A method for constructing a digital rock gene library based on massive experimental data

Abstract

The application discloses a method for constructing a digital rock gene library based on massive experimental data, and comprises the following steps: collecting different typical rock samples, carrying out relevant experimental research, obtaining relevant experimental data of the typical rock samples, and processing the relevant experimental data to form rock standardized data; collecting typical geological disaster data occurring in history and processing the geological disaster data to form historical disaster standardized data; collecting real-time dynamic monitoring data of the current geological disaster; and fusing and analyzing the three kinds of heterogeneous data sources and uniformly processing the three kinds of heterogeneous data sources to form the digital rock gene library. The application adopts the three kinds of heterogeneous data sources to construct the digital rock gene library, makes up for defects that data is incomplete and methods are single in the existing rock mechanics field, and leads to different analysis results, has strong broad-spectrum and high accuracy.

Description

Technical Field

[0001] This invention belongs to the field of rock mechanics technology, specifically relating to a method for constructing a digital rock gene bank based on massive experimental data. Background Technology

[0002] Geotechnical geological hazards include floods caused by rising groundwater levels, landslides, collapses, and debris flows triggered by rock instability. These hazards not only endanger the safety of construction facilities and equipment but also pose serious threats to worker lives and the environment. Geotechnical engineering geological hazard prediction is a technical method that predicts and provides early warnings of geological hazards through comprehensive investigation, analysis, and evaluation of the geological environment. It aims to quickly and accurately identify and analyze geological hazards, reduce the burden of manual investigation, provide crucial support for geotechnical engineering planning, design, and construction, and mitigate the risks and losses caused by geological hazards.

[0003] Geological hazards are multifactorial phenomena. In recent years, with the development of rock mechanics theory and the innovation of experimental techniques, we have gained a relatively deep understanding of geological hazards and their mechanisms. However, the formation mechanism of geological hazards is very complex, involving factors such as lithology, landforms, climate conditions, and human activities. Traditional methods for studying them include field exploration and sampling, as well as field and laboratory tests. The drawback is that these methods only target a specific engineering site, requiring repeated testing and increasing time and economic costs.

[0004] Therefore, it is urgent to use big data technology to collect, organize and reconstruct experimental data to predict the rock properties of the geological structure where a project is located, and to provide technical basis for the prediction and early warning of engineering geological disasters. Summary of the Invention

[0005] The purpose of this invention is to provide a method for constructing a digital rock gene bank based on massive experimental data in order to overcome the shortcomings of existing technologies.

[0006] The objective of this invention is achieved through the following technical solution:

[0007] A method for constructing a digital rock gene bank based on massive experimental data includes the following steps:

[0008] Collect different typical rock samples, conduct relevant experimental studies, obtain relevant experimental data of the typical rock samples, and process the relevant experimental data to form rock-standardized data;

[0009] Collect and process data on typical geological disasters that have occurred in history to form standardized historical disaster data;

[0010] Collect real-time dynamic monitoring data on geological disasters;

[0011] The standardized rock data, the standardized historical disaster data, and the real-time dynamic monitoring data are integrated, analyzed, and uniformly standardized to form a digital rock gene library.

[0012] Preferably, the relevant experimental studies include at least one of optical microscopy observation, scanning electron microscopy observation, transmission electron microscopy observation, X-ray diffraction analysis, CT scan analysis, magnetic resonance imaging analysis, infrared spectroscopy analysis, relevant physicochemical property detection experiments, acoustic wave experiments, and relevant mechanical experiments.

[0013] Preferably, the relevant experimental data includes at least the microstructure parameters, basic physicochemical properties, and mechanical parameters of the rock sample;

[0014] The microstructure parameters include at least one of the following: microcrystalline structure, grain boundary distribution, mineral grain morphology, mineral grain size, porosity, fracture spatial distribution, number of fractures, fracture length, and fracture area.

[0015] The basic physicochemical properties include at least one of the following: color, luster, transparency, water content, water absorption, density, specific gravity, mineral type and composition, permeability, swelling due to moisture, solubility, and frost resistance.

[0016] The mechanical parameters include at least one of compressive strength, flexural strength, shear strength, impact strength, elastic modulus, deformation modulus, and Poisson's ratio.

[0017] Preferably, the geological disaster data includes at least rock-related data that cause the disaster, hydrological and climatic data, geological structure data, and topographic and geomorphological data.

[0018] Preferably, the real-time dynamic monitoring data includes at least satellite remote sensing data, aerial remote sensing data, and data collected by ground and underground monitoring equipment.

[0019] Preferably, the rock formation normalization data further includes:

[0020] Relevant data from both publicly available and unavailable rock samples are collected and merged with the relevant experimental data to form the rock-standardized data.

[0021] A digital rock gene bank constructed based on the method described above.

[0022] An application method based on the digital rock gene bank described above includes the following steps:

[0023] Based on the digital rock gene library, standard rock testing items are determined, and a relationship model between the parameter values ​​of the standard rock testing items and other rock parameter values ​​is established.

[0024] For newly collected rock samples to be tested, the rock samples are tested according to the rock standard testing items, and the test results are substituted into the relational model to obtain other parameter information of the rock samples to be tested.

[0025] Preferably, determining the standard rock testing items further includes:

[0026] Determine the standard rock testing items corresponding to different geological disasters.

[0027] Preferably, if the detection results of the rock sample to be tested cannot correspond to the relationship model, relevant experimental studies are carried out on the rock sample to be tested to obtain relevant experimental data of the rock sample to be tested, and the rock standardization data, the digital rock gene library and the relationship model are further updated.

[0028] This application constructs a digital rock gene library using three heterogeneous data sources, overcoming the shortcomings of incomplete data and inconsistent analytical results in the existing field of rock mechanics. It boasts broad spectrum and high accuracy. Based on this gene library, other fundamental properties of rocks can be analyzed and predicted by rapidly detecting a few items, thus providing a technical basis for geological disaster prediction and early warning, as well as guiding human activities. Attached Figure Description

[0029] Figure 1 This is a flowchart of the method steps for constructing a digital rock gene bank provided by the present invention. Detailed Implementation

[0030] This invention provides a method for constructing a digital rock gene bank based on massive experimental data, such as... Figure 1 As shown, it includes the following steps:

[0031] S1. Collect different typical rock samples, conduct various related experimental studies, obtain relevant experimental data of typical rock samples, and process the relevant experimental data to form rock standardized data.

[0032] Typical rock samples should be as comprehensive as possible, covering rocks from different regions, geological structures (such as folds, joints, faults, etc.), topography (such as basins, mountains, plains, etc.), formation ages (such as Quaternary, Jurassic, Triassic, Ordovician, Cambrian, etc.), and types (such as igneous rocks, sedimentary rocks, metamorphic rocks, etc.). Data from publicly available and unpublished rock samples verified by authoritative departments online, in books, and in periodicals can also be collected as supplementary information. When no identical typical rock sample is available, the data from the collected sample can be directly adopted. When identical typical rock samples are available, the experimental data can be compared and analyzed with the collected data to reduce errors and improve the accuracy of the rock data.

[0033] The relevant experimental studies mainly include: (1) rapid non-destructive testing methods such as optical microscopy, scanning electron microscopy, transmission electron microscopy, CT scan analysis, magnetic resonance imaging analysis, infrared spectroscopy analysis, and X-ray diffraction analysis, which can quickly obtain the microstructure parameters of rocks; (2) relevant physical and chemical property testing experiments, such as water content experiments, density experiments, and elemental analysis experiments, which can experimentally obtain the basic physical and chemical property parameters of rocks; (3) acoustic wave experiments and various related mechanical experiments such as uniaxial compressive strength tests, direct shear tests, conventional triaxial tests, creep tests, and hydraulic fracturing experiments, which can explore the mechanical failure mechanism of rocks and collect various mechanical parameters of rocks.

[0034] The relevant experimental data include at least the microstructural parameters, basic physicochemical properties, and mechanical parameters of the rock samples.

[0035] The microstructure parameters mainly include: microcrystalline structure, grain boundary distribution, mineral grain morphology, mineral grain size, porosity, fracture spatial distribution, number of fractures, fracture length, fracture area, etc., but are not limited to the above parameters;

[0036] The basic physicochemical properties mainly include: color, luster, transparency, water content, water absorption, density, specific gravity, mineral type and composition, permeability, swelling due to moisture, solubility, and frost resistance, but are not limited to the above parameters;

[0037] Mechanical parameters include, but are not limited to, compressive strength, flexural strength, shear strength, impact strength, elastic modulus, deformation modulus, Poisson's ratio, etc.

[0038] In general, all experiments and parameters should be covered as much as possible. However, due to limitations in human and material resources, the main experiments and key parameters can be selected for testing based on the actual application.

[0039] The mechanical parameters described above directly reflect the various mechanical properties of rocks, including elasticity, plasticity, toughness, rheology, and brittleness, under geological processes and various stresses. These parameters are crucial indicators for studying rock deformation, failure, and changes under stress, and play a vital role in geological engineering projects such as tunnel engineering, retaining wall engineering, mining exploration, crushing machinery, and geological hazard prediction. Basic physicochemical properties can reflect, to some extent, the stability and bearing capacity of rocks under external influences (such as hydraulic forces, temperature fields, and stress). Microstructural parameters reveal the internal characteristics and mineral composition of rocks, and these data can largely predict some of the fundamental physicochemical and mechanical properties of rocks.

[0040] Some basic physicochemical properties and microstructure parameters can reflect the mechanical parameters of rocks, and at the same time, they can be obtained more quickly and easily than mechanical parameters, which has important application value.

[0041] S2. Collect and process data on typical geological disasters that have occurred in history to form standardized historical disaster data.

[0042] Geological disaster data should include at least the rock-related data that causes the disaster (such as rock type, mechanical strength, fissures, etc.), hydrological and climatic data (such as groundwater, rainstorms, climate environment, human activities, etc.), geological structures (such as folds, joints, faults), and topographic data (slopes, side slopes, steep slopes), etc.

[0043] The formation mechanism of geological disasters is complex, and there are many factors that cause them. For example, the main conditions for landslide formation include:

[0044] (1) Topographical conditions: slope (10-45 degrees);

[0045] (2) Lithological conditions: loosely structured rock and soil with low shear strength;

[0046] (3) Structural conditions: Landslides are prone to occur when there are structural surfaces such as joints and faults;

[0047] (4) Groundwater: can reduce shear strength;

[0048] (5) Triggering conditions: earthquake, rainstorm, unreasonable human activities (such as excavation of the slope foot).

[0049] The main conditions for a landslide to form are:

[0050] (1) Topographical conditions: steep terrain (greater than 45 degrees);

[0051] (2) Lithological conditions: The rock is hard;

[0052] (3) Structural conditions: It has joints, faults and other structural surfaces;

[0053] (4) Climate conditions: Large daily and annual temperature ranges;

[0054] (5) Triggering conditions: earthquake, rainstorm, snow melting, etc.

[0055] Historical geological disaster data can be used to analyze the causes, development trends, impacts, and the role of various factors such as rock properties in geological disasters. This is of great importance for predicting and preventing future geological disasters and guiding human activities.

[0056] S3. Collect real-time dynamic monitoring data on geological disasters.

[0057] Real-time dynamic monitoring data includes at least satellite remote sensing data, aerial remote sensing data, and data collected by ground and underground monitoring equipment, i.e., real-time dynamic monitoring data from the sky, air, ground, and depth.

[0058] Satellite remote sensing data and aerial remote sensing data can reflect current surface information from distant and near ends, respectively, and identify areas sensitive to geological hazards. Data collected by ground and underground monitoring equipment, such as observation data inside slopes, can reflect current lithology and internal geological information. These three types of dynamic monitoring data comprehensively, multi-levelly, and three-dimensionally reflect current topography, lithology, geological structure, and other information, playing an important role in the early identification, warning, and prevention of geological hazards.

[0059] S4. The above three heterogeneous data sources are integrated, analyzed, and standardized to form a digital rock gene bank.

[0060] Modern technologies such as artificial intelligence, machine learning, and deep learning can be used to extract useful information from the aforementioned standard multi-source data, forming a digital rock gene bank. This enables data sharing and services, providing an optimal data platform for geological disaster prediction and guidance of human activities.

[0061] The digital rock gene bank not only allows users to query data on different rocks, historical geological disaster data, and dynamic monitoring data, but most importantly, it enables the analysis of rock gene information, extraction of useful data, and the establishment of rock property prediction models. This provides a technical basis for geological disaster prediction and early warning, and guides human activities. Specifically:

[0062] When applying the digital rock gene bank, the first step is to determine the standard rock testing items based on the digital rock gene bank and establish a relationship model between the parameter values ​​of the standard rock testing items and other rock parameter values.

[0063] As mentioned earlier, the digital rock gene bank contains a large amount of experimental data related to typical rock samples. Furthermore, certain parameters exhibit corresponding relationships with other parameters. In particular, the mineral composition and microstructure parameters of rocks have a significant impact on their mechanical properties. Using modern data processing methods, useful data can be extracted from the digital rock gene bank to determine standard rock testing items and establish relationship models between the values ​​of these standard testing items and other rock parameters. For newly collected rock samples (such as those collected for geological disaster early warning in a mountainous area or for exploration work in a mining area), testing can be performed according to the standard rock testing items. Substituting the test results into the relationship model yields other parameter information for the rock sample, eliminating the need for comprehensive experiments and significantly saving experimental time and costs. Obtaining this other parameter information provides a basic understanding of the rock properties in the collection area, offering crucial data for geological disaster prediction, early warning, and guidance of human activities in the rock sample collection region.

[0064] The preferred standard testing items for rocks are those that can be tested using rapid, non-destructive testing methods and are representative. For example, the standard testing items for rocks are: rock density testing, infrared spectroscopy analysis, transmission electron microscopy observation, and mineral composition analysis. Of course, destructive testing methods, such as rock fracturing experiments, can also be used when necessary.

[0065] After the initial construction of the digital rock gene bank, as time goes by, real-time dynamic monitoring data and historical geological disaster data are constantly being updated, and the digital rock gene bank and its relational model also need to be continuously iterated and updated.

[0066] If the test results of the rock sample to be tested cannot correspond to the relational model, then, in the same manner as for typical rock samples, relevant experimental studies will be carried out on the rock sample to be tested to obtain relevant experimental data of the rock sample to be tested, and the rock standardization data, digital rock gene library and relational model will be further updated.

[0067] This application's digital rock gene bank includes three types of heterogeneous data. The experimental data related to typical rock sample descriptions directly reveal the relationship between standard rock testing items and other parameters. However, rock properties are diverse, and a single standard testing item reflects only a limited number of other parameters. Testing only a few items cannot reflect all the properties of a rock. Historical geological disaster data can be analyzed to identify which specific rock properties caused the corresponding geological disasters. Therefore, for different geological disasters, different standard rock testing items can be determined, reflecting the rock properties that have the greatest impact on that disaster. For example, for landslides, testing items reflecting shear strength can be selected; for collapses, testing items reflecting rock hardness can be selected. This improves testing efficiency and accurately obtains key rock properties. However, historical disaster data can only reflect historical geological disaster information and cannot reflect current geological information. Moreover, geological disasters are sporadic and intermittent. Historical disaster data is incomplete in both time and space. The rock properties and other conditions that cause current geological disasters may have changed significantly. By collecting real-time dynamic monitoring data, we can understand the relationship between current rock properties and other conditions and geological disasters, make up for the lack of timeliness of historical disaster data, and improve the reliability and applicability of newly collected rock sample testing.

[0068] Therefore, this application employs three heterogeneous data sources to construct a digital rock gene library, overcoming the shortcomings of incomplete data and limited methods in existing rock mechanics research that lead to inconsistent analytical results. This library offers broad applicability and high accuracy. Based on this gene library, other fundamental properties of rocks can be analyzed and predicted by rapidly detecting a small number of parameters, thus providing a technical basis for geological disaster prediction and early warning, as well as guiding human activities.

[0069] This digital rock gene bank enables data and service sharing across multiple units and platforms, realizing a "large system, large platform, big data, and large integration" under a cloud architecture. It breaks down data gaps between units, integrates various rock mass information services from different units, and forms a unified, orderly, large-scale, and authoritative unified information service platform.

[0070] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention. Clearly, those skilled in the art can make various alterations and modifications to the invention without departing from its spirit and scope. Thus, if these modifications and modifications of the invention fall within the scope of the claims and their equivalents, the invention is also intended to include these modifications and modifications.

Claims

1. An application method for a digital rock gene bank constructed based on massive experimental data, characterized in that, The method for constructing the digital rock gene bank includes the following steps: Different typical rock samples are collected, and relevant experimental studies are conducted to obtain relevant experimental data of the typical rock samples. The relevant experimental data is then processed to form rock-standardized data. The relevant experimental data includes at least the microstructural parameters, basic physicochemical properties, and mechanical parameters of the rock samples. The formation of rock-standardized data further includes: collecting publicly available data information on rock samples and merging it with the relevant experimental data to form the rock-standardized data. Data on typical geological disasters that have occurred in history are collected and processed to form standardized historical disaster data, which are used to analyze the causes, development trends, impacts, and the role of various factors related to rock properties in geological disasters. Collect real-time dynamic monitoring data on geological hazards to analyze the relationship between current rock properties and other conditions and geological hazards; The rock standardization data, the historical disaster standardization data, and the real-time dynamic monitoring data are integrated, analyzed, and standardized in a unified manner to form a digital rock gene library. The application method of the digital rock gene bank includes the following steps: Based on the digital rock gene library, standard rock testing items are determined, and a relationship model between the parameter values ​​of the standard rock testing items and other rock parameter values ​​is established; the standard rock testing items are representative items that can be detected by rapid non-destructive testing methods, or destructive testing methods are used. For newly collected rock samples to be tested, the rock samples are tested according to the rock standard testing items, and the test results are substituted into the relational model to obtain other parameter information of the rock samples to be tested; if the test results of the rock samples to be tested cannot correspond to the relational model, relevant experimental studies are carried out on the rock samples to be tested to obtain relevant experimental data of the rock samples to be tested, and the rock standardization data, the digital rock gene library and the relational model are further updated; The determination of standard rock testing items further includes: Determine the standard rock testing items corresponding to different geological disasters.

2. The application method of the digital rock gene bank constructed based on massive experimental data as described in claim 1, characterized in that, The relevant experimental studies include at least one of the following: optical microscopy observation, scanning electron microscopy observation, transmission electron microscopy observation, X-ray diffraction analysis, CT scan analysis, magnetic resonance imaging analysis, infrared spectroscopy analysis, relevant physicochemical property detection experiments, acoustic wave experiments, and relevant mechanical experiments.

3. The application method of the digital rock gene bank constructed based on massive experimental data as described in claim 2, characterized in that, The microstructure parameters include at least one of the following: microcrystalline structure, grain boundary distribution, mineral grain morphology, mineral grain size, porosity, fracture spatial distribution, number of fractures, fracture length, and fracture area. The basic physicochemical properties include at least one of the following: color, luster, transparency, water content, water absorption, density, specific gravity, mineral type and composition, permeability, swelling due to moisture, solubility, and frost resistance. The mechanical parameters include at least one of the following: compressive strength, flexural strength, shear strength, impact strength, elastic modulus, deformation modulus, and Poisson's ratio.

4. The application method of the digital rock gene bank constructed based on massive experimental data as described in claim 1, characterized in that, The geological disaster data includes at least the rock-related data that causes the disaster, hydrological and climatic data, geological structure data, and topographic data.

5. The application method of the digital rock gene bank constructed based on massive experimental data as described in claim 1, characterized in that, The real-time dynamic monitoring data includes at least satellite remote sensing data, aerial remote sensing data, and data collected by ground and underground monitoring equipment.

Images