A poor geological prediction method, device, equipment and storage medium

Abstract

The application discloses a kind of adverse geology advance forecast method, device, equipment and storage medium, it is related to geological survey technical field.The method is first according to the TRT three-dimensional result map of multiple sample sections and seismic wave velocity map, extract to obtain multiple sample data containing the TRT three-dimensional result map feature information of corresponding section, seismic wave velocity feature information and adverse geology type, then based on Apriori algorithm mining obtains the strong association rule of each adverse geology type and various TRT three-dimensional result map feature information and various seismic wave velocity feature information, and determines the adverse geology interpretation mark of each adverse geology type, finally if the TRT three-dimensional result map feature information and seismic wave velocity feature information of target section are matched with any one adverse geology interpretation mark of a certain adverse geology type, then the type is used as the advance forecast result of target section, so the accuracy of TRT advance geological prediction can be effectively improved.

Description

Technical Field

[0001] This invention belongs to the field of geological exploration technology, specifically relating to a method, device, equipment, and storage medium for early prediction of adverse geological conditions. Background Technology

[0002] In recent years, with the rapid development of infrastructure construction in my country, highways and railways are being built in various regions. However, in southwestern my country, where there are many mountains, the construction of highways and railways inevitably requires the construction of tunnels. Therefore, tunnel construction plays a crucial role in my country's infrastructure development. However, during tunnel construction, adverse geological conditions are unavoidable. For example, water inrush, landslides, and faults can all affect tunnel construction, causing delays or even casualties and huge economic losses. Therefore, it is essential to conduct advanced geological forecasting and predict the geological conditions ahead of the tunnel face in advance.

[0003] Currently, advanced geological prediction mainly employs two methods: geological methods and geophysical methods. Geological methods primarily include geological analysis, advanced drilling, and pilot tunneling. Geophysical methods mainly include seismic wave methods such as TSP (Tunnel Seismic Prediction), TRT (True Reflection Tomography), and TGP (Tunnel Geology Prediction). Other geophysical methods include electromagnetic wave methods (primarily using ground-penetrating radar), resistivity methods (primarily using transient electromagnetic and electrical methods like BEAM (Bore-Tunneling Electrical Ahead Monitoring), and infrared detection methods. Because the TRT advanced geological prediction system does not require blasting but uses hammering as the seismic source, it is more suitable for use in gas tunnels. Furthermore, TRT prediction technology has the characteristics of flexible operation, minimal impact on construction, and low cost. In addition, the prediction results are 3D images, so it can accurately determine the location of adverse geological conditions and can accurately predict adverse geological conditions such as faults, water-rich zones, weak rock layers, and fracture zones in front of the tunnel face.

[0004] Although TRT (Transient Reaction Time) forecasting technology has been developed in my country for over a decade, and many scholars have offered their opinions on the interpretation markers of adverse geological images from TRT, none have delved into the characteristics of the forecast images and seismic wave characteristics corresponding to various adverse geological hazards. This leads to differing interpretation results among different personnel due to variations in their expertise and habits. Therefore, how to determine the interpretation markers of adverse geological hazards based on the characteristics of TRT forecast images and seismic wave characteristics, and use them for advanced forecasting of adverse geological conditions, in order to improve the accuracy of TRT advanced geological forecasting, reduce or avoid geological hazards such as water inrush, mudslides, and collapses caused by adverse geological conditions, and provide early guidance for tunnel construction, is a topic that urgently needs to be studied by those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide a method, device, computer equipment, and computer-readable storage medium for advanced geological prediction, in order to solve the problem that existing advanced geological prediction technologies for TRT (Transient Tunneling Reaction) do not deeply study the characteristics of prediction result maps and seismic wave characteristics corresponding to various adverse geological hazards in TRT, resulting in limited accuracy of the final adverse geological prediction.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] Firstly, a method for early prediction of adverse geological conditions is provided, including:

[0008] Obtain TRT 3D result maps and seismic wave velocity maps for M sample sites, where M represents a positive integer greater than or equal to 20, and the sample sites refer to the surveyed sites that have been excavated and verified as belonging to any one of the N unfavorable geological types, where N represents a positive integer greater than or equal to 3.

[0009] Based on the TRT three-dimensional results map and seismic wave velocity map of the M sample sites, M sets of adverse geological sample data corresponding one-to-one with the M sample sites are extracted. The adverse geological sample data contains the TRT three-dimensional results map feature information, seismic wave velocity feature information and adverse geological type of the corresponding sample site.

[0010] Based on the M adverse geological sample data, strong correlation rules between each adverse geological type and the feature information of various TRT three-dimensional result maps and the feature information of various seismic wave velocity are mined based on the Apriori algorithm.

[0011] For each of the adverse geological types, based on the strong correlation rules with the corresponding TRT three-dimensional result map feature information and the various seismic wave velocity feature information, the corresponding adverse geological interpretation markers are determined, wherein the adverse geological interpretation markers include a certain TRT three-dimensional result map feature information and a certain seismic wave velocity feature information.

[0012] Obtain the TRT three-dimensional result map and the seismic wave velocity map of the target area;

[0013] Based on the TRT three-dimensional result map and the seismic wave velocity map of the target area, the feature information of the TRT three-dimensional result map and the seismic wave velocity feature information of the target area are extracted;

[0014] If the TRT 3D result map feature information and seismic wave velocity feature information of the target area are found to match any one of the adverse geological interpretation markers of one of the N adverse geological types, then that adverse geological type is taken as the adverse geological advance prediction result of the target area.

[0015] Based on the above-mentioned invention, a novel scheme for advanced prediction of adverse geological conditions based on TRT forecast map features and seismic wave features is provided. First, based on TRT 3D result maps and seismic wave velocity maps of multiple sample sites, multiple adverse geological sample data containing TRT 3D result map feature information, seismic wave velocity feature information, and adverse geological type information for the corresponding sites are extracted. Then, based on the Apriori algorithm, strong correlation rules between each adverse geological type and various TRT 3D result map feature information and various seismic wave velocity feature information are mined, and adverse geological interpretation markers for each adverse geological type are determined. Finally, if the TRT 3D result map feature information and seismic wave velocity feature information of the target site match any adverse geological interpretation marker of a certain adverse geological type, then that adverse geological type is taken as the advanced prediction result for the target site. This can effectively improve the accuracy of TRT advanced geological prediction, reduce or avoid geological disasters such as water inrush, mudslides, and collapses caused by adverse geological conditions, provide guidance for tunnel construction in advance, and facilitate practical application and promotion.

[0016] In one possible design, the N adverse geological types include water-rich zones, fractured zones, water-bearing fracture zones, weak rock layers, and faults.

[0017] In one possible design, based on the TRT 3D results and seismic wave velocity maps of the M sample sites, M sets of adverse geological sample data corresponding one-to-one with the M sample sites are extracted, including:

[0018] For each of the M sample plots, the corresponding top view feature information is extracted based on the top view in the corresponding TRT 3D result map, the corresponding side view feature information is extracted based on the side view in the corresponding TRT 3D result map, and the corresponding stereo view feature information is extracted based on the stereo view in the corresponding TRT 3D result map. Finally, the corresponding top view feature information, side view feature information and stereo view feature information are summarized to obtain the corresponding TRT 3D result map feature information.

[0019] For each sample location, based on the corresponding seismic wave velocity map, the corresponding seismic wave velocity feature information is extracted, and a certain adverse geological type that has been excavated and verified is identified as the corresponding adverse geological type.

[0020] In one possible design, based on the M adverse geological sample data, the Apriori algorithm is used to mine strong correlation rules between each adverse geological type and various TRT 3D result map feature information and various seismic wave velocity feature information among the N adverse geological types, including:

[0021] Import the M sets of adverse geological sample data into IBM SPSS MODELER software, and in response to human-computer interaction operations, set the field types and data roles in IBM SPSS MODELER software;

[0022] The Apriori algorithm of the IBM SPSS MODELER software was used for modeling: the TRT 3D result map feature information and seismic wave velocity feature information in the adverse geological sample data were used as the foreword, and the adverse geological type in the adverse geological sample data was used as the latter word. The association rules between each adverse geological type and various TRT 3D result map feature information and various seismic wave velocity feature information in the N adverse geological types were mined, as well as the support and confidence of the association rules.

[0023] For each adverse geological type, traverse the corresponding association rules with the feature information of each TRT three-dimensional result map and the feature information of each seismic wave velocity: if the support of a certain association rule is greater than the preset support threshold, and the confidence of the certain association rule is also greater than the preset confidence threshold, then the certain association rule is regarded as the corresponding strong association rule.

[0024] In one possible design, the Apriori algorithm of the IBM SPSS MODELER software is used for modeling, including:

[0025] First, respond to the human-computer interaction operation to set the filter node in the IBM SPSS MODELER software, and then start the Apriori algorithm of the IBM SPSS MODELER software for modeling.

[0026] In one possible design, the preset support threshold is greater than or equal to 5%, and the preset confidence threshold is greater than or equal to 50%.

[0027] In one possible design, for each of the adverse geological types, corresponding interpretation markers for adverse geological conditions are determined based on strong correlation rules with the characteristic information of the various TRT 3D results and the characteristic information of the various seismic wave velocities, including:

[0028] For each adverse geological type, if there are K strongly correlated rules corresponding to the various TRT 3D result map feature information and the various seismic wave velocity feature information, then according to the corresponding K strongly correlated rules, the corresponding k strongly correlated rules are simplified by Boolean operation, and then the corresponding k strongly correlated rules are used as the corresponding k adverse geological interpretation markers, where K represents a positive integer, k represents a positive integer and is not greater than K, and the adverse geological interpretation markers contain a certain TRT 3D result map feature information and a certain seismic wave velocity feature information.

[0029] Secondly, an advanced prediction device for adverse geological conditions is provided, including an image acquisition module, a data extraction module, a rule mining module, a marker determination module, and a matching prediction module;

[0030] The image acquisition module is used to acquire TRT three-dimensional result maps and seismic wave velocity maps of M sample sites, and is also used to acquire the TRT three-dimensional result map and seismic wave velocity map of the target site, wherein M represents a positive integer greater than or equal to 20, the sample site refers to a surveyed site that has been excavated and verified as being in any one of N unfavorable geological types, and N represents a positive integer greater than or equal to 3;

[0031] The data extraction module, communicatively connected to the image acquisition module, is used to extract M sets of adverse geological sample data corresponding one-to-one with the M sample sites based on the TRT three-dimensional result map and seismic wave velocity map of the M sample sites, and is also used to extract the TRT three-dimensional result map feature information and seismic wave velocity feature information of the target site based on the TRT three-dimensional result map and seismic wave velocity map of the target site, wherein the adverse geological sample data package contains the TRT three-dimensional result map feature information, seismic wave velocity feature information and adverse geological type of the corresponding sample site;

[0032] The rule mining module is communicatively connected to the data extraction module and is used to mine strong correlation rules between each adverse geological type and the feature information of various TRT three-dimensional result maps and the feature information of various seismic wave velocities in the N adverse geological types based on the M adverse geological sample data and the Apriori algorithm.

[0033] The flag determination module is communicatively connected to the rule mining module. It is used to determine the corresponding adverse geological interpretation flag for each adverse geological type based on the corresponding strong correlation rules with the feature information of the various TRT three-dimensional results and the feature information of the various seismic wave velocity. The adverse geological interpretation flag includes a certain TRT three-dimensional results feature and a certain seismic wave velocity feature.

[0034] The matching prediction module is communicatively connected to the data extraction module and the flag determination module, respectively. If the TRT three-dimensional result map feature information and seismic wave velocity feature information of the target area are found to match any one of the adverse geological interpretation flags of an adverse geological type among the N adverse geological types, then that adverse geological type is taken as the adverse geological advance prediction result of the target area.

[0035] Thirdly, the present invention provides a computer device comprising a memory, a processor, and a transceiver connected in sequence for communication, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the adverse geological advance prediction method as described in the first aspect or any possible design in the first aspect.

[0036] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the adverse geological advance prediction method as described in the first aspect or any possible design in the first aspect.

[0037] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the adverse geological advance prediction method as described in the first aspect or any possible design in the first aspect.

[0038] The beneficial effects of the above scheme are:

[0039] (1) This invention creatively provides a new scheme for advanced prediction of adverse geological conditions based on TRT prediction result map features and seismic wave features. First, based on the TRT three-dimensional result map and seismic wave velocity map of multiple sample areas, multiple adverse geological sample data containing TRT three-dimensional result map feature information, seismic wave velocity feature information and adverse geological type of the corresponding area are extracted. Then, based on the Apriori algorithm, strong correlation rules between each adverse geological type and various TRT three-dimensional result map feature information and various seismic wave velocity feature information are mined, and adverse geological interpretation markers of each adverse geological type are determined. Finally, if the TRT three-dimensional result map feature information and seismic wave velocity feature information of the target area are found to match any adverse geological interpretation marker of a certain adverse geological type, then that adverse geological type is taken as the adverse geological advanced prediction result of the target area. This can effectively improve the accuracy of TRT advanced geological prediction, reduce or avoid geological disasters such as water inrush, mud inrush and collapse caused by adverse geology, provide guidance for tunnel construction in advance, and facilitate practical application and promotion. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart illustrating the method for predicting adverse geological conditions provided in this application.

[0042] Figure 2 Example diagrams showing the feature descriptions and typical images of the top-view feature information provided in the embodiments of this application.

[0043] Figure 3 Example diagrams showing the feature descriptions and typical images of the side view feature information provided in the embodiments of this application.

[0044] Figure 4 Example diagrams showing the feature descriptions and typical images of the stereoscopic image feature information provided in the embodiments of this application.

[0045] Figure 5 Example diagrams showing the feature descriptions and typical images of seismic wave velocity characteristic information provided in the embodiments of this application.

[0046] Figure 6 Example diagrams showing the association rule mining results for various adverse geological types provided in the embodiments of this application.

[0047] Figure 7Example diagrams of two adverse geological interpretation markers for water-rich zones provided in the embodiments of this application.

[0048] Figure 8 Example diagrams of two types of unfavorable geological interpretation markers for fracture development zones provided in the embodiments of this application.

[0049] Figure 9 Example diagrams of two adverse geological interpretation markers for water-bearing fracture zones provided in the embodiments of this application.

[0050] Figure 10 Example diagrams of two types of adverse geological interpretation markers for weak rock strata provided in the embodiments of this application.

[0051] Figure 11 Example diagrams of two fault-related geological interpretation markers provided in this application embodiment.

[0052] Figure 12 Example of TRT 3D results for the right line section of Jiqu Tunnel from K93+956 to K93+840 provided in this application embodiment, wherein, Figure 12 (a) is a top view. Figure 12 (b) is a side view. Figure 12 (c) is a 3D view.

[0053] Figure 13 Example diagram of seismic wave velocity in the right line section of Jiqu Tunnel from K93+956 to K93+840, provided for an embodiment of this application.

[0054] Figure 14 Example photograph of the working face at chainage K93+946 provided in this application embodiment.

[0055] Figure 15 Example photograph of the working face at chainage K93+930 provided in this application embodiment.

[0056] Figure 16 A schematic diagram of the structure of the adverse geological advance prediction device provided in the embodiments of this application.

[0057] Figure 17 A schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0058] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0059] It should be understood that although the terms "first" and "second", etc., may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, the first object may be referred to as the second object, and similarly, the second object may be referred to as the first object, without departing from the scope of the exemplary embodiments of the invention.

[0060] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, or A and B exist simultaneously. Another example is A, B and / or C, which can mean that any one of A, B, and C or any combination thereof exists. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone or A and B exist simultaneously. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0061] Example:

[0062] like Figure 1 As shown, the adverse geological conditions prediction method provided in the first aspect of this embodiment can be executed, but is not limited to, by computer equipment with certain computing resources, such as platform servers, personal computers (PCs, referring to a type of multi-purpose computer suitable for personal use in terms of size, price, and performance; desktop computers, laptops, mini-laptops, tablets, and ultrabooks are all considered personal computers), smartphones, personal digital assistants (PDAs), or wearable devices. Figure 1 As shown, the method for early prediction of adverse geological conditions may include, but is not limited to, the following steps S1 to S7.

[0063] S1. Obtain TRT three-dimensional result maps and seismic wave velocity maps for M sample sites, where M represents a positive integer greater than or equal to 20, and the sample sites refer to the surveyed sites that have been excavated and verified as belonging to any one of the N unfavorable geological types, where N represents a positive integer greater than or equal to 3.

[0064] In step S1, the TRT three-dimensional result map, i.e., the TRT prediction result map, can be conventionally acquired based on existing TRT advanced geological prediction systems. The seismic wave velocity map can also be conventionally acquired based on existing systems. Specifically, the N adverse geological types include, but are not limited to, water-rich zones, fracture-developed zones, water-bearing fracture zones, weak rock strata, and faults (i.e., N equals 5). Furthermore, the number of sample sites can be specifically exemplified as 111 (i.e., M equals 111), of which 17 sample sites have been excavated and verified as water-rich zones, 37 sample sites have been excavated and verified as fracture-developed zones, 24 sample sites have been excavated and verified as water-bearing fracture zones, 21 sample sites have been excavated and verified as weak rock strata, and 12 sample sites have been excavated and verified as faults.

[0065] S2. Based on the TRT three-dimensional result map and seismic wave velocity map of the M sample sites, extract M sets of adverse geological sample data corresponding one-to-one with the M sample sites. The adverse geological sample data includes, but is not limited to, the TRT three-dimensional result map feature information, seismic wave velocity feature information, and adverse geological type of the corresponding sample site.

[0066] In step S2, the TRT three-dimensional result map may, but is not limited to, be subdivided into top view, side view, and stereoscopic view, so as to select the top view features, side view features, and stereoscopic view features of the TRT prediction result map, together with the seismic wave velocity features, as the four major influencing factors for interpreting adverse geological conditions. Specifically, based on the TRT three-dimensional result maps and seismic wave velocity maps of the M sample sites, M sets of adverse geological sample data corresponding one-to-one with the M sample sites are extracted, including but not limited to the following steps S21-S22.

[0067] S21. For each sample plot in the M sample plots, extract the corresponding top view feature information based on the top view in the corresponding TRT 3D result map, extract the corresponding side view feature information based on the side view in the corresponding TRT 3D result map, and extract the corresponding stereo view feature information based on the stereo view in the corresponding TRT 3D result map. Finally, summarize the corresponding top view feature information, side view feature information and stereo view feature information to obtain the corresponding TRT 3D result map feature information.

[0068] In step S21, the specific content of the top view feature information may include, but is not limited to, the following: Figure 2 As shown, there are five subdivisions of top view features: A1, A2, A3, A4, and A5; the specific content of the side view feature information may include, but is not limited to, the following: Figure 3 As shown, there are five subdivisions of side view features: B1, B2, B3, B4, and B5; the specific content of the stereoscopic view feature information may include, but is not limited to, the following: Figure 4 As shown, there are five subdivisions of the 3D image features: C1, C2, C3, C4, and C5. (As shown...) Figures 2-4 As shown, for these feature classifications, conventional classification models can be used (e.g., importing top view, side view, or stereoscopic image into a pre-trained first feature classification model based on a convolutional neural network to output the feature classification results of the corresponding image) to extract the top view feature information (i.e., A1, A2, A3, A4, or A5), side view feature information (i.e., B1, B2, B3, B4, or B5), and stereoscopic image feature information (i.e., C1, C2, C3, C4, or C5) of each sample area, thereby obtaining the feature information of the TRT three-dimensional result image.

[0069] S22. For each sample site, based on the corresponding seismic wave velocity map, extract the corresponding seismic wave velocity feature information, and identify the corresponding unfavorable geological type that has been excavated and verified as the corresponding unfavorable geological type.

[0070] In step S22, the specific content of the seismic wave velocity characteristic information may include, but is not limited to, the following: Figure 5 As shown, there are five subdivisions of seismic wave velocity characteristics: D1, D2, D3, D4, and D5. These characteristics can be categorized using, but are not limited to, conventional classification models (e.g., importing the seismic wave velocity map into a pre-trained second feature classification model based on a convolutional neural network to output the corresponding feature classification results) to extract the seismic wave velocity characteristic information (i.e., D1, D2, D3, D4, or D5) for each sample area. Furthermore, if the water-rich zone, the fractured zone, the water-bearing fracture zone, the weak rock layer, and the fault are respectively represented by E1, E2, E3, E4, and E5, then the extracted partial adverse geological sample data can be shown in Table 1 below:

[0071] Table 1. Data from some adverse geological samples (22 samples in total)

[0072]

[0073]

[0074] S3. Based on the M sets of adverse geological sample data, the strong correlation rules between each adverse geological type and the feature information of various TRT three-dimensional result maps and the feature information of various seismic wave velocities are obtained by mining based on the Apriori algorithm.

[0075] In step S3, the Apriori algorithm is a classic data mining algorithm for mining frequent itemsets and association rules. Therefore, it can mine strong association rules between the water-rich zone, the fracture development zone, the water-bearing fracture zone, the weak rock layer, and the fault and the five top-view features, the five side-view features, the five three-dimensional features, and the five seismic wave velocity features, respectively. Specifically, based on the M adverse geological sample data, the Apriori algorithm is used to mine strong association rules between each adverse geological type and various TRT three-dimensional result map feature information and various seismic wave velocity feature information in the N adverse geological types, including but not limited to the following steps S31 to S33.

[0076] S31. Import the M sets of adverse geological sample data into IBM SPSS MODEL software, and in response to human-computer interaction operations, set the field types and data roles in the IBM SPSS MODEL software.

[0077] In step S31, the IBM SPSS MODEL software is a popular statistical software widely used in data analysis, survey research, and social science research. Developed by IBM, it provides powerful data analysis tools and visualization capabilities, helping users effectively process and analyze data. Considering that the modeling process must include symbolic fields and clearly define the input or output attributes of each field, the purpose of setting the aforementioned field types is to clarify the format differences between fields so that each field within the data can be read and assigned a corresponding category, such as continuous, categorical, nominal, and symbolic. The aforementioned data roles can be divided into input and target.

[0078] S32. Start the Apriori algorithm of the IBM SPSS MODELER software for modeling: take the TRT 3D result map feature information and seismic wave velocity feature information in the adverse geological sample data as the foreword, and take the adverse geological type in the adverse geological sample data as the latter word, and mine to obtain the association rules between each adverse geological type and various TRT 3D result map feature information and various seismic wave velocity feature information in the N adverse geological types, as well as the support and confidence of the association rules.

[0079] In step S32, to eliminate data that does not need to participate in subsequent calculations and reduce the computational load, preferably, the Apriori algorithm of the IBM SPSS MODEL software is started for modeling. This includes, but is not limited to: first responding to human-computer interaction operations to set filter nodes in the IBM SPSS MODEL software, and then starting the Apriori algorithm of the IBM SPSS MODEL software for modeling. For example, the association rules between each adverse geological type and the feature information of various TRT 3D result maps and various seismic wave velocity feature information, as well as the support and confidence of the association rules, can be as follows: Figure 6 As shown. Furthermore, before modeling, a minimum conditional support of 5% and a minimum rule confidence of 50% can be set based on statistical data.

[0080] S33. For each adverse geological type, traverse the corresponding association rules with the feature information of each TRT three-dimensional result map and the feature information of each seismic wave velocity: if the support of a certain association rule is greater than the preset support threshold, and the confidence of the certain association rule is also greater than the preset confidence threshold, then the certain association rule is regarded as the corresponding strong association rule.

[0081] In step S33, a strong association rule is considered to be a rule whose support and confidence are both greater than their minimum thresholds. Therefore, if the support of a certain association rule is greater than a preset support threshold, and the confidence of that association rule is also greater than a preset confidence threshold, then that association rule can be considered as the corresponding strong association rule. Specifically, the preset support threshold is greater than or equal to 5%, and the preset confidence threshold is greater than or equal to 50%.

[0082] S4. For each adverse geological type, based on the corresponding strong correlation rules with the characteristic information of the various TRT three-dimensional results and the characteristic information of the various seismic waves, determine the corresponding adverse geological interpretation marker, wherein the adverse geological interpretation marker includes a certain TRT three-dimensional results and a certain seismic wave velocity.

[0083] In step S4, for example, the main strong association rules for the five adverse geological types E1, E2, E3, E4 and E5 obtained by the Apriori algorithm are shown in Tables 2 to 6.

[0084] Table 2. Main strong correlation rules for water-rich zones with unfavorable geological types

[0085]

[0086] Table 3. Main strong correlation rules for unfavorable geological types as fracture development zones

[0087]

[0088] Table 4. Main strong correlation rules for unfavorable geological types of water-bearing fracture zones

[0089]

[0090] Table 5. Main strong correlation rules for unfavorable geological types with weak rock strata

[0091]

[0092] Table 6. Main strong correlation rules for faults as an unfavorable geological type

[0093]

[0094] As shown in Table 2 above, there are six strong correlation rules for unfavorable geological conditions in the E1 water-rich zone. Taking the first strong correlation rule as an example, when the support of TRT result map top view = A1 → unfavorable geological conditions = E1 is 22.523% and the confidence level is 68.0%, it means that the probability of both conditions A1 and E1 appearing simultaneously in the database is 22.523%. In the M samples of unfavorable geological conditions, when the TRT result map top view feature is A1, the probability of unfavorable geological conditions being E1 is 68.0%. By analyzing the other five strong correlation rules for unfavorable geological conditions in the E1 water-rich zone, it can be seen that E1 is mainly strongly correlated with top view feature A1, side view feature B1, stereoscopic feature C1, and seismic wave velocity features D1 and D5. The appearance of any one of these five features has a high probability of obtaining unfavorable geological conditions in the E1 water-rich zone. There is only one corresponding feature among the three image features, except for the seismic wave velocity feature which has two corresponding features. The combination of image feature association rules and seismic wave velocity association rules can yield two stronger association rules as follows: (1) Top view feature = A1, side view feature = B1, stereo view feature = C1, seismic wave velocity = D1 → unfavorable geology = E1; (2) Top view feature = A1, side view feature = B1, stereo view feature = C1, seismic wave velocity = D5 → unfavorable geology = E1; and then we can obtain the following... Figure 7 The two types of unfavorable geological interpretation markers for water-rich zones are shown.

[0095] As shown in Table 3 above, there are six strong correlation rules for unfavorable geology in the E2 fracture development zone. Taking the first strong correlation rule as an example, when the top view of the TRT result map = A2 → unfavorable geology = E2, the support is 27.928% and the confidence is 90.323%. This means that the probability of both conditions A2 and E2 appearing simultaneously in the database is 27.928%. When the top view feature of the TRT result map is A2, the probability of unfavorable geology being E2 is 90.323%. Analysis of the other five strong correlation rules for unfavorable geology in the E2 fracture development zone reveals that E2 is strongly correlated with top view feature A2, side view feature B2, stereoscopic feature C2, and seismic wave velocity features D2 and D5. The presence of any one of these five features has a high probability of indicating unfavorable geology in the E2 fracture development zone. There is only one corresponding feature among the three image features, except for the seismic wave velocity feature which has two corresponding features. The combination of image feature association rules and seismic wave velocity association rules can yield two stronger association rules as follows: (1) Top view feature = A2, side view feature = B2, stereo view feature = C2, seismic wave velocity = D2 → unfavorable geology = E2; (2) Top view feature = A2, side view feature = B2, stereo view feature = C2, seismic wave velocity = D5 → unfavorable geology = E2; and then we can obtain the following... Figure 8 The two types of fracture development zones are shown as poor geological interpretation markers.

[0096] As shown in Table 4 above, there are six strong correlation rules for the unfavorable geological conditions of the E3 water-bearing fracture zone. Taking the first strong correlation rule as an example, when the top view of the TRT result map = A3 → unfavorable geological conditions = E3, the support is 18.919% and the confidence level is 90.476%. This means that the probability of both conditions A3 and E3 appearing simultaneously in the database is 18.919%. When the top view feature of the TRT result map is A3, the probability of unfavorable geological conditions being E3 is 90.476%. Analysis of the other five strong correlation rules for the unfavorable geological conditions of the E3 water-bearing fracture zone reveals that E3 is strongly correlated with top view feature A3, side view feature B3, stereoscopic feature C3, and seismic wave velocity features D2 and D5. The appearance of any one of these five features has a high probability of indicating unfavorable geological conditions in the E3 water-bearing fracture zone. There is only one corresponding feature among the three image features, except for the seismic wave velocity feature which has two corresponding features. The combination of image feature association rules and seismic wave velocity association rules can yield two stronger association rules as follows: (1) Top view feature = A3, side view feature = B3, stereo view feature = C3, seismic wave velocity = D2 → unfavorable geology = E3; (2) Top view feature = A3, side view feature = B3, stereo view feature = C3, seismic wave velocity = D5 → unfavorable geology = E3; and then we can obtain the following... Figure 9The two types of adverse geological interpretation markers for water-bearing fracture zones are shown.

[0097] As shown in Table 5 above, there are six strong correlation rules for the E4 weak rock layer unfavorable geological condition. Taking the first strong correlation rule as an example, when the TRT result map top view = A4 → unfavorable geological condition = E4, the support is 18.919% and the confidence is 90.476%. This means that the probability of both conditions A4 and E4 appearing simultaneously in the database is 18.919%. When the TRT result map top view feature is A4, the probability of unfavorable geological condition being E4 is 90.476%. Analysis of the other five strong correlation rules for the E4 weak rock layer unfavorable geological condition reveals that E4 is strongly correlated with top view feature A4, side view feature B4, 3D view feature C4, and seismic wave velocity features D2 and D5. The appearance of any one of these five features has a high probability of resulting in the E4 weak rock layer unfavorable geological condition. There is only one corresponding feature among the three image features, except for the seismic wave velocity feature which has two corresponding features. The combination of image feature association rules and seismic wave velocity association rules can yield two stronger association rules as follows: (1) Top view feature = A4, side view feature = B4, stereo view feature = C4, seismic wave velocity = D2 → unfavorable geology = E4; (2) Top view feature = A4, side view feature = B4, stereo view feature = C4, seismic wave velocity = D5 → unfavorable geology = E4; and then we can obtain the following... Figure 10 The two types of weak rock strata are shown as indicators of poor geological interpretation.

[0098] As shown in Table 6 above, there are five strong correlation rules for the E5 fault's unfavorable geological conditions. Taking the first strong correlation rule as an example, when the TRT result map top view = A5 → unfavorable geological conditions = E5, the support is 11.712% and the confidence level is 76.923%. This means that the probability of both conditions A5 and E5 appearing simultaneously in the database is 11.712%. In the database, when the TRT result map top view feature is A5, the probability of unfavorable geological conditions being E5 is 76.923%. Analysis of the other four strong correlation rules for the E5 fault's unfavorable geological conditions reveals that E5 is strongly correlated with top view feature A5, stereoscopic feature C5, and seismic wave velocity features D1 and D5, but not with side view B. The presence of any one of these four features has a high probability of indicating the E5 fault's unfavorable geological conditions. The E5 fault's unfavorable geological conditions have no correlation with the side view. It has only one corresponding feature among the other two image features, but two corresponding features with the seismic wave velocity feature. Combining the image feature correlation rules and the seismic wave velocity correlation rules yields two stronger correlation rules as follows: (1) Top view feature = A5, 3D view feature = C5, seismic wave velocity = D1 → Unfavorable geological conditions = E5; (2) Top view feature = A5, 3D view feature = C5, seismic wave velocity = D5 → Unfavorable geological conditions = E5; Furthermore, we can obtain the following... Figure 11 The two types of fault-related geological interpretation markers are shown.

[0099] In step S4, in order to quickly combine and obtain stronger correlation rules, preferably, for each adverse geological type, according to the corresponding strong correlation rules with the feature information of the various TRT three-dimensional results and the feature information of the various seismic wave velocity, the corresponding adverse geological interpretation markers are determined. This includes: for each adverse geological type, if there are K strong correlation rules with the feature information of the various TRT three-dimensional results and the feature information of the various seismic wave velocity, then according to the K strong correlation rules, the corresponding k strong correlation rules are simplified by Boolean operation to obtain the corresponding k strong correlation rules, and then the corresponding k strong correlation rules are used one by one as the corresponding k adverse geological interpretation markers, where K represents a positive integer, k represents a positive integer and is not greater than K, and the adverse geological interpretation markers contain a certain TRT three-dimensional results feature information and a certain seismic wave velocity feature information.

[0100] S5. Obtain the TRT three-dimensional result map and the seismic wave velocity map of the target area.

[0101] In step S5, the target area is the engineering section that has not yet undergone excavation verification. For example, when conducting a TRT advanced geological prediction at the working face of the right line of the Jiqu Tunnel at chainage K93+956, the engineering section located between chainage K93+956 and K93+840 of the right line of the Jiqu Tunnel can be used as the target area. The obtained TRT three-dimensional result map of the target area can be as follows: Figure 12 As shown, and the obtained seismic wave velocity map for the target area, can be seen as follows: Figure 13 As shown.

[0102] S6. Based on the TRT three-dimensional result map and the seismic wave velocity map of the target area, extract the TRT three-dimensional result map feature information and seismic wave velocity feature information of the target area.

[0103] In step S6, the specific method for extracting these feature information can be found in step S2 above, and will not be repeated here.

[0104] S7. If the TRT three-dimensional result map feature information and seismic wave velocity feature information of the target area are found to match any one of the adverse geological interpretation markers of the N adverse geological types, then the adverse geological type shall be taken as the adverse geological advance prediction result of the target area.

[0105] In step S7, for example, based on Figure 12 We can obtain the segment from K93+946 to K93+918 (i.e. Figure 12 The circled area in the image (used as a refined target area) has the following TRT 3D result map feature information: In the top view, there are a few short strips or dots of blue (low impedance) negative reflections, randomly distributed with dots or short strips of yellow (high impedance) positive reflections (i.e., top view feature A2); in the side view, there are also a few dots or short strips of blue (low impedance) negative reflections, randomly distributed with a few dots or short strips of yellow (high impedance) positive reflections (i.e., side view feature B2); in the stereoscopic view, a few dots or short strips of blue (low impedance) negative reflections and yellow (high impedance) positive reflections are also randomly distributed (i.e., stereoscopic view feature C2). And based on... Figure 13 We can obtain the segment from K93+946 to K93+918 (i.e. Figure 13The seismic wave velocity characteristics of the circled area (in the diagram) show both decreasing and increasing velocities (i.e., seismic wave velocity characteristic D2). Since the TRT 3D result map characteristics and seismic wave velocity characteristics of the K93+946~K93+918 section match the first interpretation indicator of unfavorable geology in the fracture development zone, the unfavorable geology prediction result for the K93+946~K93+918 section can be determined as a fracture development zone. Finally, based on the excavation results: when the right line of the Jiqu Tunnel was excavated to the K93+946 mileage section, the lithology of the tunnel face was mainly gray silty mudstone interspersed with a small amount of sandstone. The rock mass at the tunnel face showed well-developed fissures, was fractured, and had poor self-stabilizing capacity (see the tunnel face photo at K93+946 mileage). Figure 14 (As shown); When excavation reached the K93+930 section, the rock mass at the working face was mainly gray silty mudstone interbedded with sandstone, and the rock mass at the working face had relatively well-developed fissures (as shown in the photo of the working face at K93+930). Figure 15 As shown in the figure, the first interpretation marker of the fracture development zone is quite accurate in this application on the right line of the Jiqu Tunnel.

[0106] Therefore, based on the adverse geological conditions prediction method described in steps S1 to S7 above, a new scheme for adverse geological conditions prediction based on TRT prediction result map features and seismic wave features is provided. First, based on TRT 3D result maps and seismic wave velocity maps of multiple sample sites, multiple adverse geological sample data containing TRT 3D result map feature information, seismic wave velocity feature information, and adverse geological types for the corresponding sites are extracted. Then, based on the Apriori algorithm, strong correlation rules between each adverse geological type and various TRT 3D result map feature information and various seismic wave velocity feature information are mined, and adverse geological interpretation markers for each adverse geological type are determined. Finally, if the TRT 3D result map feature information and seismic wave velocity feature information of the target site match any adverse geological interpretation marker of a certain adverse geological type, then that adverse geological type is taken as the adverse geological conditions prediction result for the target site. This can effectively improve the accuracy of TRT advanced geological prediction, reduce or avoid geological disasters such as water inrush, mudslides, and collapses caused by adverse geological conditions, provide guidance for tunnel construction in advance, and facilitate practical application and promotion.

[0107] like Figure 16 As shown, the second aspect of this embodiment provides a virtual device for implementing the adverse geological advance prediction method described in the first aspect, including an image acquisition module, a data extraction module, a rule mining module, a marker determination module, and a matching prediction module;

[0108] The image acquisition module is used to acquire TRT three-dimensional result maps and seismic wave velocity maps of M sample sites, and is also used to acquire the TRT three-dimensional result map and seismic wave velocity map of the target site, wherein M represents a positive integer greater than or equal to 20, the sample site refers to a surveyed site that has been excavated and verified as being in any one of N unfavorable geological types, and N represents a positive integer greater than or equal to 3;

[0109] The data extraction module, communicatively connected to the image acquisition module, is used to extract M sets of adverse geological sample data corresponding one-to-one with the M sample sites based on the TRT three-dimensional result map and seismic wave velocity map of the M sample sites, and is also used to extract the TRT three-dimensional result map feature information and seismic wave velocity feature information of the target site based on the TRT three-dimensional result map and seismic wave velocity map of the target site, wherein the adverse geological sample data package contains the TRT three-dimensional result map feature information, seismic wave velocity feature information and adverse geological type of the corresponding sample site;

[0110] The rule mining module is communicatively connected to the data extraction module and is used to mine strong correlation rules between each adverse geological type and the feature information of various TRT three-dimensional result maps and the feature information of various seismic wave velocities in the N adverse geological types based on the M adverse geological sample data and the Apriori algorithm.

[0111] The flag determination module is communicatively connected to the rule mining module. It is used to determine the corresponding adverse geological interpretation flag for each adverse geological type based on the corresponding strong correlation rules with the feature information of the various TRT three-dimensional results and the feature information of the various seismic wave velocity. The adverse geological interpretation flag includes a certain TRT three-dimensional results feature and a certain seismic wave velocity feature.

[0112] The matching prediction module is communicatively connected to the data extraction module and the flag determination module, respectively. If the TRT three-dimensional result map feature information and seismic wave velocity feature information of the target area are found to match any one of the adverse geological interpretation flags of an adverse geological type among the N adverse geological types, then that adverse geological type is taken as the adverse geological advance prediction result of the target area.

[0113] The working process, working details and technical effects of the aforementioned device provided in the second aspect of this embodiment can be found in the adverse geological advance prediction method described in the first aspect, and will not be repeated here.

[0114] like Figure 17As shown, the third aspect of this embodiment provides a computer device for executing the adverse geological prediction method as described in the first aspect. The device includes a memory, a processor, and a transceiver connected in sequence. The memory stores a computer program, the transceiver sends and receives messages, and the processor reads the computer program to execute the adverse geological prediction method as described in the first aspect. Specifically, the memory may include, but is not limited to, random-access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; the processor may include, but is not limited to, a microprocessor of the STM32F105 series. Furthermore, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0115] The working process, working details and technical effects of the aforementioned computer equipment provided in the third aspect of this embodiment can be found in the adverse geological advance prediction method described in the first aspect, and will not be repeated here.

[0116] This fourth aspect of the embodiment provides a computer-readable storage medium storing instructions comprising the adverse geological conditions prediction method as described in the first aspect. Specifically, the computer-readable storage medium stores instructions that, when executed on a computer, perform the adverse geological conditions prediction method as described in the first aspect. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0117] The working process, working details and technical effects of the aforementioned computer-readable storage medium provided in the fourth aspect of this embodiment can be found in the adverse geological advance prediction method described in the first aspect, and will not be repeated here.

[0118] This fifth aspect of the embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the adverse geological prediction method as described in the first aspect. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0119] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for early prediction of adverse geological conditions, characterized in that, include: Obtain TRT 3D result maps and seismic wave velocity maps for M sample sites, where M represents a positive integer greater than or equal to 20, and the sample sites refer to the surveyed sites that have been excavated and verified as belonging to any one of the N unfavorable geological types, where N represents a positive integer greater than or equal to 3. Based on the TRT three-dimensional results map and seismic wave velocity map of the M sample sites, M sets of adverse geological sample data corresponding one-to-one with the M sample sites are extracted. The adverse geological sample data contains the TRT three-dimensional results map feature information, seismic wave velocity feature information and adverse geological type of the corresponding sample site. Based on the M adverse geological sample data, strong correlation rules between each adverse geological type and the feature information of various TRT three-dimensional result maps and the feature information of various seismic wave velocity are mined based on the Apriori algorithm. For each of the adverse geological types, based on the strong correlation rules with the corresponding TRT three-dimensional result map feature information and the various seismic wave velocity feature information, the corresponding adverse geological interpretation markers are determined, wherein the adverse geological interpretation markers include a certain TRT three-dimensional result map feature information and a certain seismic wave velocity feature information. Obtain the TRT three-dimensional result map and the seismic wave velocity map of the target area; Based on the TRT three-dimensional result map and the seismic wave velocity map of the target area, the feature information of the TRT three-dimensional result map and the seismic wave velocity feature information of the target area are extracted; If the TRT 3D result map feature information and seismic wave velocity feature information of the target area are found to match any one of the adverse geological interpretation markers of one of the N adverse geological types, then that adverse geological type is taken as the adverse geological advance prediction result of the target area.

2. The method for early prediction of adverse geological conditions according to claim 1, characterized in that, The N unfavorable geological types include water-rich zones, fractured zones, water-bearing fractured zones, weak rock strata, and faults.

3. The method for early prediction of adverse geological conditions according to claim 1, characterized in that, Based on the TRT 3D results and seismic wave velocity maps of the M sample sites, M sets of adverse geological sample data corresponding one-to-one with the M sample sites are extracted, including: For each of the M sample plots, the corresponding top view feature information is extracted based on the top view in the corresponding TRT 3D result map, the corresponding side view feature information is extracted based on the side view in the corresponding TRT 3D result map, and the corresponding stereo view feature information is extracted based on the stereo view in the corresponding TRT 3D result map. Finally, the corresponding top view feature information, side view feature information and stereo view feature information are summarized to obtain the corresponding TRT 3D result map feature information. For each sample location, based on the corresponding seismic wave velocity map, the corresponding seismic wave velocity feature information is extracted, and a certain adverse geological type that has been excavated and verified is identified as the corresponding adverse geological type.

4. The method for early prediction of adverse geological conditions according to claim 1, characterized in that, Based on the M adverse geological sample data, strong correlation rules were obtained using the Apriori algorithm between each adverse geological type and various TRT 3D result map feature information and various seismic wave velocity feature information among the N adverse geological types, including: Import the M sets of adverse geological sample data into IBM SPSS MODELER software, and in response to human-computer interaction operations, set the field types and data roles in IBM SPSS MODELER software; The Apriori algorithm of the IBM SPSS MODELER software was used for modeling: the TRT 3D result map feature information and seismic wave velocity feature information in the adverse geological sample data were used as the foreword, and the adverse geological type in the adverse geological sample data was used as the latter word. The association rules between each adverse geological type and various TRT 3D result map feature information and various seismic wave velocity feature information in the N adverse geological types were mined, as well as the support and confidence of the association rules. For each adverse geological type, traverse the corresponding association rules with the feature information of each TRT three-dimensional result map and the feature information of each seismic wave velocity: if the support of a certain association rule is greater than the preset support threshold, and the confidence of the certain association rule is also greater than the preset confidence threshold, then the certain association rule is regarded as the corresponding strong association rule.

5. The method for early prediction of adverse geological conditions according to claim 4, characterized in that, Modeling is performed using the Apriori algorithm in the IBM SPSSMODELER software, including: First, respond to the human-computer interaction operation to set the filter node in the IBM SPSS MODELER software, and then start the Apriori algorithm of the IBM SPSS MODELER software for modeling.

6. The method for early prediction of adverse geological conditions according to claim 4, characterized in that, The preset support threshold is greater than or equal to 5%, and the preset confidence threshold is greater than or equal to 50%.

7. The method for early prediction of adverse geological conditions according to claim 1, characterized in that, For each of the aforementioned adverse geological types, based on the corresponding strong correlation rules with the feature information of the various TRT three-dimensional results and the feature information of the various seismic wave velocities, the corresponding adverse geological interpretation markers are determined, including: For each adverse geological type, if there are K strongly correlated rules corresponding to the various TRT 3D result map feature information and the various seismic wave velocity feature information, then according to the corresponding K strongly correlated rules, the corresponding k strongly correlated rules are simplified by Boolean operation, and then the corresponding k strongly correlated rules are used as the corresponding k adverse geological interpretation markers, where K represents a positive integer, k represents a positive integer and is not greater than K, and the adverse geological interpretation markers contain a certain TRT 3D result map feature information and a certain seismic wave velocity feature information.

8. A device for early warning of adverse geological conditions, characterized in that, It includes an image acquisition module, a data extraction module, a rule mining module, a label determination module, and a matching prediction module; The image acquisition module is used to acquire TRT three-dimensional result maps and seismic wave velocity maps of M sample sites, and is also used to acquire the TRT three-dimensional result map and seismic wave velocity map of the target site, wherein M represents a positive integer greater than or equal to 20, the sample site refers to a surveyed site that has been excavated and verified as being in any one of N unfavorable geological types, and N represents a positive integer greater than or equal to 3; The data extraction module, communicatively connected to the image acquisition module, is used to extract M sets of adverse geological sample data corresponding one-to-one with the M sample sites based on the TRT three-dimensional result map and seismic wave velocity map of the M sample sites, and is also used to extract the TRT three-dimensional result map feature information and seismic wave velocity feature information of the target site based on the TRT three-dimensional result map and seismic wave velocity map of the target site, wherein the adverse geological sample data package contains the TRT three-dimensional result map feature information, seismic wave velocity feature information and adverse geological type of the corresponding sample site; The rule mining module is communicatively connected to the data extraction module and is used to mine strong correlation rules between each adverse geological type and the feature information of various TRT three-dimensional result maps and the feature information of various seismic wave velocities in the N adverse geological types based on the M adverse geological sample data and the Apriori algorithm. The flag determination module is communicatively connected to the rule mining module. It is used to determine the corresponding adverse geological interpretation flag for each adverse geological type based on the corresponding strong correlation rules with the feature information of the various TRT three-dimensional results and the feature information of the various seismic wave velocity. The adverse geological interpretation flag includes a certain TRT three-dimensional results feature and a certain seismic wave velocity feature. The matching prediction module is communicatively connected to the data extraction module and the flag determination module, respectively. If the TRT three-dimensional result map feature information and seismic wave velocity feature information of the target area are found to match any one of the adverse geological interpretation flags of an adverse geological type among the N adverse geological types, then that adverse geological type is taken as the adverse geological advance prediction result of the target area.

9. A computer device, characterized in that, The device includes a memory, a processor, and a transceiver connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the adverse geological advance prediction method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that... The computer-readable storage medium stores instructions that, when executed on a computer, perform the adverse geological advance prediction method as described in any one of claims 1 to 7.

Images