Deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system and method

Abstract

The present application relates to a system and method for multi-source information fusion and in-situ stereoscopic perspective of deep-earth adverse geology, wherein the system includes: a multi-source information interpretation system for performing multi-source data interpretation of adverse geology based on downhole seismic exploration data, downhole radar detection data, downhole borehole wall scanning data, downhole drilling power data, downhole seepage field data, and downhole temperature field data of a target deep-earth engineering project; a multi-source information fusion system for complementary fusion of seismic interpretation images, radar interpretation images, three-dimensional borehole wall images, formation rock mass parameters, seepage field images, and temperature field images of the multi-source data interpretation images; and an adverse geology mapping system. This solves the problems in related technologies such as the difficulty in interpreting and fusion imaging of multi-source geological information, the inability to achieve in-situ stereoscopic perspective of deep-earth adverse geology, and the reduced ability to identify geological interfaces and the accuracy of adverse geology prediction.

Description

Technical Field

[0001] The present application relates to the technical field of deep-earth adverse geological exploration, and in particular to a deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system and method. Background Art

[0002] Since the beginning of the 21st century, my country has seen rapid growth in the development and utilization of underground space, making it a veritable leader in underground space development and utilization. Underground space development is gradually moving from shallow to deep layers. Deep underground engineering construction faces an extremely complex geological environment. High ground stress, high ground temperature, and high osmotic pressure create a high risk of geological disasters and pose significant risks. Advancing detection and stereoscopic imaging of unfavorable geology in deep underground engineering projects, and achieving transparent geological construction, have become key challenges that require urgent resolution.

[0003] In related technologies, image processing and feature parameter extraction can be used to achieve rapid collection of rock structure information, advanced geological prediction methods can be used to determine the approximate fuzzy position of special geological bodies, and continuous dynamic tracking and recording can be carried out. The development characteristics and occurrence patterns of joints near special geological bodies such as faults can be used to integrate advanced geological prediction, preliminary engineering survey data and rock structure information database to achieve multi-source heterogeneous information fusion analysis of special geological bodies in fractured rock masses.

[0004] However, in related technologies, it is difficult to interpret and fuse multi-source geological information, and it is impossible to achieve in-situ three-dimensional perspective of deep-ground adverse geology, which reduces the ability to identify geological interfaces and the accuracy of adverse geological predictions, and urgently needs to be solved.

[0005] Application Contents

[0006] The present application provides a system and method for multi-source information fusion and in-situ stereoscopic perspective of deep-earth adverse geology to solve the problems in related technologies such as difficulty in interpreting and fusion imaging of multi-source geological information, inability to achieve in-situ stereoscopic perspective of deep-earth adverse geology, reduced ability to identify geological interfaces and reduced accuracy of adverse geology prediction.

[0007] A first embodiment of the present application provides a deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system, including: a multi-source information interpretation system for performing adverse geological multi-source data interpretation on downhole seismic exploration data, downhole radar detection data, downhole borehole wall scanning data, downhole drilling power data, downhole seepage field data and downhole temperature field data of a target deep-earth engineering project, and obtaining a seismic interpretation image, a radar interpretation image, a three-dimensional borehole wall image, formation rock mass parameters, a seepage field image and a temperature field image of the multi-source data interpretation image; a multi-source information fusion system for complementary fusing the seismic interpretation image, the radar interpretation image, the three-dimensional borehole wall image, formation rock mass parameters, the seepage field image and the temperature field image of the multi-source data interpretation image , generating fused interpretation images for different adverse geological bodies; an adverse geological mapping system, used to perform fused image data enhancement and adverse geological label annotation on the fused interpretation image to obtain an image recognition model training set, and use the image recognition model training set to train a model, wherein the input feature blocks and regional candidate blocks are collected through a convolutional feature extraction network, a regional candidate network, and a target area pooling network, and the feature blocks of the target area are extracted and sent to a subsequent fully connected layer to construct an adverse geological image recognition model, so as to input the fused interpretation image of any adverse geological body of the target deep earth engineering into the adverse geological image recognition model, and output at least one of the type, location, and scale information of the global adverse geological body.

[0008] Optionally, in one embodiment of the present application, it further includes: an in-situ stereoscopic perspective system for obtaining in-situ stereoscopic perspective information of the adverse geology according to at least one of the type, location and scale information of the global adverse geology body.

[0009] Optionally, in one embodiment of the present application, the adverse geological body includes at least one of a fault fracture zone, a water-rich stratum, a weak surrounding rock, a karst stratum and groundwater.

[0010] Optionally, in one embodiment of the present application, it also includes: a data acquisition system for collecting downhole seismic exploration data, downhole radar detection data, downhole wall scanning data, downhole drilling power data, downhole seepage field data and downhole temperature field data of the target deep earth engineering.

[0011] Optionally, in one embodiment of the present application, the multi-source information fusion system is also used to extract features from the seismic interpretation image, the radar interpretation image, the three-dimensional hole wall image, the formation rock parameters, the seepage field image and the temperature field image in the order of poor geological detection range from large to small, detection accuracy from low to high, and sensitivity from small to large, to obtain corresponding poor geological feature images, and perform complementary fusion based on the poor geological feature images and corresponding weights.

[0012] The second embodiment of the present application provides a method for multi-source information fusion and in-situ stereoscopic perspective of deep-earth adverse geology, including the following steps: performing multi-source data interpretation of adverse geology on downhole seismic exploration data, downhole radar detection data, downhole borehole wall scanning data, downhole drilling power data, downhole seepage field data and downhole temperature field data of the target deep-earth engineering, and obtaining seismic interpretation images, radar interpretation images, three-dimensional borehole wall images, formation rock parameters, seepage field images and temperature field images of the multi-source data interpretation images; complementary fusion of the seismic interpretation images, radar interpretation images, three-dimensional borehole wall images, formation rock parameters, seepage field images and temperature field images of the multi-source data interpretation images, and generating a targeted deep-earth adverse geology information fusion method. The method comprises the following steps: performing fusion interpretation image data enhancement and bad geological labeling on the fused interpretation image to obtain an image recognition model training set, and using the image recognition model training set to train a model, wherein the input feature blocks and region candidate blocks are collected through a convolutional feature extraction network, a region candidate network, and a target area pooling network, and the feature blocks of the target area are extracted and fed into a subsequent fully connected layer to construct a bad geological image recognition model, so as to input the fused interpretation image of any bad geological body of the target deep earth engineering into the bad geological image recognition model, and output at least one of the type, location, and scale information of the global bad geological body.

[0013] Optionally, in one embodiment of the present application, the method further comprises: obtaining in-situ stereoscopic perspective information of the adverse geology according to at least one of the type, location and scale information of the global adverse geology body.

[0014] Optionally, in one embodiment of the present application, before performing adverse geological multi-source data interpretation on the downhole seismic exploration data, downhole radar detection data, downhole wall scanning data, downhole power data, downhole seepage field data and downhole temperature field data of the target deep earth engineering, it also includes: collecting the downhole seismic exploration data, downhole radar detection data, downhole wall scanning data, downhole power data, downhole seepage field data and downhole temperature field data of the target deep earth engineering.

[0015] The third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective method as described in the above embodiment.

[0016] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned deep-earth poor geological multi-source information fusion and in-situ stereoscopic perspective system method.

[0017] The present application embodiment establishes a nonlinear mapping model between multi-source information fusion imaging results and deep-earth engineering adverse geology, enhancing the ability to identify geological interfaces, improving the accuracy of adverse geology predictions, and achieving in-situ, 3D, and refined perspective imaging of deep-earth engineering adverse geology. This solves the problems encountered in related technologies, such as the difficulty in interpreting and fusion imaging of multi-source geological information, the inability to achieve in-situ 3D perspective of deep-earth adverse geology, and the reduced ability to identify geological interfaces and the reduced accuracy of adverse geology predictions.

[0018] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0020] Figure 1 Schematic diagram of the structure of a deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system provided according to an embodiment of the present application;

[0021] Figure 2 Schematic diagram of the principle of a system for fusion of multi-source information of deep-earth adverse geological conditions and in-situ stereoscopic perspective according to one embodiment of the present application;

[0022] Figure 3 This is a flow chart of a method for fusion of multi-source information of deep-earth adverse geological conditions and in-situ stereoscopic perspective according to an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0025] The following describes the deep-earth bad geology multi-source information fusion and in-situ stereoscopic perspective system and method of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that it is difficult to interpret and fuse multi-source geological information and to realize in-situ stereoscopic perspective of deep-earth bad geology in the related technologies mentioned in the above background technology, and that the identification ability of geological interfaces and the accuracy of bad geology prediction are reduced, the present application provides a deep-earth bad geology multi-source information fusion and in-situ stereoscopic perspective method, in which a nonlinear mapping model can be established between the multi-source information fusion imaging results and deep-earth engineering bad geology, to enhance the identification ability of geological interfaces, improve the accuracy of bad geology prediction, and realize in-situ three-dimensional refined perspective imaging of deep-earth engineering bad geology. Thus, it solves the problems in the related technologies that it is difficult to interpret and fuse multi-source geological information and to realize in-situ stereoscopic perspective of deep-earth bad geology, and that the identification ability of geological interfaces and the accuracy of bad geology prediction are reduced.

[0026] Specifically, Figure 1 This is a structural diagram of a deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system provided in an embodiment of the present application.

[0027] like Figure 1 As shown, the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system 10 includes: a multi-source information interpretation system 100, a multi-source information fusion system 200 and an adverse geological mapping system 300.

[0028] Specifically, the multi-source information interpretation system 100 is used to interpret the multi-source data of adverse geology for the downhole seismic exploration data, downhole radar detection data, downhole wall scanning data, downhole drilling dynamics data, downhole seepage field data and downhole temperature field data of the target deep earth project, and obtain the seismic interpretation image, radar interpretation image, three-dimensional hole wall image, formation rock parameters, seepage field image and temperature field image of the multi-source data interpretation image.

[0029] During actual implementation, the multi-source information interpretation system 100 in the embodiment of the present application can perform, but is not limited to, interpretation of multi-source data of adverse geology on downhole seismic exploration data, downhole radar detection data, downhole wall scanning data, downhole drilling power data, downhole seepage field data, and downhole temperature field data of the target deep earth project, and obtain seismic interpretation images, radar interpretation images, three-dimensional hole wall images, formation rock parameters, seepage field images, and temperature field images of the multi-source data interpretation images.

[0030] Among them, the downhole seismic exploration data in the embodiment of the present application realizes high-quality imaging of the strata in front and to the sides of the drill bit based on the seismic reverse time migration method; the downhole radar detection data realizes large-scale and high-resolution imaging of the radial strata of the borehole based on the spatial constraint migration imaging of the borehole ground-penetrating radar; the downhole wall scanning data can be interpreted as a three-dimensional borehole wall image; the downhole drilling power data can obtain the physical laws of rock-machine parameter mapping by conducting drilling tests on rocks of different lithologies, complete the rock-machine parameter calibration of the drilling equipment, and realize the inversion of the formation rock mass parameters; the downhole seepage field data and the downhole temperature field data can be interpreted as seepage field images and temperature field images that advance axially and distribute radially along the borehole.

[0031] The embodiments of the present application can realize the interpretation of multi-source data of adverse geology, provide a basis for subsequent multi-source information fusion imaging and construction of adverse geology image recognition model, thereby realizing in-situ stereoscopic perspective of adverse geology, enhancing the recognition ability of geological interfaces, and improving the accuracy of adverse geology prediction.

[0032] The multi-source information fusion system 200 is used to complementarily fuse seismic interpretation images, radar interpretation images, three-dimensional hole wall images, formation rock parameters, seepage field images and temperature field images of multi-source data interpretation images to generate fused interpretation images for different adverse geological bodies.

[0033] As a possible implementation, the multi-source information fusion system 200 in the embodiments of the present application is used to complementarily fuse multi-source data interpretation images, including seismic interpretation images, radar interpretation images, three-dimensional borehole wall images, formation rock mass parameters, seepage field images, and temperature field images, to generate fused interpretation images for different unfavorable geological bodies. The embodiments of the present application can achieve unfavorable geological interpretation image fusion, providing a basis for the subsequent establishment of a nonlinear mapping model between the multi-source information fusion imaging results and unfavorable geology in deep earth engineering, thereby further enhancing the ability to identify geological interfaces and improving the accuracy of unfavorable geological prediction.

[0034] Optionally, in one embodiment of the present application, the multi-source information fusion system 200 is also used to extract features from seismic interpretation images, radar interpretation images, three-dimensional borehole wall images, formation rock parameters, seepage field images and temperature field images in the order of poor geological detection range from large to small, detection accuracy from low to high, and sensitivity from small to large, to obtain corresponding poor geological feature images, and perform complementary fusion based on the poor geological feature images and corresponding weights.

[0035] In some embodiments, the multi-source information fusion system 200 is also used to extract features from seismic interpretation images, radar interpretation images, three-dimensional borehole wall images, formation rock parameters, seepage field images and temperature field images in the order of extraction of poor geological detection range from large to small, detection accuracy from low to high, and sensitivity from small to large, to obtain corresponding poor geological feature images. The poor geological feature images determine feature image weights according to the different types of poor geological bodies detected, and perform complementary fusion to obtain fused interpretation images for different poor geological bodies, thereby ensuring that complementary fusion interpretation solutions can be obtained based on the sensitivity differences of different detection data to different poor geological bodies. Combined with advanced technologies such as big data, artificial intelligence, image recognition, and data fusion, in-situ three-dimensional and refined perspective imaging of poor geological conditions in deep earth engineering can be realized, which can serve the construction of major national deep earth engineering projects and is of great significance to the safe, efficient and economic construction of deep earth engineering projects.

[0036] The adverse geology mapping system 300 is used to perform fusion image data enhancement and adverse geology labeling on the fused interpreted image to obtain an image recognition model training set, and use the image recognition model training set to train a model, wherein the input feature blocks and region candidate blocks are collected through a convolutional feature extraction network, a region candidate network, and a target area pooling network, and the feature blocks of the target area are extracted and sent to a subsequent fully connected layer to construct an adverse geology image recognition model, so that the fused interpreted image of any adverse geology body of the target deep earth project is input into the adverse geology image recognition model, and at least one of the type, location, and scale information of the global adverse geology body is output.

[0037] During the actual implementation process, the poor geological mapping system 300 in the embodiment of the present application is used to perform fusion image data enhancement on the fused interpretation image and perform poor geological labeling, wherein the fusion image data enhancement adopts the idea of ​​geometric transformation, such as mirroring, contrast transformation, random cropping, zooming in and out, etc., so that the network model learns more image-invariant features, obtains an image recognition model training set, and uses the image recognition model training set to train the model, such as collecting input feature blocks and region candidate blocks through a convolutional feature extraction network, a region candidate network, and a target area pooling network, and extracting the feature blocks of the target area and sending them to the subsequent fully connected layer to construct a poor geological image recognition model. The convolutional feature extraction network in the embodiment of the present application can extract feature blocks through the poor geological fusion interpretation image, generate region candidate blocks through the region candidate network, collect input feature blocks and region candidate blocks through the target area pooling network, and extract the feature blocks of the target area based on the comprehensive information and send them to the subsequent fully connected layer to determine the poor geological category.

[0038] In the embodiment of the present application, the fused interpretation image of any adverse geological body of the target deep earth project can be input into the adverse geological image recognition model. The adverse geological image recognition model uses the characteristic blocks of the target area to calculate the adverse geological category of the target area, and at the same time regresses the bounding box again to obtain the final precise position of the detection box, thereby realizing the extraction and category determination of the global adverse geological body in the adverse geological fused interpretation image, and outputting at least one of the type, location and scale information of the global adverse geological body.

[0039] The embodiment of the present application establishes a nonlinear mapping model between the multi-source information fusion imaging results and the unfavorable geology of deep earth engineering, thereby enhancing the recognition ability of geological interfaces, improving the accuracy of unfavorable geology prediction, and realizing refined three-dimensional perspective of deep earth unfavorable geology. At the same time, it realizes multi-source information fusion of multi-physical field detection of deep earth engineering and in-situ three-dimensional perspective imaging of unfavorable geology, providing prior information for underground engineering construction methods, construction equipment selection, construction period planning, and unfavorable geology avoidance and advance processing, thereby ensuring the safety of deep underground engineering construction, avoiding casualties and major economic losses, and having great significance for leading the development of intelligent disaster prevention and mitigation equipment for international deep underground space engineering.

[0040] Optionally, in one embodiment of the present application, the deep-earth unfavorable geological multi-source information fusion and in-situ stereoscopic perspective system 10 further includes an in-situ stereoscopic perspective system. The in-situ stereoscopic perspective system is configured to obtain in-situ stereoscopic perspective information of unfavorable geological bodies based on at least one of the type, location, and scale information of the global unfavorable geological bodies.

[0041] As a possible implementation method, the in-situ stereoscopic perspective system in the embodiment of the present application can identify the fused interpretation images of different adverse geological conditions through an adverse geological image recognition model, obtain the type, location and scale information of the global adverse geological body, and obtain the in-situ stereoscopic perspective information of the adverse geological condition based on at least one of the type, location and scale information of the global adverse geological body, thereby realizing the refined stereoscopic perspective of adverse geological conditions while drilling under deep-ground conditions.

[0042] Optionally, in one embodiment of the present application, the unfavorable geological body includes at least one of a fault fracture zone, a water-rich stratum, a weak surrounding rock, a karst stratum and groundwater.

[0043] In the actual implementation process, the embodiments of the present application can, but are not limited to, further realize the refined three-dimensional perspective of adverse geology while drilling under deep-ground conditions through adverse geological bodies such as fault fracture zones, water-rich strata, weak surrounding rocks, karst strata and groundwater. By making advanced identification of various adverse geological bodies, it ensures convenient data processing and operation, intuitive imaging results, good interpretability, and easy promotion and application.

[0044] Optionally, in one embodiment of the present application, the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system 10 further includes a data acquisition system. The data acquisition system is configured to acquire while-drilling seismic exploration data, while-drilling radar detection data, while-drilling borehole wall scanning data, while-drilling drilling dynamics data, while-drilling seepage field data, and while-drilling temperature field data of the target deep-earth engineering project.

[0045] As a possible implementation method, the embodiments of the present application can, but are not limited to, collect downhole seismic exploration data, downhole radar detection data, downhole wall scanning data, downhole drilling dynamics data, downhole seepage field data and downhole temperature field data of the target deep earth project through a data acquisition system, thereby further realizing in-situ three-dimensional perspective of deep-earth adverse geology, enhancing the ability to identify geological interfaces, and improving the accuracy of adverse geological prediction.

[0046] Specifically, it can be combined Figure 2 As shown, the working principle of the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system of the embodiment of the present application is described in detail with a specific embodiment.

[0047] like Figure 2 As shown, the embodiment of the present application can realize the multi-source information interpretation function, the multi-source information fusion function, the adverse geological mapping function and the in-situ stereoscopic perspective function.

[0048] Specifically, the multi-source information interpretation function in the embodiment of the present application can interpret and image the downhole seismic exploration data, downhole radar detection data, downhole wall scanning data, downhole drilling power data, downhole seepage field data and downhole temperature field data respectively, to realize the interpretation of multi-source data of poor geology.

[0049] The multi-source information fusion function in the embodiment of the present application can extract features from the seismic interpretation images, radar interpretation images, three-dimensional hole wall images, formation rock parameters, seepage field images and temperature field images obtained by the multi-source information interpretation system in the order of poor geological detection range from large to small, detection accuracy from low to high, and sensitivity from small to large, to obtain poor geological feature images. The poor geological feature images determine the feature image weights according to the different types of poor geological bodies detected, thereby performing complementary fusion to obtain fused interpretation images for different poor geological bodies.

[0050] The adverse geological mapping function in the embodiment of the present application can first perform fusion image data enhancement and adverse geological labeling, and then construct an adverse geological image recognition model through a convolutional feature extraction network, a region candidate network and a target area pooling network.

[0051] The in-situ stereoscopic perspective function in the embodiment of the present application can identify the fused interpretation images of different adverse geological conditions through the adverse geological image recognition model, obtain the type, location, and scale information of the adverse geological body, and realize the refined stereoscopic perspective of adverse geological conditions such as fault fracture zones, water-rich formations, weak surrounding rocks, karst formations, and groundwater while drilling under deep conditions.

[0052] The multi-source information fusion and in-situ stereoscopic perspective system for deep-earth adverse geology, proposed in an embodiment of this application, can establish a nonlinear mapping model between the multi-source information fusion imaging results and deep-earth adverse geology, enhancing the ability to identify geological interfaces, improving the accuracy of adverse geology predictions, and achieving in-situ, refined stereoscopic perspective imaging of deep-earth adverse geology. This solves the problem in related technologies of difficulty in interpreting and fusion imaging of multi-source geological information, the inability to achieve in-situ stereoscopic perspective of adverse geology, and the reduced ability to identify geological interfaces and the accuracy of adverse geology predictions.

[0053] Next, the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective method proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0054] Figure 3 It is a flow chart of the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective method of an embodiment of the present application.

[0055] like Figure 3 As shown in the figure, the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective method includes the following steps:

[0056] In step S301, multi-source data interpretation of adverse geology is performed on the while-drilling seismic exploration data, while-drilling radar detection data, while-drilling borehole wall scanning data, while-drilling drilling power data, while-drilling seepage field data, and while-drilling temperature field data of the target deep earth engineering to obtain seismic interpretation images, radar interpretation images, three-dimensional borehole wall images, formation rock parameters, seepage field images, and temperature field images of the multi-source data interpretation images.

[0057] In step S302, seismic interpretation images, radar interpretation images, three-dimensional borehole wall images, formation rock mass parameters, seepage field images and temperature field images of multi-source data interpretation images are complementary fused to generate fused interpretation images for different adverse geological bodies.

[0058] In step S303, the fused interpreted image is enhanced and poor geological labels are annotated to obtain an image recognition model training set, and the image recognition model training set is used to train the model, wherein the input feature blocks and region candidate blocks are collected through the convolutional feature extraction network, the region candidate network and the target area pooling network, and the feature blocks of the target area are extracted and sent to the subsequent fully connected layer to construct a poor geological image recognition model, so that the fused interpreted image of any poor geological body of the target deep earth engineering is input into the poor geological image recognition model, and at least one of the type, location and scale information of the global poor geological body is output.

[0059] Optionally, in one embodiment of the present application, the method further includes obtaining in-situ stereoscopic perspective information of the adverse geology according to at least one of the type, location and scale information of the global adverse geology body.

[0060] Optionally, in one embodiment of the present application, before performing adverse geological multi-source data interpretation on the downhole seismic exploration data, downhole radar detection data, downhole wall scanning data, downhole power data, downhole seepage field data and downhole temperature field data of the target deep earth engineering, it also includes: collecting the downhole seismic exploration data, downhole radar detection data, downhole wall scanning data, downhole power data, downhole seepage field data and downhole temperature field data of the target deep earth engineering.

[0061] It should be noted that the above explanation of the embodiment of the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system is also applicable to the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective method of this embodiment, and will not be repeated here.

[0062] The multi-source information fusion and in-situ stereoscopic perspective method for deep-earth adverse geology proposed in the embodiments of this application establishes a nonlinear mapping model between the multi-source information fusion imaging results and deep-earth adverse geology, enhancing the ability to identify geological interfaces, improving the accuracy of adverse geology predictions, and achieving in-situ, refined stereoscopic perspective imaging of deep-earth adverse geology. This solves the problem in related technologies of difficulty in interpreting and fusion imaging of multi-source geological information, the inability to achieve in-situ stereoscopic perspective of deep-earth adverse geology, and reduced ability to identify geological interfaces and the accuracy of adverse geology predictions.

[0063] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0064] Memory 401 , processor 402 , and computer programs stored in the memory 401 and executable on the processor 402 .

[0065] When the processor 402 executes the program, the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective method provided in the above-mentioned embodiment is implemented.

[0066] Furthermore, the electronic device further includes:

[0067] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0068] The memory 401 is used to store computer programs that can be run on the processor 402 .

[0069] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0070] If the memory 401, the processor 402, and the communication interface 403 are implemented independently, the communication interface 403, the memory 401, and the processor 402 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0071] Optionally, in a specific implementation, if the memory 401 , the processor 402 and the communication interface 403 are integrated on a chip, the memory 401 , the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0072] The processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0073] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system method.

[0074] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0075] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0076] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0077] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0078] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0079] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0080] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0081] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective system, characterized by: include: The multi-source information interpretation system is used to interpret the multi-source data of adverse geology from the target deep-earth engineering's seismic exploration data, radar detection data, borehole wall scanning data, drilling power data, seepage field data, and temperature field data. The system obtains seismic interpretation images, radar interpretation images, 3D borehole wall images, formation rock mass parameters, seepage field images, and temperature field images from the multi-source data interpretation images. The multi-source information fusion system is used to extract features from the seismic interpretation image, the radar interpretation image, the three-dimensional hole wall image, the formation rock mass parameters, the seepage field image and the temperature field image in the order of poor geological detection range from large to small, detection accuracy from low to high, and sensitivity from small to large, to obtain corresponding poor geological feature images, and to perform complementary fusion based on the poor geological feature images and corresponding weights to obtain fused interpretation images for different poor geological bodies, so as to obtain complementary fusion interpretation solutions based on the sensitivity differences of different detection data for different poor geological bodies; the poor geological mapping system is used to perform fusion image data enhancement and poor geological label annotation on the fused interpretation image to obtain image recognition A recognition model training set is prepared, and a model is trained using the image recognition model training set, wherein the input feature blocks and region candidate blocks are collected through a convolutional feature extraction network, a region candidate network, and a target area pooling network, and the feature blocks of the target area are extracted and sent to a subsequent fully connected layer, and an unfavorable geological image recognition model is constructed, so that the fused interpretation image of any unfavorable geological body of the target deep earth engineering is input into the unfavorable geological image recognition model, and at least one of the type, location, and scale information of the global unfavorable geological body is output, and a nonlinear mapping model between the multi-source information fusion imaging result and the unfavorable geological body of the deep earth engineering is established; wherein the unfavorable geological body includes at least one of a fault fracture zone, a water-rich stratum, a weak surrounding rock, a karst stratum, and groundwater; The invention also includes: an in-situ stereoscopic perspective system for obtaining in-situ stereoscopic perspective information of the bad geology according to at least one of the type, location and scale information of the global bad geology body; It also includes: a data acquisition system for collecting while-drilling seismic exploration data, while-drilling radar detection data, while-drilling hole wall scanning data, while-drilling drilling power data, while-drilling seepage field data and while-drilling temperature field data of the target deep earth engineering.

2. A method for multi-source information fusion and in-situ stereoscopic perspective of deep-ground adverse geology, characterized by: The following steps are involved: Perform adverse geological multi-source data interpretation on the target deep-earth engineering's while-drilling seismic exploration data, while-drilling radar detection data, while-drilling borehole wall scanning data, while-drilling drilling power data, while-drilling seepage field data, and while-drilling temperature field data to obtain multi-source data interpretation images of seismic interpretation images, radar interpretation images, 3D borehole wall images, formation rock mass parameters, seepage field images, and temperature field images; Complementarily fusing the seismic interpretation image, radar interpretation image, three-dimensional hole wall image, formation rock mass parameters, seepage field image and temperature field image of the multi-source data interpretation image to generate fused interpretation images for different adverse geological bodies; The complementary fusion of the seismic interpretation image, the radar interpretation image, the three-dimensional hole wall image, the formation rock mass parameters, the seepage field image and the temperature field image of the multi-source data interpretation image to generate fused interpretation images for different adverse geological bodies includes: extracting features from the seismic interpretation image, the radar interpretation image, the three-dimensional hole wall image, the formation rock mass parameters, the seepage field image and the temperature field image in an extraction order of adverse geological detection range from large to small, detection accuracy from low to high, and sensitivity from small to large to obtain corresponding adverse geological feature images, and complementary fusion is performed according to the adverse geological feature images and corresponding weights to obtain fused interpretation images for different adverse geological bodies, so as to obtain complementary fusion interpretation solutions according to the sensitivity differences of different detection data to different adverse geological bodies; Performing fusion image data enhancement and poor geological labeling on the fused interpreted image to obtain an image recognition model training set, and using the image recognition model training set to train a model, wherein input feature blocks and region candidate blocks are collected through a convolutional feature extraction network, a region candidate network, and a target area pooling network, and the feature blocks of the target area are extracted and fed into a subsequent fully connected layer to construct a poor geological image recognition model, so as to input the fused interpreted image of any poor geological body of the target deep earth engineering into the poor geological image recognition model and output at least one of the type, location, and scale information of the global poor geological body; and establishing a nonlinear mapping model between the multi-source information fusion imaging results and the poor geological conditions of the deep earth engineering; The method further includes: obtaining in-situ stereoscopic perspective information of the bad geology according to at least one of the type, location and scale information of the global bad geology body; Before performing adverse geological multi-source data interpretation on the while-drilling seismic exploration data, while-drilling radar detection data, while-drilling borehole wall scanning data, while-drilling power data, while-drilling seepage field data, and while-drilling temperature field data of the target deep-earth engineering, the method further includes: collecting the while-drilling seismic exploration data, while-drilling radar detection data, while-drilling borehole wall scanning data, while-drilling power data, while-drilling seepage field data, and while-drilling temperature field data of the target deep-earth engineering; It also includes: collecting while-drilling seismic exploration data, while-drilling radar detection data, while-drilling hole wall scanning data, while-drilling drilling power data, while-drilling seepage field data and while-drilling temperature field data of the target deep earth engineering.

3. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective method as claimed in claim 2.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the deep-earth adverse geological multi-source information fusion and in-situ stereoscopic perspective method as described in claim 2.

Images