Intelligent prediction and analysis method, system, equipment, storage medium and program product for underground cavern surrounding rock

Abstract

The present invention discloses an intelligent prediction and analysis method, system, equipment, storage medium and program product for surrounding rock of underground caverns. The method comprises: classifying surrounding rock categories of the current tunnel face of the underground cavern, obtaining the surrounding rock category of the current tunnel face, predicting unfavorable geological bodies for the predicted tunnel section based on historical geophysical exploration results data, obtaining unfavorable geological body prediction information, performing spatial distribution analysis based on the unfavorable geological body prediction information, obtaining excavation space extension information of the underground cavern, quantifying features of the surrounding rock category of the current tunnel face, unfavorable geological body prediction information and excavation space extension information, and inputting the feature quantification results into a surrounding rock category prediction model to predict the surrounding rock category. Since the present invention combines the surrounding rock category of the current tunnel face, the unfavorable geological body prediction information and the excavation space extension information to achieve high-precision prediction of the surrounding rock category, the accuracy of the advanced geological prediction of the underground cavern is effectively improved, thereby effectively ensuring construction safety.

Description

Technical Field

[0001] The present invention relates to the technical field of underground cavern construction, and in particular to an intelligent prediction and analysis method, system, equipment, storage medium and program product for underground cavern surrounding rock. Background Art

[0002] With the development of the energy industry and the need for urban construction, the construction of underground caverns is crucial for fields such as water conservancy and hydropower, railway and highway transportation, energy mining, and municipal engineering. Advanced geological prediction is an effective method to understand the geological conditions in front of the face during the construction of underground caverns. It is an indispensable part of the current underground cavern construction. It plays an important role in safety assurance and disaster prevention and control, and is conducive to information-based construction. Surrounding rock category prediction is an important part of advanced geological prediction. It is of great significance to ensure the safety of underground engineering construction, rationally plan support measures, and improve the overall project benefits. At present, the advanced geological prediction system for underground caverns in the water conservancy and hydropower industry is still imperfect. The use of a single detection method leads to limited analysis data, so it is impossible to accurately predict the surrounding rock category of the unexplored cave section, resulting in low reliability of advanced geological prediction. Summary of the Invention

[0003] The main purpose of the present invention is to provide an intelligent prediction and analysis method, system, equipment, storage medium and program product for underground cavern surrounding rock, aiming to solve the technical problem that the existing technology uses a single detection method, resulting in limited analysis data, and therefore cannot accurately predict the surrounding rock type of unexplored cave sections, resulting in low reliability of advanced geological prediction.

[0004] To achieve the above object, the present invention provides an intelligent prediction and analysis method for underground cavern surrounding rock, the method comprising the following steps:

[0005] Classify the surrounding rock types of the current tunnel face of the underground cavern to obtain the surrounding rock type of the current tunnel face;

[0006] Based on historical geophysical exploration results data, the predicted section of the underground cavern is predicted to have unfavorable geological bodies, and unfavorable geological body prediction information is obtained, wherein the historical geophysical exploration results data includes seismic wave exploration results data and ground-penetrating radar exploration results data, the seismic wave exploration results data includes wave velocity diagrams and seismic wave profile diagrams, and the ground-penetrating radar exploration results data includes ground-penetrating radar profile diagrams; the historical geophysical exploration results data of the underground cavern is obtained, and the unfavorable geological body prediction information includes unfavorable geological body types and spatial distribution information corresponding to the unfavorable geological body types;

[0007] Performing a spatial distribution analysis on the underground cavern according to the adverse geological body prediction information to obtain excavation space extension information of the underground cavern;

[0008] Performing feature quantification on the current tunnel face surrounding rock category, the unfavorable geological body prediction information, and the excavation space extension information to obtain a feature quantification result, wherein the feature quantification result includes a current tunnel face surrounding rock category value, an unfavorable geological body development level value, and a spatial extension feature value;

[0009] The feature quantification results are input into a surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section. The surrounding rock category prediction model is used to determine the surrounding rock category label based on the input feature quantification results, and convert the surrounding rock category label into a surrounding rock category prediction value and then output the surrounding rock category prediction value. The surrounding rock category prediction model includes a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values.

[0010] Optionally, before inputting the feature quantification result into a surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section, the method further includes:

[0011] Acquire historical sample data of the underground cavern, wherein the historical sample data includes historical input data and historical output data, wherein the historical input data includes historical values of surrounding rock categories, historical values of unfavorable geological body development levels, and historical values of spatial extension characteristics, and the historical output data includes historical predicted values of surrounding rock categories corresponding to the historical input data;

[0012] Performing data cleaning on the historical sample data to obtain initial sample data;

[0013] Normalizing the initial sample data and performing time series alignment on the normalized initial sample data to obtain target sample data;

[0014] Construct an initial neural network model and initialize the weights and biases of the initial neural network model. The initial neural network model includes:

[0015] ;

[0016] in, is the output sample, which includes the surrounding rock category label network value, is an input sample, which includes historical values of surrounding rock types, historical values of unfavorable geological body development levels, and historical values of spatial extension characteristics. For the h The input neuron The connection weights between hidden neurons, For the hidden neurons and output neurons The connection weights between is the hidden neuron activation function, is the output neuron activation function, For the The bias of hidden neurons, For the The bias of the output neurons;

[0017] Construct a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values;

[0018] The initialized neural network model is trained based on the mapping relationship table and the target sample data to obtain a surrounding rock category prediction model.

[0019] Optionally, the training of the initialized neural network model based on the mapping relationship table and the target sample data to obtain a surrounding rock category prediction model includes:

[0020] Training the initialized neural network model based on the mapping relationship table and the target sample data;

[0021] Inputting the historical input data into the trained neural network model to obtain the surrounding rock category label network value;

[0022] Calculating a deviation value between the surrounding rock category label network value and the surrounding rock category historical prediction value corresponding to the historical input data;

[0023] Determining whether the deviation value is within a preset deviation range;

[0024] If the deviation value is within the preset deviation range, the training is stopped, and the trained neural network model is output as a surrounding rock category prediction model;

[0025] If the deviation value is not within the preset deviation range, the process returns to the step of training the initialized neural network model based on the mapping relationship table and the target sample data.

[0026] Optionally, the calculating of the deviation between the surrounding rock category label network value and the surrounding rock category historical prediction value corresponding to the historical input data includes:

[0027] Construct a sparse cross entropy loss function, which includes:

[0028] ;

[0029] in, Indicates the number of samples of historical sample data, represents the sample index, represents the true label, which is obtained based on the historical prediction value of the surrounding rock category. The model predicts the The samples belong to The probability of the class, Represents the average loss value of all samples;

[0030] Calculating an average loss value based on the sparse cross entropy loss function;

[0031] The deviation value between the surrounding rock category label network value and the surrounding rock category historical prediction value corresponding to the historical input data is determined according to the average loss value.

[0032] Optionally, performing spatial distribution analysis on the underground cavern according to the adverse geological body prediction information to obtain excavation space extension information of the underground cavern includes:

[0033] Constructing a three-dimensional geological model of the underground cavern according to the engineering geological analysis data of the underground cavern;

[0034] Obtaining current adverse geological body information of a current cave section of the underground cavern;

[0035] performing a spatial distribution analysis of bad geological bodies on the three-dimensional geological model based on the bad geological body prediction information and the current bad geological body information to obtain a spatial distribution analysis result;

[0036] It is determined whether the unfavorable geological body has extended to the current tunnel section according to the spatial distribution analysis result, and the excavation space extension information of the underground cavern is obtained based on the determination result.

[0037] Optionally, after inputting the feature quantification result into a surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section, the method further includes:

[0038] generating a plurality of engineering treatment strategies based on the tunnel face span and support type of the underground cavern, the engineering treatment strategies including a first category engineering treatment strategy, a second category engineering treatment strategy, a third category engineering treatment strategy, and a fourth category engineering treatment strategy;

[0039] When the predicted value of the surrounding rock category is greater than a first preset threshold, a first category engineering treatment strategy is sent to a construction user corresponding to the underground cavern;

[0040] When the surrounding rock category prediction value is greater than a second preset threshold and less than or equal to the first preset threshold, sending a second category engineering treatment strategy to the construction user, wherein the first preset threshold is greater than the second preset threshold;

[0041] When the surrounding rock category prediction value is greater than a third preset threshold and less than or equal to the second preset threshold, sending a third category engineering treatment strategy to the construction user, wherein the second preset threshold is greater than the third preset threshold;

[0042] When the surrounding rock category prediction value is greater than a fourth preset threshold and less than or equal to a third preset threshold, a fourth category engineering treatment strategy is sent to the construction user, wherein the third preset threshold is greater than the fourth preset threshold.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also proposes an intelligent prediction and analysis system for underground cavern surrounding rock, the intelligent prediction and analysis system for underground cavern surrounding rock comprising:

[0044] The tunnel face surrounding rock classification module is used to classify the surrounding rock of the current tunnel face of the underground cavern and obtain the surrounding rock category of the current tunnel face;

[0045] a bad geological body prediction module, configured to predict bad geological bodies for the predicted cave section of the underground cavern based on historical geophysical exploration results data, and obtain bad geological body prediction information, wherein the historical geophysical exploration results data includes seismic wave detection results data and ground-penetrating radar detection results data, the seismic wave detection results data includes wave velocity maps and seismic wave profiles, and the ground-penetrating radar detection results data includes ground-penetrating radar profiles; the historical geophysical exploration results data of the underground cavern is obtained, and the bad geological body prediction information includes bad geological body types and spatial distribution information corresponding to the bad geological body types;

[0046] A spatial distribution analysis module is used to perform spatial distribution analysis on the underground cavern according to the adverse geological body prediction information to obtain excavation space extension information of the underground cavern;

[0047] a feature quantification module for performing feature quantification on the current tunnel face surrounding rock category, the unfavorable geological body prediction information, and the excavation space extension information to obtain a feature quantification result, wherein the feature quantification result includes a current tunnel face surrounding rock category value, an unfavorable geological body development level value, and a spatial extension feature value;

[0048] The surrounding rock category prediction module is used to input the feature quantification results into the surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section. The surrounding rock category prediction model is used to determine the surrounding rock category label based on the input feature quantification results, and convert the surrounding rock category label into a surrounding rock category prediction value and then output the surrounding rock category prediction value. The surrounding rock category prediction model includes a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values.

[0049] In addition, to achieve the above-mentioned purpose, the present application also proposes an intelligent prediction and analysis device for underground cavern surrounding rock, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the intelligent prediction and analysis method for underground cavern surrounding rock as described above.

[0050] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the intelligent prediction and analysis method for underground cavern surrounding rock as described above are implemented.

[0051] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the intelligent prediction and analysis method for underground cavern surrounding rock as described above.

[0052] The present invention classifies the surrounding rock types of the current tunnel face of the underground cavern to obtain the surrounding rock type of the current tunnel face, predicts the bad geological body of the predicted tunnel section of the underground cavern based on historical geophysical exploration results data, and obtains bad geological body prediction information, the historical geophysical exploration results data includes seismic wave detection results data and ground penetrating radar detection results data, the seismic wave detection results data includes wave velocity diagrams and seismic wave profile diagrams, and the ground penetrating radar detection results data includes ground penetrating radar profile diagrams; the historical geophysical exploration results data of the underground cavern is obtained, the bad geological body prediction information includes bad geological body types and spatial distribution information corresponding to the bad geological body types; the underground cavern is spatially distributed according to the bad geological body prediction information to obtain the excavation space extension information of the underground cavern; the current tunnel face surrounding rock type, the bad geological body prediction information and the excavation space extension information are feature quantified, Obtain feature quantification results, which include the current face surrounding rock category value, the unfavorable geological body development level value and the spatial extension feature value; input the feature quantification results into a surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section, and the surrounding rock category prediction model is used to determine the surrounding rock category label according to the input feature quantification results, and output the surrounding rock category prediction value after converting the surrounding rock category label into a surrounding rock category prediction value. The surrounding rock category prediction model includes a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values; since the present invention predicts unfavorable geological bodies based on seismic wave detection results and ground penetrating radar detection results, thereby improving the accuracy of unfavorable geological body prediction, the surrounding rock category prediction is performed in combination with the current face surrounding rock category, unfavorable geological body prediction information and excavation space extension information, thereby achieving high-precision prediction of surrounding rock categories, effectively improving the accuracy of advanced geological prediction of underground caverns, and effectively ensuring construction safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0054] Figure 1 It is a schematic diagram of the structure of an intelligent prediction and analysis device for underground cavern surrounding rock in the hardware operating environment involved in an embodiment of the present invention;

[0055] Figure 2 This is a flow chart of an embodiment of an intelligent prediction and analysis method for underground cavern surrounding rock of the present invention;

[0056] Figure 3 This is a schematic diagram of the process of analyzing excavation space extension information in an embodiment of the intelligent prediction and analysis method for surrounding rock of underground caverns of the present invention;

[0057] Figure 4 A schematic diagram of a process for constructing a surrounding rock category prediction model in an embodiment of an intelligent prediction and analysis method for surrounding rock of an underground cavern according to the present invention;

[0058] Figure 5 This is a structural block diagram of an embodiment of the intelligent prediction and analysis system for underground cavern surrounding rock of the present invention.

[0059] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of an intelligent prediction and analysis device for underground cavern surrounding rock in the hardware operating environment involved in an embodiment of the present invention.

[0062] like Figure 1As shown, the intelligent prediction and analysis device for surrounding rock of underground caverns may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display and an input unit, such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a wireless fidelity (WI-FI) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may be a storage system independent of the processor 1001.

[0063] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the intelligent prediction and analysis equipment for underground cavern surrounding rock, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0064] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and an intelligent prediction and analysis program for underground cavern surrounding rock.

[0065] exist Figure 1 In the intelligent prediction and analysis device for underground cavern surrounding rock shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the intelligent prediction and analysis device for underground cavern surrounding rock of the present invention can be set in the intelligent prediction and analysis device for underground cavern surrounding rock, and the intelligent prediction and analysis device for underground cavern surrounding rock calls the intelligent prediction and analysis program for underground cavern surrounding rock stored in the memory 1005 through the processor 1001, and executes the intelligent prediction and analysis method for underground cavern surrounding rock provided by the embodiment of the present invention.

[0066] The embodiment of the present invention provides an intelligent prediction and analysis method for underground cavern surrounding rock, referring to Figure 2 , Figure 2 Schematic diagram of the process of an embodiment of the intelligent prediction and analysis method for underground cavern surrounding rock of the present invention.

[0067] In this embodiment, the intelligent prediction and analysis method for underground cavern surrounding rock includes the following steps:

[0068] Step S10: Classify the surrounding rock types of the current tunnel face of the underground cavern to obtain the surrounding rock type of the current tunnel face.

[0069] It should be noted that this embodiment can be applied to the advanced geological prediction of underground caverns. The advanced geological prediction can promote the rapid development of digitalization and refinement of geological analysis and geological prediction technologies in underground cavern construction. Among them, the advanced geological prediction can be an advanced prediction of the surrounding rock and stratum conditions in front of and around the tunnel face when the underground cavern is excavated.

[0070] It should be understood that the execution subject of this embodiment may be a computing service device with data processing, network communication, and program execution capabilities, such as a tablet computer, personal computer, mobile phone, etc., or a terminal electronic device capable of performing the aforementioned functions. This embodiment and the following embodiments will be described below using an intelligent prediction and analysis device for surrounding rock of underground caverns (hereinafter referred to as the analysis device) as an example.

[0071] It should be noted that the current tunnel face may be the tunnel face of a currently explored tunnel section in the underground cavern. The analysis device may classify the surrounding rock types of the current tunnel face of the currently explored tunnel section to obtain the surrounding rock type of the current tunnel face.

[0072] Step S20: Based on historical geophysical exploration results data, the predicted section of the underground cavern is predicted to have unfavorable geological bodies, and unfavorable geological body prediction information is obtained.

[0073] It should be noted that the predicted tunnel section may be a tunnel section of an underground cavern that has not yet been explored. In some embodiments, the analysis device may predict the type and distribution range of the adverse geological body in the predicted tunnel section based on the current tunnel section that has been explored in the underground cavern to obtain adverse geological body prediction information.

[0074] It should be noted that the historical geophysical exploration results data include seismic wave detection results data and ground-penetrating radar detection results data, the seismic wave detection results data include wave velocity diagrams and seismic wave profile diagrams, and the ground-penetrating radar detection results data include ground-penetrating radar profile diagrams; the historical geophysical exploration results data of underground caverns, the unfavorable geological body prediction information includes unfavorable geological body types and spatial distribution information corresponding to the unfavorable geological body types.

[0075] It can be understood that this embodiment obtains seismic wave detection data and ground-penetrating radar detection data through seismic wave detection and ground-penetrating radar detection, and obtains historical geophysical detection results data of underground caverns based on the seismic wave detection data and ground-penetrating radar detection data.

[0076] In some embodiments, the analysis equipment can obtain the surrounding rock geological conditions and geological structural conditions based on the historical geological analysis data of the underground cavern, determine the cavern prediction strategy based on the surrounding rock geological conditions and the geological structural conditions, collect seismic wave detection data and ground penetrating radar detection data for the underground cavern based on the cavern prediction strategy, obtain seismic wave detection data and ground penetrating radar detection data, pre-process the seismic wave detection data and the ground penetrating radar detection data, and obtain historical geophysical detection results data.

[0077] It should be noted that the analysis equipment can obtain historical geophysical exploration data through geophysical exploration methods. The geophysical exploration methods used in this embodiment include seismic wave detection (a long-distance advanced detection method) and ground-penetrating radar (a short-distance advanced detection method). Therefore, the geophysical exploration results involved include seismic wave detection results and ground-penetrating radar detection results. Seismic wave detection results include: P-wave velocity maps, S-wave velocity maps, and seismic profiles (two-dimensional time-distance images); ground-penetrating radar detection results include: radar profiles (two-dimensional time-distance images).

[0078] It should be noted that the preprocessing includes static correction processing, denoising processing, dynamic correction processing, time-depth conversion processing and normalization processing; among them, static correction is used to eliminate the time difference caused by terrain and velocity differences; dynamic correction and superposition processing are used to eliminate the propagation time difference and enhance the effective wave energy; depth conversion processing can be time-depth conversion, which is used to calculate the depth based on the electromagnetic wave velocity.

[0079] In some embodiments, the analysis equipment selects appropriate observation methods and related observation parameters according to the surrounding rock geological conditions and structural conditions; data is collected according to the observation system design plan; due to the complexity of the on-site construction environment and the different types, formats, and time dimensions of the collected data, the collected data is pre-processed by static correction, denoising, dynamic correction, time-depth conversion, and normalization to obtain geophysical exploration results data.

[0080] In some embodiments, the analysis equipment can perform geological interpretation feature analysis on the seismic wave detection results data and the ground-penetrating radar detection results data, obtain parameter change feature information of the seismic wave parameters and the ground-penetrating radar parameters, perform abnormal feature extraction on the parameter change feature information of the seismic wave parameters and the ground-penetrating radar parameters, obtain seismic wave abnormal feature information and ground-penetrating radar abnormal feature information, perform correlation analysis on the seismic wave abnormal feature information and the ground-penetrating radar abnormal feature information, obtain sample poor geological body type, and construct geophysical detection results sample data based on the sample poor geological body type and the historical geophysical detection results data.

[0081] It should be noted that the seismic wave parameters include seismic wave velocity, seismic wave frequency, and seismic wave amplitude, and the ground-penetrating radar parameters include ground-penetrating radar frequency and ground-penetrating radar amplitude. The ground-penetrating radar abnormality feature information may include abnormal frequency features and abnormal amplitude features within the ground-penetrating radar features; the seismic wave abnormality feature information may include abnormal wave velocity features, abnormal frequency features, and abnormal amplitude features within the seismic wave features.

[0082] It is understandable that the analysis equipment can analyze the signal characteristics of geophysical exploration data and explain the changes in various parameters. For seismic exploration results, the focus is on: wave velocity, frequency, amplitude, etc., and for ground penetrating radar detection results, the focus is on: frequency, amplitude, etc.; secondly, combined with the signal propagation law, the geological body characteristics that may lead to the above-mentioned signal characteristics are analyzed, including: whether there are unfavorable geological bodies, the types of unfavorable geological bodies, the spatial distribution of unfavorable geological bodies, and the geological conditions in front of the tunnel face are interpreted; finally, the surrounding rock classification results are given.

[0083] Taking the seismic wave method as an example: the longitudinal wave velocity of the seismic waves in the section between pile numbers J0+400 and J0+500 ranges from 2600 m / s to 3200 m / s, indicating that the overall surrounding rock conditions are comparable to those at the current tunnel face. The reflection signal from pile numbers J0+438 to J0+463 is strong, with low frequency and large amplitude, suggesting the presence of abundant water in this area. The rock mass quality in the section between pile numbers J0+400 and J0+500 is Class III, while that in the section between pile numbers J0+438 and J0+463 is Class IV, requiring careful attention during excavation.

[0084] In some embodiments, the analysis device can analyze whether there are any areas in the result data where the signal characteristics differ from the surrounding rock signal characteristics; if so, the possible causes of the signal change are analyzed to determine the type of unfavorable geological body causing the signal change; the unfavorable geological body contours are delineated: for seismic wave result data, reduced wave velocity, reflection wave event offset, and amplitude mutation areas may indicate the boundaries of unfavorable geological bodies; for ground penetrating radar result data, reflection wave event offset and amplitude mutation areas may indicate the boundaries of unfavorable geological bodies. Finally, based on the geological interpretation results of the geophysical exploration result data, preliminary conclusions of the geophysical exploration analysis are drawn, such as the possible types and spatial distribution information of unfavorable geological bodies and the classification of surrounding rocks analyzed by geophysical exploration.

[0085] In some embodiments, the analysis device can determine the seismic wave anomaly segment and the ground penetrating radar anomaly segment based on the seismic wave anomaly characteristic information and the ground penetrating radar anomaly characteristic information, perform spatial superposition analysis on the seismic wave anomaly segment and the ground penetrating radar anomaly segment, obtain anomaly overlapping areas and anomaly non-overlapping areas, generate geometric constraints based on the geological structure law information of the underground cavern and the sample poor geological body type, determine the pile number segment covered by the poor geological body of the sample poor geological body type according to the geometric constraints, the abnormal overlapping areas and the abnormal non-overlapping areas, determine the sample spatial distribution information of the sample poor geological body type based on the spatial position of the pile number segment, construct geophysical exploration results sample data based on the historical geophysical exploration results data, the sample poor geological body type and the sample spatial distribution information, so as to accurately combine the ground penetrating radar characteristics and the seismic wave characteristics for analysis, comprehensively analyze the poor geological body information from two dimensions, and improve the accuracy of poor geological analysis.

[0086] Step S30: performing a spatial distribution analysis on the underground cavern according to the adverse geological body prediction information to obtain excavation space extension information of the underground cavern.

[0087] It should be noted that the above-mentioned excavation spatial extension information can be the spatial extension information of the structures predicted and revealed by the previous excavation. The excavation spatial extension information can include the excavated length, the time point when a specific geological layer is reached, the spatial distribution information of the unfavorable geological bodies revealed by the excavation, etc.

[0088] Furthermore, in order to accurately analyze the excavation space extension information of the underground cavern, refer to Figure 3 , Figure 3 This is a schematic diagram of a process for analyzing mining spatial extension information in one embodiment. Step S30 may include:

[0089] Step S301: constructing a three-dimensional geological model of the underground cavern according to the engineering geological analysis data of the underground cavern;

[0090] Step S302: obtaining current adverse geological body information of the current cave section of the underground cavern;

[0091] Step S303: performing a spatial distribution analysis of bad geological bodies on the three-dimensional geological model based on the bad geological body prediction information and the current bad geological body information to obtain a spatial distribution analysis result;

[0092] Step S304: judging whether the unfavorable geological body has extended to the current tunnel section according to the spatial distribution analysis result, and obtaining the excavation space extension information of the underground cavern based on the judgment result.

[0093] It can be understood that the analysis equipment can conduct spatial distribution analysis on the adjacent unfavorable geological bodies that have been speculated in the early stage of the underground cavern and the adjacent unfavorable geological bodies that have been exposed based on engineering geological analysis and three-dimensional geological modeling technology, and determine whether the former can be extended to the current cave section, thereby obtaining the excavation space extension information of the underground cavern.

[0094] In some embodiments, the analysis equipment can obtain engineering geological analysis data of the underground cavern, including but not limited to drilling data, geological survey maps, geophysical exploration results, etc., construct an initial three-dimensional geological model based on the engineering geological analysis data, map the current bad geological body information of the current section of the underground cavern (including the type of bad geological body and the spatial distribution range of the bad geological body) to the initial geological model, obtain the target three-dimensional geological model, and analyze the extension of the bad geological body of the target three-dimensional geological model in combination with the excavation progress and the bad geological body prediction information to obtain the excavation space extension information of the underground cavern.

[0095] Step S40: performing feature quantification on the current tunnel face surrounding rock type, the adverse geological body prediction information, and the excavation space extension information to obtain a feature quantification result.

[0096] It should be noted that the characteristic quantification results include the current tunnel face surrounding rock category value, unfavorable geological body development level value and spatial extension characteristic value.

[0097] In some embodiments, the analysis equipment can convert the current tunnel face surrounding rock category obtained by engineering geological analysis into the corresponding current tunnel face surrounding rock category value as the input layer value of the neural network. The neural network input layer values corresponding to surrounding rock categories I, II, III1, III2, IV1, IV2, and V are: 1, 2, 3, 3.5, 4, 4.5, and 5, respectively. Refer to the following Table 1, which is a surrounding rock category mapping relationship table.

[0098] Table 1 Mapping relationship table of surrounding rock categories

[0099]

[0100] In some embodiments, the development of unfavorable geological bodies ahead of the tunnel face, including the type and likelihood of the unfavorable geological bodies, can be obtained based on the results of geophysical advance exploration analysis and geological exploration analysis. This system divides the unfavorable geological body development level values into four input layers: fault development level values, water-rich development level values, cave development level values, and soft rock development level values. The geophysical advance exploration analysis results and geological exploration analysis results are converted into corresponding numerical values as the neural network input layer values according to Table 2 below. For example, the unfavorable geological body development level values are divided into the following categories based on the prediction confidence: 0-25% corresponds to the absence of an unfavorable geological body, 25-50% (inclusive) corresponds to a low likelihood of the presence of an unfavorable geological body, 50-75% (inclusive) corresponds to a high likelihood of the presence of an unfavorable geological body, and 75-100% (inclusive) corresponds to the presence of an unfavorable geological body. The unfavorable geological body development level values are determined according to Table 2 below, which is a quantitative table of unfavorable geological body development levels.

[0101] Table 2 Quantitative table of development level of unfavorable geological bodies

[0102]

[0103] In some embodiments, the spatial extension characteristic value can be the spatial extension characteristic value of the structure speculated in the early excavation and revealed by the excavation. The analysis equipment can determine the spatial extension characteristic value by analyzing the spatial extension characteristics of the structure speculated in the early excavation and revealed by the excavation, and comparing it with the following Table 3, which is a quantification table of spatial extension characteristics.

[0104] Table 3 Quantification table of spatial extension features

[0105]

[0106] Step S50: inputting the feature quantification result into a surrounding rock type prediction model to predict the surrounding rock type of the predicted tunnel section.

[0107] It should be noted that the surrounding rock category prediction model is used to determine the surrounding rock category label based on the input feature quantification results, and convert the surrounding rock category label into a surrounding rock category prediction value and then output the surrounding rock category prediction value. The surrounding rock category prediction model contains a mapping relationship table between the surrounding rock category label and the surrounding rock category prediction value.

[0108] It should be noted that the surrounding rock category prediction model can be a neural network model pre-trained based on a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values and sample data, and the surrounding rock category prediction of the predicted tunnel section is performed based on the trained surrounding rock category prediction model.

[0109] It can be understood that this embodiment predicts the type of unfavorable geological body in the predicted tunnel section, obtains the prediction information of the unfavorable geological body, performs spatial distribution analysis on the underground cavern based on the prediction information of the unfavorable geological body, obtains the excavation space extension information of the underground cavern, obtains the current face surrounding rock type of the current tunnel section, and predicts the surrounding rock type of the unexplored predicted tunnel section in front of the face of the underground cavern by combining the prediction information of the unfavorable geological body of the predicted tunnel section, the current face surrounding rock type of the current tunnel section and the excavation space extension information of the underground cavern to determine the predicted surrounding rock type of the predicted tunnel section.

[0110] Furthermore, in order to improve the prediction accuracy of surrounding rock types, Figure 4 , Figure 4 FIG. 5 is a flow chart of constructing a surrounding rock type prediction model in an embodiment. Before step S50, the following steps may be included:

[0111] Step S51: Acquire historical sample data of underground caverns;

[0112] Step S52: performing data cleaning on the historical sample data to obtain initial sample data;

[0113] Step S53: normalizing the initial sample data, and performing time series alignment on the normalized initial sample data to obtain target sample data;

[0114] Step S54: constructing an initial neural network model and initializing the weights and biases of the initial neural network model;

[0115] Step S55: constructing a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values;

[0116] Step S56: training the initialized neural network model based on the mapping relationship table and the target sample data to obtain a surrounding rock category prediction model.

[0117] It should be noted that the historical sample data includes historical input data and historical output data. The historical input data includes historical values of surrounding rock categories, historical values of poor geological body development levels and historical values of spatial extension characteristics. The historical output data includes historical predicted values of surrounding rock categories corresponding to the historical input data.

[0118] It should be noted that the initial neural network model includes:

[0119] ;

[0120] in, is the output sample, which includes the surrounding rock category label network value, which can be converted into the surrounding rock category prediction value. is an input sample, which includes historical values of surrounding rock types, historical values of unfavorable geological body development levels, and historical values of spatial extension characteristics. For the h The input neuron i The connection weights between hidden neurons, For the hidden neurons and output neurons The connection weights between is the hidden neuron activation function, is the output neuron activation function, For the The bias of hidden neurons, For the The bias of the output neuron.

[0121] In some embodiments, the neural network includes three layers: an input layer, a hidden layer, and an output layer. The default input layer has 6 input nodes: These correspond to the tunnel face surrounding rock type, fault development level, water-rich development level, cave development level, soft rock development level, and the spatial extension characteristic values of structures predicted and revealed during previous excavation. After receiving sample input data, the input layer combines this data with weights and biases, and the resulting data is fed into the hidden layer. This hidden layer activates the hidden neurons to generate the output result, which is then combined with the corresponding weights and biases, processed through the output neuron activation function, and finally outputted at the output layer.

[0122] In some embodiments, data cleaning may include denoising and filling missing data on historical sample data. The analysis device may use a Min-Max normalization model to normalize the historical sample data. The Min-Max normalization model includes:

[0123] ;

[0124] in, is the normalized target sample data, is the initial sample data, is the maximum value in the initial sample data, is the minimum value in the initial sample data.

[0125] In some embodiments, the analysis device can obtain N copies of historical sample data that meet the needs of training and testing; and divide the N copies of the historical sample data into a training set and a test set according to a preset ratio, and the number of historical sample data in the training set is greater than the number of historical sample data in the test set; the training set includes historical sample input data and historical sample output data; wherein the historical sample input data includes historical values of the surrounding rock category of the face, historical values of the development level of unfavorable geological bodies, historical values of the spatial extension characteristics of the structures revealed by early excavation speculation and excavation; preprocess the historical sample input data, initialize the weights and bias of the preliminary neural network model, and use the historical sample input data in the training set after preprocessing as the input of the preliminary neural network model to the preliminary neural network model to obtain the corresponding surrounding rock category label network value.

[0126] Furthermore, in order to improve the model performance and thus improve the accuracy of surrounding rock type prediction, in some embodiments, the above step S56 may include:

[0127] Step S561: training the initialized neural network model based on the mapping relationship table and the target sample data;

[0128] Step S562: inputting the historical input data into the trained neural network model to obtain the surrounding rock category label network value;

[0129] Step S563: calculating the deviation between the surrounding rock category label network value and the surrounding rock category historical prediction value corresponding to the historical input data;

[0130] Step S564: determining whether the deviation value is within a preset deviation range;

[0131] Step S565: If the deviation value is within the preset deviation range, stop training and output the trained neural network model as a surrounding rock category prediction model;

[0132] Step S566: If the deviation value is not within the preset deviation range, return to the step of training the initialized neural network model based on the mapping relationship table and the target sample data.

[0133] It can be understood that the analysis equipment can determine the deviation value between the surrounding rock category label network value and the surrounding rock category true value corresponding to the surrounding rock category label network value, and judge whether the deviation value is within the preset deviation range; when the deviation value is within the preset deviation range, the surrounding rock category label network value is output as the surrounding rock category prediction value; when the deviation value is not within the preset deviation range, the neural network model is retrained.

[0134] Furthermore, in order to accurately calculate the deviation value and improve the model prediction accuracy, in some embodiments, the above step S563 may include:

[0135] Step S5631: constructing a sparse cross entropy loss function;

[0136] Step S5632: Calculating an average loss value based on the sparse cross entropy loss function;

[0137] Step S5633: Determine the deviation value between the surrounding rock category label network value and the surrounding rock category historical prediction value corresponding to the historical input data according to the average loss value.

[0138] In some embodiments, the analysis device may embed a loss function into a neural network model. When constructing a neural network model, a loss function is set to measure the difference between the model prediction result and the true label, and to improve the model prediction accuracy by minimizing the calculated value of the loss function operation.

[0139] In some embodiments, the analysis device may use a sparse cross entropy loss function to set a loss function, which measures the difference between the model prediction result and the true label, and improves the model prediction accuracy by minimizing the calculated value of the loss function. The sparse cross entropy loss function includes:

[0140] ;

[0141] in, The number of samples representing historical sample data (i.e., the number of data combinations input into the model, including the tunnel face surrounding rock type value, unfavorable geological body development level, previous excavation speculation, and spatial extension characteristic values of structures revealed by excavation); Indicates the sample index, which is used to traverse all samples, and the value range is from 1 to N; The true label is an integer representing the category number of the sample. In the surrounding rock classification, it may be one of the values 1, 2, 3, 3.5, 4, 4.5, and 5. The true label is obtained based on the historical prediction value of the surrounding rock category. The model predicts the The samples belong to The probability of the class, Can be , indicating that the model predicts The samples belong to j class probability; It represents the average loss value of all samples. The smaller the value, the closer the model prediction result is to the true label, and the better the model performance.

[0142] In some embodiments, the analysis device may update the model's weight parameters, bias parameters, and learning rate through continuous iterative training, and calculate the mean squared error. Training is terminated when the mean squared error is within an allowable range or the number of iterations exceeds a threshold. The training iteration termination conditions are: the mean squared error is less than 0.0001 or the maximum number of model training iterations exceeds 1000.

[0143] In some embodiments, the analysis device uses a test sample to test the accuracy of the trained model. The specific steps are as follows: the test sample is input into the model to obtain a predicted value for the surrounding rock type. This value is compared with the actual measured reference value for the surrounding rock type. The mean square error between the two values is calculated and the difference is determined to be within an allowable range. If the mean square error is within the allowable range, the model training is successful. If the mean square error is outside the allowable range, the network is retrained.

[0144] Furthermore, in order to improve construction safety, after the above step S50, the following steps are further included:

[0145] Step S60: generating a plurality of engineering treatment strategies based on the tunnel face span and support type of the underground cavern, wherein the engineering treatment strategies include a first category engineering treatment strategy, a second category engineering treatment strategy, a third category engineering treatment strategy, and a fourth category engineering treatment strategy;

[0146] Step S71: When the predicted value of the surrounding rock category is greater than a first preset threshold, a first category engineering treatment strategy is sent to the construction user corresponding to the underground cavern;

[0147] Step S72: When the surrounding rock category prediction value is greater than a second preset threshold and less than or equal to the first preset threshold, sending a second category engineering treatment strategy to the construction user, wherein the first preset threshold is greater than the second preset threshold;

[0148] Step S73: When the surrounding rock category prediction value is greater than a third preset threshold and less than or equal to the second preset threshold, sending a third category engineering treatment strategy to the construction user, wherein the second preset threshold is greater than the third preset threshold;

[0149] Step S74: When the surrounding rock category prediction value is greater than a fourth preset threshold and less than or equal to a third preset threshold, a fourth category engineering treatment strategy is sent to the construction user, wherein the third preset threshold is greater than the fourth preset threshold.

[0150] In some embodiments, the first preset threshold may be 4.50, corresponding to surrounding rock category V. The first category engineering treatment strategy may include: support types such as pipe roof, shotcrete, system anchor, steel frame, and secondary support when necessary.

[0151] The second preset threshold may be 3.50, corresponding to surrounding rock categories IV1 and IV2. The second category engineering treatment strategies may include: support types such as shotcrete, system anchors plus steel mesh, or steel frame.

[0152] The third preset threshold may be 2.00, corresponding to rock mass categories III1 and III2. The third category engineering treatment strategies may include: support types such as shotcrete, system anchors and steel mesh, and pouring concrete lining when the tunnel face has a large span.

[0153] The fourth preset threshold may be 0, corresponding to surrounding rock categories I and II. The fourth category engineering treatment strategies may include: support type is unsupported or local anchor bolts or shotcrete; when the tunnel face has a large span, shotcrete, system anchor bolts and steel mesh are used.

[0154] This embodiment classifies the surrounding rock types of the current tunnel face of the underground cavern to obtain the surrounding rock type of the current tunnel face, predicts the unfavorable geological body of the predicted tunnel section of the underground cavern based on historical geophysical exploration results data, and obtains unfavorable geological body prediction information, wherein the historical geophysical exploration results data include seismic wave detection results data and ground penetrating radar detection results data, the seismic wave detection results data include wave velocity diagrams and seismic wave profile diagrams, and the ground penetrating radar detection results data include ground penetrating radar profile diagrams; the historical geophysical exploration results data of the underground cavern are obtained, and the unfavorable geological body prediction information includes unfavorable geological body types and spatial distribution information corresponding to the unfavorable geological body types; the spatial distribution of the underground cavern is analyzed according to the unfavorable geological body prediction information to obtain the excavation space extension information of the underground cavern; and the characteristics of the surrounding rock type of the current tunnel face, the unfavorable geological body prediction information and the excavation space extension information are quantified. Obtaining feature quantification results, the feature quantification results include the current face surrounding rock category value, the unfavorable geological body development level value and the spatial extension feature value; inputting the feature quantification results into a surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section, the surrounding rock category prediction model is used to determine the surrounding rock category label according to the input feature quantification results, and output the surrounding rock category prediction value after converting the surrounding rock category label into a surrounding rock category prediction value, the surrounding rock category prediction model includes a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values; since this embodiment predicts unfavorable geological bodies based on seismic wave detection results and ground penetrating radar detection results, thereby improving the accuracy of unfavorable geological body prediction, the surrounding rock category prediction is performed in combination with the current face surrounding rock category, unfavorable geological body prediction information and excavation space extension information, thereby achieving high-precision prediction of surrounding rock categories, effectively improving the accuracy of advanced geological prediction of underground caverns, and effectively ensuring construction safety.

[0155] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, which stores an intelligent prediction and analysis program for underground cavern surrounding rock. When the intelligent prediction and analysis program for underground cavern surrounding rock is executed by a processor, the steps of the intelligent prediction and analysis method for underground cavern surrounding rock as described above are implemented.

[0156] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0157] The computer-readable storage medium may be included in the intelligent prediction and analysis device for underground cavern surrounding rock; or it may exist independently without being assembled into the intelligent prediction and analysis device for underground cavern surrounding rock.

[0158] In addition, an embodiment of the present invention also proposes a computer program product, including an intelligent prediction and analysis program for underground cavern surrounding rock, which, when executed by a processor, implements the steps of the intelligent prediction and analysis method for underground cavern surrounding rock as described above.

[0159] The specific implementation of the computer program product of the present invention is basically the same as the various embodiments of the above-mentioned underground cavern surrounding rock intelligent prediction and analysis method, and will not be repeated here.

[0160] Reference Figure 5 , Figure 5 This is a structural block diagram of an embodiment of the intelligent prediction and analysis system for underground cavern surrounding rock of the present invention.

[0161] like Figure 5As shown, the intelligent prediction and analysis system for underground cavern surrounding rock proposed in the embodiment of the present invention includes:

[0162] The tunnel face surrounding rock classification module 10 is used to classify the surrounding rock of the current tunnel face of the underground cavern and obtain the surrounding rock category of the current tunnel face;

[0163] The unfavorable geological body prediction module 20 is used to predict unfavorable geological bodies for the predicted cave section of the underground cave based on historical geophysical exploration results data, and obtain unfavorable geological body prediction information, wherein the historical geophysical exploration results data includes seismic wave detection results data and ground penetrating radar detection results data, the seismic wave detection results data includes wave velocity diagrams and seismic wave profile diagrams, and the ground penetrating radar detection results data includes ground penetrating radar profile diagrams; the historical geophysical exploration results data of the underground cave is obtained, and the unfavorable geological body prediction information includes unfavorable geological body types and spatial distribution information corresponding to the unfavorable geological body types;

[0164] A spatial distribution analysis module 30 is configured to perform spatial distribution analysis on the underground cavern according to the adverse geological body prediction information, and obtain excavation spatial extension information of the underground cavern;

[0165] A feature quantification module 40 is configured to perform feature quantification on the current tunnel face surrounding rock category, the unfavorable geological body prediction information, and the excavation space extension information to obtain a feature quantification result, wherein the feature quantification result includes a current tunnel face surrounding rock category value, an unfavorable geological body development level value, and a spatial extension feature value;

[0166] The surrounding rock category prediction module 50 is used to input the feature quantification results into the surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section. The surrounding rock category prediction model is used to determine the surrounding rock category label based on the input feature quantification results, and convert the surrounding rock category label into a surrounding rock category prediction value and then output the surrounding rock category prediction value. The surrounding rock category prediction model includes a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values.

[0167] This embodiment classifies the surrounding rock types of the current tunnel face of the underground cavern to obtain the surrounding rock type of the current tunnel face, predicts the unfavorable geological body of the predicted tunnel section of the underground cavern based on historical geophysical exploration results data, and obtains unfavorable geological body prediction information, wherein the historical geophysical exploration results data include seismic wave detection results data and ground penetrating radar detection results data, the seismic wave detection results data include wave velocity diagrams and seismic wave profile diagrams, and the ground penetrating radar detection results data include ground penetrating radar profile diagrams; the historical geophysical exploration results data of the underground cavern are obtained, and the unfavorable geological body prediction information includes unfavorable geological body types and spatial distribution information corresponding to the unfavorable geological body types; the spatial distribution of the underground cavern is analyzed according to the unfavorable geological body prediction information to obtain the excavation space extension information of the underground cavern; and the characteristics of the surrounding rock type of the current tunnel face, the unfavorable geological body prediction information and the excavation space extension information are quantified. Obtaining feature quantification results, the feature quantification results include the current face surrounding rock category value, the unfavorable geological body development level value and the spatial extension feature value; inputting the feature quantification results into a surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section, the surrounding rock category prediction model is used to determine the surrounding rock category label according to the input feature quantification results, and output the surrounding rock category prediction value after converting the surrounding rock category label into a surrounding rock category prediction value, the surrounding rock category prediction model includes a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values; since this embodiment predicts unfavorable geological bodies based on seismic wave detection results and ground penetrating radar detection results, thereby improving the accuracy of unfavorable geological body prediction, the surrounding rock category prediction is performed in combination with the current face surrounding rock category, unfavorable geological body prediction information and excavation space extension information, thereby achieving high-precision prediction of surrounding rock categories, effectively improving the accuracy of advanced geological prediction of underground caverns, and effectively ensuring construction safety.

[0168] The intelligent prediction and analysis system for underground cavern surrounding rock provided by this application utilizes the intelligent prediction and analysis method for underground cavern surrounding rock in the above-mentioned embodiments, and is capable of resolving the technical issues of intelligent prediction and analysis for underground cavern surrounding rock. Compared with the prior art, the beneficial effects of the intelligent prediction and analysis system for underground cavern surrounding rock provided by this application are the same as those of the intelligent prediction and analysis method for underground cavern surrounding rock provided by the above-mentioned embodiments. The other technical features of the intelligent prediction and analysis system for underground cavern surrounding rock are the same as those disclosed in the above-mentioned embodiments, and are not further described here.

[0169] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0170] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0171] In addition, for technical details not fully described in this embodiment, please refer to the intelligent prediction and analysis method for underground cavern surrounding rock provided in any embodiment of the present invention, and will not be repeated here.

[0172] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0173] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0174] Through the above description of the embodiments, those skilled in the art will clearly understand that the above-mentioned embodiments and methods can be implemented by means of software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, a magnetic disk, or an optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0175] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent prediction and analysis method for underground cavern surrounding rock, characterized in that: The intelligent prediction and analysis method for underground cavern surrounding rock includes: Classify the surrounding rock types of the current tunnel face of the underground cavern to obtain the surrounding rock type of the current tunnel face; Performing a bad geological body prediction on the predicted cave section of the underground cavern based on historical geophysical exploration results data to obtain bad geological body prediction information, wherein the historical geophysical exploration results data includes seismic wave detection results data and ground-penetrating radar detection results data, the seismic wave detection results data includes a wave velocity map and a seismic wave profile map, the ground-penetrating radar detection results data includes a ground-penetrating radar profile map, and the bad geological body prediction information includes bad geological body types and spatial distribution information corresponding to the bad geological body types; Performing a spatial distribution analysis on the underground cavern according to the adverse geological body prediction information to obtain excavation spatial extension information of the underground cavern, wherein the excavation spatial extension information is spatial extension information of the structure speculated and revealed by the excavation in the early stage; Performing feature quantification on the surrounding rock category of the current tunnel face, the unfavorable geological body prediction information, and the excavation space extension information to obtain a feature quantification result, wherein the feature quantification result includes a surrounding rock category value, an unfavorable geological body development level value, and a spatial extension feature value; The feature quantification results are input into a surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section. The surrounding rock category prediction model is used to determine the surrounding rock category label based on the input feature quantification results, and convert the surrounding rock category label into a surrounding rock category prediction value and then output the surrounding rock category prediction value. The surrounding rock category prediction model includes a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values.

2. The intelligent prediction and analysis method for underground cavern surrounding rock according to claim 1, characterized in that: Before inputting the characteristic quantification result into the surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section, the method further includes: Acquire historical sample data of the underground cavern, wherein the historical sample data includes historical input data and historical output data, wherein the historical input data includes historical values of surrounding rock categories, historical values of unfavorable geological body development levels, and historical values of spatial extension characteristics, and the historical output data includes historical predicted values of surrounding rock categories corresponding to the historical input data; Performing data cleaning on the historical sample data to obtain initial sample data; Normalizing the initial sample data and performing time series alignment on the normalized initial sample data to obtain target sample data; Construct an initial neural network model and initialize the weights and biases of the initial neural network model. The initial neural network model includes: in, is the output sample, which includes the surrounding rock category label network value, is an input sample, which includes historical values of surrounding rock types, historical values of unfavorable geological body development levels, and historical values of spatial extension characteristics. For the h The input neuron The connection weights between hidden neurons, For the hidden neurons and output neurons The connection weights between is the hidden neuron activation function, is the output neuron activation function, For the i The bias of hidden neurons, For the k The bias of the output neurons; Construct a mapping relationship table between surrounding rock category labels and surrounding rock category label network values; The initialized neural network model is trained based on the mapping relationship table and the target sample data to obtain a surrounding rock category prediction model.

3. The intelligent prediction and analysis method for underground cavern surrounding rock according to claim 2, characterized in that: The initializing neural network model is trained based on the mapping relationship table and the target sample data to obtain a surrounding rock category prediction model, including: Training the initialized neural network model based on the mapping relationship table and the target sample data; Inputting the historical input data into the trained neural network model to obtain the surrounding rock category label network value; Calculating a deviation value between the surrounding rock category label network value and the surrounding rock category historical prediction value corresponding to the historical input data; Determining whether the deviation value is within a preset deviation range; If the deviation value is within the preset deviation range, the training is stopped, and the trained neural network model is output as a surrounding rock category prediction model; If the deviation value is not within the preset deviation range, the process returns to the step of training the initialized neural network model based on the mapping relationship table and the target sample data.

4. The intelligent prediction and analysis method for underground cavern surrounding rock according to claim 3, characterized in that: The calculating of the deviation value between the surrounding rock category label network value and the surrounding rock category historical prediction value corresponding to the historical input data includes: Construct a sparse cross entropy loss function, which includes: in, Indicates the number of samples of historical sample data, represents the sample index, represents the true label, which is obtained based on the historical prediction value of the surrounding rock category. The model predicts the The samples belong to The probability of the class, Represents the average loss value of all samples; Calculating an average loss value based on the sparse cross entropy loss function; The deviation value between the surrounding rock category label network value and the surrounding rock category historical prediction value corresponding to the historical input data is determined according to the average loss value.

5. The intelligent prediction and analysis method for underground cavern surrounding rock according to any one of claims 1 to 4, characterized in that: After inputting the characteristic quantification result into the surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section, the method further includes: generating a plurality of engineering treatment strategies based on the tunnel face span and support type of the underground cavern, the engineering treatment strategies including a first category engineering treatment strategy, a second category engineering treatment strategy, a third category engineering treatment strategy, and a fourth category engineering treatment strategy; When the predicted value of the surrounding rock category is greater than a first preset threshold, a first category engineering treatment strategy is sent to a construction user corresponding to the underground cavern; When the surrounding rock category prediction value is greater than a second preset threshold and less than or equal to the first preset threshold, sending a second category engineering treatment strategy to the construction user, wherein the first preset threshold is greater than the second preset threshold; When the surrounding rock category prediction value is greater than a third preset threshold and less than or equal to the second preset threshold, sending a third category engineering treatment strategy to the construction user, wherein the second preset threshold is greater than the third preset threshold; When the surrounding rock category prediction value is greater than a fourth preset threshold and less than or equal to a third preset threshold, a fourth category engineering treatment strategy is sent to the construction user, wherein the third preset threshold is greater than the fourth preset threshold.

6. An intelligent prediction and analysis system for underground cavern surrounding rock, characterized in that: The underground cavern surrounding rock intelligent prediction and analysis system includes: The tunnel face surrounding rock classification module is used to classify the surrounding rock of the current tunnel face of the underground cavern and obtain the surrounding rock category of the current tunnel face; a bad geological body prediction module, configured to predict bad geological bodies for the predicted cave section of the underground cavern based on historical geophysical exploration results data, and obtain bad geological body prediction information, wherein the historical geophysical exploration results data includes seismic wave detection results data and ground-penetrating radar detection results data, the seismic wave detection results data includes wave velocity maps and seismic wave profiles, and the ground-penetrating radar detection results data includes ground-penetrating radar profiles; the historical geophysical exploration results data of the underground cavern is obtained, and the bad geological body prediction information includes bad geological body types and spatial distribution information corresponding to the bad geological body types; A spatial distribution analysis module is used to perform spatial distribution analysis on the underground cavern according to the adverse geological body prediction information to obtain excavation spatial extension information of the underground cavern, wherein the excavation spatial extension information is spatial extension information of the structure speculated and revealed by the excavation in the early stage; a feature quantification module for performing feature quantification on the surrounding rock category of the current tunnel face, the unfavorable geological body prediction information, and the excavation space extension information to obtain a feature quantification result, wherein the feature quantification result includes a surrounding rock category value, an unfavorable geological body development level value, and a spatial extension feature value; The surrounding rock category prediction module is used to input the feature quantification results into the surrounding rock category prediction model to predict the surrounding rock category of the predicted tunnel section. The surrounding rock category prediction model is used to determine the surrounding rock category label based on the input feature quantification results, and convert the surrounding rock category label into a surrounding rock category prediction value and then output the surrounding rock category prediction value. The surrounding rock category prediction model includes a mapping relationship table between surrounding rock category labels and surrounding rock category prediction values.

7. An intelligent prediction and analysis device for underground cavern surrounding rock, characterized in that: The intelligent prediction and analysis device for underground cavern surrounding rock includes: a memory, a processor, and an intelligent prediction and analysis program for underground cavern surrounding rock stored in the memory and runnable on the processor. The intelligent prediction and analysis program for underground cavern surrounding rock is configured to implement the intelligent prediction and analysis method for underground cavern surrounding rock as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an intelligent prediction and analysis program for underground cavern surrounding rock, and when the intelligent prediction and analysis program for underground cavern surrounding rock is executed by a processor, the intelligent prediction and analysis method for underground cavern surrounding rock according to any one of claims 1 to 5 is implemented.

9. A computer program product, characterized in that The computer program product includes an intelligent prediction and analysis program for underground cavern surrounding rock, which, when executed by a processor, implements the steps of the intelligent prediction and analysis method for underground cavern surrounding rock as described in any one of claims 1 to 5.

Images