition model is a multi-target recognition model; inputting the deviated well drilling data into the pre-trained third recognition model to obtain the initial model data specifically includes: inputting the deviated well drilling data into the multi-target recognition model and outputting the initial model data.

[0014] Furthermore, the method also includes: acquiring first sub-model data and second sub-model data from the advanced detection body, wherein the first sub-model data is constructed based on the geometric parameters of the inclined shaft and the second sub-model data is constructed based on the geological parameters of the inclined shaft; generating an inclined shaft BIM model based on the first sub-model data, the second sub-model data and the initial model data; and sending the inclined shaft BIM model to at least one client for display.

[0015] Meanwhile, the present invention also proposes an advanced detector driven by the aforementioned adaptive control method, the detector comprising: a first data acquisition module, a second data acquisition module, a data acquisition module, a first data processing module, a second data processing module, a driving module, and an updating module; The first data acquisition module is used to acquire the initial model data of the data deviated shaft from the integrated control platform; The second data acquisition module is used to obtain configuration data from the client; The data acquisition module is used to collect deviated shaft exploration data during the advanced exploration process; The first data processing module is used to process the probe data to obtain the first model data, and to fuse the first model data and the initial model data to obtain the first BIM model data; The second data processing module is used to input the first BIM model data into the driving model to obtain the first driving data; The drive module is used to drive the advanced probe to move according to the first drive data; The update module is used to update the initial model data using the first BIM model data.

[0016] Furthermore, the present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of the method as described above.

[0017] Furthermore, the present invention also provides a computer program product that, when executed by a processor, implements the steps of the method as described above.

[0018] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention adopts an adaptive advanced detection body to realize unmanned advanced geological exploration of inclined shafts. It can collect multi-dimensional geological data of inclined shafts in real time and continuously, including geological structure, occurrence, lithology and images, which fundamentally avoids the operational safety risks of inclined shaft collapse, rockfall and fall, and the detection efficiency is higher. At the same time, the present invention uses the initial model data calculated based on the inclined shaft drilling data and the first model data calculated based on the real-time collected detection data. The first driving data for driving the advanced detection body is obtained by driving the model, and the advanced detection body is driven to move in the inclined shaft using the first driving data. Since the initial model data characterizes the rock mechanical properties of the inclined shaft and the first model data characterizes the geometric and geological properties of the inclined shaft, the generated first driving data can drive the advanced detection body to collect detailed data on key parts. The advanced detection data collected can reflect the characteristics and subtle features of key parts, which improves the accuracy of the advanced detection of the inclined shaft.

[0019] (2) Based on BIM technology, this invention realizes real-time visualization of the inclined shaft advance detection process, intuitively presents the geological conditions of the inclined shaft, and facilitates relevant personnel to quickly assess construction risks and take timely risk prevention and control measures. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the adaptive control method for inclined shaft advance detection provided in an embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram illustrating the generation of initial model data provided in an embodiment of the present invention.

[0022] Figure 3 This is an interactive diagram of the advanced detection device, integrated management and control platform, and client provided in the embodiments of the present invention.

[0023] Figure 4 This is a schematic diagram of the advanced detection body provided in an embodiment of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] See Figure 1 This invention proposes an adaptive control method for advanced detection of inclined shafts in water conservancy and hydropower projects, applied to advanced detection bodies. The method includes: S1: Obtain the initial model data of the deviated well from the control platform. The initial model data is obtained based on the deviated well drilling data.

[0026] The advanced probe sends an acquisition request to the control platform. The acquisition request includes the deviated well identifier. Based on the deviated well identifier, the initial model data corresponding to the deviated well identifier is acquired. The initial model data is generated based on the deviated well drilling sequence data.

[0027] Inclined shaft construction typically employs a reverse shaft drilling technique. This involves drilling directional holes from top to bottom in the horizontal section of the water diversion system according to the designed location, azimuth, and inclination angle, with a diameter typically ranging from 20 to 40 cm. After the directional holes are drilled, a reverse shaft drilling rig is used to pull the shaft upwards, creating a chute well with a diameter of 2 to 2.4 m. Sensors for drilling pressure, rotational speed, torque, drilling speed, and displacement are installed on the drilling rig used for drilling the directional holes to collect real-time data during the inclined shaft drilling sequence. After the chute well is completed, a forward probe is used to conduct an inclined shaft forward probe from top to bottom within the chute well.

[0028] This invention transmits real-time acquired deviated well drilling sequence data to an integrated control platform. The integrated control platform uses a preset third recognition model to identify the deviated well drilling sequence data to obtain initial model data. The deviated well drilling sequence data includes time T, position POS, drill pressure DP, torque TOR, rotational speed RSP, drilling speed DSP, and displacement DIS. The initial model data includes at least position POS, lithology LITH, rock mass compressive strength RC, rock mass integrity KV, and surrounding rock grade RANK. The pre-trained third recognition model is a multi-object recognition model. The deviated well drilling sequence data is input into the pre-trained third recognition model to obtain the initial model data. Specifically, this includes inputting the deviated well drilling sequence data into the multi-object recognition model and outputting the initial model data.

[0029] The third recognition model adopts a multi-target recognition model, including an input layer, an encoding layer, a first multi-tower network layer, a memory layer, a second multi-tower network layer, a decoding layer, and an output layer: The input layer uses the input deviated well drilling sequence data and transmits the deviated well drilling sequence data to the coding layer; The encoding layer is used to encode the deviated well drilling sequence data into a first feature vector, and then transmit the first feature vector to multiple tower networks in the first multi-tower network layer: Where T, POS, DP, TOR, RSP, DSP, and DIS represent time, position, drilling pressure, torque, rotational speed, drilling speed, and displacement, respectively, and the coding layer adopts the seq2seq sequence model.

[0030] The first multi-tower network layer comprises three tower networks, used to process the first feature vector to generate three intermediate vectors corresponding to lithology (LITH), rock mass compressive strength (RC), and rock mass integrity (KV) in the initial model data, and to transmit the three intermediate vectors to the memory layer; each tower network consists of N layers of LSTM neural networks:

[0031]

[0032]

[0033] Where N is the number of layers, which can be 2-4.

[0034] The memory layer is used to remember the values ​​from time tT to time t. The three intermediate vectors are used to obtain the memory vector, which is then input into the second multi-tower network layer. , Where T is the memory cycle.

[0035] The second multi-tower network layer also includes three tower networks, used to process the memory vectors and generate three decoded vectors corresponding to the lithology LITH, rock mass compressive strength RC, and rock mass integrity KV in the initial model data, and transmit the three decoded vectors to the decoding layer; each tower network consists of N layers of LSTM neural networks:

[0036]

[0037]

[0038] Where N is the number of layers, which can be 2-4.

[0039] The decoding layer comprises four decoding sub-modules. The first decoding sub-module processes the first decoding vector to obtain the lithology LITH. The second decoding sub-module processes the second decoding vector to obtain the rock mass compressive strength RC. The third decoding sub-module processes the third decoding vector to obtain the rock mass integrity KV. The fourth decoding sub-module processes the first, second, and third decoding vectors to obtain the surrounding rock grade RANK.

[0040]

[0041]

[0042]

[0043] in, , , These correspond to lithology (LITH), rock mass compressive strength (RC), rock mass integrity (KV), and surrounding rock grade (RANK), respectively; First decoding submodule Fourth decoding submodule Using a classification model, the first decoding submodule Fourth decoding submodule A generative model is used.

[0044] The fourth decoding submodule is used to process the first, second, and third decoding vectors to obtain the surrounding rock grade RANK, specifically including: The first decoded vector, the second decoded vector, and the third decoded vector are concatenated to obtain the first concatenated vector: ; The fourth decoding submodule is used to decode the first concatenated vector to obtain the surrounding rock grade: .

[0045] The output layer is used to output the results obtained from the decoding layer.

[0046] S2: Acquire the detection data collected by the detection equipment, and process the detection data to obtain the first model data.

[0047] The detection data in step S2 includes 3D point cloud data and imaging data. The processing of the detection data to obtain the first model data specifically includes: The three-dimensional point cloud data is identified based on the pre-trained first recognition model to obtain the inclined shaft geometric parameters. The inclined shaft geometric parameters include at least the position POS and the inclined shaft contour corresponding to the position POS. The pre-trained second recognition model is used to identify the imaging data and obtain the geological parameters of the inclined well. The geological parameters of the inclined well include at least the location POS and the geological body type, occurrence and lithology corresponding to the location POS.

[0048] The advanced detection device is equipped with a 3D laser scanning unit, enabling rapid 360° scanning and detection of the inclined shaft to obtain 3D point cloud data (3DPoint). By identifying the 3D point cloud data, the geometric parameters of the inclined shaft are obtained, including at least its location and contour. The pre-trained first recognition model uses the ConvPoint model, a convolutional neural network model based on continuous convolutional layers; alternatively, models such as PointNet, PointCNN, and KPConv can also be used.

[0049] in These are the geometric parameters of the inclined shaft, including at least the position POS and the inclined shaft profile corresponding to that position POS.

[0050] Simultaneously, the intelligent robot is equipped with a high-definition camera to acquire imaging data from within the inclined shaft. By identifying this imaging data, the geological parameters of the inclined shaft are obtained. These parameters include the type, occurrence, and lithology of geological bodies at different locations. The pre-trained second recognition model uses a stacked convolutional neural network model (CNN_STACKED), but various modified convolutional neural networks can also be used.

[0051] in Geological parameters for the deviated well include at least its location and the type, occurrence, and lithology of the geological body at that location.

[0052] S3: Merge the first model data and the initial model data to obtain the first BIM model data, specifically including: The first sub-model data is constructed based on the geometric parameters of the inclined shaft; the first sub-model data includes the location POS and the inclined shaft profile CONT. The second sub-model data is constructed based on the geological parameters of the inclined shaft; the second sub-model data includes location (POS), geological body type (GB_CAT), geological body occurrence (GB_ATT), and lithology (LITH); The first sub-model data, the second sub-model data, and the initial model data are merged to obtain the first BIM model data; based on the location POS, the first sub-model data, the second sub-model data, and the initial model data are correlated and merged to obtain the first BIM model data X. BIM Location (POS), surrounding rock grade (RANK), lithology (LITH), integrity (KV), deviated shaft profile (CONT), geological body category (GB_CAT), geological body occurrence (GB_ATT).

[0053] After calculating and obtaining the first sub-model data and the second sub-model data, the advanced detection body also transmits the first sub-model data and the second sub-model data to the integrated control platform in real time. The integrated control platform generates the inclined shaft BIM model based on the first sub-model data, the second sub-model data and the initial model data.

[0054] S4: Input the first BIM model data into the driving model to obtain the first driving data, specifically: Obtain a pre-trained driving model; obtain second driving data at multiple time points of the advanced probe; input the first BIM model data and the second driving data at multiple time points into the driving model to generate the first driving data.

[0055] In one embodiment, the advanced detection body employs a tracked displacement device, therefore the drive data uses velocity SP, acceleration ACC, and azimuth ORI, i.e., the drive data can be expressed as:

[0056] In another embodiment, the advanced detection body employs a four-wheel or multi-wheel displacement device, therefore the first driving data also includes the azimuth angle of each wheel, i.e., the driving data can be expressed as: ,in Let be the azimuth angle of the k-th wheel at time t.

[0057] The driving model adopts an encoder-decoder architecture. The encoder includes a first encoding module and a second encoding module. The first encoding module encodes the first BIM model data to obtain a first vector. Since different data in the first BIM model data have varying impacts on the detection, different weights are used for different feature data. For example, higher weights are applied to surrounding rock grade (RANK), lithology (LITH), integrity (KV), shaft outline (CONT), and geological body category (GB_CAT), while lower weights are applied to location (POS) and geological body attitude (GB_ATT). The first encoding module uses a convolutional neural network model based on an attention mechanism. .

[0058] The second encoding module is used to encode the second driving data at multiple time points to obtain the second vector. The second encoding module adopts the BILSTM model.

[0059] , where n can be obtained based on the actual calculation accuracy and efficiency.

[0060] Decoder is used for and The concatenated vector is decoded to obtain the first driving data, specifically... Decoder BI_LSTM network.

[0061] Similarly, when the advanced detection body uses a tracked displacement device, the predicted first driving data can be expressed as:

[0062] When the advanced detection body uses a four-wheel or multi-wheel displacement device, the predicted first driving data can be expressed as: ,in To predict the azimuth angle of the k-th wheel at time t+1.

[0063] S5: Drive the advanced probe to move according to the first driving data.

[0064] The driving data generated by the driving model can drive the advanced detection body to move slowly at locations with low surrounding rock grade, poor integrity, incomplete well outline (e.g., protrusions and depressions), geological intrusions, and cracks. It can also drive the advanced detection body to move rapidly at locations with high surrounding rock grade, good integrity, intact well outline, and little or no lithological change.

[0065] S6: Update the initial model data using the first BIM model data; The initial model data is updated using the first BIM model data. Specifically, the first BIM model data at the current moment and the initial model data are used together as the initial model data for the next moment.

[0066] S7: Repeat steps S2-S6 until the advance detection of the inclined shaft is completed.

[0067] See Figure 2 and Figure 3 This invention also proposes an adaptive control method for advanced detection of inclined shafts in water conservancy and hydropower projects, applied to an integrated control platform. The method includes: SA: Acquire deviated well drilling data; SB: Input the deviated well drilling data into the preset third identification model to obtain initial model data; SC: In response to the acquisition request of the advanced detector, the initial model data is sent to the advanced detector so that the advanced detector can be adaptively driven according to the method of steps S1-S7.

[0068] The integrated control platform can be deployed on a central server or applied to edge servers. The integrated control platform acquires the deviated well drilling sequence data and uses a preset third identification model to identify the deviated well drilling sequence data. The method for obtaining the initial model data has been described in detail previously and will not be repeated here.

[0069] During the exploration process of the advanced probe, the integrated management and control platform also obtains the first sub-model data and the second sub-model data from the advanced probe in real time, and generates the inclined shaft BIM model based on the first sub-model data, the second sub-model data and the initial model data, and sends the inclined shaft BIM model to at least one client for display.

[0070] The inclined shaft BIM model is generated based on the first sub-model data, the second sub-model data, and the initial model data. Specifically, the initial model data is used as the first layer data of the inclined shaft BIM model, the first sub-model data is used as the second layer data of the inclined shaft BIM model, and the second sub-model data is used as the third layer data of the inclined shaft BIM model. The first layer data, the second layer data, and the third layer data are superimposed layer by layer to generate the inclined shaft BIM model.

[0071] See Figure 4 The present invention also proposes an advanced detector driven by the aforementioned adaptive control method, the detector comprising: a first data acquisition module, a second data acquisition module, a data acquisition module, a first data processing module, a second data processing module, a driving module, and an updating module; The first data acquisition module is used to acquire the initial model data of the data deviated shaft from the integrated control platform; The second data acquisition module is used to acquire configuration data from the client; the acquired configuration data includes at least the acquisition parameters of each collector. The data acquisition module is used to collect deviated shaft exploration data during the advanced exploration process; The first data processing module is used to process the probe data to obtain the first model data, and to fuse the first model data and the initial model data to obtain the first BIM model data; The second data processing module is used to input the first BIM model data into the driving model to obtain the first driving data; The drive module is used to drive the advanced probe to move according to the first drive data; The update module is used to update the initial model data using the first BIM model data.

[0072] The data acquisition module includes a first acquisition submodule and a second acquisition submodule. The first acquisition submodule uses a 3D laser scanning device to achieve rapid scanning and detection of the inclined shaft over a 360° area, thereby obtaining 3D point cloud data (3DPoint). The second acquisition submodule uses a high-definition camera device to obtain imaging data (Image) from within the inclined shaft.

[0073] The first data processing module processes the probe data to obtain the first model data, specifically including: A pre-trained first recognition model is used to identify 3D point cloud data and obtain the geometric parameters of the inclined shaft. The geometric parameters of the inclined shaft include at least its location and contour. The pre-trained first recognition model adopts the ConvPoint model, a convolutional neural network model based on continuous convolutional layers; other models such as PointNet, PointCNN, and KPConv can also be used. A pre-trained second recognition model is used to identify the imaging data and obtain the geological parameters of the inclined well. The geological parameters of the inclined well include the type, occurrence, and lithology of geological bodies at different locations. The pre-trained second recognition model uses the stacked convolutional neural network model CNN_STACKED, but various variations of convolutional neural networks can also be used.

[0074] By integrating the first model data and the initial model data, the first BIM model data is obtained, which specifically includes: The first sub-model data is constructed based on the geometric parameters of the inclined shaft; the first sub-model data includes the location POS and the inclined shaft profile CONT. The second sub-model data is constructed based on the geological parameters of the inclined shaft; the second sub-model data includes location (POS), geological body type (GB_CAT), geological body occurrence (GB_ATT), and lithology (LITH); The first sub-model data, the second sub-model data, and the initial model data are merged to obtain the first BIM model data; based on the location POS, the first sub-model data, the second sub-model data, and the initial model data are correlated and merged to obtain the first BIM model data X. BIM Location (POS), surrounding rock grade (RANK), lithology (LITH), integrity (KV), deviated shaft profile (CONT), geological body category (GB_CAT), geological body occurrence (GB_ATT).

[0075] The second data processing module inputs the first BIM model data into the driving model to obtain the first driving data. Specifically, this includes: acquiring a pre-trained driving model; acquiring second driving data of the advanced probe at multiple times; and inputting the first BIM model data and the second driving data at multiple times into the driving model to generate the first driving data.

[0076] The driving module drives the advanced probe to move according to the first driving data. Specifically, this includes: driving the advanced probe to move according to the first driving data. The driving data generated by the driving model can drive the advanced probe to move slowly at locations with low surrounding rock grade, poor integrity, incomplete well outline (e.g., protrusions and depressions), geological intrusions, and fractures. It can also drive the advanced probe to move rapidly at locations with high surrounding rock grade, good integrity, intact well outline, and little or no lithological change.

[0077] The update module updates the initial model data using the first BIM model data, specifically by using the first BIM model data and the initial model data at the current moment together as the initial model data for the next moment.

[0078] This invention also proposes a comprehensive control platform, which is deployed on a central server or an edge server, and the platform includes: The first acquisition module is used to acquire deviated well drilling sequence data; The first processing module is used to input the deviated well drilling sequence data into a preset third identification model to obtain initial model data; The first sending module is used to send the initial model data to the advanced detector in response to the acquisition request of the advanced detector, so as to realize the adaptive driving of the advanced detector.

[0079] The integrated management and control platform also includes: The second acquisition module is used to acquire the first sub-model data and the second sub-model data from the advanced probe in real time. The second processing module is used to generate the inclined shaft BIM model based on the first sub-model data, the second sub-model data, and the initial model data. The second sending module is used to send the inclined shaft BIM model to at least one client for display.

[0080] The inclined shaft BIM model is generated based on the first sub-model data, the second sub-model data, and the initial model data. Specifically, the initial model data is used as the first layer data of the inclined shaft BIM model, the first sub-model data is used as the second layer data of the inclined shaft BIM model, and the second sub-model data is used as the third layer data of the inclined shaft BIM model. The first layer data, the second layer data, and the third layer data are superimposed layer by layer to generate the inclined shaft BIM model.

[0081] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0082] The memory in this embodiment of the invention can be volatile memory or non-volatile memory, or may include both. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the methods described in this invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0083] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The steps of the method disclosed in the embodiments of this application can be directly implemented by a hardware processor, or by a combination of hardware and software modules in the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0084] It should be noted that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiments can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above methods.

[0085] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. An adaptive control method for advance detection of inclined shafts in water conservancy and hydropower projects, applied to advance detection bodies, characterized in that, The method includes: S1: Obtain the initial model data of the deviated well from the control platform. The initial model data is obtained based on the deviated well drilling data. S2: Acquire the detection data collected by the detection equipment, and process the detection data to obtain the first model data; S3: Merge the first model data and the initial model data to obtain the first BIM model data; S4: Input the first BIM model data into the driving model to obtain the first driving data; S5: Drive the advanced detector to move according to the first driving data; S6: Update the initial model data using the first BIM model data; S7: Repeat steps S2-S6 until the advance detection of the inclined shaft is completed.

2. The adaptive control method for advance detection of inclined shafts in water conservancy and hydropower projects according to claim 1, characterized in that, The detection data in step S2 includes three-dimensional point cloud data and imaging data. The processing of the detection data to obtain the first model data specifically includes: The first recognition model, which is pre-trained, is used to identify three-dimensional point cloud data and obtain the geometric parameters of the inclined shaft. The geometric parameters of the inclined shaft include at least the location and the contour of the inclined shaft corresponding to the location. The pre-trained second recognition model is used to identify the imaging data and obtain the geological parameters of the inclined well. The geological parameters of the inclined well include at least the location and the geological body type, occurrence and lithology corresponding to the location.

3. The adaptive control method for advance detection of inclined shafts in water conservancy and hydropower projects according to claim 2, characterized in that, Step S3, which involves fusing the first model data and the initial model data to obtain the first BIM model data, specifically includes: The first sub-model data is constructed based on the geometric parameters of the inclined shaft; The second sub-model data was constructed based on the geological parameters of the inclined shaft; The first sub-model data, the second sub-model data, and the initial model data are merged to obtain the first BIM model data.

4. The adaptive control method for advance detection of inclined shafts in water conservancy and hydropower projects according to claim 3, characterized in that, In step S4, the first BIM model data is input into the driving model to obtain the first driving data, specifically including: Obtain the pre-trained driving model; Acquire second driving data of the advanced probe at multiple moments; The first BIM model data and the second driving data at multiple times are input into the driving model to generate the first driving data.

5. The adaptive control method for advance detection of inclined shafts in water conservancy and hydropower projects according to claim 3 or 4, characterized in that, The method further includes: transmitting the first sub-model data and the second sub-model data to the integrated control platform in real time, wherein the integrated control platform generates a BIM model of the inclined shaft based on the first sub-model data, the second sub-model data and the initial model data.

6. An adaptive control method for advance detection of inclined shafts in water conservancy and hydropower projects, applied to an integrated control platform, characterized in that, The method includes: Acquire deviated well drilling sequence data; The deviated well drilling sequence data is input into a preset third identification model to obtain initial model data; In response to a request to acquire a leading probe, the initial model data is sent to the leading probe as described in any one of claims 1-5.

7. The adaptive control method for advance detection of inclined shafts in water conservancy and hydropower projects according to claim 6, characterized in that, The deviated well drilling sequence data includes at least time, location, drilling pressure, torque, rotational speed, drilling speed, and displacement; the initial model data includes at least location, lithology, rock mass compressive strength, rock mass integrity, and surrounding rock grade; the pre-trained third recognition model is a multi-object recognition model. The step of inputting the deviated well drilling sequence data into the pre-trained third recognition model to obtain initial model data specifically includes: inputting the deviated well drilling sequence data into the multi-target recognition model and outputting the initial model data.

8. The adaptive control method for advance detection of inclined shafts in water conservancy and hydropower projects according to claim 6, characterized in that, The method further includes: First sub-model data and second sub-model data are obtained from the advanced probe. The first sub-model data is constructed based on the geometric parameters of the inclined shaft, and the second sub-model data is constructed based on the geological parameters of the inclined shaft. Generate the inclined shaft BIM model based on the first sub-model data, the second sub-model data, and the initial model data; The BIM model of the inclined shaft is sent to at least one client for display.

9. A forward detection device driven by the adaptive control method according to any one of claims 1-5, characterized in that, The advanced detection device includes a first data acquisition module, a second data acquisition module, a data collection module, a first data processing module, a second data processing module, a driving module, and an update module; The first data acquisition module is used to acquire the initial model data of the data deviator from the integrated control platform; The second data acquisition module is used to obtain configuration data from the client; The data acquisition module is used to acquire deviated well detection data during the advanced detection process; The first data processing module is used to process the probe data to obtain the first model data, and to fuse the first model data and the initial model data to obtain the first BIM model data; The second data processing module is used to input the first BIM model data into the driving model to obtain the first driving data; The driving module is used to drive the advanced detector to move according to the first driving data; The update module is used to update the initial model data using the first BIM model data.

10. A computer-readable storage medium for storing computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-5 or the method according to any one of claims 6-8.

Images